diff options
Diffstat (limited to 'drivers')
291 files changed, 10636 insertions, 4137 deletions
diff --git a/drivers/base/base.h b/drivers/base/base.h index eb4c0ace9242..0738ccad08b2 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -207,7 +207,7 @@ static inline int devtmpfs_init(void) { return 0; } #endif #ifdef CONFIG_BLOCK -extern struct class block_class; +extern const struct class block_class; static inline bool is_blockdev(struct device *dev) { return dev->class == &block_class; diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index f37ad34c80ec..0d01890160f3 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -13,6 +13,8 @@ #include <linux/msi.h> #include <linux/slab.h> +/* Begin of removal area. Once everything is converted over. Cleanup the includes too! */ + #define DEV_ID_SHIFT 21 #define MAX_DEV_MSIS (1 << (32 - DEV_ID_SHIFT)) @@ -204,8 +206,8 @@ static void platform_msi_free_priv_data(struct device *dev) * Returns: * Zero for success, or an error code in case of failure */ -int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, - irq_write_msi_msg_t write_msi_msg) +static int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, + irq_write_msi_msg_t write_msi_msg) { int err; @@ -219,18 +221,6 @@ int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, return err; } -EXPORT_SYMBOL_GPL(platform_msi_domain_alloc_irqs); - -/** - * platform_msi_domain_free_irqs - Free MSI interrupts for @dev - * @dev: The device for which to free interrupts - */ -void platform_msi_domain_free_irqs(struct device *dev) -{ - msi_domain_free_irqs_all(dev, MSI_DEFAULT_DOMAIN); - platform_msi_free_priv_data(dev); -} -EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs); /** * platform_msi_get_host_data - Query the private data associated with @@ -350,3 +340,104 @@ int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int vir return msi_domain_populate_irqs(domain->parent, dev, virq, nr_irqs, &data->arg); } + +/* End of removal area */ + +/* Real per device domain interfaces */ + +/* + * This indirection can go when platform_device_msi_init_and_alloc_irqs() + * is switched to a proper irq_chip::irq_write_msi_msg() callback. Keep it + * simple for now. + */ +static void platform_msi_write_msi_msg(struct irq_data *d, struct msi_msg *msg) +{ + irq_write_msi_msg_t cb = d->chip_data; + + cb(irq_data_get_msi_desc(d), msg); +} + +static void platform_msi_set_desc_byindex(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->desc = desc; + arg->hwirq = desc->msi_index; +} + +static const struct msi_domain_template platform_msi_template = { + .chip = { + .name = "pMSI", + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_write_msi_msg = platform_msi_write_msi_msg, + /* The rest is filled in by the platform MSI parent */ + }, + + .ops = { + .set_desc = platform_msi_set_desc_byindex, + }, + + .info = { + .bus_token = DOMAIN_BUS_DEVICE_MSI, + }, +}; + +/** + * platform_device_msi_init_and_alloc_irqs - Initialize platform device MSI + * and allocate interrupts for @dev + * @dev: The device for which to allocate interrupts + * @nvec: The number of interrupts to allocate + * @write_msi_msg: Callback to write an interrupt message for @dev + * + * Returns: + * Zero for success, or an error code in case of failure + * + * This creates a MSI domain on @dev which has @dev->msi.domain as + * parent. The parent domain sets up the new domain. The domain has + * a fixed size of @nvec. The domain is managed by devres and will + * be removed when the device is removed. + * + * Note: For migration purposes this falls back to the original platform_msi code + * up to the point where all platforms have been converted to the MSI + * parent model. + */ +int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nvec, + irq_write_msi_msg_t write_msi_msg) +{ + struct irq_domain *domain = dev->msi.domain; + + if (!domain || !write_msi_msg) + return -EINVAL; + + /* Migration support. Will go away once everything is converted */ + if (!irq_domain_is_msi_parent(domain)) + return platform_msi_domain_alloc_irqs(dev, nvec, write_msi_msg); + + /* + * @write_msi_msg is stored in the resulting msi_domain_info::data. + * The underlying domain creation mechanism will assign that + * callback to the resulting irq chip. + */ + if (!msi_create_device_irq_domain(dev, MSI_DEFAULT_DOMAIN, + &platform_msi_template, + nvec, NULL, write_msi_msg)) + return -ENODEV; + + return msi_domain_alloc_irqs_range(dev, MSI_DEFAULT_DOMAIN, 0, nvec - 1); +} +EXPORT_SYMBOL_GPL(platform_device_msi_init_and_alloc_irqs); + +/** + * platform_device_msi_free_irqs_all - Free all interrupts for @dev + * @dev: The device for which to free interrupts + */ +void platform_device_msi_free_irqs_all(struct device *dev) +{ + struct irq_domain *domain = dev->msi.domain; + + msi_domain_free_irqs_all(dev, MSI_DEFAULT_DOMAIN); + + /* Migration support. Will go away once everything is converted */ + if (!irq_domain_is_msi_parent(domain)) + platform_msi_free_priv_data(dev); +} +EXPORT_SYMBOL_GPL(platform_device_msi_free_irqs_all); diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 2b98114a9fe0..a25414228e47 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1779,7 +1779,7 @@ static int fd_alloc_disk(int drive, int system) struct gendisk *disk; int err; - disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL); + disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL); if (IS_ERR(disk)) return PTR_ERR(disk); diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index b1b47d88f5db..b6dac8cee70f 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -24,8 +24,8 @@ static DEFINE_MUTEX(aoeblk_mutex); static struct kmem_cache *buf_pool_cache; static struct dentry *aoe_debugfs_dir; -/* GPFS needs a larger value than the default. */ -static int aoe_maxsectors; +/* random default picked from the historic block max_sectors cap */ +static int aoe_maxsectors = 2560; module_param(aoe_maxsectors, int, 0644); MODULE_PARM_DESC(aoe_maxsectors, "When nonzero, set the maximum number of sectors per I/O request"); @@ -334,6 +334,10 @@ aoeblk_gdalloc(void *vp) mempool_t *mp; struct blk_mq_tag_set *set; sector_t ssize; + struct queue_limits lim = { + .max_hw_sectors = aoe_maxsectors, + .io_opt = SZ_2M, + }; ulong flags; int late = 0; int err; @@ -371,7 +375,7 @@ aoeblk_gdalloc(void *vp) goto err_mempool; } - gd = blk_mq_alloc_disk(set, d); + gd = blk_mq_alloc_disk(set, &lim, d); if (IS_ERR(gd)) { pr_err("aoe: cannot allocate block queue for %ld.%d\n", d->aoemajor, d->aoeminor); @@ -384,14 +388,9 @@ aoeblk_gdalloc(void *vp) WARN_ON(d->flags & DEVFL_TKILL); WARN_ON(d->gd); WARN_ON(d->flags & DEVFL_UP); - /* random number picked from the history block max_sectors cap */ - blk_queue_max_hw_sectors(gd->queue, 2560u); - blk_queue_io_opt(gd->queue, SZ_2M); d->bufpool = mp; d->blkq = gd->queue; d->gd = gd; - if (aoe_maxsectors) - blk_queue_max_hw_sectors(gd->queue, aoe_maxsectors); gd->major = AOE_MAJOR; gd->first_minor = d->sysminor; gd->minors = AOE_PARTITIONS; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index d7317425be51..cc9077b588d7 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -419,13 +419,16 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu rcu_read_lock(); for_each_netdev_rcu(&init_net, ifp) { dev_hold(ifp); - if (!is_aoe_netif(ifp)) - goto cont; + if (!is_aoe_netif(ifp)) { + dev_put(ifp); + continue; + } skb = new_skb(sizeof *h + sizeof *ch); if (skb == NULL) { printk(KERN_INFO "aoe: skb alloc failure\n"); - goto cont; + dev_put(ifp); + continue; } skb_put(skb, sizeof *h + sizeof *ch); skb->dev = ifp; @@ -440,9 +443,6 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu h->major = cpu_to_be16(aoemajor); h->minor = aoeminor; h->cmd = AOECMD_CFG; - -cont: - dev_put(ifp); } rcu_read_unlock(); } diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c index c51ea95bc2ce..923a134fd766 100644 --- a/drivers/block/aoe/aoenet.c +++ b/drivers/block/aoe/aoenet.c @@ -63,6 +63,7 @@ tx(int id) __must_hold(&txlock) pr_warn("aoe: packet could not be sent on %s. %s\n", ifp ? ifp->name : "netif", "consider increasing tx_queue_len"); + dev_put(ifp); spin_lock_irq(&txlock); } return 0; diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 50949207798d..cacc4ba942a8 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1994,7 +1994,7 @@ static int ataflop_alloc_disk(unsigned int drive, unsigned int type) { struct gendisk *disk; - disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL); + disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL); if (IS_ERR(disk)) return PTR_ERR(disk); diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 970bd6ff38c4..e322cef6596b 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -318,6 +318,16 @@ static int brd_alloc(int i) struct gendisk *disk; char buf[DISK_NAME_LEN]; int err = -ENOMEM; + struct queue_limits lim = { + /* + * This is so fdisk will align partitions on 4k, because of + * direct_access API needing 4k alignment, returning a PFN + * (This is only a problem on very small devices <= 4M, + * otherwise fdisk will align on 1M. Regardless this call + * is harmless) + */ + .physical_block_size = PAGE_SIZE, + }; list_for_each_entry(brd, &brd_devices, brd_list) if (brd->brd_number == i) @@ -335,10 +345,11 @@ static int brd_alloc(int i) debugfs_create_u64(buf, 0444, brd_debugfs_dir, &brd->brd_nr_pages); - disk = brd->brd_disk = blk_alloc_disk(NUMA_NO_NODE); - if (!disk) + disk = brd->brd_disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); goto out_free_dev; - + } disk->major = RAMDISK_MAJOR; disk->first_minor = i * max_part; disk->minors = max_part; @@ -347,15 +358,6 @@ static int brd_alloc(int i) strscpy(disk->disk_name, buf, DISK_NAME_LEN); set_capacity(disk, rd_size * 2); - /* - * This is so fdisk will align partitions on 4k, because of - * direct_access API needing 4k alignment, returning a PFN - * (This is only a problem on very small devices <= 4M, - * otherwise fdisk will align on 1M. Regardless this call - * is harmless) - */ - blk_queue_physical_block_size(disk->queue, PAGE_SIZE); - /* Tell the block layer that this is not a rotational device */ blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, disk->queue); diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index c21e3732759e..94dc0a235919 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -524,9 +524,9 @@ struct drbd_md { struct drbd_backing_dev { struct block_device *backing_bdev; - struct bdev_handle *backing_bdev_handle; + struct file *backing_bdev_file; struct block_device *md_bdev; - struct bdev_handle *md_bdev_handle; + struct file *f_md_bdev; struct drbd_md md; struct disk_conf *disk_conf; /* RCU, for updates: resource->conf_update */ sector_t known_size; /* last known size of that backing device */ diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 6bc86106c7b2..113b441d4d36 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2690,6 +2690,14 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig int id; int vnr = adm_ctx->volume; enum drbd_ret_code err = ERR_NOMEM; + struct queue_limits lim = { + /* + * Setting the max_hw_sectors to an odd value of 8kibyte here. + * This triggers a max_bio_size message upon first attach or + * connect. + */ + .max_hw_sectors = DRBD_MAX_BIO_SIZE_SAFE >> 8, + }; device = minor_to_device(minor); if (device) @@ -2708,9 +2716,11 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_init_set_defaults(device); - disk = blk_alloc_disk(NUMA_NO_NODE); - if (!disk) + disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); goto out_no_disk; + } device->vdisk = disk; device->rq_queue = disk->queue; @@ -2727,9 +2737,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); blk_queue_write_cache(disk->queue, true, true); - /* Setting the max_hw_sectors to an odd value of 8kibyte here - This triggers a max_bio_size message upon first attach or connect */ - blk_queue_max_hw_sectors(disk->queue, DRBD_MAX_BIO_SIZE_SAFE >> 8); device->md_io.page = alloc_page(GFP_KERNEL); if (!device->md_io.page) diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 43747a1aae43..5d65c9754d83 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1189,9 +1189,31 @@ static int drbd_check_al_size(struct drbd_device *device, struct disk_conf *dc) return 0; } -static void blk_queue_discard_granularity(struct request_queue *q, unsigned int granularity) +static unsigned int drbd_max_peer_bio_size(struct drbd_device *device) { - q->limits.discard_granularity = granularity; + /* + * We may ignore peer limits if the peer is modern enough. From 8.3.8 + * onwards the peer can use multiple BIOs for a single peer_request. + */ + if (device->state.conn < C_WF_REPORT_PARAMS) + return device->peer_max_bio_size; + + if (first_peer_device(device)->connection->agreed_pro_version < 94) + return min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET); + + /* + * Correct old drbd (up to 8.3.7) if it believes it can do more than + * 32KiB. + */ + if (first_peer_device(device)->connection->agreed_pro_version == 94) + return DRBD_MAX_SIZE_H80_PACKET; + + /* + * drbd 8.3.8 onwards, before 8.4.0 + */ + if (first_peer_device(device)->connection->agreed_pro_version < 100) + return DRBD_MAX_BIO_SIZE_P95; + return DRBD_MAX_BIO_SIZE; } static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection) @@ -1204,149 +1226,119 @@ static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection) return AL_EXTENT_SIZE >> 9; } -static void decide_on_discard_support(struct drbd_device *device, +static bool drbd_discard_supported(struct drbd_connection *connection, struct drbd_backing_dev *bdev) { - struct drbd_connection *connection = - first_peer_device(device)->connection; - struct request_queue *q = device->rq_queue; - unsigned int max_discard_sectors; - if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev)) - goto not_supported; + return false; if (connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) { drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n"); - goto not_supported; + return false; } - /* - * We don't care for the granularity, really. - * - * Stacking limits below should fix it for the local device. Whether or - * not it is a suitable granularity on the remote device is not our - * problem, really. If you care, you need to use devices with similar - * topology on all peers. - */ - blk_queue_discard_granularity(q, 512); - max_discard_sectors = drbd_max_discard_sectors(connection); - blk_queue_max_discard_sectors(q, max_discard_sectors); - blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); - return; - -not_supported: - blk_queue_discard_granularity(q, 0); - blk_queue_max_discard_sectors(q, 0); + return true; } -static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q) +/* This is the workaround for "bio would need to, but cannot, be split" */ +static unsigned int drbd_backing_dev_max_segments(struct drbd_device *device) { - /* Fixup max_write_zeroes_sectors after blk_stack_limits(): - * if we can handle "zeroes" efficiently on the protocol, - * we want to do that, even if our backend does not announce - * max_write_zeroes_sectors itself. */ - struct drbd_connection *connection = first_peer_device(device)->connection; - /* If the peer announces WZEROES support, use it. Otherwise, rather - * send explicit zeroes than rely on some discard-zeroes-data magic. */ - if (connection->agreed_features & DRBD_FF_WZEROES) - q->limits.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS; - else - q->limits.max_write_zeroes_sectors = 0; -} + unsigned int max_segments; -static void fixup_discard_support(struct drbd_device *device, struct request_queue *q) -{ - unsigned int max_discard = device->rq_queue->limits.max_discard_sectors; - unsigned int discard_granularity = - device->rq_queue->limits.discard_granularity >> SECTOR_SHIFT; + rcu_read_lock(); + max_segments = rcu_dereference(device->ldev->disk_conf)->max_bio_bvecs; + rcu_read_unlock(); - if (discard_granularity > max_discard) { - blk_queue_discard_granularity(q, 0); - blk_queue_max_discard_sectors(q, 0); - } + if (!max_segments) + return BLK_MAX_SEGMENTS; + return max_segments; } -static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backing_dev *bdev, - unsigned int max_bio_size, struct o_qlim *o) +void drbd_reconsider_queue_parameters(struct drbd_device *device, + struct drbd_backing_dev *bdev, struct o_qlim *o) { + struct drbd_connection *connection = + first_peer_device(device)->connection; struct request_queue * const q = device->rq_queue; - unsigned int max_hw_sectors = max_bio_size >> 9; - unsigned int max_segments = 0; + unsigned int now = queue_max_hw_sectors(q) << 9; + struct queue_limits lim; struct request_queue *b = NULL; - struct disk_conf *dc; + unsigned int new; if (bdev) { b = bdev->backing_bdev->bd_disk->queue; - max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9); - rcu_read_lock(); - dc = rcu_dereference(device->ldev->disk_conf); - max_segments = dc->max_bio_bvecs; - rcu_read_unlock(); - - blk_set_stacking_limits(&q->limits); + device->local_max_bio_size = + queue_max_hw_sectors(b) << SECTOR_SHIFT; } - blk_queue_max_hw_sectors(q, max_hw_sectors); - /* This is the workaround for "bio would need to, but cannot, be split" */ - blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS); - blk_queue_segment_boundary(q, PAGE_SIZE-1); - decide_on_discard_support(device, bdev); - - if (b) { - blk_stack_limits(&q->limits, &b->limits, 0); - disk_update_readahead(device->vdisk); + /* + * We may later detach and re-attach on a disconnected Primary. Avoid + * decreasing the value in this case. + * + * We want to store what we know the peer DRBD can handle, not what the + * peer IO backend can handle. + */ + new = min3(DRBD_MAX_BIO_SIZE, device->local_max_bio_size, + max(drbd_max_peer_bio_size(device), device->peer_max_bio_size)); + if (new != now) { + if (device->state.role == R_PRIMARY && new < now) + drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n", + new, now); + drbd_info(device, "max BIO size = %u\n", new); } - fixup_write_zeroes(device, q); - fixup_discard_support(device, q); -} - -void drbd_reconsider_queue_parameters(struct drbd_device *device, struct drbd_backing_dev *bdev, struct o_qlim *o) -{ - unsigned int now, new, local, peer; - - now = queue_max_hw_sectors(device->rq_queue) << 9; - local = device->local_max_bio_size; /* Eventually last known value, from volatile memory */ - peer = device->peer_max_bio_size; /* Eventually last known value, from meta data */ + lim = queue_limits_start_update(q); if (bdev) { - local = queue_max_hw_sectors(bdev->backing_bdev->bd_disk->queue) << 9; - device->local_max_bio_size = local; + blk_set_stacking_limits(&lim); + lim.max_segments = drbd_backing_dev_max_segments(device); + } else { + lim.max_segments = BLK_MAX_SEGMENTS; } - local = min(local, DRBD_MAX_BIO_SIZE); - /* We may ignore peer limits if the peer is modern enough. - Because new from 8.3.8 onwards the peer can use multiple - BIOs for a single peer_request */ - if (device->state.conn >= C_WF_REPORT_PARAMS) { - if (first_peer_device(device)->connection->agreed_pro_version < 94) - peer = min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET); - /* Correct old drbd (up to 8.3.7) if it believes it can do more than 32KiB */ - else if (first_peer_device(device)->connection->agreed_pro_version == 94) - peer = DRBD_MAX_SIZE_H80_PACKET; - else if (first_peer_device(device)->connection->agreed_pro_version < 100) - peer = DRBD_MAX_BIO_SIZE_P95; /* drbd 8.3.8 onwards, before 8.4.0 */ - else - peer = DRBD_MAX_BIO_SIZE; + lim.max_hw_sectors = new >> SECTOR_SHIFT; + lim.seg_boundary_mask = PAGE_SIZE - 1; - /* We may later detach and re-attach on a disconnected Primary. - * Avoid this setting to jump back in that case. - * We want to store what we know the peer DRBD can handle, - * not what the peer IO backend can handle. */ - if (peer > device->peer_max_bio_size) - device->peer_max_bio_size = peer; + /* + * We don't care for the granularity, really. + * + * Stacking limits below should fix it for the local device. Whether or + * not it is a suitable granularity on the remote device is not our + * problem, really. If you care, you need to use devices with similar + * topology on all peers. + */ + if (drbd_discard_supported(connection, bdev)) { + lim.discard_granularity = 512; + lim.max_hw_discard_sectors = + drbd_max_discard_sectors(connection); + } else { + lim.discard_granularity = 0; + lim.max_hw_discard_sectors = 0; } - new = min(local, peer); - if (device->state.role == R_PRIMARY && new < now) - drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n", new, now); + if (bdev) + blk_stack_limits(&lim, &b->limits, 0); - if (new != now) - drbd_info(device, "max BIO size = %u\n", new); + /* + * If we can handle "zeroes" efficiently on the protocol, we want to do + * that, even if our backend does not announce max_write_zeroes_sectors + * itself. + */ + if (connection->agreed_features & DRBD_FF_WZEROES) + lim.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS; + else + lim.max_write_zeroes_sectors = 0; + + if ((lim.discard_granularity >> SECTOR_SHIFT) > + lim.max_hw_discard_sectors) { + lim.discard_granularity = 0; + lim.max_hw_discard_sectors = 0; + } - drbd_setup_queue_param(device, bdev, new, o); + if (queue_limits_commit_update(q, &lim)) + drbd_err(device, "setting new queue limits failed\n"); } /* Starts the worker thread */ @@ -1635,45 +1627,45 @@ success: return 0; } -static struct bdev_handle *open_backing_dev(struct drbd_device *device, +static struct file *open_backing_dev(struct drbd_device *device, const char *bdev_path, void *claim_ptr, bool do_bd_link) { - struct bdev_handle *handle; + struct file *file; int err = 0; - handle = bdev_open_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE, - claim_ptr, NULL); - if (IS_ERR(handle)) { + file = bdev_file_open_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE, + claim_ptr, NULL); + if (IS_ERR(file)) { drbd_err(device, "open(\"%s\") failed with %ld\n", - bdev_path, PTR_ERR(handle)); - return handle; + bdev_path, PTR_ERR(file)); + return file; } if (!do_bd_link) - return handle; + return file; - err = bd_link_disk_holder(handle->bdev, device->vdisk); + err = bd_link_disk_holder(file_bdev(file), device->vdisk); if (err) { - bdev_release(handle); + fput(file); drbd_err(device, "bd_link_disk_holder(\"%s\", ...) failed with %d\n", bdev_path, err); - handle = ERR_PTR(err); + file = ERR_PTR(err); } - return handle; + return file; } static int open_backing_devices(struct drbd_device *device, struct disk_conf *new_disk_conf, struct drbd_backing_dev *nbc) { - struct bdev_handle *handle; + struct file *file; - handle = open_backing_dev(device, new_disk_conf->backing_dev, device, + file = open_backing_dev(device, new_disk_conf->backing_dev, device, true); - if (IS_ERR(handle)) + if (IS_ERR(file)) return ERR_OPEN_DISK; - nbc->backing_bdev = handle->bdev; - nbc->backing_bdev_handle = handle; + nbc->backing_bdev = file_bdev(file); + nbc->backing_bdev_file = file; /* * meta_dev_idx >= 0: external fixed size, possibly multiple @@ -1683,7 +1675,7 @@ static int open_backing_devices(struct drbd_device *device, * should check it for you already; but if you don't, or * someone fooled it, we need to double check here) */ - handle = open_backing_dev(device, new_disk_conf->meta_dev, + file = open_backing_dev(device, new_disk_conf->meta_dev, /* claim ptr: device, if claimed exclusively; shared drbd_m_holder, * if potentially shared with other drbd minors */ (new_disk_conf->meta_dev_idx < 0) ? (void*)device : (void*)drbd_m_holder, @@ -1691,21 +1683,21 @@ static int open_backing_devices(struct drbd_device *device, * as would happen with internal metadata. */ (new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_FLEX_INT && new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_INTERNAL)); - if (IS_ERR(handle)) + if (IS_ERR(file)) return ERR_OPEN_MD_DISK; - nbc->md_bdev = handle->bdev; - nbc->md_bdev_handle = handle; + nbc->md_bdev = file_bdev(file); + nbc->f_md_bdev = file; return NO_ERROR; } static void close_backing_dev(struct drbd_device *device, - struct bdev_handle *handle, bool do_bd_unlink) + struct file *bdev_file, bool do_bd_unlink) { - if (!handle) + if (!bdev_file) return; if (do_bd_unlink) - bd_unlink_disk_holder(handle->bdev, device->vdisk); - bdev_release(handle); + bd_unlink_disk_holder(file_bdev(bdev_file), device->vdisk); + fput(bdev_file); } void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev) @@ -1713,9 +1705,9 @@ void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev * if (ldev == NULL) return; - close_backing_dev(device, ldev->md_bdev_handle, + close_backing_dev(device, ldev->f_md_bdev, ldev->md_bdev != ldev->backing_bdev); - close_backing_dev(device, ldev->backing_bdev_handle, true); + close_backing_dev(device, ldev->backing_bdev_file, true); kfree(ldev->disk_conf); kfree(ldev); @@ -2131,9 +2123,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) fail: conn_reconfig_done(connection); if (nbc) { - close_backing_dev(device, nbc->md_bdev_handle, + close_backing_dev(device, nbc->f_md_bdev, nbc->md_bdev != nbc->backing_bdev); - close_backing_dev(device, nbc->backing_bdev_handle, true); + close_backing_dev(device, nbc->backing_bdev_file, true); kfree(nbc); } kfree(new_disk_conf); diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 287a8d1d3f70..e858e7e0383f 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -1542,9 +1542,10 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device, int notify_resource_state_change(struct sk_buff *skb, unsigned int seq, - struct drbd_resource_state_change *resource_state_change, + void *state_change, enum drbd_notification_type type) { + struct drbd_resource_state_change *resource_state_change = state_change; struct drbd_resource *resource = resource_state_change->resource; struct resource_info resource_info = { .res_role = resource_state_change->role[NEW], @@ -1558,13 +1559,14 @@ int notify_resource_state_change(struct sk_buff *skb, int notify_connection_state_change(struct sk_buff *skb, unsigned int seq, - struct drbd_connection_state_change *connection_state_change, + void *state_change, enum drbd_notification_type type) { - struct drbd_connection *connection = connection_state_change->connection; + struct drbd_connection_state_change *p = state_change; + struct drbd_connection *connection = p->connection; struct connection_info connection_info = { - .conn_connection_state = connection_state_change->cstate[NEW], - .conn_role = connection_state_change->peer_role[NEW], + .conn_connection_state = p->cstate[NEW], + .conn_role = p->peer_role[NEW], }; return notify_connection_state(skb, seq, connection, &connection_info, type); @@ -1572,9 +1574,10 @@ int notify_connection_state_change(struct sk_buff *skb, int notify_device_state_change(struct sk_buff *skb, unsigned int seq, - struct drbd_device_state_change *device_state_change, + void *state_change, enum drbd_notification_type type) { + struct drbd_device_state_change *device_state_change = state_change; struct drbd_device *device = device_state_change->device; struct device_info device_info = { .dev_disk_state = device_state_change->disk_state[NEW], @@ -1585,9 +1588,10 @@ int notify_device_state_change(struct sk_buff *skb, int notify_peer_device_state_change(struct sk_buff *skb, unsigned int seq, - struct drbd_peer_device_state_change *p, + void *state_change, enum drbd_notification_type type) { + struct drbd_peer_device_state_change *p = state_change; struct drbd_peer_device *peer_device = p->peer_device; struct peer_device_info peer_device_info = { .peer_repl_state = p->repl_state[NEW], @@ -1605,8 +1609,8 @@ static void broadcast_state_change(struct drbd_state_change *state_change) struct drbd_resource_state_change *resource_state_change = &state_change->resource[0]; bool resource_state_has_changed; unsigned int n_device, n_connection, n_peer_device, n_peer_devices; - int (*last_func)(struct sk_buff *, unsigned int, void *, - enum drbd_notification_type) = NULL; + int (*last_func)(struct sk_buff *, unsigned int, + void *, enum drbd_notification_type) = NULL; void *last_arg = NULL; #define HAS_CHANGED(state) ((state)[OLD] != (state)[NEW]) @@ -1616,7 +1620,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change) }) #define REMEMBER_STATE_CHANGE(func, arg, type) \ ({ FINAL_STATE_CHANGE(type | NOTIFY_CONTINUES); \ - last_func = (typeof(last_func))func; \ + last_func = func; \ last_arg = arg; \ }) diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h index 9d78d8e3912e..a56a57d67686 100644 --- a/drivers/block/drbd/drbd_state_change.h +++ b/drivers/block/drbd/drbd_state_change.h @@ -46,19 +46,19 @@ extern void forget_state_change(struct drbd_state_change *); extern int notify_resource_state_change(struct sk_buff *, unsigned int, - struct drbd_resource_state_change *, + void *, enum drbd_notification_type type); extern int notify_connection_state_change(struct sk_buff *, unsigned int, - struct drbd_connection_state_change *, + void *, enum drbd_notification_type type); extern int notify_device_state_change(struct sk_buff *, unsigned int, - struct drbd_device_state_change *, + void *, enum drbd_notification_type type); extern int notify_peer_device_state_change(struct sk_buff *, unsigned int, - struct drbd_peer_device_state_change *, + void *, enum drbd_notification_type type); #endif /* DRBD_STATE_CHANGE_H */ diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index d0e41d52d6a9..1b399ec8c07d 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -530,14 +530,13 @@ static struct format_descr format_req; static char *floppy_track_buffer; static int max_buffer_sectors; -typedef void (*done_f)(int); static const struct cont_t { void (*interrupt)(void); /* this is called after the interrupt of the * main command */ void (*redo)(void); /* this is called to retry the operation */ void (*error)(void); /* this is called to tally an error */ - done_f done; /* this is called to say if the operation has + void (*done)(int); /* this is called to say if the operation has * succeeded/failed */ } *cont; @@ -985,6 +984,10 @@ static void empty(void) { } +static void empty_done(int result) +{ +} + static void (*floppy_work_fn)(void); static void floppy_work_workfn(struct work_struct *work) @@ -1998,14 +2001,14 @@ static const struct cont_t wakeup_cont = { .interrupt = empty, .redo = do_wakeup, .error = empty, - .done = (done_f)empty + .done = empty_done, }; static const struct cont_t intr_cont = { .interrupt = empty, .redo = process_fd_request, .error = empty, - .done = (done_f)empty + .done = empty_done, }; /* schedules handler, waiting for completion. May be interrupted, will then @@ -4513,13 +4516,15 @@ static bool floppy_available(int drive) static int floppy_alloc_disk(unsigned int drive, unsigned int type) { + struct queue_limits lim = { + .max_hw_sectors = 64, + }; struct gendisk *disk; - disk = blk_mq_alloc_disk(&tag_sets[drive], NULL); + disk = blk_mq_alloc_disk(&tag_sets[drive], &lim, NULL); if (IS_ERR(disk)) return PTR_ERR(disk); - blk_queue_max_hw_sectors(disk->queue, 64); disk->major = FLOPPY_MAJOR; disk->first_minor = TOMINOR(drive) | (type << 2); disk->minors = 1; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f8145499da38..28a95fd366fe 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -750,12 +750,13 @@ static void loop_sysfs_exit(struct loop_device *lo) &loop_attribute_group); } -static void loop_config_discard(struct loop_device *lo) +static void loop_config_discard(struct loop_device *lo, + struct queue_limits *lim) { struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; - struct request_queue *q = lo->lo_queue; - u32 granularity, max_discard_sectors; + u32 granularity = 0, max_discard_sectors = 0; + struct kstatfs sbuf; /* * If the backing device is a block device, mirror its zeroing @@ -775,29 +776,17 @@ static void loop_config_discard(struct loop_device *lo) * We use punch hole to reclaim the free space used by the * image a.k.a. discard. */ - } else if (!file->f_op->fallocate) { - max_discard_sectors = 0; - granularity = 0; - - } else { - struct kstatfs sbuf; - + } else if (file->f_op->fallocate && !vfs_statfs(&file->f_path, &sbuf)) { max_discard_sectors = UINT_MAX >> 9; - if (!vfs_statfs(&file->f_path, &sbuf)) - granularity = sbuf.f_bsize; - else - max_discard_sectors = 0; + granularity = sbuf.f_bsize; } - if (max_discard_sectors) { - q->limits.discard_granularity = granularity; - blk_queue_max_discard_sectors(q, max_discard_sectors); - blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); - } else { - q->limits.discard_granularity = 0; - blk_queue_max_discard_sectors(q, 0); - blk_queue_max_write_zeroes_sectors(q, 0); - } + lim->max_hw_discard_sectors = max_discard_sectors; + lim->max_write_zeroes_sectors = max_discard_sectors; + if (max_discard_sectors) + lim->discard_granularity = granularity; + else + lim->discard_granularity = 0; } struct loop_worker { @@ -986,6 +975,20 @@ loop_set_status_from_info(struct loop_device *lo, return 0; } +static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize, + bool update_discard_settings) +{ + struct queue_limits lim; + + lim = queue_limits_start_update(lo->lo_queue); + lim.logical_block_size = bsize; + lim.physical_block_size = bsize; + lim.io_min = bsize; + if (update_discard_settings) + loop_config_discard(lo, &lim); + return queue_limits_commit_update(lo->lo_queue, &lim); +} + static int loop_configure(struct loop_device *lo, blk_mode_t mode, struct block_device *bdev, const struct loop_config *config) @@ -1083,11 +1086,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, else bsize = 512; - blk_queue_logical_block_size(lo->lo_queue, bsize); - blk_queue_physical_block_size(lo->lo_queue, bsize); - blk_queue_io_min(lo->lo_queue, bsize); + error = loop_reconfigure_limits(lo, bsize, true); + if (WARN_ON_ONCE(error)) + goto out_unlock; - loop_config_discard(lo); loop_update_rotational(lo); loop_update_dio(lo); loop_sysfs_init(lo); @@ -1154,9 +1156,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release) lo->lo_offset = 0; lo->lo_sizelimit = 0; memset(lo->lo_file_name, 0, LO_NAME_SIZE); - blk_queue_logical_block_size(lo->lo_queue, 512); - blk_queue_physical_block_size(lo->lo_queue, 512); - blk_queue_io_min(lo->lo_queue, 512); + loop_reconfigure_limits(lo, 512, false); invalidate_disk(lo->lo_disk); loop_sysfs_exit(lo); /* let user-space know about this change */ @@ -1488,9 +1488,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) invalidate_bdev(lo->lo_device); blk_mq_freeze_queue(lo->lo_queue); - blk_queue_logical_block_size(lo->lo_queue, arg); - blk_queue_physical_block_size(lo->lo_queue, arg); - blk_queue_io_min(lo->lo_queue, arg); + err = loop_reconfigure_limits(lo, arg, false); loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue); @@ -1982,6 +1980,12 @@ static const struct blk_mq_ops loop_mq_ops = { static int loop_add(int i) { + struct queue_limits lim = { + /* + * Random number picked from the historic block max_sectors cap. + */ + .max_hw_sectors = 2560u, + }; struct loop_device *lo; struct gendisk *disk; int err; @@ -2025,16 +2029,13 @@ static int loop_add(int i) if (err) goto out_free_idr; - disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, lo); + disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, &lim, lo); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_cleanup_tags; } lo->lo_queue = lo->lo_disk->queue; - /* random number picked from the history block max_sectors cap */ - blk_queue_max_hw_sectors(lo->lo_queue, 2560u); - /* * By default, we do buffer IO, so it doesn't make sense to enable * merge because the I/O submitted to backing file is handled page by diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index b200950e8fb5..43a187609ef7 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3401,6 +3401,12 @@ static const struct blk_mq_ops mtip_mq_ops = { */ static int mtip_block_initialize(struct driver_data *dd) { + struct queue_limits lim = { + .physical_block_size = 4096, + .max_hw_sectors = 0xffff, + .max_segments = MTIP_MAX_SG, + .max_segment_size = 0x400000, + }; int rv = 0, wait_for_rebuild = 0; sector_t capacity; unsigned int index = 0; @@ -3431,7 +3437,7 @@ static int mtip_block_initialize(struct driver_data *dd) goto block_queue_alloc_tag_error; } - dd->disk = blk_mq_alloc_disk(&dd->tags, dd); + dd->disk = blk_mq_alloc_disk(&dd->tags, &lim, dd); if (IS_ERR(dd->disk)) { dev_err(&dd->pdev->dev, "Unable to allocate request queue\n"); @@ -3481,12 +3487,7 @@ skip_create_disk: /* Set device limits. */ blk_queue_flag_set(QUEUE_FLAG_NONROT, dd->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, dd->queue); - blk_queue_max_segments(dd->queue, MTIP_MAX_SG); - blk_queue_physical_block_size(dd->queue, 4096); - blk_queue_max_hw_sectors(dd->queue, 0xffff); - blk_queue_max_segment_size(dd->queue, 0x400000); dma_set_max_seg_size(&dd->pdev->dev, 0x400000); - blk_queue_io_min(dd->queue, 4096); /* Set the capacity of the device in 512 byte sectors. */ if (!(mtip_hw_get_capacity(dd, &capacity))) { diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c index d914156db2d8..27b2187e7a6d 100644 --- a/drivers/block/n64cart.c +++ b/drivers/block/n64cart.c @@ -114,6 +114,10 @@ static const struct block_device_operations n64cart_fops = { */ static int __init n64cart_probe(struct platform_device *pdev) { + struct queue_limits lim = { + .physical_block_size = 4096, + .logical_block_size = 4096, + }; struct gendisk *disk; int err = -ENOMEM; @@ -131,9 +135,11 @@ static int __init n64cart_probe(struct platform_device *pdev) if (IS_ERR(reg_base)) return PTR_ERR(reg_base); - disk = blk_alloc_disk(NUMA_NO_NODE); - if (!disk) + disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); goto out; + } disk->first_minor = 0; disk->flags = GENHD_FL_NO_PART; @@ -145,8 +151,6 @@ static int __init n64cart_probe(struct platform_device *pdev) set_disk_ro(disk, 1); blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); - blk_queue_physical_block_size(disk->queue, 4096); - blk_queue_logical_block_size(disk->queue, 4096); err = add_disk(disk); if (err) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 33a8f37bb6a1..9d4ec9273bf9 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -316,9 +316,12 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock, nsock->sent = 0; } -static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, +static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { + struct queue_limits lim; + int error; + if (!blksize) blksize = 1u << NBD_DEF_BLKSIZE_BITS; @@ -334,10 +337,16 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, if (!nbd->pid) return 0; + lim = queue_limits_start_update(nbd->disk->queue); if (nbd->config->flags & NBD_FLAG_SEND_TRIM) - blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); - blk_queue_logical_block_size(nbd->disk->queue, blksize); - blk_queue_physical_block_size(nbd->disk->queue, blksize); + lim.max_hw_discard_sectors = UINT_MAX; + else + lim.max_hw_discard_sectors = 0; + lim.logical_block_size = blksize; + lim.physical_block_size = blksize; + error = queue_limits_commit_update(nbd->disk->queue, &lim); + if (error) + return error; if (max_part) set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); @@ -346,6 +355,18 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, return 0; } +static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, + loff_t blksize) +{ + int error; + + blk_mq_freeze_queue(nbd->disk->queue); + error = __nbd_set_size(nbd, bytesize, blksize); + blk_mq_unfreeze_queue(nbd->disk->queue); + + return error; +} + static void nbd_complete_rq(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); @@ -1351,7 +1372,6 @@ static void nbd_config_put(struct nbd_device *nbd) nbd->config = NULL; nbd->tag_set.timeout = 0; - blk_queue_max_discard_sectors(nbd->disk->queue, 0); mutex_unlock(&nbd->config_lock); nbd_put(nbd); @@ -1783,6 +1803,12 @@ static const struct blk_mq_ops nbd_mq_ops = { static struct nbd_device *nbd_dev_add(int index, unsigned int refs) { + struct queue_limits lim = { + .max_hw_sectors = 65536, + .max_user_sectors = 256, + .max_segments = USHRT_MAX, + .max_segment_size = UINT_MAX, + }; struct nbd_device *nbd; struct gendisk *disk; int err = -ENOMEM; @@ -1823,7 +1849,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) if (err < 0) goto out_free_tags; - disk = blk_mq_alloc_disk(&nbd->tag_set, NULL); + disk = blk_mq_alloc_disk(&nbd->tag_set, &lim, NULL); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_free_idr; @@ -1843,11 +1869,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) * Tell the block layer that we are not a rotational device */ blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); - blk_queue_max_discard_sectors(disk->queue, 0); - blk_queue_max_segment_size(disk->queue, UINT_MAX); - blk_queue_max_segments(disk->queue, USHRT_MAX); - blk_queue_max_hw_sectors(disk->queue, 65536); - disk->queue->limits.max_sectors = 256; mutex_init(&nbd->config_lock); refcount_set(&nbd->config_refs, 0); @@ -2433,6 +2454,12 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) } dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST); + if (!dev_list) { + nlmsg_free(reply); + ret = -EMSGSIZE; + goto out; + } + if (index == -1) { ret = idr_for_each(&nbd_index_idr, &status_cb, reply); if (ret) { diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 36755f263e8e..71c39bcd872c 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -115,6 +115,18 @@ module_param_string(init_hctx, g_init_hctx_str, sizeof(g_init_hctx_str), 0444); MODULE_PARM_DESC(init_hctx, "Fault injection to fail hctx init. init_hctx=<interval>,<probability>,<space>,<times>"); #endif +/* + * Historic queue modes. + * + * These days nothing but NULL_Q_MQ is actually supported, but we keep it the + * enum for error reporting. + */ +enum { + NULL_Q_BIO = 0, + NULL_Q_RQ = 1, + NULL_Q_MQ = 2, +}; + static int g_queue_mode = NULL_Q_MQ; static int null_param_store_val(const char *str, int *val, int min, int max) @@ -165,8 +177,8 @@ static bool g_blocking; module_param_named(blocking, g_blocking, bool, 0444); MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device"); -static bool shared_tags; -module_param(shared_tags, bool, 0444); +static bool g_shared_tags; +module_param_named(shared_tags, g_shared_tags, bool, 0444); MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq"); static bool g_shared_tag_bitmap; @@ -426,6 +438,7 @@ NULLB_DEVICE_ATTR(zone_max_open, uint, NULL); NULLB_DEVICE_ATTR(zone_max_active, uint, NULL); NULLB_DEVICE_ATTR(virt_boundary, bool, NULL); NULLB_DEVICE_ATTR(no_sched, bool, NULL); +NULLB_DEVICE_ATTR(shared_tags, bool, NULL); NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL); static ssize_t nullb_device_power_show(struct config_item *item, char *page) @@ -571,6 +584,7 @@ static struct configfs_attribute *nullb_device_attrs[] = { &nullb_device_attr_zone_offline, &nullb_device_attr_virt_boundary, &nullb_device_attr_no_sched, + &nullb_device_attr_shared_tags, &nullb_device_attr_shared_tag_bitmap, NULL, }; @@ -653,10 +667,11 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page) "badblocks,blocking,blocksize,cache_size," "completion_nsec,discard,home_node,hw_queue_depth," "irqmode,max_sectors,mbps,memory_backed,no_sched," - "poll_queues,power,queue_mode,shared_tag_bitmap,size," - "submit_queues,use_per_node_hctx,virt_boundary,zoned," - "zone_capacity,zone_max_active,zone_max_open," - "zone_nr_conv,zone_offline,zone_readonly,zone_size\n"); + "poll_queues,power,queue_mode,shared_tag_bitmap," + "shared_tags,size,submit_queues,use_per_node_hctx," + "virt_boundary,zoned,zone_capacity,zone_max_active," + "zone_max_open,zone_nr_conv,zone_offline,zone_readonly," + "zone_size\n"); } CONFIGFS_ATTR_RO(memb_group_, features); @@ -738,6 +753,7 @@ static struct nullb_device *null_alloc_dev(void) dev->zone_max_active = g_zone_max_active; dev->virt_boundary = g_virt_boundary; dev->no_sched = g_no_sched; + dev->shared_tags = g_shared_tags; dev->shared_tag_bitmap = g_shared_tag_bitmap; return dev; } @@ -752,98 +768,11 @@ static void null_free_dev(struct nullb_device *dev) kfree(dev); } -static void put_tag(struct nullb_queue *nq, unsigned int tag) -{ - clear_bit_unlock(tag, nq->tag_map); - - if (waitqueue_active(&nq->wait)) - wake_up(&nq->wait); -} - -static unsigned int get_tag(struct nullb_queue *nq) -{ - unsigned int tag; - - do { - tag = find_first_zero_bit(nq->tag_map, nq->queue_depth); - if (tag >= nq->queue_depth) - return -1U; - } while (test_and_set_bit_lock(tag, nq->tag_map)); - - return tag; -} - -static void free_cmd(struct nullb_cmd *cmd) -{ - put_tag(cmd->nq, cmd->tag); -} - -static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer); - -static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq) -{ - struct nullb_cmd *cmd; - unsigned int tag; - - tag = get_tag(nq); - if (tag != -1U) { - cmd = &nq->cmds[tag]; - cmd->tag = tag; - cmd->error = BLK_STS_OK; - cmd->nq = nq; - if (nq->dev->irqmode == NULL_IRQ_TIMER) { - hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL); - cmd->timer.function = null_cmd_timer_expired; - } - return cmd; - } - - return NULL; -} - -static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, struct bio *bio) -{ - struct nullb_cmd *cmd; - DEFINE_WAIT(wait); - - do { - /* - * This avoids multiple return statements, multiple calls to - * __alloc_cmd() and a fast path call to prepare_to_wait(). - */ - cmd = __alloc_cmd(nq); - if (cmd) { - cmd->bio = bio; - return cmd; - } - prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE); - io_schedule(); - finish_wait(&nq->wait, &wait); - } while (1); -} - -static void end_cmd(struct nullb_cmd *cmd) -{ - int queue_mode = cmd->nq->dev->queue_mode; - - switch (queue_mode) { - case NULL_Q_MQ: - blk_mq_end_request(cmd->rq, cmd->error); - return; - case NULL_Q_BIO: - cmd->bio->bi_status = cmd->error; - bio_endio(cmd->bio); - break; - } - - free_cmd(cmd); -} - static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer) { - end_cmd(container_of(timer, struct nullb_cmd, timer)); + struct nullb_cmd *cmd = container_of(timer, struct nullb_cmd, timer); + blk_mq_end_request(blk_mq_rq_from_pdu(cmd), cmd->error); return HRTIMER_NORESTART; } @@ -856,7 +785,9 @@ static void null_cmd_end_timer(struct nullb_cmd *cmd) static void null_complete_rq(struct request *rq) { - end_cmd(blk_mq_rq_to_pdu(rq)); + struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); + + blk_mq_end_request(rq, cmd->error); } static struct nullb_page *null_alloc_page(void) @@ -1273,7 +1204,7 @@ static int null_transfer(struct nullb *nullb, struct page *page, static int null_handle_rq(struct nullb_cmd *cmd) { - struct request *rq = cmd->rq; + struct request *rq = blk_mq_rq_from_pdu(cmd); struct nullb *nullb = cmd->nq->dev->nullb; int err; unsigned int len; @@ -1298,63 +1229,21 @@ static int null_handle_rq(struct nullb_cmd *cmd) return 0; } -static int null_handle_bio(struct nullb_cmd *cmd) -{ - struct bio *bio = cmd->bio; - struct nullb *nullb = cmd->nq->dev->nullb; - int err; - unsigned int len; - sector_t sector = bio->bi_iter.bi_sector; - struct bio_vec bvec; - struct bvec_iter iter; - - spin_lock_irq(&nullb->lock); - bio_for_each_segment(bvec, bio, iter) { - len = bvec.bv_len; - err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset, - op_is_write(bio_op(bio)), sector, - bio->bi_opf & REQ_FUA); - if (err) { - spin_unlock_irq(&nullb->lock); - return err; - } - sector += len >> SECTOR_SHIFT; - } - spin_unlock_irq(&nullb->lock); - return 0; -} - -static void null_stop_queue(struct nullb *nullb) -{ - struct request_queue *q = nullb->q; - - if (nullb->dev->queue_mode == NULL_Q_MQ) - blk_mq_stop_hw_queues(q); -} - -static void null_restart_queue_async(struct nullb *nullb) -{ - struct request_queue *q = nullb->q; - - if (nullb->dev->queue_mode == NULL_Q_MQ) - blk_mq_start_stopped_hw_queues(q, true); -} - static inline blk_status_t null_handle_throttled(struct nullb_cmd *cmd) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; blk_status_t sts = BLK_STS_OK; - struct request *rq = cmd->rq; + struct request *rq = blk_mq_rq_from_pdu(cmd); if (!hrtimer_active(&nullb->bw_timer)) hrtimer_restart(&nullb->bw_timer); if (atomic_long_sub_return(blk_rq_bytes(rq), &nullb->cur_bytes) < 0) { - null_stop_queue(nullb); + blk_mq_stop_hw_queues(nullb->q); /* race with timer */ if (atomic_long_read(&nullb->cur_bytes) > 0) - null_restart_queue_async(nullb); + blk_mq_start_stopped_hw_queues(nullb->q, true); /* requeue request */ sts = BLK_STS_DEV_RESOURCE; } @@ -1381,37 +1270,29 @@ static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd, sector_t nr_sectors) { struct nullb_device *dev = cmd->nq->dev; - int err; if (op == REQ_OP_DISCARD) return null_handle_discard(dev, sector, nr_sectors); + return errno_to_blk_status(null_handle_rq(cmd)); - if (dev->queue_mode == NULL_Q_BIO) - err = null_handle_bio(cmd); - else - err = null_handle_rq(cmd); - - return errno_to_blk_status(err); } static void nullb_zero_read_cmd_buffer(struct nullb_cmd *cmd) { + struct request *rq = blk_mq_rq_from_pdu(cmd); struct nullb_device *dev = cmd->nq->dev; struct bio *bio; - if (dev->memory_backed) - return; - - if (dev->queue_mode == NULL_Q_BIO && bio_op(cmd->bio) == REQ_OP_READ) { - zero_fill_bio(cmd->bio); - } else if (req_op(cmd->rq) == REQ_OP_READ) { - __rq_for_each_bio(bio, cmd->rq) + if (!dev->memory_backed && req_op(rq) == REQ_OP_READ) { + __rq_for_each_bio(bio, rq) zero_fill_bio(bio); } } static inline void nullb_complete_cmd(struct nullb_cmd *cmd) { + struct request *rq = blk_mq_rq_from_pdu(cmd); + /* * Since root privileges are required to configure the null_blk * driver, it is fine that this driver does not initialize the @@ -1425,20 +1306,10 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd) /* Complete IO by inline, softirq or timer */ switch (cmd->nq->dev->irqmode) { case NULL_IRQ_SOFTIRQ: - switch (cmd->nq->dev->queue_mode) { - case NULL_Q_MQ: - blk_mq_complete_request(cmd->rq); - break; - case NULL_Q_BIO: - /* - * XXX: no proper submitting cpu information available. - */ - end_cmd(cmd); - break; - } + blk_mq_complete_request(rq); break; case NULL_IRQ_NONE: - end_cmd(cmd); + blk_mq_end_request(rq, cmd->error); break; case NULL_IRQ_TIMER: null_cmd_end_timer(cmd); @@ -1499,7 +1370,7 @@ static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer) return HRTIMER_NORESTART; atomic_long_set(&nullb->cur_bytes, mb_per_tick(mbps)); - null_restart_queue_async(nullb); + blk_mq_start_stopped_hw_queues(nullb->q, true); hrtimer_forward_now(&nullb->bw_timer, timer_interval); @@ -1516,26 +1387,6 @@ static void nullb_setup_bwtimer(struct nullb *nullb) hrtimer_start(&nullb->bw_timer, timer_interval, HRTIMER_MODE_REL); } -static struct nullb_queue *nullb_to_queue(struct nullb *nullb) -{ - int index = 0; - - if (nullb->nr_queues != 1) - index = raw_smp_processor_id() / ((nr_cpu_ids + nullb->nr_queues - 1) / nullb->nr_queues); - - return &nullb->queues[index]; -} - -static void null_submit_bio(struct bio *bio) -{ - sector_t sector = bio->bi_iter.bi_sector; - sector_t nr_sectors = bio_sectors(bio); - struct nullb *nullb = bio->bi_bdev->bd_disk->private_data; - struct nullb_queue *nq = nullb_to_queue(nullb); - - null_handle_cmd(alloc_cmd(nq, bio), sector, nr_sectors, bio_op(bio)); -} - #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION static bool should_timeout_request(struct request *rq) @@ -1655,7 +1506,7 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) blk_rq_sectors(req)); if (!blk_mq_add_to_batch(req, iob, (__force int) cmd->error, blk_mq_end_request_batch)) - end_cmd(cmd); + blk_mq_end_request(req, cmd->error); nr++; } @@ -1711,7 +1562,6 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cmd->timer.function = null_cmd_timer_expired; } - cmd->rq = rq; cmd->error = BLK_STS_OK; cmd->nq = nq; cmd->fake_timeout = should_timeout_request(rq) || @@ -1770,34 +1620,8 @@ static void null_queue_rqs(struct request **rqlist) *rqlist = requeue_list; } -static void cleanup_queue(struct nullb_queue *nq) -{ - bitmap_free(nq->tag_map); - kfree(nq->cmds); -} - -static void cleanup_queues(struct nullb *nullb) -{ - int i; - - for (i = 0; i < nullb->nr_queues; i++) - cleanup_queue(&nullb->queues[i]); - - kfree(nullb->queues); -} - -static void null_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) -{ - struct nullb_queue *nq = hctx->driver_data; - struct nullb *nullb = nq->dev->nullb; - - nullb->nr_queues--; -} - static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) { - init_waitqueue_head(&nq->wait); - nq->queue_depth = nullb->queue_depth; nq->dev = nullb->dev; INIT_LIST_HEAD(&nq->poll_list); spin_lock_init(&nq->poll_lock); @@ -1815,7 +1639,6 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, nq = &nullb->queues[hctx_idx]; hctx->driver_data = nq; null_init_queue(nullb, nq); - nullb->nr_queues++; return 0; } @@ -1828,7 +1651,6 @@ static const struct blk_mq_ops null_mq_ops = { .poll = null_poll, .map_queues = null_map_queues, .init_hctx = null_init_hctx, - .exit_hctx = null_exit_hctx, }; static void null_del_dev(struct nullb *nullb) @@ -1849,21 +1671,20 @@ static void null_del_dev(struct nullb *nullb) if (test_bit(NULLB_DEV_FL_THROTTLED, &nullb->dev->flags)) { hrtimer_cancel(&nullb->bw_timer); atomic_long_set(&nullb->cur_bytes, LONG_MAX); - null_restart_queue_async(nullb); + blk_mq_start_stopped_hw_queues(nullb->q, true); } put_disk(nullb->disk); - if (dev->queue_mode == NULL_Q_MQ && - nullb->tag_set == &nullb->__tag_set) + if (nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); - cleanup_queues(nullb); + kfree(nullb->queues); if (null_cache_active(nullb)) null_free_device_storage(nullb->dev, true); kfree(nullb); dev->nullb = NULL; } -static void null_config_discard(struct nullb *nullb) +static void null_config_discard(struct nullb *nullb, struct queue_limits *lim) { if (nullb->dev->discard == false) return; @@ -1880,43 +1701,14 @@ static void null_config_discard(struct nullb *nullb) return; } - blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9); + lim->max_hw_discard_sectors = UINT_MAX >> 9; } -static const struct block_device_operations null_bio_ops = { - .owner = THIS_MODULE, - .submit_bio = null_submit_bio, - .report_zones = null_report_zones, -}; - -static const struct block_device_operations null_rq_ops = { +static const struct block_device_operations null_ops = { .owner = THIS_MODULE, .report_zones = null_report_zones, }; -static int setup_commands(struct nullb_queue *nq) -{ - struct nullb_cmd *cmd; - int i; - - nq->cmds = kcalloc(nq->queue_depth, sizeof(*cmd), GFP_KERNEL); - if (!nq->cmds) - return -ENOMEM; - - nq->tag_map = bitmap_zalloc(nq->queue_depth, GFP_KERNEL); - if (!nq->tag_map) { - kfree(nq->cmds); - return -ENOMEM; - } - - for (i = 0; i < nq->queue_depth; i++) { - cmd = &nq->cmds[i]; - cmd->tag = -1U; - } - - return 0; -} - static int setup_queues(struct nullb *nullb) { int nqueues = nr_cpu_ids; @@ -1929,101 +1721,66 @@ static int setup_queues(struct nullb *nullb) if (!nullb->queues) return -ENOMEM; - nullb->queue_depth = nullb->dev->hw_queue_depth; return 0; } -static int init_driver_queues(struct nullb *nullb) +static int null_init_tag_set(struct blk_mq_tag_set *set, int poll_queues) { - struct nullb_queue *nq; - int i, ret = 0; - - for (i = 0; i < nullb->dev->submit_queues; i++) { - nq = &nullb->queues[i]; - - null_init_queue(nullb, nq); - - ret = setup_commands(nq); - if (ret) - return ret; - nullb->nr_queues++; + set->ops = &null_mq_ops; + set->cmd_size = sizeof(struct nullb_cmd); + set->timeout = 5 * HZ; + set->nr_maps = 1; + if (poll_queues) { + set->nr_hw_queues += poll_queues; + set->nr_maps += 2; } - return 0; + return blk_mq_alloc_tag_set(set); } -static int null_gendisk_register(struct nullb *nullb) +static int null_init_global_tag_set(void) { - sector_t size = ((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT; - struct gendisk *disk = nullb->disk; + int error; - set_capacity(disk, size); - - disk->major = null_major; - disk->first_minor = nullb->index; - disk->minors = 1; - if (queue_is_mq(nullb->q)) - disk->fops = &null_rq_ops; - else - disk->fops = &null_bio_ops; - disk->private_data = nullb; - strscpy_pad(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); + if (tag_set.ops) + return 0; - if (nullb->dev->zoned) { - int ret = null_register_zoned_dev(nullb); + tag_set.nr_hw_queues = g_submit_queues; + tag_set.queue_depth = g_hw_queue_depth; + tag_set.numa_node = g_home_node; + tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + if (g_no_sched) + tag_set.flags |= BLK_MQ_F_NO_SCHED; + if (g_shared_tag_bitmap) + tag_set.flags |= BLK_MQ_F_TAG_HCTX_SHARED; + if (g_blocking) + tag_set.flags |= BLK_MQ_F_BLOCKING; - if (ret) - return ret; - } - - return add_disk(disk); + error = null_init_tag_set(&tag_set, g_poll_queues); + if (error) + tag_set.ops = NULL; + return error; } -static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set) +static int null_setup_tagset(struct nullb *nullb) { - unsigned int flags = BLK_MQ_F_SHOULD_MERGE; - int hw_queues, numa_node; - unsigned int queue_depth; - int poll_queues; - - if (nullb) { - hw_queues = nullb->dev->submit_queues; - poll_queues = nullb->dev->poll_queues; - queue_depth = nullb->dev->hw_queue_depth; - numa_node = nullb->dev->home_node; - if (nullb->dev->no_sched) - flags |= BLK_MQ_F_NO_SCHED; - if (nullb->dev->shared_tag_bitmap) - flags |= BLK_MQ_F_TAG_HCTX_SHARED; - if (nullb->dev->blocking) - flags |= BLK_MQ_F_BLOCKING; - } else { - hw_queues = g_submit_queues; - poll_queues = g_poll_queues; - queue_depth = g_hw_queue_depth; - numa_node = g_home_node; - if (g_no_sched) - flags |= BLK_MQ_F_NO_SCHED; - if (g_shared_tag_bitmap) - flags |= BLK_MQ_F_TAG_HCTX_SHARED; - if (g_blocking) - flags |= BLK_MQ_F_BLOCKING; - } - - set->ops = &null_mq_ops; - set->cmd_size = sizeof(struct nullb_cmd); - set->flags = flags; - set->driver_data = nullb; - set->nr_hw_queues = hw_queues; - set->queue_depth = queue_depth; - set->numa_node = numa_node; - if (poll_queues) { - set->nr_hw_queues += poll_queues; - set->nr_maps = 3; - } else { - set->nr_maps = 1; + if (nullb->dev->shared_tags) { + nullb->tag_set = &tag_set; + return null_init_global_tag_set(); } - return blk_mq_alloc_tag_set(set); + nullb->tag_set = &nullb->__tag_set; + nullb->tag_set->driver_data = nullb; + nullb->tag_set->nr_hw_queues = nullb->dev->submit_queues; + nullb->tag_set->queue_depth = nullb->dev->hw_queue_depth; + nullb->tag_set->numa_node = nullb->dev->home_node; + nullb->tag_set->flags = BLK_MQ_F_SHOULD_MERGE; + if (nullb->dev->no_sched) + nullb->tag_set->flags |= BLK_MQ_F_NO_SCHED; + if (nullb->dev->shared_tag_bitmap) + nullb->tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED; + if (nullb->dev->blocking) + nullb->tag_set->flags |= BLK_MQ_F_BLOCKING; + return null_init_tag_set(nullb->tag_set, nullb->dev->poll_queues); } static int null_validate_conf(struct nullb_device *dev) @@ -2032,11 +1789,15 @@ static int null_validate_conf(struct nullb_device *dev) pr_err("legacy IO path is no longer available\n"); return -EINVAL; } + if (dev->queue_mode == NULL_Q_BIO) { + pr_err("BIO-based IO path is no longer available, using blk-mq instead.\n"); + dev->queue_mode = NULL_Q_MQ; + } dev->blocksize = round_down(dev->blocksize, 512); dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096); - if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) { + if (dev->use_per_node_hctx) { if (dev->submit_queues != nr_online_nodes) dev->submit_queues = nr_online_nodes; } else if (dev->submit_queues > nr_cpu_ids) @@ -2048,8 +1809,6 @@ static int null_validate_conf(struct nullb_device *dev) if (dev->poll_queues > g_poll_queues) dev->poll_queues = g_poll_queues; dev->prev_poll_queues = dev->poll_queues; - - dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ); dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER); /* Do memory allocation, so set blocking */ @@ -2060,9 +1819,6 @@ static int null_validate_conf(struct nullb_device *dev) dev->cache_size = min_t(unsigned long, ULONG_MAX / 1024 / 1024, dev->cache_size); dev->mbps = min_t(unsigned int, 1024 * 40, dev->mbps); - /* can not stop a queue */ - if (dev->queue_mode == NULL_Q_BIO) - dev->mbps = 0; if (dev->zoned && (!dev->zone_size || !is_power_of_2(dev->zone_size))) { @@ -2102,6 +1858,12 @@ static bool null_setup_fault(void) static int null_add_dev(struct nullb_device *dev) { + struct queue_limits lim = { + .logical_block_size = dev->blocksize, + .physical_block_size = dev->blocksize, + .max_hw_sectors = dev->max_sectors, + }; + struct nullb *nullb; int rv; @@ -2123,36 +1885,25 @@ static int null_add_dev(struct nullb_device *dev) if (rv) goto out_free_nullb; - if (dev->queue_mode == NULL_Q_MQ) { - if (shared_tags) { - nullb->tag_set = &tag_set; - rv = 0; - } else { - nullb->tag_set = &nullb->__tag_set; - rv = null_init_tag_set(nullb, nullb->tag_set); - } + rv = null_setup_tagset(nullb); + if (rv) + goto out_cleanup_queues; + if (dev->virt_boundary) + lim.virt_boundary_mask = PAGE_SIZE - 1; + null_config_discard(nullb, &lim); + if (dev->zoned) { + rv = null_init_zoned_dev(dev, &lim); if (rv) - goto out_cleanup_queues; - - nullb->tag_set->timeout = 5 * HZ; - nullb->disk = blk_mq_alloc_disk(nullb->tag_set, nullb); - if (IS_ERR(nullb->disk)) { - rv = PTR_ERR(nullb->disk); goto out_cleanup_tags; - } - nullb->q = nullb->disk->queue; - } else if (dev->queue_mode == NULL_Q_BIO) { - rv = -ENOMEM; - nullb->disk = blk_alloc_disk(nullb->dev->home_node); - if (!nullb->disk) - goto out_cleanup_queues; + } - nullb->q = nullb->disk->queue; - rv = init_driver_queues(nullb); - if (rv) - goto out_cleanup_disk; + nullb->disk = blk_mq_alloc_disk(nullb->tag_set, &lim, nullb); + if (IS_ERR(nullb->disk)) { + rv = PTR_ERR(nullb->disk); + goto out_cleanup_zone; } + nullb->q = nullb->disk->queue; if (dev->mbps) { set_bit(NULLB_DEV_FL_THROTTLED, &dev->flags); @@ -2164,12 +1915,6 @@ static int null_add_dev(struct nullb_device *dev) blk_queue_write_cache(nullb->q, true, true); } - if (dev->zoned) { - rv = null_init_zoned_dev(dev, nullb->q); - if (rv) - goto out_cleanup_disk; - } - nullb->q->queuedata = nullb; blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q); @@ -2177,22 +1922,12 @@ static int null_add_dev(struct nullb_device *dev) rv = ida_alloc(&nullb_indexes, GFP_KERNEL); if (rv < 0) { mutex_unlock(&lock); - goto out_cleanup_zone; + goto out_cleanup_disk; } nullb->index = rv; dev->index = rv; mutex_unlock(&lock); - blk_queue_logical_block_size(nullb->q, dev->blocksize); - blk_queue_physical_block_size(nullb->q, dev->blocksize); - if (dev->max_sectors) - blk_queue_max_hw_sectors(nullb->q, dev->max_sectors); - - if (dev->virt_boundary) - blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1); - - null_config_discard(nullb); - if (config_item_name(&dev->group.cg_item)) { /* Use configfs dir name as the device name */ snprintf(nullb->disk_name, sizeof(nullb->disk_name), @@ -2201,7 +1936,22 @@ static int null_add_dev(struct nullb_device *dev) sprintf(nullb->disk_name, "nullb%d", nullb->index); } - rv = null_gendisk_register(nullb); + set_capacity(nullb->disk, + ((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT); + nullb->disk->major = null_major; + nullb->disk->first_minor = nullb->index; + nullb->disk->minors = 1; + nullb->disk->fops = &null_ops; + nullb->disk->private_data = nullb; + strscpy_pad(nullb->disk->disk_name, nullb->disk_name, DISK_NAME_LEN); + + if (nullb->dev->zoned) { + rv = null_register_zoned_dev(nullb); + if (rv) + goto out_ida_free; + } + + rv = add_disk(nullb->disk); if (rv) goto out_ida_free; @@ -2220,10 +1970,10 @@ out_cleanup_zone: out_cleanup_disk: put_disk(nullb->disk); out_cleanup_tags: - if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set) + if (nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); out_cleanup_queues: - cleanup_queues(nullb); + kfree(nullb->queues); out_free_nullb: kfree(nullb); dev->nullb = NULL; @@ -2299,7 +2049,7 @@ static int __init null_init(void) return -EINVAL; } - if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) { + if (g_use_per_node_hctx) { if (g_submit_queues != nr_online_nodes) { pr_warn("submit_queues param is set to %u.\n", nr_online_nodes); @@ -2311,18 +2061,12 @@ static int __init null_init(void) g_submit_queues = 1; } - if (g_queue_mode == NULL_Q_MQ && shared_tags) { - ret = null_init_tag_set(NULL, &tag_set); - if (ret) - return ret; - } - config_group_init(&nullb_subsys.su_group); mutex_init(&nullb_subsys.su_mutex); ret = configfs_register_subsystem(&nullb_subsys); if (ret) - goto err_tagset; + return ret; mutex_init(&lock); @@ -2349,9 +2093,6 @@ err_dev: unregister_blkdev(null_major, "nullb"); err_conf: configfs_unregister_subsystem(&nullb_subsys); -err_tagset: - if (g_queue_mode == NULL_Q_MQ && shared_tags) - blk_mq_free_tag_set(&tag_set); return ret; } @@ -2370,7 +2111,7 @@ static void __exit null_exit(void) } mutex_unlock(&lock); - if (g_queue_mode == NULL_Q_MQ && shared_tags) + if (tag_set.ops) blk_mq_free_tag_set(&tag_set); } diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index 929f659dd255..477b97746823 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -16,11 +16,6 @@ #include <linux/mutex.h> struct nullb_cmd { - union { - struct request *rq; - struct bio *bio; - }; - unsigned int tag; blk_status_t error; bool fake_timeout; struct nullb_queue *nq; @@ -28,16 +23,11 @@ struct nullb_cmd { }; struct nullb_queue { - unsigned long *tag_map; - wait_queue_head_t wait; - unsigned int queue_depth; struct nullb_device *dev; unsigned int requeue_selection; struct list_head poll_list; spinlock_t poll_lock; - - struct nullb_cmd *cmds; }; struct nullb_zone { @@ -60,13 +50,6 @@ struct nullb_zone { unsigned int capacity; }; -/* Queue modes */ -enum { - NULL_Q_BIO = 0, - NULL_Q_RQ = 1, - NULL_Q_MQ = 2, -}; - struct nullb_device { struct nullb *nullb; struct config_group group; @@ -119,6 +102,7 @@ struct nullb_device { bool zoned; /* if device is zoned */ bool virt_boundary; /* virtual boundary on/off for the device */ bool no_sched; /* no IO scheduler for the device */ + bool shared_tags; /* share tag set between devices for blk-mq */ bool shared_tag_bitmap; /* use hostwide shared tags */ }; @@ -130,14 +114,12 @@ struct nullb { struct gendisk *disk; struct blk_mq_tag_set *tag_set; struct blk_mq_tag_set __tag_set; - unsigned int queue_depth; atomic_long_t cur_bytes; struct hrtimer bw_timer; unsigned long cache_flush_pos; spinlock_t lock; struct nullb_queue *queues; - unsigned int nr_queues; char disk_name[DISK_NAME_LEN]; }; @@ -147,7 +129,7 @@ blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op, sector_t sector, unsigned int nr_sectors); #ifdef CONFIG_BLK_DEV_ZONED -int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q); +int null_init_zoned_dev(struct nullb_device *dev, struct queue_limits *lim); int null_register_zoned_dev(struct nullb *nullb); void null_free_zoned_dev(struct nullb_device *dev); int null_report_zones(struct gendisk *disk, sector_t sector, @@ -160,7 +142,7 @@ ssize_t zone_cond_store(struct nullb_device *dev, const char *page, size_t count, enum blk_zone_cond cond); #else static inline int null_init_zoned_dev(struct nullb_device *dev, - struct request_queue *q) + struct queue_limits *lim) { pr_err("CONFIG_BLK_DEV_ZONED not enabled\n"); return -EINVAL; diff --git a/drivers/block/null_blk/trace.h b/drivers/block/null_blk/trace.h index 6b2b370e786f..ef2d05d5f0df 100644 --- a/drivers/block/null_blk/trace.h +++ b/drivers/block/null_blk/trace.h @@ -41,10 +41,11 @@ TRACE_EVENT(nullb_zone_op, __field(unsigned int, zone_cond) ), TP_fast_assign( - __entry->op = req_op(cmd->rq); + __entry->op = req_op(blk_mq_rq_from_pdu(cmd)); __entry->zone_no = zone_no; __entry->zone_cond = zone_cond; - __assign_disk_name(__entry->disk, cmd->rq->q->disk); + __assign_disk_name(__entry->disk, + blk_mq_rq_from_pdu(cmd)->q->disk); ), TP_printk("%s req=%-15s zone_no=%u zone_cond=%-10s", __print_disk_name(__entry->disk), diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index 6f5e0994862e..1689e2584104 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -58,7 +58,8 @@ static inline void null_unlock_zone(struct nullb_device *dev, mutex_unlock(&zone->mutex); } -int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) +int null_init_zoned_dev(struct nullb_device *dev, + struct queue_limits *lim) { sector_t dev_capacity_sects, zone_capacity_sects; struct nullb_zone *zone; @@ -151,27 +152,22 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) sector += dev->zone_size_sects; } + lim->zoned = true; + lim->chunk_sectors = dev->zone_size_sects; + lim->max_zone_append_sectors = dev->zone_size_sects; + lim->max_open_zones = dev->zone_max_open; + lim->max_active_zones = dev->zone_max_active; return 0; } int null_register_zoned_dev(struct nullb *nullb) { - struct nullb_device *dev = nullb->dev; struct request_queue *q = nullb->q; - disk_set_zoned(nullb->disk); blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q); blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE); - blk_queue_chunk_sectors(q, dev->zone_size_sects); nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0); - blk_queue_max_zone_append_sectors(q, dev->zone_size_sects); - disk_set_max_open_zones(nullb->disk, dev->zone_max_open); - disk_set_max_active_zones(nullb->disk, dev->zone_max_active); - - if (queue_is_mq(q)) - return blk_revalidate_disk_zones(nullb->disk, NULL); - - return 0; + return blk_revalidate_disk_zones(nullb->disk, NULL); } void null_free_zoned_dev(struct nullb_device *dev) @@ -394,10 +390,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, */ if (append) { sector = zone->wp; - if (dev->queue_mode == NULL_Q_MQ) - cmd->rq->__sector = sector; - else - cmd->bio->bi_iter.bi_sector = sector; + blk_mq_rq_from_pdu(cmd)->__sector = sector; } else if (sector != zone->wp) { ret = BLK_STS_IOERR; goto unlock; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index d56d972aadb3..21728e9ea5c3 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -340,8 +340,8 @@ static ssize_t device_map_show(const struct class *c, const struct class_attribu n += sysfs_emit_at(data, n, "%s %u:%u %u:%u\n", pd->disk->disk_name, MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev), - MAJOR(pd->bdev_handle->bdev->bd_dev), - MINOR(pd->bdev_handle->bdev->bd_dev)); + MAJOR(file_bdev(pd->bdev_file)->bd_dev), + MINOR(file_bdev(pd->bdev_file)->bd_dev)); } mutex_unlock(&ctl_mutex); return n; @@ -438,7 +438,7 @@ static int pkt_seq_show(struct seq_file *m, void *p) int states[PACKET_NUM_STATES]; seq_printf(m, "Writer %s mapped to %pg:\n", pd->disk->disk_name, - pd->bdev_handle->bdev); + file_bdev(pd->bdev_file)); seq_printf(m, "\nSettings:\n"); seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2); @@ -715,7 +715,7 @@ static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *nod */ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc) { - struct request_queue *q = bdev_get_queue(pd->bdev_handle->bdev); + struct request_queue *q = bdev_get_queue(file_bdev(pd->bdev_file)); struct scsi_cmnd *scmd; struct request *rq; int ret = 0; @@ -828,6 +828,12 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd, */ static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio) { + /* + * Some CDRW drives can not handle writes larger than one packet, + * even if the size is a multiple of the packet size. + */ + bio->bi_opf |= REQ_NOMERGE; + spin_lock(&pd->iosched.lock); if (bio_data_dir(bio) == READ) bio_list_add(&pd->iosched.read_queue, bio); @@ -1048,7 +1054,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) continue; bio = pkt->r_bios[f]; - bio_init(bio, pd->bdev_handle->bdev, bio->bi_inline_vecs, 1, + bio_init(bio, file_bdev(pd->bdev_file), bio->bi_inline_vecs, 1, REQ_OP_READ); bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9); bio->bi_end_io = pkt_end_io_read; @@ -1264,7 +1270,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) struct device *ddev = disk_to_dev(pd->disk); int f; - bio_init(pkt->w_bio, pd->bdev_handle->bdev, pkt->w_bio->bi_inline_vecs, + bio_init(pkt->w_bio, file_bdev(pd->bdev_file), pkt->w_bio->bi_inline_vecs, pkt->frames, REQ_OP_WRITE); pkt->w_bio->bi_iter.bi_sector = pkt->sector; pkt->w_bio->bi_end_io = pkt_end_io_packet_write; @@ -2162,20 +2168,20 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write) int ret; long lba; struct request_queue *q; - struct bdev_handle *bdev_handle; + struct file *bdev_file; /* * We need to re-open the cdrom device without O_NONBLOCK to be able * to read/write from/to it. It is already opened in O_NONBLOCK mode * so open should not fail. */ - bdev_handle = bdev_open_by_dev(pd->bdev_handle->bdev->bd_dev, + bdev_file = bdev_file_open_by_dev(file_bdev(pd->bdev_file)->bd_dev, BLK_OPEN_READ, pd, NULL); - if (IS_ERR(bdev_handle)) { - ret = PTR_ERR(bdev_handle); + if (IS_ERR(bdev_file)) { + ret = PTR_ERR(bdev_file); goto out; } - pd->open_bdev_handle = bdev_handle; + pd->f_open_bdev = bdev_file; ret = pkt_get_last_written(pd, &lba); if (ret) { @@ -2184,18 +2190,13 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write) } set_capacity(pd->disk, lba << 2); - set_capacity_and_notify(pd->bdev_handle->bdev->bd_disk, lba << 2); + set_capacity_and_notify(file_bdev(pd->bdev_file)->bd_disk, lba << 2); - q = bdev_get_queue(pd->bdev_handle->bdev); + q = bdev_get_queue(file_bdev(pd->bdev_file)); if (write) { ret = pkt_open_write(pd); if (ret) goto out_putdev; - /* - * Some CDRW drives can not handle writes larger than one packet, - * even if the size is a multiple of the packet size. - */ - blk_queue_max_hw_sectors(q, pd->settings.size); set_bit(PACKET_WRITABLE, &pd->flags); } else { pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); @@ -2218,7 +2219,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write) return 0; out_putdev: - bdev_release(bdev_handle); + fput(bdev_file); out: return ret; } @@ -2237,8 +2238,8 @@ static void pkt_release_dev(struct pktcdvd_device *pd, int flush) pkt_lock_door(pd, 0); pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); - bdev_release(pd->open_bdev_handle); - pd->open_bdev_handle = NULL; + fput(pd->f_open_bdev); + pd->f_open_bdev = NULL; pkt_shrink_pktlist(pd); } @@ -2326,7 +2327,7 @@ static void pkt_end_io_read_cloned(struct bio *bio) static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio) { - struct bio *cloned_bio = bio_alloc_clone(pd->bdev_handle->bdev, bio, + struct bio *cloned_bio = bio_alloc_clone(file_bdev(pd->bdev_file), bio, GFP_NOIO, &pkt_bio_set); struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO); @@ -2338,9 +2339,9 @@ static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio) pkt_queue_bio(pd, cloned_bio); } -static void pkt_make_request_write(struct request_queue *q, struct bio *bio) +static void pkt_make_request_write(struct bio *bio) { - struct pktcdvd_device *pd = q->queuedata; + struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data; sector_t zone; struct packet_data *pkt; int was_empty, blocked_bio; @@ -2432,7 +2433,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) static void pkt_submit_bio(struct bio *bio) { - struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata; + struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data; struct device *ddev = disk_to_dev(pd->disk); struct bio *split; @@ -2476,7 +2477,7 @@ static void pkt_submit_bio(struct bio *bio) split = bio; } - pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split); + pkt_make_request_write(split); } while (split != bio); return; @@ -2484,20 +2485,11 @@ end_io: bio_io_error(bio); } -static void pkt_init_queue(struct pktcdvd_device *pd) -{ - struct request_queue *q = pd->disk->queue; - - blk_queue_logical_block_size(q, CD_FRAMESIZE); - blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS); - q->queuedata = pd; -} - static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) { struct device *ddev = disk_to_dev(pd->disk); int i; - struct bdev_handle *bdev_handle; + struct file *bdev_file; struct scsi_device *sdev; if (pd->pkt_dev == dev) { @@ -2508,9 +2500,9 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) struct pktcdvd_device *pd2 = pkt_devs[i]; if (!pd2) continue; - if (pd2->bdev_handle->bdev->bd_dev == dev) { + if (file_bdev(pd2->bdev_file)->bd_dev == dev) { dev_err(ddev, "%pg already setup\n", - pd2->bdev_handle->bdev); + file_bdev(pd2->bdev_file)); return -EBUSY; } if (pd2->pkt_dev == dev) { @@ -2519,13 +2511,13 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) } } - bdev_handle = bdev_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_NDELAY, + bdev_file = bdev_file_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_NDELAY, NULL, NULL); - if (IS_ERR(bdev_handle)) - return PTR_ERR(bdev_handle); - sdev = scsi_device_from_queue(bdev_handle->bdev->bd_disk->queue); + if (IS_ERR(bdev_file)) + return PTR_ERR(bdev_file); + sdev = scsi_device_from_queue(file_bdev(bdev_file)->bd_disk->queue); if (!sdev) { - bdev_release(bdev_handle); + fput(bdev_file); return -EINVAL; } put_device(&sdev->sdev_gendev); @@ -2533,10 +2525,8 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); - pd->bdev_handle = bdev_handle; - set_blocksize(bdev_handle->bdev, CD_FRAMESIZE); - - pkt_init_queue(pd); + pd->bdev_file = bdev_file; + set_blocksize(file_bdev(bdev_file), CD_FRAMESIZE); atomic_set(&pd->cdrw.pending_bios, 0); pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name); @@ -2546,11 +2536,11 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) } proc_create_single_data(pd->disk->disk_name, 0, pkt_proc, pkt_seq_show, pd); - dev_notice(ddev, "writer mapped to %pg\n", bdev_handle->bdev); + dev_notice(ddev, "writer mapped to %pg\n", file_bdev(bdev_file)); return 0; out_mem: - bdev_release(bdev_handle); + fput(bdev_file); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return -ENOMEM; @@ -2605,9 +2595,9 @@ static unsigned int pkt_check_events(struct gendisk *disk, if (!pd) return 0; - if (!pd->bdev_handle) + if (!pd->bdev_file) return 0; - attached_disk = pd->bdev_handle->bdev->bd_disk; + attached_disk = file_bdev(pd->bdev_file)->bd_disk; if (!attached_disk || !attached_disk->fops->check_events) return 0; return attached_disk->fops->check_events(attached_disk, clearing); @@ -2634,6 +2624,10 @@ static const struct block_device_operations pktcdvd_ops = { */ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) { + struct queue_limits lim = { + .max_hw_sectors = PACKET_MAX_SECTORS, + .logical_block_size = CD_FRAMESIZE, + }; int idx; int ret = -ENOMEM; struct pktcdvd_device *pd; @@ -2673,10 +2667,11 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) pd->write_congestion_on = write_congestion_on; pd->write_congestion_off = write_congestion_off; - ret = -ENOMEM; - disk = blk_alloc_disk(NUMA_NO_NODE); - if (!disk) + disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(disk)) { + ret = PTR_ERR(disk); goto out_mem; + } pd->disk = disk; disk->major = pktdev_major; disk->first_minor = idx; @@ -2692,7 +2687,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) goto out_mem2; /* inherit events of the host device */ - disk->events = pd->bdev_handle->bdev->bd_disk->events; + disk->events = file_bdev(pd->bdev_file)->bd_disk->events; ret = add_disk(disk); if (ret) @@ -2757,7 +2752,7 @@ static int pkt_remove_dev(dev_t pkt_dev) pkt_debugfs_dev_remove(pd); pkt_sysfs_dev_remove(pd); - bdev_release(pd->bdev_handle); + fput(pd->bdev_file); remove_proc_entry(pd->disk->disk_name, pkt_proc); dev_notice(ddev, "writer unmapped\n"); @@ -2784,7 +2779,7 @@ static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd) pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index); if (pd) { - ctrl_cmd->dev = new_encode_dev(pd->bdev_handle->bdev->bd_dev); + ctrl_cmd->dev = new_encode_dev(file_bdev(pd->bdev_file)->bd_dev); ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev); } else { ctrl_cmd->dev = 0; diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 36d7b36c60c7..b810ac0a5c4b 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -382,6 +382,14 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) struct ps3disk_private *priv; int error; unsigned int devidx; + struct queue_limits lim = { + .logical_block_size = dev->blk_size, + .max_hw_sectors = dev->bounce_size >> 9, + .max_segments = -1, + .max_segment_size = dev->bounce_size, + .dma_alignment = dev->blk_size - 1, + }; + struct request_queue *queue; struct gendisk *gendisk; @@ -431,7 +439,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) if (error) goto fail_teardown; - gendisk = blk_mq_alloc_disk(&priv->tag_set, dev); + gendisk = blk_mq_alloc_disk(&priv->tag_set, &lim, dev); if (IS_ERR(gendisk)) { dev_err(&dev->sbd.core, "%s:%u: blk_mq_alloc_disk failed\n", __func__, __LINE__); @@ -441,15 +449,8 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) queue = gendisk->queue; - blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9); - blk_queue_dma_alignment(queue, dev->blk_size-1); - blk_queue_logical_block_size(queue, dev->blk_size); - blk_queue_write_cache(queue, true, false); - blk_queue_max_segments(queue, -1); - blk_queue_max_segment_size(queue, dev->bounce_size); - priv->gendisk = gendisk; gendisk->major = ps3disk_major; gendisk->first_minor = devidx * PS3DISK_MINORS; diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 38d42af01b25..bdcf083b45e2 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -730,10 +730,10 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) ps3vram_proc_init(dev); - gendisk = blk_alloc_disk(NUMA_NO_NODE); - if (!gendisk) { + gendisk = blk_alloc_disk(NULL, NUMA_NO_NODE); + if (IS_ERR(gendisk)) { dev_err(&dev->core, "blk_alloc_disk failed\n"); - error = -ENOMEM; + error = PTR_ERR(gendisk); goto out_cache_cleanup; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 12b5d53ec856..26ff5cd2bf0a 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -575,7 +575,7 @@ static const struct attribute_group rbd_bus_group = { }; __ATTRIBUTE_GROUPS(rbd_bus); -static struct bus_type rbd_bus_type = { +static const struct bus_type rbd_bus_type = { .name = "rbd", .bus_groups = rbd_bus_groups, }; @@ -4952,6 +4952,14 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) struct request_queue *q; unsigned int objset_bytes = rbd_dev->layout.object_size * rbd_dev->layout.stripe_count; + struct queue_limits lim = { + .max_hw_sectors = objset_bytes >> SECTOR_SHIFT, + .max_user_sectors = objset_bytes >> SECTOR_SHIFT, + .io_min = rbd_dev->opts->alloc_size, + .io_opt = rbd_dev->opts->alloc_size, + .max_segments = USHRT_MAX, + .max_segment_size = UINT_MAX, + }; int err; memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set)); @@ -4966,7 +4974,13 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) if (err) return err; - disk = blk_mq_alloc_disk(&rbd_dev->tag_set, rbd_dev); + if (rbd_dev->opts->trim) { + lim.discard_granularity = rbd_dev->opts->alloc_size; + lim.max_hw_discard_sectors = objset_bytes >> SECTOR_SHIFT; + lim.max_write_zeroes_sectors = objset_bytes >> SECTOR_SHIFT; + } + + disk = blk_mq_alloc_disk(&rbd_dev->tag_set, &lim, rbd_dev); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_tag_set; @@ -4987,19 +5001,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */ - blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT); - q->limits.max_sectors = queue_max_hw_sectors(q); - blk_queue_max_segments(q, USHRT_MAX); - blk_queue_max_segment_size(q, UINT_MAX); - blk_queue_io_min(q, rbd_dev->opts->alloc_size); - blk_queue_io_opt(q, rbd_dev->opts->alloc_size); - - if (rbd_dev->opts->trim) { - q->limits.discard_granularity = rbd_dev->opts->alloc_size; - blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT); - blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT); - } - if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 4044c369d22a..b7ffe03c6160 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1329,43 +1329,6 @@ static void rnbd_init_mq_hw_queues(struct rnbd_clt_dev *dev) } } -static void setup_request_queue(struct rnbd_clt_dev *dev, - struct rnbd_msg_open_rsp *rsp) -{ - blk_queue_logical_block_size(dev->queue, - le16_to_cpu(rsp->logical_block_size)); - blk_queue_physical_block_size(dev->queue, - le16_to_cpu(rsp->physical_block_size)); - blk_queue_max_hw_sectors(dev->queue, - dev->sess->max_io_size / SECTOR_SIZE); - - /* - * we don't support discards to "discontiguous" segments - * in on request - */ - blk_queue_max_discard_segments(dev->queue, 1); - - blk_queue_max_discard_sectors(dev->queue, - le32_to_cpu(rsp->max_discard_sectors)); - dev->queue->limits.discard_granularity = - le32_to_cpu(rsp->discard_granularity); - dev->queue->limits.discard_alignment = - le32_to_cpu(rsp->discard_alignment); - if (le16_to_cpu(rsp->secure_discard)) - blk_queue_max_secure_erase_sectors(dev->queue, - le32_to_cpu(rsp->max_discard_sectors)); - blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue); - blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue); - blk_queue_max_segments(dev->queue, dev->sess->max_segments); - blk_queue_io_opt(dev->queue, dev->sess->max_io_size); - blk_queue_virt_boundary(dev->queue, SZ_4K - 1); - blk_queue_write_cache(dev->queue, - !!(rsp->cache_policy & RNBD_WRITEBACK), - !!(rsp->cache_policy & RNBD_FUA)); - blk_queue_max_write_zeroes_sectors(dev->queue, - le32_to_cpu(rsp->max_write_zeroes_sectors)); -} - static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, struct rnbd_msg_open_rsp *rsp, int idx) { @@ -1403,18 +1366,41 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, static int rnbd_client_setup_device(struct rnbd_clt_dev *dev, struct rnbd_msg_open_rsp *rsp) { + struct queue_limits lim = { + .logical_block_size = le16_to_cpu(rsp->logical_block_size), + .physical_block_size = le16_to_cpu(rsp->physical_block_size), + .io_opt = dev->sess->max_io_size, + .max_hw_sectors = dev->sess->max_io_size / SECTOR_SIZE, + .max_hw_discard_sectors = le32_to_cpu(rsp->max_discard_sectors), + .discard_granularity = le32_to_cpu(rsp->discard_granularity), + .discard_alignment = le32_to_cpu(rsp->discard_alignment), + .max_segments = dev->sess->max_segments, + .virt_boundary_mask = SZ_4K - 1, + .max_write_zeroes_sectors = + le32_to_cpu(rsp->max_write_zeroes_sectors), + }; int idx = dev->clt_device_id; dev->size = le64_to_cpu(rsp->nsectors) * le16_to_cpu(rsp->logical_block_size); - dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, dev); + if (rsp->secure_discard) { + lim.max_secure_erase_sectors = + le32_to_cpu(rsp->max_discard_sectors); + } + + dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, &lim, dev); if (IS_ERR(dev->gd)) return PTR_ERR(dev->gd); dev->queue = dev->gd->queue; rnbd_init_mq_hw_queues(dev); - setup_request_queue(dev, rsp); + blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue); + blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue); + blk_queue_write_cache(dev->queue, + !!(rsp->cache_policy & RNBD_WRITEBACK), + !!(rsp->cache_policy & RNBD_FUA)); + return rnbd_clt_setup_gen_disk(dev, rsp, idx); } diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 3a0d5dcec6f2..f6e3a3c4b76c 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -145,7 +145,7 @@ static int process_rdma(struct rnbd_srv_session *srv_sess, priv->sess_dev = sess_dev; priv->id = id; - bio = bio_alloc(sess_dev->bdev_handle->bdev, 1, + bio = bio_alloc(file_bdev(sess_dev->bdev_file), 1, rnbd_to_bio_flags(le32_to_cpu(msg->rw)), GFP_KERNEL); if (bio_add_page(bio, virt_to_page(data), datalen, offset_in_page(data)) != datalen) { @@ -219,7 +219,7 @@ void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id) rnbd_put_sess_dev(sess_dev); wait_for_completion(&dc); /* wait for inflights to drop to zero */ - bdev_release(sess_dev->bdev_handle); + fput(sess_dev->bdev_file); mutex_lock(&sess_dev->dev->lock); list_del(&sess_dev->dev_list); if (!sess_dev->readonly) @@ -534,7 +534,7 @@ rnbd_srv_get_or_create_srv_dev(struct block_device *bdev, static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, struct rnbd_srv_sess_dev *sess_dev) { - struct block_device *bdev = sess_dev->bdev_handle->bdev; + struct block_device *bdev = file_bdev(sess_dev->bdev_file); rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP); rsp->device_id = cpu_to_le32(sess_dev->device_id); @@ -560,7 +560,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, static struct rnbd_srv_sess_dev * rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess, const struct rnbd_msg_open *open_msg, - struct bdev_handle *handle, bool readonly, + struct file *bdev_file, bool readonly, struct rnbd_srv_dev *srv_dev) { struct rnbd_srv_sess_dev *sdev = rnbd_sess_dev_alloc(srv_sess); @@ -572,7 +572,7 @@ rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess, strscpy(sdev->pathname, open_msg->dev_name, sizeof(sdev->pathname)); - sdev->bdev_handle = handle; + sdev->bdev_file = bdev_file; sdev->sess = srv_sess; sdev->dev = srv_dev; sdev->readonly = readonly; @@ -678,7 +678,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, struct rnbd_srv_dev *srv_dev; struct rnbd_srv_sess_dev *srv_sess_dev; const struct rnbd_msg_open *open_msg = msg; - struct bdev_handle *bdev_handle; + struct file *bdev_file; blk_mode_t open_flags = BLK_OPEN_READ; char *full_path; struct rnbd_msg_open_rsp *rsp = data; @@ -716,15 +716,15 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, goto reject; } - bdev_handle = bdev_open_by_path(full_path, open_flags, NULL, NULL); - if (IS_ERR(bdev_handle)) { - ret = PTR_ERR(bdev_handle); + bdev_file = bdev_file_open_by_path(full_path, open_flags, NULL, NULL); + if (IS_ERR(bdev_file)) { + ret = PTR_ERR(bdev_file); pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %pe\n", - full_path, srv_sess->sessname, bdev_handle); + full_path, srv_sess->sessname, bdev_file); goto free_path; } - srv_dev = rnbd_srv_get_or_create_srv_dev(bdev_handle->bdev, srv_sess, + srv_dev = rnbd_srv_get_or_create_srv_dev(file_bdev(bdev_file), srv_sess, open_msg->access_mode); if (IS_ERR(srv_dev)) { pr_err("Opening device '%s' on session %s failed, creating srv_dev failed, err: %pe\n", @@ -734,7 +734,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, } srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg, - bdev_handle, + bdev_file, open_msg->access_mode == RNBD_ACCESS_RO, srv_dev); if (IS_ERR(srv_sess_dev)) { @@ -750,7 +750,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, */ mutex_lock(&srv_dev->lock); if (!srv_dev->dev_kobj.state_in_sysfs) { - ret = rnbd_srv_create_dev_sysfs(srv_dev, bdev_handle->bdev); + ret = rnbd_srv_create_dev_sysfs(srv_dev, file_bdev(bdev_file)); if (ret) { mutex_unlock(&srv_dev->lock); rnbd_srv_err(srv_sess_dev, @@ -793,7 +793,7 @@ srv_dev_put: } rnbd_put_srv_dev(srv_dev); blkdev_put: - bdev_release(bdev_handle); + fput(bdev_file); free_path: kfree(full_path); reject: diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h index 343cc682b617..18d873808b8d 100644 --- a/drivers/block/rnbd/rnbd-srv.h +++ b/drivers/block/rnbd/rnbd-srv.h @@ -46,7 +46,7 @@ struct rnbd_srv_dev { struct rnbd_srv_sess_dev { /* Entry inside rnbd_srv_dev struct */ struct list_head dev_list; - struct bdev_handle *bdev_handle; + struct file *bdev_file; struct rnbd_srv_session *sess; struct rnbd_srv_dev *dev; struct kobject kobj; diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 7bf4b48e2282..c99dd6698977 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -784,6 +784,14 @@ static const struct blk_mq_ops vdc_mq_ops = { static int probe_disk(struct vdc_port *port) { + struct queue_limits lim = { + .physical_block_size = port->vdisk_phys_blksz, + .max_hw_sectors = port->max_xfer_size, + /* Each segment in a request is up to an aligned page in size. */ + .seg_boundary_mask = PAGE_SIZE - 1, + .max_segment_size = PAGE_SIZE, + .max_segments = port->ring_cookies, + }; struct request_queue *q; struct gendisk *g; int err; @@ -824,7 +832,7 @@ static int probe_disk(struct vdc_port *port) if (err) return err; - g = blk_mq_alloc_disk(&port->tag_set, port); + g = blk_mq_alloc_disk(&port->tag_set, &lim, port); if (IS_ERR(g)) { printk(KERN_ERR PFX "%s: Could not allocate gendisk.\n", port->vio.name); @@ -835,12 +843,6 @@ static int probe_disk(struct vdc_port *port) port->disk = g; q = g->queue; - /* Each segment in a request is up to an aligned page in size. */ - blk_queue_segment_boundary(q, PAGE_SIZE - 1); - blk_queue_max_segment_size(q, PAGE_SIZE); - - blk_queue_max_segments(q, port->ring_cookies); - blk_queue_max_hw_sectors(q, port->max_xfer_size); g->major = vdc_major; g->first_minor = port->vio.vdev->dev_no << PARTITION_SHIFT; g->minors = 1 << PARTITION_SHIFT; @@ -872,8 +874,6 @@ static int probe_disk(struct vdc_port *port) } } - blk_queue_physical_block_size(q, port->vdisk_phys_blksz); - pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n", g->disk_name, port->vdisk_size, (port->vdisk_size >> (20 - 9)), diff --git a/drivers/block/swim.c b/drivers/block/swim.c index f85b6af414b4..6731678f3a41 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -820,7 +820,7 @@ static int swim_floppy_init(struct swim_priv *swd) goto exit_put_disks; swd->unit[drive].disk = - blk_mq_alloc_disk(&swd->unit[drive].tag_set, + blk_mq_alloc_disk(&swd->unit[drive].tag_set, NULL, &swd->unit[drive]); if (IS_ERR(swd->unit[drive].disk)) { blk_mq_free_tag_set(&swd->unit[drive].tag_set); @@ -916,7 +916,7 @@ out: return ret; } -static int swim_remove(struct platform_device *dev) +static void swim_remove(struct platform_device *dev) { struct swim_priv *swd = platform_get_drvdata(dev); int drive; @@ -937,13 +937,11 @@ static int swim_remove(struct platform_device *dev) release_mem_region(res->start, resource_size(res)); kfree(swd); - - return 0; } static struct platform_driver swim_driver = { .probe = swim_probe, - .remove = swim_remove, + .remove_new = swim_remove, .driver = { .name = CARDNAME, }, diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index c2bc85826358..a04756ac778e 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1210,7 +1210,7 @@ static int swim3_attach(struct macio_dev *mdev, if (rc) goto out_unregister; - disk = blk_mq_alloc_disk(&fs->tag_set, fs); + disk = blk_mq_alloc_disk(&fs->tag_set, NULL, fs); if (IS_ERR(disk)) { rc = PTR_ERR(disk); goto out_free_tag_set; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 1dfb2e77898b..bea3d5cf8a83 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -246,21 +246,12 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub) return 0; } -static int ublk_dev_param_zoned_apply(struct ublk_device *ub) +static void ublk_dev_param_zoned_apply(struct ublk_device *ub) { - const struct ublk_param_zoned *p = &ub->params.zoned; - - disk_set_zoned(ub->ub_disk); blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue); blk_queue_required_elevator_features(ub->ub_disk->queue, ELEVATOR_F_ZBD_SEQ_WRITE); - disk_set_max_active_zones(ub->ub_disk, p->max_active_zones); - disk_set_max_open_zones(ub->ub_disk, p->max_open_zones); - blk_queue_max_zone_append_sectors(ub->ub_disk->queue, p->max_zone_append_sectors); - ub->ub_disk->nr_zones = ublk_get_nr_zones(ub); - - return 0; } /* Based on virtblk_alloc_report_buffer */ @@ -432,9 +423,8 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub) return -EOPNOTSUPP; } -static int ublk_dev_param_zoned_apply(struct ublk_device *ub) +static void ublk_dev_param_zoned_apply(struct ublk_device *ub) { - return -EOPNOTSUPP; } static int ublk_revalidate_disk_zones(struct ublk_device *ub) @@ -498,11 +488,6 @@ static void ublk_dev_param_basic_apply(struct ublk_device *ub) struct request_queue *q = ub->ub_disk->queue; const struct ublk_param_basic *p = &ub->params.basic; - blk_queue_logical_block_size(q, 1 << p->logical_bs_shift); - blk_queue_physical_block_size(q, 1 << p->physical_bs_shift); - blk_queue_io_min(q, 1 << p->io_min_shift); - blk_queue_io_opt(q, 1 << p->io_opt_shift); - blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE, p->attrs & UBLK_ATTR_FUA); if (p->attrs & UBLK_ATTR_ROTATIONAL) @@ -510,29 +495,12 @@ static void ublk_dev_param_basic_apply(struct ublk_device *ub) else blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - blk_queue_max_hw_sectors(q, p->max_sectors); - blk_queue_chunk_sectors(q, p->chunk_sectors); - blk_queue_virt_boundary(q, p->virt_boundary_mask); - if (p->attrs & UBLK_ATTR_READ_ONLY) set_disk_ro(ub->ub_disk, true); set_capacity(ub->ub_disk, p->dev_sectors); } -static void ublk_dev_param_discard_apply(struct ublk_device *ub) -{ - struct request_queue *q = ub->ub_disk->queue; - const struct ublk_param_discard *p = &ub->params.discard; - - q->limits.discard_alignment = p->discard_alignment; - q->limits.discard_granularity = p->discard_granularity; - blk_queue_max_discard_sectors(q, p->max_discard_sectors); - blk_queue_max_write_zeroes_sectors(q, - p->max_write_zeroes_sectors); - blk_queue_max_discard_segments(q, p->max_discard_segments); -} - static int ublk_validate_params(const struct ublk_device *ub) { /* basic param is the only one which must be set */ @@ -576,20 +544,12 @@ static int ublk_validate_params(const struct ublk_device *ub) return 0; } -static int ublk_apply_params(struct ublk_device *ub) +static void ublk_apply_params(struct ublk_device *ub) { - if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC)) - return -EINVAL; - ublk_dev_param_basic_apply(ub); - if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) - ublk_dev_param_discard_apply(ub); - if (ub->params.types & UBLK_PARAM_TYPE_ZONED) - return ublk_dev_param_zoned_apply(ub); - - return 0; + ublk_dev_param_zoned_apply(ub); } static inline bool ublk_support_user_copy(const struct ublk_queue *ubq) @@ -645,14 +605,16 @@ static inline bool ublk_need_get_data(const struct ublk_queue *ubq) return ubq->flags & UBLK_F_NEED_GET_DATA; } -static struct ublk_device *ublk_get_device(struct ublk_device *ub) +/* Called in slow path only, keep it noinline for trace purpose */ +static noinline struct ublk_device *ublk_get_device(struct ublk_device *ub) { if (kobject_get_unless_zero(&ub->cdev_dev.kobj)) return ub; return NULL; } -static void ublk_put_device(struct ublk_device *ub) +/* Called in slow path only, keep it noinline for trace purpose */ +static noinline void ublk_put_device(struct ublk_device *ub) { put_device(&ub->cdev_dev); } @@ -711,7 +673,7 @@ static void ublk_free_disk(struct gendisk *disk) struct ublk_device *ub = disk->private_data; clear_bit(UB_STATE_USED, &ub->state); - put_device(&ub->cdev_dev); + ublk_put_device(ub); } static void ublk_store_owner_uid_gid(unsigned int *owner_uid, @@ -2182,7 +2144,7 @@ static void ublk_remove(struct ublk_device *ub) cancel_work_sync(&ub->stop_work); cancel_work_sync(&ub->quiesce_work); cdev_device_del(&ub->cdev, &ub->cdev_dev); - put_device(&ub->cdev_dev); + ublk_put_device(ub); ublks_added--; } @@ -2205,12 +2167,47 @@ static struct ublk_device *ublk_get_device_from_id(int idx) static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) { const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); + const struct ublk_param_basic *p = &ub->params.basic; int ublksrv_pid = (int)header->data[0]; + struct queue_limits lim = { + .logical_block_size = 1 << p->logical_bs_shift, + .physical_block_size = 1 << p->physical_bs_shift, + .io_min = 1 << p->io_min_shift, + .io_opt = 1 << p->io_opt_shift, + .max_hw_sectors = p->max_sectors, + .chunk_sectors = p->chunk_sectors, + .virt_boundary_mask = p->virt_boundary_mask, + + }; struct gendisk *disk; int ret = -EINVAL; if (ublksrv_pid <= 0) return -EINVAL; + if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC)) + return -EINVAL; + + if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) { + const struct ublk_param_discard *pd = &ub->params.discard; + + lim.discard_alignment = pd->discard_alignment; + lim.discard_granularity = pd->discard_granularity; + lim.max_hw_discard_sectors = pd->max_discard_sectors; + lim.max_write_zeroes_sectors = pd->max_write_zeroes_sectors; + lim.max_discard_segments = pd->max_discard_segments; + } + + if (ub->params.types & UBLK_PARAM_TYPE_ZONED) { + const struct ublk_param_zoned *p = &ub->params.zoned; + + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) + return -EOPNOTSUPP; + + lim.zoned = true; + lim.max_active_zones = p->max_active_zones; + lim.max_open_zones = p->max_open_zones; + lim.max_zone_append_sectors = p->max_zone_append_sectors; + } if (wait_for_completion_interruptible(&ub->completion) != 0) return -EINTR; @@ -2222,7 +2219,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) goto out_unlock; } - disk = blk_mq_alloc_disk(&ub->tag_set, NULL); + disk = blk_mq_alloc_disk(&ub->tag_set, &lim, NULL); if (IS_ERR(disk)) { ret = PTR_ERR(disk); goto out_unlock; @@ -2234,15 +2231,13 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) ub->dev_info.ublksrv_pid = ublksrv_pid; ub->ub_disk = disk; - ret = ublk_apply_params(ub); - if (ret) - goto out_put_disk; + ublk_apply_params(ub); /* don't probe partitions if any one ubq daemon is un-trusted */ if (ub->nr_privileged_daemon != ub->nr_queues_ready) set_bit(GD_SUPPRESS_PART_SCAN, &disk->state); - get_device(&ub->cdev_dev); + ublk_get_device(ub); ub->dev_info.state = UBLK_S_DEV_LIVE; if (ublk_dev_is_zoned(ub)) { @@ -2262,7 +2257,6 @@ out_put_cdev: ub->dev_info.state = UBLK_S_DEV_DEAD; ublk_put_device(ub); } -out_put_disk: if (ret) put_disk(disk); out_unlock: @@ -2474,7 +2468,7 @@ static inline bool ublk_idr_freed(int id) return ptr == NULL; } -static int ublk_ctrl_del_dev(struct ublk_device **p_ub) +static int ublk_ctrl_del_dev(struct ublk_device **p_ub, bool wait) { struct ublk_device *ub = *p_ub; int idx = ub->ub_number; @@ -2508,7 +2502,7 @@ static int ublk_ctrl_del_dev(struct ublk_device **p_ub) * - the device number is freed already, we will not find this * device via ublk_get_device_from_id() */ - if (wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx))) + if (wait && wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx))) return -EINTR; return 0; } @@ -2907,7 +2901,10 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, ret = ublk_ctrl_add_dev(cmd); break; case UBLK_CMD_DEL_DEV: - ret = ublk_ctrl_del_dev(&ub); + ret = ublk_ctrl_del_dev(&ub, true); + break; + case UBLK_U_CMD_DEL_DEV_ASYNC: + ret = ublk_ctrl_del_dev(&ub, false); break; case UBLK_CMD_GET_QUEUE_AFFINITY: ret = ublk_ctrl_get_queue_affinity(ub, cmd); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 2bf14a0e2815..42dea7601d87 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -720,25 +720,24 @@ fail_report: return ret; } -static int virtblk_probe_zoned_device(struct virtio_device *vdev, - struct virtio_blk *vblk, - struct request_queue *q) +static int virtblk_read_zoned_limits(struct virtio_blk *vblk, + struct queue_limits *lim) { + struct virtio_device *vdev = vblk->vdev; u32 v, wg; dev_dbg(&vdev->dev, "probing host-managed zoned device\n"); - disk_set_zoned(vblk->disk); - blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q); + lim->zoned = true; virtio_cread(vdev, struct virtio_blk_config, zoned.max_open_zones, &v); - disk_set_max_open_zones(vblk->disk, v); + lim->max_open_zones = v; dev_dbg(&vdev->dev, "max open zones = %u\n", v); virtio_cread(vdev, struct virtio_blk_config, zoned.max_active_zones, &v); - disk_set_max_active_zones(vblk->disk, v); + lim->max_active_zones = v; dev_dbg(&vdev->dev, "max active zones = %u\n", v); virtio_cread(vdev, struct virtio_blk_config, @@ -747,8 +746,8 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, dev_warn(&vdev->dev, "zero write granularity reported\n"); return -ENODEV; } - blk_queue_physical_block_size(q, wg); - blk_queue_io_min(q, wg); + lim->physical_block_size = wg; + lim->io_min = wg; dev_dbg(&vdev->dev, "write granularity = %u\n", wg); @@ -764,13 +763,13 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, vblk->zone_sectors); return -ENODEV; } - blk_queue_chunk_sectors(q, vblk->zone_sectors); + lim->chunk_sectors = vblk->zone_sectors; dev_dbg(&vdev->dev, "zone sectors = %u\n", vblk->zone_sectors); if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { dev_warn(&vblk->vdev->dev, "ignoring negotiated F_DISCARD for zoned device\n"); - blk_queue_max_discard_sectors(q, 0); + lim->max_hw_discard_sectors = 0; } virtio_cread(vdev, struct virtio_blk_config, @@ -785,25 +784,21 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, wg, v); return -ENODEV; } - blk_queue_max_zone_append_sectors(q, v); + lim->max_zone_append_sectors = v; dev_dbg(&vdev->dev, "max append sectors = %u\n", v); - return blk_revalidate_disk_zones(vblk->disk, NULL); + return 0; } - #else - /* - * Zoned block device support is not configured in this kernel. - * Host-managed zoned devices can't be supported, but others are - * good to go as regular block devices. + * Zoned block device support is not configured in this kernel, host-managed + * zoned devices can't be supported. */ #define virtblk_report_zones NULL - -static inline int virtblk_probe_zoned_device(struct virtio_device *vdev, - struct virtio_blk *vblk, struct request_queue *q) +static inline int virtblk_read_zoned_limits(struct virtio_blk *vblk, + struct queue_limits *lim) { - dev_err(&vdev->dev, + dev_err(&vblk->vdev->dev, "virtio_blk: zoned devices are not supported"); return -EOPNOTSUPP; } @@ -1248,31 +1243,17 @@ static const struct blk_mq_ops virtio_mq_ops = { static unsigned int virtblk_queue_depth; module_param_named(queue_depth, virtblk_queue_depth, uint, 0444); -static int virtblk_probe(struct virtio_device *vdev) +static int virtblk_read_limits(struct virtio_blk *vblk, + struct queue_limits *lim) { - struct virtio_blk *vblk; - struct request_queue *q; - int err, index; - + struct virtio_device *vdev = vblk->vdev; u32 v, blk_size, max_size, sg_elems, opt_io_size; u32 max_discard_segs = 0; u32 discard_granularity = 0; u16 min_io_size; u8 physical_block_exp, alignment_offset; - unsigned int queue_depth; size_t max_dma_size; - - if (!vdev->config->get) { - dev_err(&vdev->dev, "%s failure: config access disabled\n", - __func__); - return -EINVAL; - } - - err = ida_alloc_range(&vd_index_ida, 0, - minor_to_index(1 << MINORBITS) - 1, GFP_KERNEL); - if (err < 0) - goto out; - index = err; + int err; /* We need to know how many segments before we allocate. */ err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SEG_MAX, @@ -1286,78 +1267,11 @@ static int virtblk_probe(struct virtio_device *vdev) /* Prevent integer overflows and honor max vq size */ sg_elems = min_t(u32, sg_elems, VIRTIO_BLK_MAX_SG_ELEMS - 2); - vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL); - if (!vblk) { - err = -ENOMEM; - goto out_free_index; - } - - mutex_init(&vblk->vdev_mutex); - - vblk->vdev = vdev; - - INIT_WORK(&vblk->config_work, virtblk_config_changed_work); - - err = init_vq(vblk); - if (err) - goto out_free_vblk; - - /* Default queue sizing is to fill the ring. */ - if (!virtblk_queue_depth) { - queue_depth = vblk->vqs[0].vq->num_free; - /* ... but without indirect descs, we use 2 descs per req */ - if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC)) - queue_depth /= 2; - } else { - queue_depth = virtblk_queue_depth; - } - - memset(&vblk->tag_set, 0, sizeof(vblk->tag_set)); - vblk->tag_set.ops = &virtio_mq_ops; - vblk->tag_set.queue_depth = queue_depth; - vblk->tag_set.numa_node = NUMA_NO_NODE; - vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - vblk->tag_set.cmd_size = - sizeof(struct virtblk_req) + - sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT; - vblk->tag_set.driver_data = vblk; - vblk->tag_set.nr_hw_queues = vblk->num_vqs; - vblk->tag_set.nr_maps = 1; - if (vblk->io_queues[HCTX_TYPE_POLL]) - vblk->tag_set.nr_maps = 3; - - err = blk_mq_alloc_tag_set(&vblk->tag_set); - if (err) - goto out_free_vq; - - vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, vblk); - if (IS_ERR(vblk->disk)) { - err = PTR_ERR(vblk->disk); - goto out_free_tags; - } - q = vblk->disk->queue; - - virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN); - - vblk->disk->major = major; - vblk->disk->first_minor = index_to_minor(index); - vblk->disk->minors = 1 << PART_BITS; - vblk->disk->private_data = vblk; - vblk->disk->fops = &virtblk_fops; - vblk->index = index; - - /* configure queue flush support */ - virtblk_update_cache_mode(vdev); - - /* If disk is read-only in the host, the guest should obey */ - if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO)) - set_disk_ro(vblk->disk, 1); - /* We can handle whatever the host told us to handle. */ - blk_queue_max_segments(q, sg_elems); + lim->max_segments = sg_elems; /* No real sector limit. */ - blk_queue_max_hw_sectors(q, UINT_MAX); + lim->max_hw_sectors = UINT_MAX; max_dma_size = virtio_max_dma_size(vdev); max_size = max_dma_size > U32_MAX ? U32_MAX : max_dma_size; @@ -1369,7 +1283,7 @@ static int virtblk_probe(struct virtio_device *vdev) if (!err) max_size = min(max_size, v); - blk_queue_max_segment_size(q, max_size); + lim->max_segment_size = max_size; /* Host can optionally specify the block size of the device */ err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE, @@ -1381,38 +1295,37 @@ static int virtblk_probe(struct virtio_device *vdev) dev_err(&vdev->dev, "virtio_blk: invalid block size: 0x%x\n", blk_size); - goto out_cleanup_disk; + return err; } - blk_queue_logical_block_size(q, blk_size); + lim->logical_block_size = blk_size; } else - blk_size = queue_logical_block_size(q); + blk_size = lim->logical_block_size; /* Use topology information if available */ err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, struct virtio_blk_config, physical_block_exp, &physical_block_exp); if (!err && physical_block_exp) - blk_queue_physical_block_size(q, - blk_size * (1 << physical_block_exp)); + lim->physical_block_size = blk_size * (1 << physical_block_exp); err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, struct virtio_blk_config, alignment_offset, &alignment_offset); if (!err && alignment_offset) - blk_queue_alignment_offset(q, blk_size * alignment_offset); + lim->alignment_offset = blk_size * alignment_offset; err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, struct virtio_blk_config, min_io_size, &min_io_size); if (!err && min_io_size) - blk_queue_io_min(q, blk_size * min_io_size); + lim->io_min = blk_size * min_io_size; err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, struct virtio_blk_config, opt_io_size, &opt_io_size); if (!err && opt_io_size) - blk_queue_io_opt(q, blk_size * opt_io_size); + lim->io_opt = blk_size * opt_io_size; if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { virtio_cread(vdev, struct virtio_blk_config, @@ -1420,7 +1333,7 @@ static int virtblk_probe(struct virtio_device *vdev) virtio_cread(vdev, struct virtio_blk_config, max_discard_sectors, &v); - blk_queue_max_discard_sectors(q, v ? v : UINT_MAX); + lim->max_hw_discard_sectors = v ? v : UINT_MAX; virtio_cread(vdev, struct virtio_blk_config, max_discard_seg, &max_discard_segs); @@ -1429,7 +1342,7 @@ static int virtblk_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) { virtio_cread(vdev, struct virtio_blk_config, max_write_zeroes_sectors, &v); - blk_queue_max_write_zeroes_sectors(q, v ? v : UINT_MAX); + lim->max_write_zeroes_sectors = v ? v : UINT_MAX; } /* The discard and secure erase limits are combined since the Linux @@ -1455,8 +1368,7 @@ static int virtblk_probe(struct virtio_device *vdev) if (!v) { dev_err(&vdev->dev, "virtio_blk: secure_erase_sector_alignment can't be 0\n"); - err = -EINVAL; - goto out_cleanup_disk; + return -EINVAL; } discard_granularity = min_not_zero(discard_granularity, v); @@ -1470,11 +1382,10 @@ static int virtblk_probe(struct virtio_device *vdev) if (!v) { dev_err(&vdev->dev, "virtio_blk: max_secure_erase_sectors can't be 0\n"); - err = -EINVAL; - goto out_cleanup_disk; + return -EINVAL; } - blk_queue_max_secure_erase_sectors(q, v); + lim->max_secure_erase_sectors = v; virtio_cread(vdev, struct virtio_blk_config, max_secure_erase_seg, &v); @@ -1485,8 +1396,7 @@ static int virtblk_probe(struct virtio_device *vdev) if (!v) { dev_err(&vdev->dev, "virtio_blk: max_secure_erase_seg can't be 0\n"); - err = -EINVAL; - goto out_cleanup_disk; + return -EINVAL; } max_discard_segs = min_not_zero(max_discard_segs, v); @@ -1502,45 +1412,142 @@ static int virtblk_probe(struct virtio_device *vdev) if (!max_discard_segs) max_discard_segs = sg_elems; - blk_queue_max_discard_segments(q, - min(max_discard_segs, MAX_DISCARD_SEGMENTS)); + lim->max_discard_segments = + min(max_discard_segs, MAX_DISCARD_SEGMENTS); if (discard_granularity) - q->limits.discard_granularity = discard_granularity << SECTOR_SHIFT; + lim->discard_granularity = + discard_granularity << SECTOR_SHIFT; else - q->limits.discard_granularity = blk_size; + lim->discard_granularity = blk_size; } - virtblk_update_capacity(vblk, false); - virtio_device_ready(vdev); - - /* - * All steps that follow use the VQs therefore they need to be - * placed after the virtio_device_ready() call above. - */ if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) { u8 model; - virtio_cread(vdev, struct virtio_blk_config, zoned.model, - &model); + virtio_cread(vdev, struct virtio_blk_config, zoned.model, &model); switch (model) { case VIRTIO_BLK_Z_NONE: case VIRTIO_BLK_Z_HA: - /* Present the host-aware device as non-zoned */ - break; + /* treat host-aware devices as non-zoned */ + return 0; case VIRTIO_BLK_Z_HM: - err = virtblk_probe_zoned_device(vdev, vblk, q); + err = virtblk_read_zoned_limits(vblk, lim); if (err) - goto out_cleanup_disk; + return err; break; default: - dev_err(&vdev->dev, "unsupported zone model %d\n", - model); - err = -EINVAL; - goto out_cleanup_disk; + dev_err(&vdev->dev, "unsupported zone model %d\n", model); + return -EINVAL; } } + return 0; +} + +static int virtblk_probe(struct virtio_device *vdev) +{ + struct virtio_blk *vblk; + struct queue_limits lim = { }; + int err, index; + unsigned int queue_depth; + + if (!vdev->config->get) { + dev_err(&vdev->dev, "%s failure: config access disabled\n", + __func__); + return -EINVAL; + } + + err = ida_alloc_range(&vd_index_ida, 0, + minor_to_index(1 << MINORBITS) - 1, GFP_KERNEL); + if (err < 0) + goto out; + index = err; + + vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL); + if (!vblk) { + err = -ENOMEM; + goto out_free_index; + } + + mutex_init(&vblk->vdev_mutex); + + vblk->vdev = vdev; + + INIT_WORK(&vblk->config_work, virtblk_config_changed_work); + + err = init_vq(vblk); + if (err) + goto out_free_vblk; + + /* Default queue sizing is to fill the ring. */ + if (!virtblk_queue_depth) { + queue_depth = vblk->vqs[0].vq->num_free; + /* ... but without indirect descs, we use 2 descs per req */ + if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC)) + queue_depth /= 2; + } else { + queue_depth = virtblk_queue_depth; + } + + memset(&vblk->tag_set, 0, sizeof(vblk->tag_set)); + vblk->tag_set.ops = &virtio_mq_ops; + vblk->tag_set.queue_depth = queue_depth; + vblk->tag_set.numa_node = NUMA_NO_NODE; + vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + vblk->tag_set.cmd_size = + sizeof(struct virtblk_req) + + sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT; + vblk->tag_set.driver_data = vblk; + vblk->tag_set.nr_hw_queues = vblk->num_vqs; + vblk->tag_set.nr_maps = 1; + if (vblk->io_queues[HCTX_TYPE_POLL]) + vblk->tag_set.nr_maps = 3; + + err = blk_mq_alloc_tag_set(&vblk->tag_set); + if (err) + goto out_free_vq; + + err = virtblk_read_limits(vblk, &lim); + if (err) + goto out_free_tags; + + vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, &lim, vblk); + if (IS_ERR(vblk->disk)) { + err = PTR_ERR(vblk->disk); + goto out_free_tags; + } + + virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN); + + vblk->disk->major = major; + vblk->disk->first_minor = index_to_minor(index); + vblk->disk->minors = 1 << PART_BITS; + vblk->disk->private_data = vblk; + vblk->disk->fops = &virtblk_fops; + vblk->index = index; + + /* configure queue flush support */ + virtblk_update_cache_mode(vdev); + + /* If disk is read-only in the host, the guest should obey */ + if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO)) + set_disk_ro(vblk->disk, 1); + + virtblk_update_capacity(vblk, false); + virtio_device_ready(vdev); + + /* + * All steps that follow use the VQs therefore they need to be + * placed after the virtio_device_ready() call above. + */ + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) { + blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue); + err = blk_revalidate_disk_zones(vblk->disk, NULL); + if (err) + goto out_cleanup_disk; + } + err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups); if (err) goto out_cleanup_disk; diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 4defd7f387c7..944576d582fb 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -465,7 +465,7 @@ static int xen_vbd_translate(struct phys_req *req, struct xen_blkif *blkif, } req->dev = vbd->pdevice; - req->bdev = vbd->bdev_handle->bdev; + req->bdev = file_bdev(vbd->bdev_file); rc = 0; out: @@ -969,7 +969,7 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring, int err = 0; int status = BLKIF_RSP_OKAY; struct xen_blkif *blkif = ring->blkif; - struct block_device *bdev = blkif->vbd.bdev_handle->bdev; + struct block_device *bdev = file_bdev(blkif->vbd.bdev_file); struct phys_req preq; xen_blkif_get(blkif); diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index 1432c83183d0..b427d54bc120 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -221,7 +221,7 @@ struct xen_vbd { unsigned char type; /* phys device that this vbd maps to. */ u32 pdevice; - struct bdev_handle *bdev_handle; + struct file *bdev_file; /* Cached size parameter. */ sector_t size; unsigned int flush_support:1; @@ -360,7 +360,7 @@ struct pending_req { }; -#define vbd_sz(_v) bdev_nr_sectors((_v)->bdev_handle->bdev) +#define vbd_sz(_v) bdev_nr_sectors(file_bdev((_v)->bdev_file)) #define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt)) #define xen_blkif_put(_b) \ diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index e34219ea2b05..0621878940ae 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -81,7 +81,7 @@ static void xen_update_blkif_status(struct xen_blkif *blkif) int i; /* Not ready to connect? */ - if (!blkif->rings || !blkif->rings[0].irq || !blkif->vbd.bdev_handle) + if (!blkif->rings || !blkif->rings[0].irq || !blkif->vbd.bdev_file) return; /* Already connected? */ @@ -99,13 +99,12 @@ static void xen_update_blkif_status(struct xen_blkif *blkif) return; } - err = sync_blockdev(blkif->vbd.bdev_handle->bdev); + err = sync_blockdev(file_bdev(blkif->vbd.bdev_file)); if (err) { xenbus_dev_error(blkif->be->dev, err, "block flush"); return; } - invalidate_inode_pages2( - blkif->vbd.bdev_handle->bdev->bd_inode->i_mapping); + invalidate_inode_pages2(blkif->vbd.bdev_file->f_mapping); for (i = 0; i < blkif->nr_rings; i++) { ring = &blkif->rings[i]; @@ -473,9 +472,9 @@ static void xenvbd_sysfs_delif(struct xenbus_device *dev) static void xen_vbd_free(struct xen_vbd *vbd) { - if (vbd->bdev_handle) - bdev_release(vbd->bdev_handle); - vbd->bdev_handle = NULL; + if (vbd->bdev_file) + fput(vbd->bdev_file); + vbd->bdev_file = NULL; } static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, @@ -483,7 +482,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, int cdrom) { struct xen_vbd *vbd; - struct bdev_handle *bdev_handle; + struct file *bdev_file; vbd = &blkif->vbd; vbd->handle = handle; @@ -492,17 +491,17 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, vbd->pdevice = MKDEV(major, minor); - bdev_handle = bdev_open_by_dev(vbd->pdevice, vbd->readonly ? + bdev_file = bdev_file_open_by_dev(vbd->pdevice, vbd->readonly ? BLK_OPEN_READ : BLK_OPEN_WRITE, NULL, NULL); - if (IS_ERR(bdev_handle)) { + if (IS_ERR(bdev_file)) { pr_warn("xen_vbd_create: device %08x could not be opened\n", vbd->pdevice); return -ENOENT; } - vbd->bdev_handle = bdev_handle; - if (vbd->bdev_handle->bdev->bd_disk == NULL) { + vbd->bdev_file = bdev_file; + if (file_bdev(vbd->bdev_file)->bd_disk == NULL) { pr_warn("xen_vbd_create: device %08x doesn't exist\n", vbd->pdevice); xen_vbd_free(vbd); @@ -510,14 +509,14 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, } vbd->size = vbd_sz(vbd); - if (cdrom || disk_to_cdi(vbd->bdev_handle->bdev->bd_disk)) + if (cdrom || disk_to_cdi(file_bdev(vbd->bdev_file)->bd_disk)) vbd->type |= VDISK_CDROM; - if (vbd->bdev_handle->bdev->bd_disk->flags & GENHD_FL_REMOVABLE) + if (file_bdev(vbd->bdev_file)->bd_disk->flags & GENHD_FL_REMOVABLE) vbd->type |= VDISK_REMOVABLE; - if (bdev_write_cache(bdev_handle->bdev)) + if (bdev_write_cache(file_bdev(bdev_file))) vbd->flush_support = true; - if (bdev_max_secure_erase_sectors(bdev_handle->bdev)) + if (bdev_max_secure_erase_sectors(file_bdev(bdev_file))) vbd->discard_secure = true; pr_debug("Successful creation of handle=%04x (dom=%u)\n", @@ -570,7 +569,7 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info struct xen_blkif *blkif = be->blkif; int err; int state = 0; - struct block_device *bdev = be->blkif->vbd.bdev_handle->bdev; + struct block_device *bdev = file_bdev(be->blkif->vbd.bdev_file); if (!xenbus_read_unsigned(dev->nodename, "discard-enable", 1)) return; @@ -932,7 +931,7 @@ again: } err = xenbus_printf(xbt, dev->nodename, "sector-size", "%lu", (unsigned long)bdev_logical_block_size( - be->blkif->vbd.bdev_handle->bdev)); + file_bdev(be->blkif->vbd.bdev_file))); if (err) { xenbus_dev_fatal(dev, err, "writing %s/sector-size", dev->nodename); @@ -940,7 +939,7 @@ again: } err = xenbus_printf(xbt, dev->nodename, "physical-sector-size", "%u", bdev_physical_block_size( - be->blkif->vbd.bdev_handle->bdev)); + file_bdev(be->blkif->vbd.bdev_file))); if (err) xenbus_dev_error(dev, err, "writing %s/physical-sector-size", dev->nodename); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 434fab306777..fd7c0ff2139c 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -941,39 +941,35 @@ static const struct blk_mq_ops blkfront_mq_ops = { .complete = blkif_complete_rq, }; -static void blkif_set_queue_limits(struct blkfront_info *info) +static void blkif_set_queue_limits(const struct blkfront_info *info, + struct queue_limits *lim) { - struct request_queue *rq = info->rq; - struct gendisk *gd = info->gd; unsigned int segments = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; - blk_queue_flag_set(QUEUE_FLAG_VIRT, rq); - if (info->feature_discard) { - blk_queue_max_discard_sectors(rq, get_capacity(gd)); - rq->limits.discard_granularity = info->discard_granularity ?: - info->physical_sector_size; - rq->limits.discard_alignment = info->discard_alignment; + lim->max_hw_discard_sectors = UINT_MAX; + if (info->discard_granularity) + lim->discard_granularity = info->discard_granularity; + lim->discard_alignment = info->discard_alignment; if (info->feature_secdiscard) - blk_queue_max_secure_erase_sectors(rq, - get_capacity(gd)); + lim->max_secure_erase_sectors = UINT_MAX; } /* Hard sector size and max sectors impersonate the equiv. hardware. */ - blk_queue_logical_block_size(rq, info->sector_size); - blk_queue_physical_block_size(rq, info->physical_sector_size); - blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512); + lim->logical_block_size = info->sector_size; + lim->physical_block_size = info->physical_sector_size; + lim->max_hw_sectors = (segments * XEN_PAGE_SIZE) / 512; /* Each segment in a request is up to an aligned page in size. */ - blk_queue_segment_boundary(rq, PAGE_SIZE - 1); - blk_queue_max_segment_size(rq, PAGE_SIZE); + lim->seg_boundary_mask = PAGE_SIZE - 1; + lim->max_segment_size = PAGE_SIZE; /* Ensure a merged request will fit in a single I/O ring slot. */ - blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG); + lim->max_segments = segments / GRANTS_PER_PSEG; /* Make sure buffer addresses are sector-aligned. */ - blk_queue_dma_alignment(rq, 511); + lim->dma_alignment = 511; } static const char *flush_info(struct blkfront_info *info) @@ -1070,6 +1066,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, struct blkfront_info *info, u16 sector_size, unsigned int physical_sector_size) { + struct queue_limits lim = {}; struct gendisk *gd; int nr_minors = 1; int err; @@ -1136,11 +1133,13 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, if (err) goto out_release_minors; - gd = blk_mq_alloc_disk(&info->tag_set, info); + blkif_set_queue_limits(info, &lim); + gd = blk_mq_alloc_disk(&info->tag_set, &lim, info); if (IS_ERR(gd)) { err = PTR_ERR(gd); goto out_free_tag_set; } + blk_queue_flag_set(QUEUE_FLAG_VIRT, gd->queue); strcpy(gd->disk_name, DEV_NAME); ptr = encode_disk_name(gd->disk_name + sizeof(DEV_NAME) - 1, offset); @@ -1162,7 +1161,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, info->gd = gd; info->sector_size = sector_size; info->physical_sector_size = physical_sector_size; - blkif_set_queue_limits(info); xlvbd_flush(info); @@ -2006,18 +2004,19 @@ static int blkfront_probe(struct xenbus_device *dev, static int blkif_recover(struct blkfront_info *info) { + struct queue_limits lim; unsigned int r_index; struct request *req, *n; int rc; struct bio *bio; - unsigned int segs; struct blkfront_ring_info *rinfo; + lim = queue_limits_start_update(info->rq); blkfront_gather_backend_features(info); - /* Reset limits changed by blk_mq_update_nr_hw_queues(). */ - blkif_set_queue_limits(info); - segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; - blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG); + blkif_set_queue_limits(info, &lim); + rc = queue_limits_commit_update(info->rq, &lim); + if (rc) + return rc; for_each_rinfo(info, rinfo, r_index) { rc = blkfront_setup_indirect(rinfo); @@ -2037,7 +2036,9 @@ static int blkif_recover(struct blkfront_info *info) list_for_each_entry_safe(req, n, &info->requests, queuelist) { /* Requeue pending requests (flush or discard) */ list_del_init(&req->queuelist); - BUG_ON(req->nr_phys_segments > segs); + BUG_ON(req->nr_phys_segments > + (info->max_indirect_segments ? : + BLKIF_MAX_SEGMENTS_PER_REQUEST)); blk_mq_requeue_request(req, false); } blk_mq_start_stopped_hw_queues(info->rq, true); diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index 11493167b0a8..7c5f4e4d9b50 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -318,7 +318,7 @@ static int z2ram_register_disk(int minor) struct gendisk *disk; int err; - disk = blk_mq_alloc_disk(&tag_set, NULL); + disk = blk_mq_alloc_disk(&tag_set, NULL, NULL); if (IS_ERR(disk)) return PTR_ERR(disk); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 6772e0c654fa..da7a20fa6152 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -426,11 +426,11 @@ static void reset_bdev(struct zram *zram) if (!zram->backing_dev) return; - bdev_release(zram->bdev_handle); + fput(zram->bdev_file); /* hope filp_close flush all of IO */ filp_close(zram->backing_dev, NULL); zram->backing_dev = NULL; - zram->bdev_handle = NULL; + zram->bdev_file = NULL; zram->disk->fops = &zram_devops; kvfree(zram->bitmap); zram->bitmap = NULL; @@ -476,7 +476,7 @@ static ssize_t backing_dev_store(struct device *dev, struct address_space *mapping; unsigned int bitmap_sz; unsigned long nr_pages, *bitmap = NULL; - struct bdev_handle *bdev_handle = NULL; + struct file *bdev_file = NULL; int err; struct zram *zram = dev_to_zram(dev); @@ -513,11 +513,11 @@ static ssize_t backing_dev_store(struct device *dev, goto out; } - bdev_handle = bdev_open_by_dev(inode->i_rdev, + bdev_file = bdev_file_open_by_dev(inode->i_rdev, BLK_OPEN_READ | BLK_OPEN_WRITE, zram, NULL); - if (IS_ERR(bdev_handle)) { - err = PTR_ERR(bdev_handle); - bdev_handle = NULL; + if (IS_ERR(bdev_file)) { + err = PTR_ERR(bdev_file); + bdev_file = NULL; goto out; } @@ -531,7 +531,7 @@ static ssize_t backing_dev_store(struct device *dev, reset_bdev(zram); - zram->bdev_handle = bdev_handle; + zram->bdev_file = bdev_file; zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; @@ -544,8 +544,8 @@ static ssize_t backing_dev_store(struct device *dev, out: kvfree(bitmap); - if (bdev_handle) - bdev_release(bdev_handle); + if (bdev_file) + fput(bdev_file); if (backing_dev) filp_close(backing_dev, NULL); @@ -587,7 +587,7 @@ static void read_from_bdev_async(struct zram *zram, struct page *page, { struct bio *bio; - bio = bio_alloc(zram->bdev_handle->bdev, 1, parent->bi_opf, GFP_NOIO); + bio = bio_alloc(file_bdev(zram->bdev_file), 1, parent->bi_opf, GFP_NOIO); bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); __bio_add_page(bio, page, PAGE_SIZE, 0); bio_chain(bio, parent); @@ -703,7 +703,7 @@ static ssize_t writeback_store(struct device *dev, continue; } - bio_init(&bio, zram->bdev_handle->bdev, &bio_vec, 1, + bio_init(&bio, file_bdev(zram->bdev_file), &bio_vec, 1, REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); __bio_add_page(&bio, page, PAGE_SIZE, 0); @@ -785,7 +785,7 @@ static void zram_sync_read(struct work_struct *work) struct bio_vec bv; struct bio bio; - bio_init(&bio, zw->zram->bdev_handle->bdev, &bv, 1, REQ_OP_READ); + bio_init(&bio, file_bdev(zw->zram->bdev_file), &bv, 1, REQ_OP_READ); bio.bi_iter.bi_sector = zw->entry * (PAGE_SIZE >> 9); __bio_add_page(&bio, zw->page, PAGE_SIZE, 0); zw->error = submit_bio_wait(&bio); @@ -2177,6 +2177,28 @@ ATTRIBUTE_GROUPS(zram_disk); */ static int zram_add(void) { + struct queue_limits lim = { + .logical_block_size = ZRAM_LOGICAL_BLOCK_SIZE, + /* + * To ensure that we always get PAGE_SIZE aligned and + * n*PAGE_SIZED sized I/O requests. + */ + .physical_block_size = PAGE_SIZE, + .io_min = PAGE_SIZE, + .io_opt = PAGE_SIZE, + .max_hw_discard_sectors = UINT_MAX, + /* + * zram_bio_discard() will clear all logical blocks if logical + * block size is identical with physical block size(PAGE_SIZE). + * But if it is different, we will skip discarding some parts of + * logical blocks in the part of the request range which isn't + * aligned to physical block size. So we can't ensure that all + * discarded logical blocks are zeroed. + */ +#if ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE + .max_write_zeroes_sectors = UINT_MAX, +#endif + }; struct zram *zram; int ret, device_id; @@ -2195,11 +2217,11 @@ static int zram_add(void) #endif /* gendisk structure */ - zram->disk = blk_alloc_disk(NUMA_NO_NODE); - if (!zram->disk) { + zram->disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(zram->disk)) { pr_err("Error allocating disk structure for device %d\n", device_id); - ret = -ENOMEM; + ret = PTR_ERR(zram->disk); goto out_free_idr; } @@ -2216,29 +2238,6 @@ static int zram_add(void) /* zram devices sort of resembles non-rotational disks */ blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue); blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue); - - /* - * To ensure that we always get PAGE_SIZE aligned - * and n*PAGE_SIZED sized I/O requests. - */ - blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE); - blk_queue_logical_block_size(zram->disk->queue, - ZRAM_LOGICAL_BLOCK_SIZE); - blk_queue_io_min(zram->disk->queue, PAGE_SIZE); - blk_queue_io_opt(zram->disk->queue, PAGE_SIZE); - blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX); - - /* - * zram_bio_discard() will clear all logical blocks if logical block - * size is identical with physical block size(PAGE_SIZE). But if it is - * different, we will skip discarding some parts of logical blocks in - * the part of the request range which isn't aligned to physical block - * size. So we can't ensure that all discarded logical blocks are - * zeroed. - */ - if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE) - blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue); ret = device_add_disk(NULL, zram->disk, zram_disk_groups); if (ret) diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 3b94d12f41b4..37bf29f34d26 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -132,7 +132,7 @@ struct zram { spinlock_t wb_limit_lock; bool wb_limit_enable; u64 bd_wb_limit; - struct bdev_handle *bdev_handle; + struct file *bdev_file; unsigned long *bitmap; unsigned long nr_pages; #endif diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index d668b174ace9..eefdd422ad8e 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -724,11 +724,6 @@ static void probe_gdrom_setupdisk(void) static int probe_gdrom_setupqueue(void) { - blk_queue_logical_block_size(gd.gdrom_rq, GDROM_HARD_SECTOR); - /* using DMA so memory will need to be contiguous */ - blk_queue_max_segments(gd.gdrom_rq, 1); - /* set a large max size to get most from DMA */ - blk_queue_max_segment_size(gd.gdrom_rq, 0x40000); gd.disk->queue = gd.gdrom_rq; return gdrom_init_dma_mode(); } @@ -743,6 +738,13 @@ static const struct blk_mq_ops gdrom_mq_ops = { */ static int probe_gdrom(struct platform_device *devptr) { + struct queue_limits lim = { + .logical_block_size = GDROM_HARD_SECTOR, + /* using DMA so memory will need to be contiguous */ + .max_segments = 1, + /* set a large max size to get most from DMA */ + .max_segment_size = 0x40000, + }; int err; /* @@ -778,7 +780,7 @@ static int probe_gdrom(struct platform_device *devptr) if (err) goto probe_fail_free_cd_info; - gd.disk = blk_mq_alloc_disk(&gd.tag_set, NULL); + gd.disk = blk_mq_alloc_disk(&gd.tag_set, &lim, NULL); if (IS_ERR(gd.disk)) { err = PTR_ERR(gd.disk); goto probe_fail_free_tag_set; @@ -829,7 +831,7 @@ probe_fail_no_mem: return err; } -static int remove_gdrom(struct platform_device *devptr) +static void remove_gdrom(struct platform_device *devptr) { blk_mq_free_tag_set(&gd.tag_set); free_irq(HW_EVENT_GDROM_CMD, &gd); @@ -840,13 +842,11 @@ static int remove_gdrom(struct platform_device *devptr) unregister_cdrom(gd.cd_info); kfree(gd.cd_info); kfree(gd.toc); - - return 0; } static struct platform_driver gdrom_driver = { .probe = probe_gdrom, - .remove = remove_gdrom, + .remove_new = remove_gdrom, .driver = { .name = GDROM_DEV_NAME, }, diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index e054de92de91..8d4a52056684 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -1807,7 +1807,7 @@ TIMER_ACPI_DECLARE(arch_timer, ACPI_SIG_GTDT, arch_timer_acpi_init); #endif int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *ts, - struct clocksource **cs) + enum clocksource_ids *cs_id) { struct arm_smccc_res hvc_res; u32 ptp_counter; @@ -1831,8 +1831,8 @@ int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *ts, *ts = ktime_to_timespec64(ktime); if (cycle) *cycle = (u64)hvc_res.a2 << 32 | hvc_res.a3; - if (cs) - *cs = &clocksource_counter; + if (cs_id) + *cs_id = CSID_ARM_ARCH_COUNTER; return 0; } diff --git a/drivers/comedi/drivers/comedi_8255.c b/drivers/comedi/drivers/comedi_8255.c index e4974b508328..a933ef53845a 100644 --- a/drivers/comedi/drivers/comedi_8255.c +++ b/drivers/comedi/drivers/comedi_8255.c @@ -159,6 +159,7 @@ static int __subdev_8255_init(struct comedi_device *dev, return -ENOMEM; spriv->context = context; + spriv->io = io; s->type = COMEDI_SUBD_DIO; s->subdev_flags = SDF_READABLE | SDF_WRITABLE; diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c index 30ea8b53ebf8..05ae9122823f 100644 --- a/drivers/comedi/drivers/comedi_test.c +++ b/drivers/comedi/drivers/comedi_test.c @@ -87,6 +87,8 @@ struct waveform_private { struct comedi_device *dev; /* parent comedi device */ u64 ao_last_scan_time; /* time of previous AO scan in usec */ unsigned int ao_scan_period; /* AO scan period in usec */ + bool ai_timer_enable:1; /* should AI timer be running? */ + bool ao_timer_enable:1; /* should AO timer be running? */ unsigned short ao_loopbacks[N_CHANS]; }; @@ -236,8 +238,12 @@ static void waveform_ai_timer(struct timer_list *t) time_increment = devpriv->ai_convert_time - now; else time_increment = 1; - mod_timer(&devpriv->ai_timer, - jiffies + usecs_to_jiffies(time_increment)); + spin_lock(&dev->spinlock); + if (devpriv->ai_timer_enable) { + mod_timer(&devpriv->ai_timer, + jiffies + usecs_to_jiffies(time_increment)); + } + spin_unlock(&dev->spinlock); } overrun: @@ -393,9 +399,12 @@ static int waveform_ai_cmd(struct comedi_device *dev, * Seem to need an extra jiffy here, otherwise timer expires slightly * early! */ + spin_lock_bh(&dev->spinlock); + devpriv->ai_timer_enable = true; devpriv->ai_timer.expires = jiffies + usecs_to_jiffies(devpriv->ai_convert_period) + 1; add_timer(&devpriv->ai_timer); + spin_unlock_bh(&dev->spinlock); return 0; } @@ -404,6 +413,9 @@ static int waveform_ai_cancel(struct comedi_device *dev, { struct waveform_private *devpriv = dev->private; + spin_lock_bh(&dev->spinlock); + devpriv->ai_timer_enable = false; + spin_unlock_bh(&dev->spinlock); if (in_softirq()) { /* Assume we were called from the timer routine itself. */ del_timer(&devpriv->ai_timer); @@ -495,8 +507,12 @@ static void waveform_ao_timer(struct timer_list *t) unsigned int time_inc = devpriv->ao_last_scan_time + devpriv->ao_scan_period - now; - mod_timer(&devpriv->ao_timer, - jiffies + usecs_to_jiffies(time_inc)); + spin_lock(&dev->spinlock); + if (devpriv->ao_timer_enable) { + mod_timer(&devpriv->ao_timer, + jiffies + usecs_to_jiffies(time_inc)); + } + spin_unlock(&dev->spinlock); } underrun: @@ -517,9 +533,12 @@ static int waveform_ao_inttrig_start(struct comedi_device *dev, async->inttrig = NULL; devpriv->ao_last_scan_time = ktime_to_us(ktime_get()); + spin_lock_bh(&dev->spinlock); + devpriv->ao_timer_enable = true; devpriv->ao_timer.expires = jiffies + usecs_to_jiffies(devpriv->ao_scan_period); add_timer(&devpriv->ao_timer); + spin_unlock_bh(&dev->spinlock); return 1; } @@ -604,6 +623,9 @@ static int waveform_ao_cancel(struct comedi_device *dev, struct waveform_private *devpriv = dev->private; s->async->inttrig = NULL; + spin_lock_bh(&dev->spinlock); + devpriv->ao_timer_enable = false; + spin_unlock_bh(&dev->spinlock); if (in_softirq()) { /* Assume we were called from the timer routine itself. */ del_timer(&devpriv->ao_timer); diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c index 09c77afb33ca..3f24481fc04a 100644 --- a/drivers/counter/counter-core.c +++ b/drivers/counter/counter-core.c @@ -31,10 +31,11 @@ struct counter_device_allochelper { struct counter_device counter; /* - * This is cache line aligned to ensure private data behaves like if it - * were kmalloced separately. + * This ensures private data behaves like if it were kmalloced + * separately. Also ensures the minimum alignment for safe DMA + * operations (which may or may not mean cache alignment). */ - unsigned long privdata[] ____cacheline_aligned; + unsigned long privdata[] __aligned(ARCH_DMA_MINALIGN); }; static void counter_device_release(struct device *dev) diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c index 1262a7773ef3..de50c00ba218 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c @@ -299,22 +299,6 @@ theend: return err; } -static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq) -{ - struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq); - struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); - struct sun8i_ce_dev *ce = op->ce; - struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq); - int flow, err; - - flow = rctx->flow; - err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm)); - local_bh_disable(); - crypto_finalize_skcipher_request(engine, breq, err); - local_bh_enable(); -} - static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine, void *async_req) { @@ -360,6 +344,23 @@ static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine, dma_unmap_single(ce->dev, rctx->addr_key, op->keylen, DMA_TO_DEVICE); } +static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq) +{ + struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq); + struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); + struct sun8i_ce_dev *ce = op->ce; + struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq); + int flow, err; + + flow = rctx->flow; + err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm)); + sun8i_ce_cipher_unprepare(engine, areq); + local_bh_disable(); + crypto_finalize_skcipher_request(engine, breq, err); + local_bh_enable(); +} + int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq) { int err = sun8i_ce_cipher_prepare(engine, areq); @@ -368,7 +369,6 @@ int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq) return err; sun8i_ce_cipher_run(engine, areq); - sun8i_ce_cipher_unprepare(engine, areq); return 0; } diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig index 32268e239bf1..f394e45e11ab 100644 --- a/drivers/crypto/ccp/Kconfig +++ b/drivers/crypto/ccp/Kconfig @@ -38,7 +38,7 @@ config CRYPTO_DEV_CCP_CRYPTO config CRYPTO_DEV_SP_PSP bool "Platform Security Processor (PSP) device" default y - depends on CRYPTO_DEV_CCP_DD && X86_64 + depends on CRYPTO_DEV_CCP_DD && X86_64 && AMD_IOMMU help Provide support for the AMD Platform Security Processor (PSP). The PSP is a dedicated processor that provides support for key diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index b04bc1d3d627..f44efbb89c34 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -21,14 +21,18 @@ #include <linux/hw_random.h> #include <linux/ccp.h> #include <linux/firmware.h> +#include <linux/panic_notifier.h> #include <linux/gfp.h> #include <linux/cpufeature.h> #include <linux/fs.h> #include <linux/fs_struct.h> #include <linux/psp.h> +#include <linux/amd-iommu.h> #include <asm/smp.h> #include <asm/cacheflush.h> +#include <asm/e820/types.h> +#include <asm/sev.h> #include "psp-dev.h" #include "sev-dev.h" @@ -37,6 +41,19 @@ #define SEV_FW_FILE "amd/sev.fw" #define SEV_FW_NAME_SIZE 64 +/* Minimum firmware version required for the SEV-SNP support */ +#define SNP_MIN_API_MAJOR 1 +#define SNP_MIN_API_MINOR 51 + +/* + * Maximum number of firmware-writable buffers that might be specified + * in the parameters of a legacy SEV command buffer. + */ +#define CMD_BUF_FW_WRITABLE_MAX 2 + +/* Leave room in the descriptor array for an end-of-list indicator. */ +#define CMD_BUF_DESC_MAX (CMD_BUF_FW_WRITABLE_MAX + 1) + static DEFINE_MUTEX(sev_cmd_mutex); static struct sev_misc_dev *misc_dev; @@ -68,9 +85,14 @@ static int psp_timeout; * The TMR is a 1MB area that must be 1MB aligned. Use the page allocator * to allocate the memory, which will return aligned memory for the specified * allocation order. + * + * When SEV-SNP is enabled the TMR needs to be 2MB aligned and 2MB sized. */ -#define SEV_ES_TMR_SIZE (1024 * 1024) +#define SEV_TMR_SIZE (1024 * 1024) +#define SNP_TMR_SIZE (2 * 1024 * 1024) + static void *sev_es_tmr; +static size_t sev_es_tmr_size = SEV_TMR_SIZE; /* INIT_EX NV Storage: * The NV Storage is a 32Kb area and must be 4Kb page aligned. Use the page @@ -80,6 +102,13 @@ static void *sev_es_tmr; #define NV_LENGTH (32 * 1024) static void *sev_init_ex_buffer; +/* + * SEV_DATA_RANGE_LIST: + * Array containing range of pages that firmware transitions to HV-fixed + * page state. + */ +static struct sev_data_range_list *snp_range_list; + static inline bool sev_version_greater_or_equal(u8 maj, u8 min) { struct sev_device *sev = psp_master->sev_data; @@ -115,6 +144,25 @@ static int sev_wait_cmd_ioc(struct sev_device *sev, { int ret; + /* + * If invoked during panic handling, local interrupts are disabled, + * so the PSP command completion interrupt can't be used. Poll for + * PSP command completion instead. + */ + if (irqs_disabled()) { + unsigned long timeout_usecs = (timeout * USEC_PER_SEC) / 10; + + /* Poll for SEV command completion: */ + while (timeout_usecs--) { + *reg = ioread32(sev->io_regs + sev->vdata->cmdresp_reg); + if (*reg & PSP_CMDRESP_RESP) + return 0; + + udelay(10); + } + return -ETIMEDOUT; + } + ret = wait_event_timeout(sev->int_queue, sev->int_rcvd, timeout * HZ); if (!ret) @@ -130,6 +178,8 @@ static int sev_cmd_buffer_len(int cmd) switch (cmd) { case SEV_CMD_INIT: return sizeof(struct sev_data_init); case SEV_CMD_INIT_EX: return sizeof(struct sev_data_init_ex); + case SEV_CMD_SNP_SHUTDOWN_EX: return sizeof(struct sev_data_snp_shutdown_ex); + case SEV_CMD_SNP_INIT_EX: return sizeof(struct sev_data_snp_init_ex); case SEV_CMD_PLATFORM_STATUS: return sizeof(struct sev_user_data_status); case SEV_CMD_PEK_CSR: return sizeof(struct sev_data_pek_csr); case SEV_CMD_PEK_CERT_IMPORT: return sizeof(struct sev_data_pek_cert_import); @@ -158,23 +208,27 @@ static int sev_cmd_buffer_len(int cmd) case SEV_CMD_GET_ID: return sizeof(struct sev_data_get_id); case SEV_CMD_ATTESTATION_REPORT: return sizeof(struct sev_data_attestation_report); case SEV_CMD_SEND_CANCEL: return sizeof(struct sev_data_send_cancel); + case SEV_CMD_SNP_GCTX_CREATE: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_LAUNCH_START: return sizeof(struct sev_data_snp_launch_start); + case SEV_CMD_SNP_LAUNCH_UPDATE: return sizeof(struct sev_data_snp_launch_update); + case SEV_CMD_SNP_ACTIVATE: return sizeof(struct sev_data_snp_activate); + case SEV_CMD_SNP_DECOMMISSION: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_PAGE_RECLAIM: return sizeof(struct sev_data_snp_page_reclaim); + case SEV_CMD_SNP_GUEST_STATUS: return sizeof(struct sev_data_snp_guest_status); + case SEV_CMD_SNP_LAUNCH_FINISH: return sizeof(struct sev_data_snp_launch_finish); + case SEV_CMD_SNP_DBG_DECRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_DBG_ENCRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_PAGE_UNSMASH: return sizeof(struct sev_data_snp_page_unsmash); + case SEV_CMD_SNP_PLATFORM_STATUS: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_GUEST_REQUEST: return sizeof(struct sev_data_snp_guest_request); + case SEV_CMD_SNP_CONFIG: return sizeof(struct sev_user_data_snp_config); + case SEV_CMD_SNP_COMMIT: return sizeof(struct sev_data_snp_commit); default: return 0; } return 0; } -static void *sev_fw_alloc(unsigned long len) -{ - struct page *page; - - page = alloc_pages(GFP_KERNEL, get_order(len)); - if (!page) - return NULL; - - return page_address(page); -} - static struct file *open_file_as_root(const char *filename, int flags, umode_t mode) { struct file *fp; @@ -305,13 +359,485 @@ static int sev_write_init_ex_file_if_required(int cmd_id) return sev_write_init_ex_file(); } +/* + * snp_reclaim_pages() needs __sev_do_cmd_locked(), and __sev_do_cmd_locked() + * needs snp_reclaim_pages(), so a forward declaration is needed. + */ +static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret); + +static int snp_reclaim_pages(unsigned long paddr, unsigned int npages, bool locked) +{ + int ret, err, i; + + paddr = __sme_clr(ALIGN_DOWN(paddr, PAGE_SIZE)); + + for (i = 0; i < npages; i++, paddr += PAGE_SIZE) { + struct sev_data_snp_page_reclaim data = {0}; + + data.paddr = paddr; + + if (locked) + ret = __sev_do_cmd_locked(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err); + else + ret = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err); + + if (ret) + goto cleanup; + + ret = rmp_make_shared(__phys_to_pfn(paddr), PG_LEVEL_4K); + if (ret) + goto cleanup; + } + + return 0; + +cleanup: + /* + * If there was a failure reclaiming the page then it is no longer safe + * to release it back to the system; leak it instead. + */ + snp_leak_pages(__phys_to_pfn(paddr), npages - i); + return ret; +} + +static int rmp_mark_pages_firmware(unsigned long paddr, unsigned int npages, bool locked) +{ + unsigned long pfn = __sme_clr(paddr) >> PAGE_SHIFT; + int rc, i; + + for (i = 0; i < npages; i++, pfn++) { + rc = rmp_make_private(pfn, 0, PG_LEVEL_4K, 0, true); + if (rc) + goto cleanup; + } + + return 0; + +cleanup: + /* + * Try unrolling the firmware state changes by + * reclaiming the pages which were already changed to the + * firmware state. + */ + snp_reclaim_pages(paddr, i, locked); + + return rc; +} + +static struct page *__snp_alloc_firmware_pages(gfp_t gfp_mask, int order) +{ + unsigned long npages = 1ul << order, paddr; + struct sev_device *sev; + struct page *page; + + if (!psp_master || !psp_master->sev_data) + return NULL; + + page = alloc_pages(gfp_mask, order); + if (!page) + return NULL; + + /* If SEV-SNP is initialized then add the page in RMP table. */ + sev = psp_master->sev_data; + if (!sev->snp_initialized) + return page; + + paddr = __pa((unsigned long)page_address(page)); + if (rmp_mark_pages_firmware(paddr, npages, false)) + return NULL; + + return page; +} + +void *snp_alloc_firmware_page(gfp_t gfp_mask) +{ + struct page *page; + + page = __snp_alloc_firmware_pages(gfp_mask, 0); + + return page ? page_address(page) : NULL; +} +EXPORT_SYMBOL_GPL(snp_alloc_firmware_page); + +static void __snp_free_firmware_pages(struct page *page, int order, bool locked) +{ + struct sev_device *sev = psp_master->sev_data; + unsigned long paddr, npages = 1ul << order; + + if (!page) + return; + + paddr = __pa((unsigned long)page_address(page)); + if (sev->snp_initialized && + snp_reclaim_pages(paddr, npages, locked)) + return; + + __free_pages(page, order); +} + +void snp_free_firmware_page(void *addr) +{ + if (!addr) + return; + + __snp_free_firmware_pages(virt_to_page(addr), 0, false); +} +EXPORT_SYMBOL_GPL(snp_free_firmware_page); + +static void *sev_fw_alloc(unsigned long len) +{ + struct page *page; + + page = __snp_alloc_firmware_pages(GFP_KERNEL, get_order(len)); + if (!page) + return NULL; + + return page_address(page); +} + +/** + * struct cmd_buf_desc - descriptors for managing legacy SEV command address + * parameters corresponding to buffers that may be written to by firmware. + * + * @paddr_ptr: pointer to the address parameter in the command buffer which may + * need to be saved/restored depending on whether a bounce buffer + * is used. In the case of a bounce buffer, the command buffer + * needs to be updated with the address of the new bounce buffer + * snp_map_cmd_buf_desc() has allocated specifically for it. Must + * be NULL if this descriptor is only an end-of-list indicator. + * + * @paddr_orig: storage for the original address parameter, which can be used to + * restore the original value in @paddr_ptr in cases where it is + * replaced with the address of a bounce buffer. + * + * @len: length of buffer located at the address originally stored at @paddr_ptr + * + * @guest_owned: true if the address corresponds to guest-owned pages, in which + * case bounce buffers are not needed. + */ +struct cmd_buf_desc { + u64 *paddr_ptr; + u64 paddr_orig; + u32 len; + bool guest_owned; +}; + +/* + * If a legacy SEV command parameter is a memory address, those pages in + * turn need to be transitioned to/from firmware-owned before/after + * executing the firmware command. + * + * Additionally, in cases where those pages are not guest-owned, a bounce + * buffer is needed in place of the original memory address parameter. + * + * A set of descriptors are used to keep track of this handling, and + * initialized here based on the specific commands being executed. + */ +static void snp_populate_cmd_buf_desc_list(int cmd, void *cmd_buf, + struct cmd_buf_desc *desc_list) +{ + switch (cmd) { + case SEV_CMD_PDH_CERT_EXPORT: { + struct sev_data_pdh_cert_export *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->pdh_cert_address; + desc_list[0].len = data->pdh_cert_len; + desc_list[1].paddr_ptr = &data->cert_chain_address; + desc_list[1].len = data->cert_chain_len; + break; + } + case SEV_CMD_GET_ID: { + struct sev_data_get_id *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_PEK_CSR: { + struct sev_data_pek_csr *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_LAUNCH_UPDATE_DATA: { + struct sev_data_launch_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_LAUNCH_UPDATE_VMSA: { + struct sev_data_launch_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_LAUNCH_MEASURE: { + struct sev_data_launch_measure *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_LAUNCH_UPDATE_SECRET: { + struct sev_data_launch_secret *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_DBG_DECRYPT: { + struct sev_data_dbg *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->dst_addr; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_DBG_ENCRYPT: { + struct sev_data_dbg *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->dst_addr; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_ATTESTATION_REPORT: { + struct sev_data_attestation_report *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_SEND_START: { + struct sev_data_send_start *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->session_address; + desc_list[0].len = data->session_len; + break; + } + case SEV_CMD_SEND_UPDATE_DATA: { + struct sev_data_send_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->hdr_address; + desc_list[0].len = data->hdr_len; + desc_list[1].paddr_ptr = &data->trans_address; + desc_list[1].len = data->trans_len; + break; + } + case SEV_CMD_SEND_UPDATE_VMSA: { + struct sev_data_send_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->hdr_address; + desc_list[0].len = data->hdr_len; + desc_list[1].paddr_ptr = &data->trans_address; + desc_list[1].len = data->trans_len; + break; + } + case SEV_CMD_RECEIVE_UPDATE_DATA: { + struct sev_data_receive_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_RECEIVE_UPDATE_VMSA: { + struct sev_data_receive_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + default: + break; + } +} + +static int snp_map_cmd_buf_desc(struct cmd_buf_desc *desc) +{ + unsigned int npages; + + if (!desc->len) + return 0; + + /* Allocate a bounce buffer if this isn't a guest owned page. */ + if (!desc->guest_owned) { + struct page *page; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(desc->len)); + if (!page) { + pr_warn("Failed to allocate bounce buffer for SEV legacy command.\n"); + return -ENOMEM; + } + + desc->paddr_orig = *desc->paddr_ptr; + *desc->paddr_ptr = __psp_pa(page_to_virt(page)); + } + + npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT; + + /* Transition the buffer to firmware-owned. */ + if (rmp_mark_pages_firmware(*desc->paddr_ptr, npages, true)) { + pr_warn("Error moving pages to firmware-owned state for SEV legacy command.\n"); + return -EFAULT; + } + + return 0; +} + +static int snp_unmap_cmd_buf_desc(struct cmd_buf_desc *desc) +{ + unsigned int npages; + + if (!desc->len) + return 0; + + npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT; + + /* Transition the buffers back to hypervisor-owned. */ + if (snp_reclaim_pages(*desc->paddr_ptr, npages, true)) { + pr_warn("Failed to reclaim firmware-owned pages while issuing SEV legacy command.\n"); + return -EFAULT; + } + + /* Copy data from bounce buffer and then free it. */ + if (!desc->guest_owned) { + void *bounce_buf = __va(__sme_clr(*desc->paddr_ptr)); + void *dst_buf = __va(__sme_clr(desc->paddr_orig)); + + memcpy(dst_buf, bounce_buf, desc->len); + __free_pages(virt_to_page(bounce_buf), get_order(desc->len)); + + /* Restore the original address in the command buffer. */ + *desc->paddr_ptr = desc->paddr_orig; + } + + return 0; +} + +static int snp_map_cmd_buf_desc_list(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list) +{ + int i; + + snp_populate_cmd_buf_desc_list(cmd, cmd_buf, desc_list); + + for (i = 0; i < CMD_BUF_DESC_MAX; i++) { + struct cmd_buf_desc *desc = &desc_list[i]; + + if (!desc->paddr_ptr) + break; + + if (snp_map_cmd_buf_desc(desc)) + goto err_unmap; + } + + return 0; + +err_unmap: + for (i--; i >= 0; i--) + snp_unmap_cmd_buf_desc(&desc_list[i]); + + return -EFAULT; +} + +static int snp_unmap_cmd_buf_desc_list(struct cmd_buf_desc *desc_list) +{ + int i, ret = 0; + + for (i = 0; i < CMD_BUF_DESC_MAX; i++) { + struct cmd_buf_desc *desc = &desc_list[i]; + + if (!desc->paddr_ptr) + break; + + if (snp_unmap_cmd_buf_desc(&desc_list[i])) + ret = -EFAULT; + } + + return ret; +} + +static bool sev_cmd_buf_writable(int cmd) +{ + switch (cmd) { + case SEV_CMD_PLATFORM_STATUS: + case SEV_CMD_GUEST_STATUS: + case SEV_CMD_LAUNCH_START: + case SEV_CMD_RECEIVE_START: + case SEV_CMD_LAUNCH_MEASURE: + case SEV_CMD_SEND_START: + case SEV_CMD_SEND_UPDATE_DATA: + case SEV_CMD_SEND_UPDATE_VMSA: + case SEV_CMD_PEK_CSR: + case SEV_CMD_PDH_CERT_EXPORT: + case SEV_CMD_GET_ID: + case SEV_CMD_ATTESTATION_REPORT: + return true; + default: + return false; + } +} + +/* After SNP is INIT'ed, the behavior of legacy SEV commands is changed. */ +static bool snp_legacy_handling_needed(int cmd) +{ + struct sev_device *sev = psp_master->sev_data; + + return cmd < SEV_CMD_SNP_INIT && sev->snp_initialized; +} + +static int snp_prep_cmd_buf(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list) +{ + if (!snp_legacy_handling_needed(cmd)) + return 0; + + if (snp_map_cmd_buf_desc_list(cmd, cmd_buf, desc_list)) + return -EFAULT; + + /* + * Before command execution, the command buffer needs to be put into + * the firmware-owned state. + */ + if (sev_cmd_buf_writable(cmd)) { + if (rmp_mark_pages_firmware(__pa(cmd_buf), 1, true)) + return -EFAULT; + } + + return 0; +} + +static int snp_reclaim_cmd_buf(int cmd, void *cmd_buf) +{ + if (!snp_legacy_handling_needed(cmd)) + return 0; + + /* + * After command completion, the command buffer needs to be put back + * into the hypervisor-owned state. + */ + if (sev_cmd_buf_writable(cmd)) + if (snp_reclaim_pages(__pa(cmd_buf), 1, true)) + return -EFAULT; + + return 0; +} + static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) { + struct cmd_buf_desc desc_list[CMD_BUF_DESC_MAX] = {0}; struct psp_device *psp = psp_master; struct sev_device *sev; unsigned int cmdbuff_hi, cmdbuff_lo; unsigned int phys_lsb, phys_msb; unsigned int reg, ret = 0; + void *cmd_buf; int buf_len; if (!psp || !psp->sev_data) @@ -331,12 +857,47 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) * work for some memory, e.g. vmalloc'd addresses, and @data may not be * physically contiguous. */ - if (data) - memcpy(sev->cmd_buf, data, buf_len); + if (data) { + /* + * Commands are generally issued one at a time and require the + * sev_cmd_mutex, but there could be recursive firmware requests + * due to SEV_CMD_SNP_PAGE_RECLAIM needing to be issued while + * preparing buffers for another command. This is the only known + * case of nesting in the current code, so exactly one + * additional command buffer is available for that purpose. + */ + if (!sev->cmd_buf_active) { + cmd_buf = sev->cmd_buf; + sev->cmd_buf_active = true; + } else if (!sev->cmd_buf_backup_active) { + cmd_buf = sev->cmd_buf_backup; + sev->cmd_buf_backup_active = true; + } else { + dev_err(sev->dev, + "SEV: too many firmware commands in progress, no command buffers available.\n"); + return -EBUSY; + } + + memcpy(cmd_buf, data, buf_len); + + /* + * The behavior of the SEV-legacy commands is altered when the + * SNP firmware is in the INIT state. + */ + ret = snp_prep_cmd_buf(cmd, cmd_buf, desc_list); + if (ret) { + dev_err(sev->dev, + "SEV: failed to prepare buffer for legacy command 0x%x. Error: %d\n", + cmd, ret); + return ret; + } + } else { + cmd_buf = sev->cmd_buf; + } /* Get the physical address of the command buffer */ - phys_lsb = data ? lower_32_bits(__psp_pa(sev->cmd_buf)) : 0; - phys_msb = data ? upper_32_bits(__psp_pa(sev->cmd_buf)) : 0; + phys_lsb = data ? lower_32_bits(__psp_pa(cmd_buf)) : 0; + phys_msb = data ? upper_32_bits(__psp_pa(cmd_buf)) : 0; dev_dbg(sev->dev, "sev command id %#x buffer 0x%08x%08x timeout %us\n", cmd, phys_msb, phys_lsb, psp_timeout); @@ -390,20 +951,41 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) ret = sev_write_init_ex_file_if_required(cmd); } - print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, - buf_len, false); - /* * Copy potential output from the PSP back to data. Do this even on * failure in case the caller wants to glean something from the error. */ - if (data) - memcpy(data, sev->cmd_buf, buf_len); + if (data) { + int ret_reclaim; + /* + * Restore the page state after the command completes. + */ + ret_reclaim = snp_reclaim_cmd_buf(cmd, cmd_buf); + if (ret_reclaim) { + dev_err(sev->dev, + "SEV: failed to reclaim buffer for legacy command %#x. Error: %d\n", + cmd, ret_reclaim); + return ret_reclaim; + } + + memcpy(data, cmd_buf, buf_len); + + if (sev->cmd_buf_backup_active) + sev->cmd_buf_backup_active = false; + else + sev->cmd_buf_active = false; + + if (snp_unmap_cmd_buf_desc_list(desc_list)) + return -EFAULT; + } + + print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, + buf_len, false); return ret; } -static int sev_do_cmd(int cmd, void *data, int *psp_ret) +int sev_do_cmd(int cmd, void *data, int *psp_ret) { int rc; @@ -413,6 +995,7 @@ static int sev_do_cmd(int cmd, void *data, int *psp_ret) return rc; } +EXPORT_SYMBOL_GPL(sev_do_cmd); static int __sev_init_locked(int *error) { @@ -427,7 +1010,7 @@ static int __sev_init_locked(int *error) data.tmr_address = __pa(sev_es_tmr); data.flags |= SEV_INIT_FLAGS_SEV_ES; - data.tmr_len = SEV_ES_TMR_SIZE; + data.tmr_len = sev_es_tmr_size; } return __sev_do_cmd_locked(SEV_CMD_INIT, &data, error); @@ -450,7 +1033,7 @@ static int __sev_init_ex_locked(int *error) data.tmr_address = __pa(sev_es_tmr); data.flags |= SEV_INIT_FLAGS_SEV_ES; - data.tmr_len = SEV_ES_TMR_SIZE; + data.tmr_len = sev_es_tmr_size; } return __sev_do_cmd_locked(SEV_CMD_INIT_EX, &data, error); @@ -464,26 +1047,218 @@ static inline int __sev_do_init_locked(int *psp_ret) return __sev_init_locked(psp_ret); } -static int __sev_platform_init_locked(int *error) +static void snp_set_hsave_pa(void *arg) +{ + wrmsrl(MSR_VM_HSAVE_PA, 0); +} + +static int snp_filter_reserved_mem_regions(struct resource *rs, void *arg) +{ + struct sev_data_range_list *range_list = arg; + struct sev_data_range *range = &range_list->ranges[range_list->num_elements]; + size_t size; + + /* + * Ensure the list of HV_FIXED pages that will be passed to firmware + * do not exceed the page-sized argument buffer. + */ + if ((range_list->num_elements * sizeof(struct sev_data_range) + + sizeof(struct sev_data_range_list)) > PAGE_SIZE) + return -E2BIG; + + switch (rs->desc) { + case E820_TYPE_RESERVED: + case E820_TYPE_PMEM: + case E820_TYPE_ACPI: + range->base = rs->start & PAGE_MASK; + size = PAGE_ALIGN((rs->end + 1) - rs->start); + range->page_count = size >> PAGE_SHIFT; + range_list->num_elements++; + break; + default: + break; + } + + return 0; +} + +static int __sev_snp_init_locked(int *error) { - int rc = 0, psp_ret = SEV_RET_NO_FW_CALL; struct psp_device *psp = psp_master; + struct sev_data_snp_init_ex data; struct sev_device *sev; + void *arg = &data; + int cmd, rc = 0; - if (!psp || !psp->sev_data) + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) return -ENODEV; sev = psp->sev_data; - if (sev->state == SEV_STATE_INIT) + if (sev->snp_initialized) return 0; - if (sev_init_ex_buffer) { - rc = sev_read_init_ex_file(); - if (rc) + if (!sev_version_greater_or_equal(SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR)) { + dev_dbg(sev->dev, "SEV-SNP support requires firmware version >= %d:%d\n", + SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR); + return 0; + } + + /* SNP_INIT requires MSR_VM_HSAVE_PA to be cleared on all CPUs. */ + on_each_cpu(snp_set_hsave_pa, NULL, 1); + + /* + * Starting in SNP firmware v1.52, the SNP_INIT_EX command takes a list + * of system physical address ranges to convert into HV-fixed page + * states during the RMP initialization. For instance, the memory that + * UEFI reserves should be included in the that list. This allows system + * components that occasionally write to memory (e.g. logging to UEFI + * reserved regions) to not fail due to RMP initialization and SNP + * enablement. + * + */ + if (sev_version_greater_or_equal(SNP_MIN_API_MAJOR, 52)) { + /* + * Firmware checks that the pages containing the ranges enumerated + * in the RANGES structure are either in the default page state or in the + * firmware page state. + */ + snp_range_list = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!snp_range_list) { + dev_err(sev->dev, + "SEV: SNP_INIT_EX range list memory allocation failed\n"); + return -ENOMEM; + } + + /* + * Retrieve all reserved memory regions from the e820 memory map + * to be setup as HV-fixed pages. + */ + rc = walk_iomem_res_desc(IORES_DESC_NONE, IORESOURCE_MEM, 0, ~0, + snp_range_list, snp_filter_reserved_mem_regions); + if (rc) { + dev_err(sev->dev, + "SEV: SNP_INIT_EX walk_iomem_res_desc failed rc = %d\n", rc); return rc; + } + + memset(&data, 0, sizeof(data)); + data.init_rmp = 1; + data.list_paddr_en = 1; + data.list_paddr = __psp_pa(snp_range_list); + cmd = SEV_CMD_SNP_INIT_EX; + } else { + cmd = SEV_CMD_SNP_INIT; + arg = NULL; + } + + /* + * The following sequence must be issued before launching the first SNP + * guest to ensure all dirty cache lines are flushed, including from + * updates to the RMP table itself via the RMPUPDATE instruction: + * + * - WBINVD on all running CPUs + * - SEV_CMD_SNP_INIT[_EX] firmware command + * - WBINVD on all running CPUs + * - SEV_CMD_SNP_DF_FLUSH firmware command + */ + wbinvd_on_all_cpus(); + + rc = __sev_do_cmd_locked(cmd, arg, error); + if (rc) + return rc; + + /* Prepare for first SNP guest launch after INIT. */ + wbinvd_on_all_cpus(); + rc = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, error); + if (rc) + return rc; + + sev->snp_initialized = true; + dev_dbg(sev->dev, "SEV-SNP firmware initialized\n"); + + sev_es_tmr_size = SNP_TMR_SIZE; + + return rc; +} + +static void __sev_platform_init_handle_tmr(struct sev_device *sev) +{ + if (sev_es_tmr) + return; + + /* Obtain the TMR memory area for SEV-ES use */ + sev_es_tmr = sev_fw_alloc(sev_es_tmr_size); + if (sev_es_tmr) { + /* Must flush the cache before giving it to the firmware */ + if (!sev->snp_initialized) + clflush_cache_range(sev_es_tmr, sev_es_tmr_size); + } else { + dev_warn(sev->dev, "SEV: TMR allocation failed, SEV-ES support unavailable\n"); + } +} + +/* + * If an init_ex_path is provided allocate a buffer for the file and + * read in the contents. Additionally, if SNP is initialized, convert + * the buffer pages to firmware pages. + */ +static int __sev_platform_init_handle_init_ex_path(struct sev_device *sev) +{ + struct page *page; + int rc; + + if (!init_ex_path) + return 0; + + if (sev_init_ex_buffer) + return 0; + + page = alloc_pages(GFP_KERNEL, get_order(NV_LENGTH)); + if (!page) { + dev_err(sev->dev, "SEV: INIT_EX NV memory allocation failed\n"); + return -ENOMEM; + } + + sev_init_ex_buffer = page_address(page); + + rc = sev_read_init_ex_file(); + if (rc) + return rc; + + /* If SEV-SNP is initialized, transition to firmware page. */ + if (sev->snp_initialized) { + unsigned long npages; + + npages = 1UL << get_order(NV_LENGTH); + if (rmp_mark_pages_firmware(__pa(sev_init_ex_buffer), npages, false)) { + dev_err(sev->dev, "SEV: INIT_EX NV memory page state change failed.\n"); + return -ENOMEM; + } } + return 0; +} + +static int __sev_platform_init_locked(int *error) +{ + int rc, psp_ret = SEV_RET_NO_FW_CALL; + struct sev_device *sev; + + if (!psp_master || !psp_master->sev_data) + return -ENODEV; + + sev = psp_master->sev_data; + + if (sev->state == SEV_STATE_INIT) + return 0; + + __sev_platform_init_handle_tmr(sev); + + rc = __sev_platform_init_handle_init_ex_path(sev); + if (rc) + return rc; + rc = __sev_do_init_locked(&psp_ret); if (rc && psp_ret == SEV_RET_SECURE_DATA_INVALID) { /* @@ -520,12 +1295,46 @@ static int __sev_platform_init_locked(int *error) return 0; } -int sev_platform_init(int *error) +static int _sev_platform_init_locked(struct sev_platform_init_args *args) +{ + struct sev_device *sev; + int rc; + + if (!psp_master || !psp_master->sev_data) + return -ENODEV; + + sev = psp_master->sev_data; + + if (sev->state == SEV_STATE_INIT) + return 0; + + /* + * Legacy guests cannot be running while SNP_INIT(_EX) is executing, + * so perform SEV-SNP initialization at probe time. + */ + rc = __sev_snp_init_locked(&args->error); + if (rc && rc != -ENODEV) { + /* + * Don't abort the probe if SNP INIT failed, + * continue to initialize the legacy SEV firmware. + */ + dev_err(sev->dev, "SEV-SNP: failed to INIT rc %d, error %#x\n", + rc, args->error); + } + + /* Defer legacy SEV/SEV-ES support if allowed by caller/module. */ + if (args->probe && !psp_init_on_probe) + return 0; + + return __sev_platform_init_locked(&args->error); +} + +int sev_platform_init(struct sev_platform_init_args *args) { int rc; mutex_lock(&sev_cmd_mutex); - rc = __sev_platform_init_locked(error); + rc = _sev_platform_init_locked(args); mutex_unlock(&sev_cmd_mutex); return rc; @@ -556,17 +1365,6 @@ static int __sev_platform_shutdown_locked(int *error) return ret; } -static int sev_platform_shutdown(int *error) -{ - int rc; - - mutex_lock(&sev_cmd_mutex); - rc = __sev_platform_shutdown_locked(NULL); - mutex_unlock(&sev_cmd_mutex); - - return rc; -} - static int sev_get_platform_state(int *state, int *error) { struct sev_user_data_status data; @@ -842,6 +1640,72 @@ fw_err: return ret; } +static int __sev_snp_shutdown_locked(int *error, bool panic) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_shutdown_ex data; + int ret; + + if (!sev->snp_initialized) + return 0; + + memset(&data, 0, sizeof(data)); + data.len = sizeof(data); + data.iommu_snp_shutdown = 1; + + /* + * If invoked during panic handling, local interrupts are disabled + * and all CPUs are stopped, so wbinvd_on_all_cpus() can't be called. + * In that case, a wbinvd() is done on remote CPUs via the NMI + * callback, so only a local wbinvd() is needed here. + */ + if (!panic) + wbinvd_on_all_cpus(); + else + wbinvd(); + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, error); + /* SHUTDOWN may require DF_FLUSH */ + if (*error == SEV_RET_DFFLUSH_REQUIRED) { + ret = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, NULL); + if (ret) { + dev_err(sev->dev, "SEV-SNP DF_FLUSH failed\n"); + return ret; + } + /* reissue the shutdown command */ + ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, + error); + } + if (ret) { + dev_err(sev->dev, "SEV-SNP firmware shutdown failed\n"); + return ret; + } + + /* + * SNP_SHUTDOWN_EX with IOMMU_SNP_SHUTDOWN set to 1 disables SNP + * enforcement by the IOMMU and also transitions all pages + * associated with the IOMMU to the Reclaim state. + * Firmware was transitioning the IOMMU pages to Hypervisor state + * before version 1.53. But, accounting for the number of assigned + * 4kB pages in a 2M page was done incorrectly by not transitioning + * to the Reclaim state. This resulted in RMP #PF when later accessing + * the 2M page containing those pages during kexec boot. Hence, the + * firmware now transitions these pages to Reclaim state and hypervisor + * needs to transition these pages to shared state. SNP Firmware + * version 1.53 and above are needed for kexec boot. + */ + ret = amd_iommu_snp_disable(); + if (ret) { + dev_err(sev->dev, "SNP IOMMU shutdown failed\n"); + return ret; + } + + sev->snp_initialized = false; + dev_dbg(sev->dev, "SEV-SNP firmware shutdown\n"); + + return ret; +} + static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) { struct sev_device *sev = psp_master->sev_data; @@ -1084,6 +1948,85 @@ e_free_pdh: return ret; } +static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_addr buf; + struct page *status_page; + void *data; + int ret; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + status_page = alloc_page(GFP_KERNEL_ACCOUNT); + if (!status_page) + return -ENOMEM; + + data = page_address(status_page); + + /* + * Firmware expects status page to be in firmware-owned state, otherwise + * it will report firmware error code INVALID_PAGE_STATE (0x1A). + */ + if (rmp_mark_pages_firmware(__pa(data), 1, true)) { + ret = -EFAULT; + goto cleanup; + } + + buf.address = __psp_pa(data); + ret = __sev_do_cmd_locked(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &argp->error); + + /* + * Status page will be transitioned to Reclaim state upon success, or + * left in Firmware state in failure. Use snp_reclaim_pages() to + * transition either case back to Hypervisor-owned state. + */ + if (snp_reclaim_pages(__pa(data), 1, true)) + return -EFAULT; + + if (ret) + goto cleanup; + + if (copy_to_user((void __user *)argp->data, data, + sizeof(struct sev_user_data_snp_status))) + ret = -EFAULT; + +cleanup: + __free_pages(status_page, 0); + return ret; +} + +static int sev_ioctl_do_snp_commit(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_commit buf; + + if (!sev->snp_initialized) + return -EINVAL; + + buf.len = sizeof(buf); + + return __sev_do_cmd_locked(SEV_CMD_SNP_COMMIT, &buf, &argp->error); +} + +static int sev_ioctl_do_snp_set_config(struct sev_issue_cmd *argp, bool writable) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_snp_config config; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + if (!writable) + return -EPERM; + + if (copy_from_user(&config, (void __user *)argp->data, sizeof(config))) + return -EFAULT; + + return __sev_do_cmd_locked(SEV_CMD_SNP_CONFIG, &config, &argp->error); +} + static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -1135,6 +2078,15 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) case SEV_GET_ID2: ret = sev_ioctl_do_get_id2(&input); break; + case SNP_PLATFORM_STATUS: + ret = sev_ioctl_do_snp_platform_status(&input); + break; + case SNP_COMMIT: + ret = sev_ioctl_do_snp_commit(&input); + break; + case SNP_SET_CONFIG: + ret = sev_ioctl_do_snp_set_config(&input, writable); + break; default: ret = -EINVAL; goto out; @@ -1245,10 +2197,12 @@ int sev_dev_init(struct psp_device *psp) if (!sev) goto e_err; - sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 0); + sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 1); if (!sev->cmd_buf) goto e_sev; + sev->cmd_buf_backup = (uint8_t *)sev->cmd_buf + PAGE_SIZE; + psp->sev_data = sev; sev->dev = dev; @@ -1287,24 +2241,51 @@ e_err: return ret; } -static void sev_firmware_shutdown(struct sev_device *sev) +static void __sev_firmware_shutdown(struct sev_device *sev, bool panic) { - sev_platform_shutdown(NULL); + int error; + + __sev_platform_shutdown_locked(NULL); if (sev_es_tmr) { - /* The TMR area was encrypted, flush it from the cache */ - wbinvd_on_all_cpus(); + /* + * The TMR area was encrypted, flush it from the cache. + * + * If invoked during panic handling, local interrupts are + * disabled and all CPUs are stopped, so wbinvd_on_all_cpus() + * can't be used. In that case, wbinvd() is done on remote CPUs + * via the NMI callback, and done for this CPU later during + * SNP shutdown, so wbinvd_on_all_cpus() can be skipped. + */ + if (!panic) + wbinvd_on_all_cpus(); - free_pages((unsigned long)sev_es_tmr, - get_order(SEV_ES_TMR_SIZE)); + __snp_free_firmware_pages(virt_to_page(sev_es_tmr), + get_order(sev_es_tmr_size), + true); sev_es_tmr = NULL; } if (sev_init_ex_buffer) { - free_pages((unsigned long)sev_init_ex_buffer, - get_order(NV_LENGTH)); + __snp_free_firmware_pages(virt_to_page(sev_init_ex_buffer), + get_order(NV_LENGTH), + true); sev_init_ex_buffer = NULL; } + + if (snp_range_list) { + kfree(snp_range_list); + snp_range_list = NULL; + } + + __sev_snp_shutdown_locked(&error, panic); +} + +static void sev_firmware_shutdown(struct sev_device *sev) +{ + mutex_lock(&sev_cmd_mutex); + __sev_firmware_shutdown(sev, false); + mutex_unlock(&sev_cmd_mutex); } void sev_dev_destroy(struct psp_device *psp) @@ -1322,6 +2303,29 @@ void sev_dev_destroy(struct psp_device *psp) psp_clear_sev_irq_handler(psp); } +static int snp_shutdown_on_panic(struct notifier_block *nb, + unsigned long reason, void *arg) +{ + struct sev_device *sev = psp_master->sev_data; + + /* + * If sev_cmd_mutex is already acquired, then it's likely + * another PSP command is in flight and issuing a shutdown + * would fail in unexpected ways. Rather than create even + * more confusion during a panic, just bail out here. + */ + if (mutex_is_locked(&sev_cmd_mutex)) + return NOTIFY_DONE; + + __sev_firmware_shutdown(sev, true); + + return NOTIFY_DONE; +} + +static struct notifier_block snp_panic_notifier = { + .notifier_call = snp_shutdown_on_panic, +}; + int sev_issue_cmd_external_user(struct file *filep, unsigned int cmd, void *data, int *error) { @@ -1335,7 +2339,8 @@ EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user); void sev_pci_init(void) { struct sev_device *sev = psp_master->sev_data; - int error, rc; + struct sev_platform_init_args args = {0}; + int rc; if (!sev) return; @@ -1348,36 +2353,18 @@ void sev_pci_init(void) if (sev_update_firmware(sev->dev) == 0) sev_get_api_version(); - /* If an init_ex_path is provided rely on INIT_EX for PSP initialization - * instead of INIT. - */ - if (init_ex_path) { - sev_init_ex_buffer = sev_fw_alloc(NV_LENGTH); - if (!sev_init_ex_buffer) { - dev_err(sev->dev, - "SEV: INIT_EX NV memory allocation failed\n"); - goto err; - } - } - - /* Obtain the TMR memory area for SEV-ES use */ - sev_es_tmr = sev_fw_alloc(SEV_ES_TMR_SIZE); - if (sev_es_tmr) - /* Must flush the cache before giving it to the firmware */ - clflush_cache_range(sev_es_tmr, SEV_ES_TMR_SIZE); - else - dev_warn(sev->dev, - "SEV: TMR allocation failed, SEV-ES support unavailable\n"); - - if (!psp_init_on_probe) - return; - /* Initialize the platform */ - rc = sev_platform_init(&error); + args.probe = true; + rc = sev_platform_init(&args); if (rc) dev_err(sev->dev, "SEV: failed to INIT error %#x, rc %d\n", - error, rc); + args.error, rc); + dev_info(sev->dev, "SEV%s API:%d.%d build:%d\n", sev->snp_initialized ? + "-SNP" : "", sev->api_major, sev->api_minor, sev->build); + + atomic_notifier_chain_register(&panic_notifier_list, + &snp_panic_notifier); return; err: @@ -1392,4 +2379,7 @@ void sev_pci_exit(void) return; sev_firmware_shutdown(sev); + + atomic_notifier_chain_unregister(&panic_notifier_list, + &snp_panic_notifier); } diff --git a/drivers/crypto/ccp/sev-dev.h b/drivers/crypto/ccp/sev-dev.h index 778c95155e74..3e4e5574e88a 100644 --- a/drivers/crypto/ccp/sev-dev.h +++ b/drivers/crypto/ccp/sev-dev.h @@ -52,6 +52,11 @@ struct sev_device { u8 build; void *cmd_buf; + void *cmd_buf_backup; + bool cmd_buf_active; + bool cmd_buf_backup_active; + + bool snp_initialized; }; int sev_dev_init(struct psp_device *psp); diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index 1b13b4aa16ec..a235e6c300f1 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -332,12 +332,12 @@ static int rk_hash_run(struct crypto_engine *engine, void *breq) theend: pm_runtime_put_autosuspend(rkc->dev); + rk_hash_unprepare(engine, breq); + local_bh_disable(); crypto_finalize_hash_request(engine, breq, err); local_bh_enable(); - rk_hash_unprepare(engine, breq); - return 0; } diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index 1ebfbe88e733..97ebc791a30b 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -747,8 +747,8 @@ static int mv_xor_v2_probe(struct platform_device *pdev) if (IS_ERR(xor_dev->clk)) return PTR_ERR(xor_dev->clk); - ret = platform_msi_domain_alloc_irqs(&pdev->dev, 1, - mv_xor_v2_set_msi_msg); + ret = platform_device_msi_init_and_alloc_irqs(&pdev->dev, 1, + mv_xor_v2_set_msi_msg); if (ret) return ret; @@ -851,7 +851,7 @@ free_hw_desq: xor_dev->desc_size * MV_XOR_V2_DESC_NUM, xor_dev->hw_desq_virt, xor_dev->hw_desq); free_msi_irqs: - platform_msi_domain_free_irqs(&pdev->dev); + platform_device_msi_free_irqs_all(&pdev->dev); return ret; } @@ -867,7 +867,7 @@ static void mv_xor_v2_remove(struct platform_device *pdev) devm_free_irq(&pdev->dev, xor_dev->irq, xor_dev); - platform_msi_domain_free_irqs(&pdev->dev); + platform_device_msi_free_irqs_all(&pdev->dev); tasklet_kill(&xor_dev->irq_tasklet); } diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c index d63b93dc7047..202ac95227cb 100644 --- a/drivers/dma/qcom/hidma.c +++ b/drivers/dma/qcom/hidma.c @@ -696,7 +696,7 @@ static void hidma_free_msis(struct hidma_dev *dmadev) devm_free_irq(dev, virq, &dmadev->lldev); } - platform_msi_domain_free_irqs(dev); + platform_device_msi_free_irqs_all(dev); #endif } @@ -706,8 +706,8 @@ static int hidma_request_msi(struct hidma_dev *dmadev, #ifdef CONFIG_GENERIC_MSI_IRQ int rc, i, virq; - rc = platform_msi_domain_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS, - hidma_write_msi_msg); + rc = platform_device_msi_init_and_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS, + hidma_write_msi_msg); if (rc) return rc; diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index 241db366b2c7..7f686d179fc9 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -42,11 +42,6 @@ struct dpll_pin_registration { void *priv; }; -struct dpll_pin *netdev_dpll_pin(const struct net_device *dev) -{ - return rcu_dereference_rtnl(dev->dpll_pin); -} - struct dpll_device *dpll_device_get_by_id(int id) { if (xa_get_mark(&dpll_device_xa, id, DPLL_REGISTERED)) @@ -513,6 +508,26 @@ err_pin_prop: return ERR_PTR(ret); } +static void dpll_netdev_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin) +{ + rtnl_lock(); + rcu_assign_pointer(dev->dpll_pin, dpll_pin); + rtnl_unlock(); +} + +void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) +{ + WARN_ON(!dpll_pin); + dpll_netdev_pin_assign(dev, dpll_pin); +} +EXPORT_SYMBOL(dpll_netdev_pin_set); + +void dpll_netdev_pin_clear(struct net_device *dev) +{ + dpll_netdev_pin_assign(dev, NULL); +} +EXPORT_SYMBOL(dpll_netdev_pin_clear); + /** * dpll_pin_get - find existing or create new dpll pin * @clock_id: clock_id of creator diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 4ca9ad16cd95..b57355e0c214 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -8,6 +8,7 @@ */ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/netdevice.h> #include <net/genetlink.h> #include "dpll_core.h" #include "dpll_netlink.h" @@ -48,18 +49,6 @@ dpll_msg_add_dev_parent_handle(struct sk_buff *msg, u32 id) } /** - * dpll_msg_pin_handle_size - get size of pin handle attribute for given pin - * @pin: pin pointer - * - * Return: byte size of pin handle attribute for given pin. - */ -size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) -{ - return pin ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */ -} -EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size); - -/** * dpll_msg_add_pin_handle - attach pin handle attribute to a given message * @msg: pointer to sk_buff message to attach a pin handle * @pin: pin pointer @@ -68,7 +57,7 @@ EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size); * * 0 - success * * -EMSGSIZE - no space in message to attach pin handle */ -int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +static int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) { if (!pin) return 0; @@ -76,7 +65,28 @@ int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) return -EMSGSIZE; return 0; } -EXPORT_SYMBOL_GPL(dpll_msg_add_pin_handle); + +static struct dpll_pin *dpll_netdev_pin(const struct net_device *dev) +{ + return rcu_dereference_rtnl(dev->dpll_pin); +} + +/** + * dpll_netdev_pin_handle_size - get size of pin handle attribute of a netdev + * @dev: netdev from which to get the pin + * + * Return: byte size of pin handle attribute, or 0 if @dev has no pin. + */ +size_t dpll_netdev_pin_handle_size(const struct net_device *dev) +{ + return dpll_netdev_pin(dev) ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */ +} + +int dpll_netdev_add_pin_handle(struct sk_buff *msg, + const struct net_device *dev) +{ + return dpll_msg_add_pin_handle(msg, dpll_netdev_pin(dev)); +} static int dpll_msg_add_mode(struct sk_buff *msg, struct dpll_device *dpll, diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 5a7f3fabee22..16c8de5050e5 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -78,6 +78,7 @@ config EDAC_GHES config EDAC_AMD64 tristate "AMD64 (Opteron, Athlon64)" depends on AMD_NB && EDAC_DECODE_MCE + imply AMD_ATL help Support for error detection and correction of DRAM ECC errors on the AMD64 families (>= K8) of memory controllers. diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 537b9987a431..1f3520d76861 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/ras.h> #include "amd64_edac.h" #include <asm/amd_nb.h> @@ -1051,281 +1052,6 @@ static int fixup_node_id(int node_id, struct mce *m) return nid - gpu_node_map.base_node_id + 1; } -/* Protect the PCI config register pairs used for DF indirect access. */ -static DEFINE_MUTEX(df_indirect_mutex); - -/* - * Data Fabric Indirect Access uses FICAA/FICAD. - * - * Fabric Indirect Configuration Access Address (FICAA): Constructed based - * on the device's Instance Id and the PCI function and register offset of - * the desired register. - * - * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO - * and FICAD HI registers but so far we only need the LO register. - * - * Use Instance Id 0xFF to indicate a broadcast read. - */ -#define DF_BROADCAST 0xFF -static int __df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) -{ - struct pci_dev *F4; - u32 ficaa; - int err = -ENODEV; - - if (node >= amd_nb_num()) - goto out; - - F4 = node_to_amd_nb(node)->link; - if (!F4) - goto out; - - ficaa = (instance_id == DF_BROADCAST) ? 0 : 1; - ficaa |= reg & 0x3FC; - ficaa |= (func & 0x7) << 11; - ficaa |= instance_id << 16; - - mutex_lock(&df_indirect_mutex); - - err = pci_write_config_dword(F4, 0x5C, ficaa); - if (err) { - pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa); - goto out_unlock; - } - - err = pci_read_config_dword(F4, 0x98, lo); - if (err) - pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa); - -out_unlock: - mutex_unlock(&df_indirect_mutex); - -out: - return err; -} - -static int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) -{ - return __df_indirect_read(node, func, reg, instance_id, lo); -} - -static int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo) -{ - return __df_indirect_read(node, func, reg, DF_BROADCAST, lo); -} - -struct addr_ctx { - u64 ret_addr; - u32 tmp; - u16 nid; - u8 inst_id; -}; - -static int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) -{ - u64 dram_base_addr, dram_limit_addr, dram_hole_base; - - u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask; - u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets; - u8 intlv_addr_sel, intlv_addr_bit; - u8 num_intlv_bits, hashed_bit; - u8 lgcy_mmio_hole_en, base = 0; - u8 cs_mask, cs_id = 0; - bool hash_enabled = false; - - struct addr_ctx ctx; - - memset(&ctx, 0, sizeof(ctx)); - - /* Start from the normalized address */ - ctx.ret_addr = norm_addr; - - ctx.nid = nid; - ctx.inst_id = umc; - - /* Read D18F0x1B4 (DramOffset), check if base 1 is used. */ - if (df_indirect_read_instance(nid, 0, 0x1B4, umc, &ctx.tmp)) - goto out_err; - - /* Remove HiAddrOffset from normalized address, if enabled: */ - if (ctx.tmp & BIT(0)) { - u64 hi_addr_offset = (ctx.tmp & GENMASK_ULL(31, 20)) << 8; - - if (norm_addr >= hi_addr_offset) { - ctx.ret_addr -= hi_addr_offset; - base = 1; - } - } - - /* Read D18F0x110 (DramBaseAddress). */ - if (df_indirect_read_instance(nid, 0, 0x110 + (8 * base), umc, &ctx.tmp)) - goto out_err; - - /* Check if address range is valid. */ - if (!(ctx.tmp & BIT(0))) { - pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n", - __func__, ctx.tmp); - goto out_err; - } - - lgcy_mmio_hole_en = ctx.tmp & BIT(1); - intlv_num_chan = (ctx.tmp >> 4) & 0xF; - intlv_addr_sel = (ctx.tmp >> 8) & 0x7; - dram_base_addr = (ctx.tmp & GENMASK_ULL(31, 12)) << 16; - - /* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */ - if (intlv_addr_sel > 3) { - pr_err("%s: Invalid interleave address select %d.\n", - __func__, intlv_addr_sel); - goto out_err; - } - - /* Read D18F0x114 (DramLimitAddress). */ - if (df_indirect_read_instance(nid, 0, 0x114 + (8 * base), umc, &ctx.tmp)) - goto out_err; - - intlv_num_sockets = (ctx.tmp >> 8) & 0x1; - intlv_num_dies = (ctx.tmp >> 10) & 0x3; - dram_limit_addr = ((ctx.tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0); - - intlv_addr_bit = intlv_addr_sel + 8; - - /* Re-use intlv_num_chan by setting it equal to log2(#channels) */ - switch (intlv_num_chan) { - case 0: intlv_num_chan = 0; break; - case 1: intlv_num_chan = 1; break; - case 3: intlv_num_chan = 2; break; - case 5: intlv_num_chan = 3; break; - case 7: intlv_num_chan = 4; break; - - case 8: intlv_num_chan = 1; - hash_enabled = true; - break; - default: - pr_err("%s: Invalid number of interleaved channels %d.\n", - __func__, intlv_num_chan); - goto out_err; - } - - num_intlv_bits = intlv_num_chan; - - if (intlv_num_dies > 2) { - pr_err("%s: Invalid number of interleaved nodes/dies %d.\n", - __func__, intlv_num_dies); - goto out_err; - } - - num_intlv_bits += intlv_num_dies; - - /* Add a bit if sockets are interleaved. */ - num_intlv_bits += intlv_num_sockets; - - /* Assert num_intlv_bits <= 4 */ - if (num_intlv_bits > 4) { - pr_err("%s: Invalid interleave bits %d.\n", - __func__, num_intlv_bits); - goto out_err; - } - - if (num_intlv_bits > 0) { - u64 temp_addr_x, temp_addr_i, temp_addr_y; - u8 die_id_bit, sock_id_bit, cs_fabric_id; - - /* - * Read FabricBlockInstanceInformation3_CS[BlockFabricID]. - * This is the fabric id for this coherent slave. Use - * umc/channel# as instance id of the coherent slave - * for FICAA. - */ - if (df_indirect_read_instance(nid, 0, 0x50, umc, &ctx.tmp)) - goto out_err; - - cs_fabric_id = (ctx.tmp >> 8) & 0xFF; - die_id_bit = 0; - - /* If interleaved over more than 1 channel: */ - if (intlv_num_chan) { - die_id_bit = intlv_num_chan; - cs_mask = (1 << die_id_bit) - 1; - cs_id = cs_fabric_id & cs_mask; - } - - sock_id_bit = die_id_bit; - - /* Read D18F1x208 (SystemFabricIdMask). */ - if (intlv_num_dies || intlv_num_sockets) - if (df_indirect_read_broadcast(nid, 1, 0x208, &ctx.tmp)) - goto out_err; - - /* If interleaved over more than 1 die. */ - if (intlv_num_dies) { - sock_id_bit = die_id_bit + intlv_num_dies; - die_id_shift = (ctx.tmp >> 24) & 0xF; - die_id_mask = (ctx.tmp >> 8) & 0xFF; - - cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit; - } - - /* If interleaved over more than 1 socket. */ - if (intlv_num_sockets) { - socket_id_shift = (ctx.tmp >> 28) & 0xF; - socket_id_mask = (ctx.tmp >> 16) & 0xFF; - - cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit; - } - - /* - * The pre-interleaved address consists of XXXXXXIIIYYYYY - * where III is the ID for this CS, and XXXXXXYYYYY are the - * address bits from the post-interleaved address. - * "num_intlv_bits" has been calculated to tell us how many "I" - * bits there are. "intlv_addr_bit" tells us how many "Y" bits - * there are (where "I" starts). - */ - temp_addr_y = ctx.ret_addr & GENMASK_ULL(intlv_addr_bit - 1, 0); - temp_addr_i = (cs_id << intlv_addr_bit); - temp_addr_x = (ctx.ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits; - ctx.ret_addr = temp_addr_x | temp_addr_i | temp_addr_y; - } - - /* Add dram base address */ - ctx.ret_addr += dram_base_addr; - - /* If legacy MMIO hole enabled */ - if (lgcy_mmio_hole_en) { - if (df_indirect_read_broadcast(nid, 0, 0x104, &ctx.tmp)) - goto out_err; - - dram_hole_base = ctx.tmp & GENMASK(31, 24); - if (ctx.ret_addr >= dram_hole_base) - ctx.ret_addr += (BIT_ULL(32) - dram_hole_base); - } - - if (hash_enabled) { - /* Save some parentheses and grab ls-bit at the end. */ - hashed_bit = (ctx.ret_addr >> 12) ^ - (ctx.ret_addr >> 18) ^ - (ctx.ret_addr >> 21) ^ - (ctx.ret_addr >> 30) ^ - cs_id; - - hashed_bit &= BIT(0); - - if (hashed_bit != ((ctx.ret_addr >> intlv_addr_bit) & BIT(0))) - ctx.ret_addr ^= BIT(intlv_addr_bit); - } - - /* Is calculated system address is above DRAM limit address? */ - if (ctx.ret_addr > dram_limit_addr) - goto out_err; - - *sys_addr = ctx.ret_addr; - return 0; - -out_err: - return -EINVAL; -} - static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16); /* @@ -1915,7 +1641,7 @@ ddr3: /* On F10h and later ErrAddr is MC4_ADDR[47:1] */ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m) { - u16 mce_nid = topology_die_id(m->extcpu); + u16 mce_nid = topology_amd_node_id(m->extcpu); struct mem_ctl_info *mci; u8 start_bit = 1; u8 end_bit = 47; @@ -3073,9 +2799,10 @@ static void decode_umc_error(int node_id, struct mce *m) { u8 ecc_type = (m->status >> 45) & 0x3; struct mem_ctl_info *mci; + unsigned long sys_addr; struct amd64_pvt *pvt; + struct atl_err a_err; struct err_info err; - u64 sys_addr; node_id = fixup_node_id(node_id, m); @@ -3106,7 +2833,12 @@ static void decode_umc_error(int node_id, struct mce *m) pvt->ops->get_err_info(m, &err); - if (umc_normaddr_to_sysaddr(m->addr, pvt->mc_node_id, err.channel, &sys_addr)) { + a_err.addr = m->addr; + a_err.ipid = m->ipid; + a_err.cpu = m->extcpu; + + sys_addr = amd_convert_umc_mca_addr_to_sys_addr(&a_err); + if (IS_ERR_VALUE(sys_addr)) { err.err_code = ERR_NORM_ADDR; goto log_error; } @@ -3446,7 +3178,7 @@ static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, u16 nid) int cpu; for_each_online_cpu(cpu) - if (topology_die_id(cpu) == nid) + if (topology_amd_node_id(cpu) == nid) cpumask_set_cpu(cpu, mask); } diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c index 2b83d6de9352..3fd22a1eb1a9 100644 --- a/drivers/edac/i10nm_base.c +++ b/drivers/edac/i10nm_base.c @@ -951,6 +951,7 @@ static const struct x86_cpu_id i10nm_cpuids[] = { X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(EMERALDRAPIDS_X, X86_STEPPINGS(0x0, 0xf), &spr_cfg), X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(GRANITERAPIDS_X, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ATOM_CRESTMONT_X, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ATOM_CRESTMONT, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), {} }; MODULE_DEVICE_TABLE(x86cpu, i10nm_cpuids); diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 2b0ecdeba5cd..cdd8480e7368 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -238,6 +238,7 @@ static struct work_struct ecclog_work; #define DID_ADL_N_SKU9 0x4678 #define DID_ADL_N_SKU10 0x4679 #define DID_ADL_N_SKU11 0x467c +#define DID_ADL_N_SKU12 0x4632 /* Compute die IDs for Raptor Lake-P with IBECC */ #define DID_RPL_P_SKU1 0xa706 @@ -583,6 +584,7 @@ static const struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), (kernel_ulong_t)&rpl_p_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), (kernel_ulong_t)&rpl_p_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), (kernel_ulong_t)&rpl_p_cfg }, diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index ec8b6c9fedfd..8130c3dc64da 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -584,7 +584,7 @@ static void decode_mc3_mce(struct mce *m) static void decode_mc4_mce(struct mce *m) { unsigned int fam = x86_family(m->cpuid); - int node_id = topology_die_id(m->extcpu); + int node_id = topology_amd_node_id(m->extcpu); u16 ec = EC(m->status); u8 xec = XEC(m->status, 0x1f); u8 offset = 0; @@ -746,7 +746,7 @@ static void decode_smca_error(struct mce *m) if ((bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0 && decode_dram_ecc) - decode_dram_ecc(topology_die_id(m->extcpu), m); + decode_dram_ecc(topology_amd_node_id(m->extcpu), m); } static inline void amd_decode_err_code(u16 ec) diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index 709babce43ba..5527055b0964 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -1324,11 +1324,9 @@ static int mc_probe(struct platform_device *pdev) struct synps_edac_priv *priv; struct mem_ctl_info *mci; void __iomem *baseaddr; - struct resource *res; int rc; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - baseaddr = devm_ioremap_resource(&pdev->dev, res); + baseaddr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(baseaddr)) return PTR_ERR(baseaddr); diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c index 62caf454b567..1688a5050f63 100644 --- a/drivers/edac/versal_edac.c +++ b/drivers/edac/versal_edac.c @@ -42,8 +42,11 @@ #define ECCW0_FLIP_CTRL 0x109C #define ECCW0_FLIP0_OFFSET 0x10A0 +#define ECCW0_FLIP0_BITS 31 +#define ECCW0_FLIP1_OFFSET 0x10A4 #define ECCW1_FLIP_CTRL 0x10AC #define ECCW1_FLIP0_OFFSET 0x10B0 +#define ECCW1_FLIP1_OFFSET 0x10B4 #define ECCR0_CERR_STAT_OFFSET 0x10BC #define ECCR0_CE_ADDR_LO_OFFSET 0x10C0 #define ECCR0_CE_ADDR_HI_OFFSET 0x10C4 @@ -116,9 +119,6 @@ #define XDDR_BUS_WIDTH_32 1 #define XDDR_BUS_WIDTH_16 2 -#define ECC_CEPOISON_MASK 0x1 -#define ECC_UEPOISON_MASK 0x3 - #define XDDR_MAX_ROW_CNT 18 #define XDDR_MAX_COL_CNT 10 #define XDDR_MAX_RANK_CNT 2 @@ -133,6 +133,7 @@ * https://docs.xilinx.com/r/en-US/am012-versal-register-reference/PCSR_LOCK-XRAM_SLCR-Register */ #define PCSR_UNLOCK_VAL 0xF9E8D7C6 +#define PCSR_LOCK_VAL 1 #define XDDR_ERR_TYPE_CE 0 #define XDDR_ERR_TYPE_UE 1 @@ -142,6 +143,7 @@ #define XILINX_DRAM_SIZE_12G 3 #define XILINX_DRAM_SIZE_16G 4 #define XILINX_DRAM_SIZE_32G 5 +#define NUM_UE_BITPOS 2 /** * struct ecc_error_info - ECC error log information. @@ -479,7 +481,7 @@ static void err_callback(const u32 *payload, void *data) writel(regval, priv->ddrmc_baseaddr + XDDR_ISR_OFFSET); /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); edac_dbg(3, "Total error count CE %d UE %d\n", priv->ce_cnt, priv->ue_cnt); } @@ -650,7 +652,7 @@ static void enable_intr(struct edac_priv *priv) writel(XDDR_IRQ_UE_MASK, priv->ddrmc_baseaddr + XDDR_IRQ1_EN_OFFSET); /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); } static void disable_intr(struct edac_priv *priv) @@ -663,7 +665,7 @@ static void disable_intr(struct edac_priv *priv) priv->ddrmc_baseaddr + XDDR_IRQ_DIS_OFFSET); /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); } #define to_mci(k) container_of(k, struct mem_ctl_info, dev) @@ -734,38 +736,63 @@ static void poison_setup(struct edac_priv *priv) writel(regval, priv->ddrmc_noc_baseaddr + XDDR_NOC_REG_ADEC15_OFFSET); } -static ssize_t xddr_inject_data_poison_store(struct mem_ctl_info *mci, - const char __user *data) +static void xddr_inject_data_ce_store(struct mem_ctl_info *mci, u8 ce_bitpos) { + u32 ecc0_flip0, ecc1_flip0, ecc0_flip1, ecc1_flip1; struct edac_priv *priv = mci->pvt_info; - writel(0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET); - writel(0, priv->ddrmc_baseaddr + ECCW1_FLIP0_OFFSET); - - if (strncmp(data, "CE", 2) == 0) { - writel(ECC_CEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW0_FLIP0_OFFSET); - writel(ECC_CEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW1_FLIP0_OFFSET); + if (ce_bitpos < ECCW0_FLIP0_BITS) { + ecc0_flip0 = BIT(ce_bitpos); + ecc1_flip0 = BIT(ce_bitpos); + ecc0_flip1 = 0; + ecc1_flip1 = 0; } else { - writel(ECC_UEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW0_FLIP0_OFFSET); - writel(ECC_UEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW1_FLIP0_OFFSET); + ce_bitpos = ce_bitpos - ECCW0_FLIP0_BITS; + ecc0_flip1 = BIT(ce_bitpos); + ecc1_flip1 = BIT(ce_bitpos); + ecc0_flip0 = 0; + ecc1_flip0 = 0; } - /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); - - return 0; + writel(ecc0_flip0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET); + writel(ecc1_flip0, priv->ddrmc_baseaddr + ECCW1_FLIP0_OFFSET); + writel(ecc0_flip1, priv->ddrmc_baseaddr + ECCW0_FLIP1_OFFSET); + writel(ecc1_flip1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET); } -static ssize_t inject_data_poison_store(struct file *file, const char __user *data, - size_t count, loff_t *ppos) +/* + * To inject a correctable error, the following steps are needed: + * + * - Write the correctable error bit position value: + * echo <bit_pos val> > /sys/kernel/debug/edac/<controller instance>/inject_ce + * + * poison_setup() derives the row, column, bank, group and rank and + * writes to the ADEC registers based on the address given by the user. + * + * The ADEC12 and ADEC13 are mask registers; write 0 to make sure default + * configuration is there and no addresses are masked. + * + * The row, column, bank, group and rank registers are written to the + * match ADEC bit to generate errors at the particular address. ADEC14 + * and ADEC15 have the match bits. + * + * xddr_inject_data_ce_store() updates the ECC FLIP registers with the + * bits to be corrupted based on the bit position given by the user. + * + * Upon doing a read to the address the errors are injected. + */ +static ssize_t inject_data_ce_store(struct file *file, const char __user *data, + size_t count, loff_t *ppos) { struct device *dev = file->private_data; struct mem_ctl_info *mci = to_mci(dev); struct edac_priv *priv = mci->pvt_info; + u8 ce_bitpos; + int ret; + + ret = kstrtou8_from_user(data, count, 0, &ce_bitpos); + if (ret) + return ret; /* Unlock the PCSR registers */ writel(PCSR_UNLOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); @@ -773,17 +800,110 @@ static ssize_t inject_data_poison_store(struct file *file, const char __user *da poison_setup(priv); + xddr_inject_data_ce_store(mci, ce_bitpos); + ret = count; + /* Lock the PCSR registers */ - writel(1, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + + return ret; +} + +static const struct file_operations xddr_inject_ce_fops = { + .open = simple_open, + .write = inject_data_ce_store, + .llseek = generic_file_llseek, +}; + +static void xddr_inject_data_ue_store(struct mem_ctl_info *mci, u32 val0, u32 val1) +{ + struct edac_priv *priv = mci->pvt_info; + + writel(val0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET); + writel(val0, priv->ddrmc_baseaddr + ECCW0_FLIP1_OFFSET); + writel(val1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET); + writel(val1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET); +} + +/* + * To inject an uncorrectable error, the following steps are needed: + * echo <bit_pos val> > /sys/kernel/debug/edac/<controller instance>/inject_ue + * + * poison_setup() derives the row, column, bank, group and rank and + * writes to the ADEC registers based on the address given by the user. + * + * The ADEC12 and ADEC13 are mask registers; write 0 so that none of the + * addresses are masked. The row, column, bank, group and rank registers + * are written to the match ADEC bit to generate errors at the + * particular address. ADEC14 and ADEC15 have the match bits. + * + * xddr_inject_data_ue_store() updates the ECC FLIP registers with the + * bits to be corrupted based on the bit position given by the user. For + * uncorrectable errors + * 2 bit errors are injected. + * + * Upon doing a read to the address the errors are injected. + */ +static ssize_t inject_data_ue_store(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + struct device *dev = file->private_data; + struct mem_ctl_info *mci = to_mci(dev); + struct edac_priv *priv = mci->pvt_info; + char buf[6], *pbuf, *token[2]; + u32 val0 = 0, val1 = 0; + u8 len, ue0, ue1; + int i, ret; + + len = min_t(size_t, count, sizeof(buf)); + if (copy_from_user(buf, data, len)) + return -EFAULT; + + buf[len] = '\0'; + pbuf = &buf[0]; + for (i = 0; i < NUM_UE_BITPOS; i++) + token[i] = strsep(&pbuf, ","); + + ret = kstrtou8(token[0], 0, &ue0); + if (ret) + return ret; + + ret = kstrtou8(token[1], 0, &ue1); + if (ret) + return ret; + + if (ue0 < ECCW0_FLIP0_BITS) { + val0 = BIT(ue0); + } else { + ue0 = ue0 - ECCW0_FLIP0_BITS; + val1 = BIT(ue0); + } + + if (ue1 < ECCW0_FLIP0_BITS) { + val0 |= BIT(ue1); + } else { + ue1 = ue1 - ECCW0_FLIP0_BITS; + val1 |= BIT(ue1); + } - xddr_inject_data_poison_store(mci, data); + /* Unlock the PCSR registers */ + writel(PCSR_UNLOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_UNLOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + poison_setup(priv); + + xddr_inject_data_ue_store(mci, val0, val1); + + /* Lock the PCSR registers */ + writel(PCSR_LOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); return count; } -static const struct file_operations xddr_inject_enable_fops = { +static const struct file_operations xddr_inject_ue_fops = { .open = simple_open, - .write = inject_data_poison_store, + .write = inject_data_ue_store, .llseek = generic_file_llseek, }; @@ -795,8 +915,17 @@ static void create_debugfs_attributes(struct mem_ctl_info *mci) if (!priv->debugfs) return; - edac_debugfs_create_file("inject_error", 0200, priv->debugfs, - &mci->dev, &xddr_inject_enable_fops); + if (!edac_debugfs_create_file("inject_ce", 0200, priv->debugfs, + &mci->dev, &xddr_inject_ce_fops)) { + debugfs_remove_recursive(priv->debugfs); + return; + } + + if (!edac_debugfs_create_file("inject_ue", 0200, priv->debugfs, + &mci->dev, &xddr_inject_ue_fops)) { + debugfs_remove_recursive(priv->debugfs); + return; + } debugfs_create_x64("address", 0600, priv->debugfs, &priv->err_inject_addr); mci->debugfs = priv->debugfs; @@ -1031,7 +1160,7 @@ free_edac_mc: return rc; } -static int mc_remove(struct platform_device *pdev) +static void mc_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); struct edac_priv *priv = mci->pvt_info; @@ -1049,8 +1178,6 @@ static int mc_remove(struct platform_device *pdev) XPM_EVENT_ERROR_MASK_DDRMC_NCR, err_callback, mci); edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); - - return 0; } static struct platform_driver xilinx_ddr_edac_mc_driver = { @@ -1059,7 +1186,7 @@ static struct platform_driver xilinx_ddr_edac_mc_driver = { .of_match_table = xlnx_edac_match, }, .probe = mc_probe, - .remove = mc_remove, + .remove_new = mc_remove, }; module_platform_driver(xilinx_ddr_edac_mc_driver); diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 9db9290c3269..7bc71f4be64a 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -3773,6 +3773,7 @@ static int pci_probe(struct pci_dev *dev, return 0; fail_msi: + devm_free_irq(&dev->dev, dev->irq, ohci); pci_disable_msi(dev); return err; @@ -3800,6 +3801,7 @@ static void pci_remove(struct pci_dev *dev) software_reset(ohci); + devm_free_irq(&dev->dev, dev->irq, ohci); pci_disable_msi(dev); dev_notice(&dev->dev, "removing fw-ohci device\n"); diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c index 682e417be5a3..fbeeaee4ac85 100644 --- a/drivers/firmware/microchip/mpfs-auto-update.c +++ b/drivers/firmware/microchip/mpfs-auto-update.c @@ -384,7 +384,8 @@ static int mpfs_auto_update_available(struct mpfs_auto_update_priv *priv) u32 *response_msg; int ret; - response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(response_msg), + response_msg = devm_kzalloc(priv->dev, + AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(*response_msg), GFP_KERNEL); if (!response_msg) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 5853cf022917..1a9bbb04bd5e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -6539,7 +6539,7 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector) struct edid *edid; struct i2c_adapter *ddc; - if (dc_link->aux_mode) + if (dc_link && dc_link->aux_mode) ddc = &aconnector->dm_dp_aux.aux.ddc; else ddc = &aconnector->i2c->base; @@ -11169,14 +11169,23 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector, if (range->flags != 1) continue; - amdgpu_dm_connector->min_vfreq = range->min_vfreq; - amdgpu_dm_connector->max_vfreq = range->max_vfreq; - amdgpu_dm_connector->pixel_clock_mhz = - range->pixel_clock_mhz * 10; - connector->display_info.monitor_range.min_vfreq = range->min_vfreq; connector->display_info.monitor_range.max_vfreq = range->max_vfreq; + if (edid->revision >= 4) { + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MIN_VFREQ) + connector->display_info.monitor_range.min_vfreq += 255; + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MAX_VFREQ) + connector->display_info.monitor_range.max_vfreq += 255; + } + + amdgpu_dm_connector->min_vfreq = + connector->display_info.monitor_range.min_vfreq; + amdgpu_dm_connector->max_vfreq = + connector->display_info.monitor_range.max_vfreq; + amdgpu_dm_connector->pixel_clock_mhz = + range->pixel_clock_mhz * 10; + break; } diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 087d57850304..39c5e1dfa275 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2558,6 +2558,7 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev, { struct amdgpu_device *adev = dev_get_drvdata(dev); int err, ret; + u32 pwm_mode; int value; if (amdgpu_in_reset(adev)) @@ -2569,13 +2570,22 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev, if (err) return err; + if (value == 0) + pwm_mode = AMD_FAN_CTRL_NONE; + else if (value == 1) + pwm_mode = AMD_FAN_CTRL_MANUAL; + else if (value == 2) + pwm_mode = AMD_FAN_CTRL_AUTO; + else + return -EINVAL; + ret = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (ret < 0) { pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); return ret; } - ret = amdgpu_dpm_set_fan_control_mode(adev, value); + ret = amdgpu_dpm_set_fan_control_mode(adev, pwm_mode); pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 2ff6deedef95..da1f43999d09 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -451,7 +451,7 @@ static int vangogh_init_smc_tables(struct smu_context *smu) #ifdef CONFIG_X86 /* AMD x86 APU only */ - smu->cpu_core_num = boot_cpu_data.x86_max_cores; + smu->cpu_core_num = topology_num_cores_per_package(); #else smu->cpu_core_num = 4; #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index 4894f7ee737b..6dae5ad74ff0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -229,8 +229,6 @@ int smu_v14_0_check_fw_version(struct smu_context *smu) smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_2; break; case IP_VERSION(14, 0, 0): - if ((smu->smc_fw_version < 0x5d3a00)) - dev_warn(smu->adev->dev, "The PMFW version(%x) is behind in this BIOS!\n", smu->smc_fw_version); smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0; break; default: diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c index 47fdbae4adfc..9310c4758e38 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c @@ -261,7 +261,10 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu, *value = metrics->MpipuclkFrequency; break; case METRICS_AVERAGE_GFXACTIVITY: - *value = metrics->GfxActivity / 100; + if ((smu->smc_fw_version > 0x5d4600)) + *value = metrics->GfxActivity; + else + *value = metrics->GfxActivity / 100; break; case METRICS_AVERAGE_VCNACTIVITY: *value = metrics->VcnActivity / 100; diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 3f479483d7d8..23b4e9a3361d 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -760,9 +760,11 @@ static void output_poll_execute(struct work_struct *work) changed = dev->mode_config.delayed_event; dev->mode_config.delayed_event = false; - if (!drm_kms_helper_poll && dev->mode_config.poll_running) { - drm_kms_helper_disable_hpd(dev); - dev->mode_config.poll_running = false; + if (!drm_kms_helper_poll) { + if (dev->mode_config.poll_running) { + drm_kms_helper_disable_hpd(dev); + dev->mode_config.poll_running = false; + } goto out; } diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c index 47cd6bb04366..06900ff307b2 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_well.c +++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c @@ -246,7 +246,14 @@ static enum phy icl_aux_pw_to_phy(struct drm_i915_private *i915, enum aux_ch aux_ch = icl_aux_pw_to_ch(power_well); struct intel_digital_port *dig_port = aux_ch_to_digital_port(i915, aux_ch); - return intel_port_to_phy(i915, dig_port->base.port); + /* + * FIXME should we care about the (VBT defined) dig_port->aux_ch + * relationship or should this be purely defined by the hardware layout? + * Currently if the port doesn't appear in the VBT, or if it's declared + * as HDMI-only and routed to a combo PHY, the encoder either won't be + * present at all or it will not have an aux_ch assigned. + */ + return dig_port ? intel_port_to_phy(i915, dig_port->base.port) : PHY_NONE; } static void hsw_wait_for_power_well_enable(struct drm_i915_private *dev_priv, @@ -414,7 +421,8 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, intel_de_rmw(dev_priv, regs->driver, 0, HSW_PWR_WELL_CTL_REQ(pw_idx)); - if (DISPLAY_VER(dev_priv) < 12) + /* FIXME this is a mess */ + if (phy != PHY_NONE) intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy), 0, ICL_LANE_ENABLE_AUX); @@ -437,7 +445,10 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv, drm_WARN_ON(&dev_priv->drm, !IS_ICELAKE(dev_priv)); - intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy), ICL_LANE_ENABLE_AUX, 0); + /* FIXME this is a mess */ + if (phy != PHY_NONE) + intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy), + ICL_LANE_ENABLE_AUX, 0); intel_de_rmw(dev_priv, regs->driver, HSW_PWR_WELL_CTL_REQ(pw_idx), 0); diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 3fdd8a517983..ac7fe6281afe 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -609,6 +609,13 @@ struct intel_connector { * and active (i.e. dpms ON state). */ bool (*get_hw_state)(struct intel_connector *); + /* + * Optional hook called during init/resume to sync any state + * stored in the connector (eg. DSC state) wrt. the HW state. + */ + void (*sync_state)(struct intel_connector *connector, + const struct intel_crtc_state *crtc_state); + /* Panel info for eDP and LVDS */ struct intel_panel panel; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index ae647d03af25..94d2a15d8444 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -5699,6 +5699,9 @@ intel_dp_detect(struct drm_connector *connector, goto out; } + if (!intel_dp_is_edp(intel_dp)) + intel_psr_init_dpcd(intel_dp); + intel_dp_detect_dsc_caps(intel_dp, intel_connector); intel_dp_configure_mst(intel_dp); @@ -5859,6 +5862,19 @@ intel_dp_connector_unregister(struct drm_connector *connector) intel_connector_unregister(connector); } +void intel_dp_connector_sync_state(struct intel_connector *connector, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(connector->base.dev); + + if (crtc_state && crtc_state->dsc.compression_enable) { + drm_WARN_ON(&i915->drm, !connector->dp.dsc_decompression_aux); + connector->dp.dsc_decompression_enabled = true; + } else { + connector->dp.dsc_decompression_enabled = false; + } +} + void intel_dp_encoder_flush_work(struct drm_encoder *encoder) { struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder)); diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index 05db46b111f2..375d0677cd8c 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -45,6 +45,8 @@ bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state, int intel_dp_min_bpp(enum intel_output_format output_format); bool intel_dp_init_connector(struct intel_digital_port *dig_port, struct intel_connector *intel_connector); +void intel_dp_connector_sync_state(struct intel_connector *connector, + const struct intel_crtc_state *crtc_state); void intel_dp_set_link_params(struct intel_dp *intel_dp, int link_rate, int lane_count); int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c index 3a595cd433d4..8538d1ce2fcb 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c @@ -330,23 +330,13 @@ static const struct hdcp2_dp_msg_data hdcp2_dp_msg_data[] = { 0, 0 }, }; -static struct drm_dp_aux * -intel_dp_hdcp_get_aux(struct intel_connector *connector) -{ - struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - - if (intel_encoder_is_mst(connector->encoder)) - return &connector->port->aux; - else - return &dig_port->dp.aux; -} - static int intel_dp_hdcp2_read_rx_status(struct intel_connector *connector, u8 *rx_status) { struct drm_i915_private *i915 = to_i915(connector->base.dev); - struct drm_dp_aux *aux = intel_dp_hdcp_get_aux(connector); + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); + struct drm_dp_aux *aux = &dig_port->dp.aux; ssize_t ret; ret = drm_dp_dpcd_read(aux, @@ -399,7 +389,9 @@ intel_dp_hdcp2_wait_for_msg(struct intel_connector *connector, const struct hdcp2_dp_msg_data *hdcp2_msg_data) { struct drm_i915_private *i915 = to_i915(connector->base.dev); - struct intel_hdcp *hdcp = &connector->hdcp; + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); + struct intel_dp *dp = &dig_port->dp; + struct intel_hdcp *hdcp = &dp->attached_connector->hdcp; u8 msg_id = hdcp2_msg_data->msg_id; int ret, timeout; bool msg_ready = false; @@ -454,8 +446,9 @@ int intel_dp_hdcp2_write_msg(struct intel_connector *connector, unsigned int offset; u8 *byte = buf; ssize_t ret, bytes_to_write, len; + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); + struct drm_dp_aux *aux = &dig_port->dp.aux; const struct hdcp2_dp_msg_data *hdcp2_msg_data; - struct drm_dp_aux *aux; hdcp2_msg_data = get_hdcp2_dp_msg_data(*byte); if (!hdcp2_msg_data) @@ -463,8 +456,6 @@ int intel_dp_hdcp2_write_msg(struct intel_connector *connector, offset = hdcp2_msg_data->offset; - aux = intel_dp_hdcp_get_aux(connector); - /* No msg_id in DP HDCP2.2 msgs */ bytes_to_write = size - 1; byte++; @@ -490,7 +481,8 @@ static ssize_t get_receiver_id_list_rx_info(struct intel_connector *connector, u32 *dev_cnt, u8 *byte) { - struct drm_dp_aux *aux = intel_dp_hdcp_get_aux(connector); + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); + struct drm_dp_aux *aux = &dig_port->dp.aux; ssize_t ret; u8 *rx_info = byte; @@ -515,8 +507,9 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector, { struct intel_digital_port *dig_port = intel_attached_dig_port(connector); struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - struct intel_hdcp *hdcp = &connector->hdcp; - struct drm_dp_aux *aux; + struct drm_dp_aux *aux = &dig_port->dp.aux; + struct intel_dp *dp = &dig_port->dp; + struct intel_hdcp *hdcp = &dp->attached_connector->hdcp; unsigned int offset; u8 *byte = buf; ssize_t ret, bytes_to_recv, len; @@ -530,8 +523,6 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector, return -EINVAL; offset = hdcp2_msg_data->offset; - aux = intel_dp_hdcp_get_aux(connector); - ret = intel_dp_hdcp2_wait_for_msg(connector, hdcp2_msg_data); if (ret < 0) return ret; @@ -561,13 +552,8 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector, /* Entire msg read timeout since initiate of msg read */ if (bytes_to_recv == size - 1 && hdcp2_msg_data->msg_read_timeout > 0) { - if (intel_encoder_is_mst(connector->encoder)) - msg_end = ktime_add_ms(ktime_get_raw(), - hdcp2_msg_data->msg_read_timeout * - connector->port->parent->num_ports); - else - msg_end = ktime_add_ms(ktime_get_raw(), - hdcp2_msg_data->msg_read_timeout); + msg_end = ktime_add_ms(ktime_get_raw(), + hdcp2_msg_data->msg_read_timeout); } ret = drm_dp_dpcd_read(aux, offset, @@ -651,12 +637,11 @@ static int intel_dp_hdcp2_capable(struct intel_connector *connector, bool *capable) { - struct drm_dp_aux *aux; + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); + struct drm_dp_aux *aux = &dig_port->dp.aux; u8 rx_caps[3]; int ret; - aux = intel_dp_hdcp_get_aux(connector); - *capable = false; ret = drm_dp_dpcd_read(aux, DP_HDCP_2_2_REG_RX_CAPS_OFFSET, diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 8a9432335030..a01a59f57ae5 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -1534,6 +1534,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo return NULL; intel_connector->get_hw_state = intel_dp_mst_get_hw_state; + intel_connector->sync_state = intel_dp_connector_sync_state; intel_connector->mst_port = intel_dp; intel_connector->port = port; drm_dp_mst_get_port_malloc(port); diff --git a/drivers/gpu/drm/i915/display/intel_modeset_setup.c b/drivers/gpu/drm/i915/display/intel_modeset_setup.c index 94eece7f63be..caeca3a8442c 100644 --- a/drivers/gpu/drm/i915/display/intel_modeset_setup.c +++ b/drivers/gpu/drm/i915/display/intel_modeset_setup.c @@ -318,12 +318,6 @@ static void intel_modeset_update_connector_atomic_state(struct drm_i915_private const struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); - if (crtc_state->dsc.compression_enable) { - drm_WARN_ON(&i915->drm, !connector->dp.dsc_decompression_aux); - connector->dp.dsc_decompression_enabled = true; - } else { - connector->dp.dsc_decompression_enabled = false; - } conn_state->max_bpc = (crtc_state->pipe_bpp ?: 24) / 3; } } @@ -775,8 +769,9 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) drm_connector_list_iter_begin(&i915->drm, &conn_iter); for_each_intel_connector_iter(connector, &conn_iter) { + struct intel_crtc_state *crtc_state = NULL; + if (connector->get_hw_state(connector)) { - struct intel_crtc_state *crtc_state; struct intel_crtc *crtc; connector->base.dpms = DRM_MODE_DPMS_ON; @@ -802,6 +797,10 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) connector->base.dpms = DRM_MODE_DPMS_OFF; connector->base.encoder = NULL; } + + if (connector->sync_state) + connector->sync_state(connector, crtc_state); + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] hw state readout: %s\n", connector->base.base.id, connector->base.name, diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 57bbf3e3af92..4faaf4b3fc53 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -2776,9 +2776,6 @@ void intel_psr_init(struct intel_dp *intel_dp) if (!(HAS_PSR(dev_priv) || HAS_DP20(dev_priv))) return; - if (!intel_dp_is_edp(intel_dp)) - intel_psr_init_dpcd(intel_dp); - /* * HSW spec explicitly says PSR is tied to port A. * BDW+ platforms have a instance of PSR registers per transcoder but diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 1d3ebdf4069b..c08b67593565 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -379,6 +379,9 @@ i915_gem_userptr_release(struct drm_i915_gem_object *obj) { GEM_WARN_ON(obj->userptr.page_ref); + if (!obj->userptr.notifier.mm) + return; + mmu_interval_notifier_remove(&obj->userptr.notifier); obj->userptr.notifier.mm = NULL; } diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c index 2990dd4d4a0d..e14ac0ab1314 100644 --- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c +++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c @@ -3,6 +3,8 @@ * Copyright © 2021 Intel Corporation */ +#include <linux/jiffies.h> + //#include "gt/intel_engine_user.h" #include "gt/intel_gt.h" #include "i915_drv.h" @@ -12,7 +14,7 @@ #define REDUCED_TIMESLICE 5 #define REDUCED_PREEMPT 10 -#define WAIT_FOR_RESET_TIME 10000 +#define WAIT_FOR_RESET_TIME_MS 10000 struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt) { @@ -91,7 +93,7 @@ int intel_selftest_wait_for_rq(struct i915_request *rq) { long ret; - ret = i915_request_wait(rq, 0, WAIT_FOR_RESET_TIME); + ret = i915_request_wait(rq, 0, msecs_to_jiffies(WAIT_FOR_RESET_TIME_MS)); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h index 0d9fc741a719..932c9fd0b2d8 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h @@ -11,6 +11,7 @@ struct nvkm_client { u32 debug; struct rb_root objroot; + spinlock_t obj_lock; void *data; int (*event)(u64 token, void *argv, u32 argc); diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 49c2bcbef129..5a887d67dc0e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -764,7 +764,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, return -ENOMEM; if (unlikely(nouveau_cli_uvmm(cli))) - return -ENOSYS; + return nouveau_abi16_put(abi16, -ENOSYS); list_for_each_entry(temp, &abi16->channels, head) { if (temp->chan->chid == req->channel) { diff --git a/drivers/gpu/drm/nouveau/nvkm/core/client.c b/drivers/gpu/drm/nouveau/nvkm/core/client.c index ebdeb8eb9e77..c55662937ab2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/client.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/client.c @@ -180,6 +180,7 @@ nvkm_client_new(const char *name, u64 device, const char *cfg, const char *dbg, client->device = device; client->debug = nvkm_dbgopt(dbg, "CLIENT"); client->objroot = RB_ROOT; + spin_lock_init(&client->obj_lock); client->event = event; INIT_LIST_HEAD(&client->umem); spin_lock_init(&client->lock); diff --git a/drivers/gpu/drm/nouveau/nvkm/core/object.c b/drivers/gpu/drm/nouveau/nvkm/core/object.c index 7c554c14e884..aea3ba72027a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/object.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/object.c @@ -30,8 +30,10 @@ nvkm_object_search(struct nvkm_client *client, u64 handle, const struct nvkm_object_func *func) { struct nvkm_object *object; + unsigned long flags; if (handle) { + spin_lock_irqsave(&client->obj_lock, flags); struct rb_node *node = client->objroot.rb_node; while (node) { object = rb_entry(node, typeof(*object), node); @@ -40,9 +42,12 @@ nvkm_object_search(struct nvkm_client *client, u64 handle, else if (handle > object->object) node = node->rb_right; - else + else { + spin_unlock_irqrestore(&client->obj_lock, flags); goto done; + } } + spin_unlock_irqrestore(&client->obj_lock, flags); return ERR_PTR(-ENOENT); } else { object = &client->object; @@ -57,30 +62,39 @@ done: void nvkm_object_remove(struct nvkm_object *object) { + unsigned long flags; + + spin_lock_irqsave(&object->client->obj_lock, flags); if (!RB_EMPTY_NODE(&object->node)) rb_erase(&object->node, &object->client->objroot); + spin_unlock_irqrestore(&object->client->obj_lock, flags); } bool nvkm_object_insert(struct nvkm_object *object) { - struct rb_node **ptr = &object->client->objroot.rb_node; + struct rb_node **ptr; struct rb_node *parent = NULL; + unsigned long flags; + spin_lock_irqsave(&object->client->obj_lock, flags); + ptr = &object->client->objroot.rb_node; while (*ptr) { struct nvkm_object *this = rb_entry(*ptr, typeof(*this), node); parent = *ptr; - if (object->object < this->object) + if (object->object < this->object) { ptr = &parent->rb_left; - else - if (object->object > this->object) + } else if (object->object > this->object) { ptr = &parent->rb_right; - else + } else { + spin_unlock_irqrestore(&object->client->obj_lock, flags); return false; + } } rb_link_node(&object->node, parent, ptr); rb_insert_color(&object->node, &object->client->objroot); + spin_unlock_irqrestore(&object->client->obj_lock, flags); return true; } diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index c4c0f08e9202..4945a1e787eb 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1768,11 +1768,11 @@ static const struct panel_desc starry_qfh032011_53g_desc = { }; static const struct drm_display_mode starry_himax83102_j02_default_mode = { - .clock = 162850, + .clock = 162680, .hdisplay = 1200, - .hsync_start = 1200 + 50, - .hsync_end = 1200 + 50 + 20, - .htotal = 1200 + 50 + 20 + 50, + .hsync_start = 1200 + 60, + .hsync_end = 1200 + 60 + 20, + .htotal = 1200 + 60 + 20 + 40, .vdisplay = 1920, .vsync_start = 1920 + 116, .vsync_end = 1920 + 116 + 8, diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c index be2d9d7764be..e48863a44556 100644 --- a/drivers/gpu/drm/tests/drm_buddy_test.c +++ b/drivers/gpu/drm/tests/drm_buddy_test.c @@ -189,7 +189,7 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test) &allocated, DRM_BUDDY_RANGE_ALLOCATION), "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", - bias_start, bias_end, size); + bias_start, bias_end, size, ps); bias_rem -= size; /* @@ -260,30 +260,30 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test) KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, ps, ps, list, 0), - "buddy_alloc hit an error size=%u\n", + "buddy_alloc hit an error size=%lu\n", ps); } while (++i < n_pages); KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 3 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc didn't error size=%u\n", 3 * ps); + "buddy_alloc didn't error size=%lu\n", 3 * ps); drm_buddy_free_list(&mm, &middle); KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 3 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc didn't error size=%u\n", 3 * ps); + "buddy_alloc didn't error size=%lu\n", 3 * ps); KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 2 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc didn't error size=%u\n", 2 * ps); + "buddy_alloc didn't error size=%lu\n", 2 * ps); drm_buddy_free_list(&mm, &right); KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 3 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc didn't error size=%u\n", 3 * ps); + "buddy_alloc didn't error size=%lu\n", 3 * ps); /* * At this point we should have enough contiguous space for 2 blocks, * however they are never buddies (since we freed middle and right) so @@ -292,13 +292,13 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test) KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 2 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc hit an error size=%u\n", 2 * ps); + "buddy_alloc hit an error size=%lu\n", 2 * ps); drm_buddy_free_list(&mm, &left); KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 3 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc hit an error size=%u\n", 3 * ps); + "buddy_alloc hit an error size=%lu\n", 3 * ps); total = 0; list_for_each_entry(block, &allocated, link) diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c index 1eb0c304f960..f37c0d765865 100644 --- a/drivers/gpu/drm/tests/drm_mm_test.c +++ b/drivers/gpu/drm/tests/drm_mm_test.c @@ -157,7 +157,7 @@ static void drm_test_mm_init(struct kunit *test) /* After creation, it should all be one massive hole */ if (!assert_one_hole(test, &mm, 0, size)) { - KUNIT_FAIL(test, ""); + KUNIT_FAIL(test, "mm not one hole on creation"); goto out; } @@ -171,14 +171,14 @@ static void drm_test_mm_init(struct kunit *test) /* After filling the range entirely, there should be no holes */ if (!assert_no_holes(test, &mm)) { - KUNIT_FAIL(test, ""); + KUNIT_FAIL(test, "mm has holes when filled"); goto out; } /* And then after emptying it again, the massive hole should be back */ drm_mm_remove_node(&tmp); if (!assert_one_hole(test, &mm, 0, size)) { - KUNIT_FAIL(test, ""); + KUNIT_FAIL(test, "mm does not have single hole after emptying"); goto out; } diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c index a6523df0f1d3..c347e2c29f81 100644 --- a/drivers/gpu/drm/xe/tests/xe_migrate.c +++ b/drivers/gpu/drm/xe/tests/xe_migrate.c @@ -114,21 +114,21 @@ static void test_copy(struct xe_migrate *m, struct xe_bo *bo, region | XE_BO_NEEDS_CPU_ACCESS); if (IS_ERR(remote)) { - KUNIT_FAIL(test, "Failed to allocate remote bo for %s: %li\n", - str, PTR_ERR(remote)); + KUNIT_FAIL(test, "Failed to allocate remote bo for %s: %pe\n", + str, remote); return; } err = xe_bo_validate(remote, NULL, false); if (err) { - KUNIT_FAIL(test, "Failed to validate system bo for %s: %li\n", + KUNIT_FAIL(test, "Failed to validate system bo for %s: %i\n", str, err); goto out_unlock; } err = xe_bo_vmap(remote); if (err) { - KUNIT_FAIL(test, "Failed to vmap system bo for %s: %li\n", + KUNIT_FAIL(test, "Failed to vmap system bo for %s: %i\n", str, err); goto out_unlock; } diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c index 044c20881de7..0650b2fa75ef 100644 --- a/drivers/gpu/drm/xe/xe_tile.c +++ b/drivers/gpu/drm/xe/xe_tile.c @@ -167,9 +167,10 @@ int xe_tile_init_noalloc(struct xe_tile *tile) goto err_mem_access; tile->mem.kernel_bb_pool = xe_sa_bo_manager_init(tile, SZ_1M, 16); - if (IS_ERR(tile->mem.kernel_bb_pool)) + if (IS_ERR(tile->mem.kernel_bb_pool)) { err = PTR_ERR(tile->mem.kernel_bb_pool); - + goto err_mem_access; + } xe_wa_apply_tile_workarounds(tile); xe_tile_sysfs_init(tile); diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 56f7e06c673e..adbf674355b2 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -322,125 +322,89 @@ static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer, pagecount = hv_gpadl_size(type, size) >> HV_HYP_PAGE_SHIFT; - /* do we need a gpadl body msg */ pfnsize = MAX_SIZE_CHANNEL_MESSAGE - sizeof(struct vmbus_channel_gpadl_header) - sizeof(struct gpa_range); + pfncount = umin(pagecount, pfnsize / sizeof(u64)); + + msgsize = sizeof(struct vmbus_channel_msginfo) + + sizeof(struct vmbus_channel_gpadl_header) + + sizeof(struct gpa_range) + pfncount * sizeof(u64); + msgheader = kzalloc(msgsize, GFP_KERNEL); + if (!msgheader) + return -ENOMEM; + + INIT_LIST_HEAD(&msgheader->submsglist); + msgheader->msgsize = msgsize; + + gpadl_header = (struct vmbus_channel_gpadl_header *) + msgheader->msg; + gpadl_header->rangecount = 1; + gpadl_header->range_buflen = sizeof(struct gpa_range) + + pagecount * sizeof(u64); + gpadl_header->range[0].byte_offset = 0; + gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); + for (i = 0; i < pfncount; i++) + gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( + type, kbuffer, size, send_offset, i); + *msginfo = msgheader; + + pfnsum = pfncount; + pfnleft = pagecount - pfncount; + + /* how many pfns can we fit in a body message */ + pfnsize = MAX_SIZE_CHANNEL_MESSAGE - + sizeof(struct vmbus_channel_gpadl_body); pfncount = pfnsize / sizeof(u64); - if (pagecount > pfncount) { - /* we need a gpadl body */ - /* fill in the header */ + /* + * If pfnleft is zero, everything fits in the header and no body + * messages are needed + */ + while (pfnleft) { + pfncurr = umin(pfncount, pfnleft); msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_header) + - sizeof(struct gpa_range) + pfncount * sizeof(u64); - msgheader = kzalloc(msgsize, GFP_KERNEL); - if (!msgheader) - goto nomem; - - INIT_LIST_HEAD(&msgheader->submsglist); - msgheader->msgsize = msgsize; - - gpadl_header = (struct vmbus_channel_gpadl_header *) - msgheader->msg; - gpadl_header->rangecount = 1; - gpadl_header->range_buflen = sizeof(struct gpa_range) + - pagecount * sizeof(u64); - gpadl_header->range[0].byte_offset = 0; - gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); - for (i = 0; i < pfncount; i++) - gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( - type, kbuffer, size, send_offset, i); - *msginfo = msgheader; - - pfnsum = pfncount; - pfnleft = pagecount - pfncount; - - /* how many pfns can we fit */ - pfnsize = MAX_SIZE_CHANNEL_MESSAGE - - sizeof(struct vmbus_channel_gpadl_body); - pfncount = pfnsize / sizeof(u64); - - /* fill in the body */ - while (pfnleft) { - if (pfnleft > pfncount) - pfncurr = pfncount; - else - pfncurr = pfnleft; - - msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_body) + - pfncurr * sizeof(u64); - msgbody = kzalloc(msgsize, GFP_KERNEL); - - if (!msgbody) { - struct vmbus_channel_msginfo *pos = NULL; - struct vmbus_channel_msginfo *tmp = NULL; - /* - * Free up all the allocated messages. - */ - list_for_each_entry_safe(pos, tmp, - &msgheader->submsglist, - msglistentry) { - - list_del(&pos->msglistentry); - kfree(pos); - } - - goto nomem; - } - - msgbody->msgsize = msgsize; - gpadl_body = - (struct vmbus_channel_gpadl_body *)msgbody->msg; + sizeof(struct vmbus_channel_gpadl_body) + + pfncurr * sizeof(u64); + msgbody = kzalloc(msgsize, GFP_KERNEL); + if (!msgbody) { + struct vmbus_channel_msginfo *pos = NULL; + struct vmbus_channel_msginfo *tmp = NULL; /* - * Gpadl is u32 and we are using a pointer which could - * be 64-bit - * This is governed by the guest/host protocol and - * so the hypervisor guarantees that this is ok. + * Free up all the allocated messages. */ - for (i = 0; i < pfncurr; i++) - gpadl_body->pfn[i] = hv_gpadl_hvpfn(type, - kbuffer, size, send_offset, pfnsum + i); - - /* add to msg header */ - list_add_tail(&msgbody->msglistentry, - &msgheader->submsglist); - pfnsum += pfncurr; - pfnleft -= pfncurr; + list_for_each_entry_safe(pos, tmp, + &msgheader->submsglist, + msglistentry) { + + list_del(&pos->msglistentry); + kfree(pos); + } + kfree(msgheader); + return -ENOMEM; } - } else { - /* everything fits in a header */ - msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_header) + - sizeof(struct gpa_range) + pagecount * sizeof(u64); - msgheader = kzalloc(msgsize, GFP_KERNEL); - if (msgheader == NULL) - goto nomem; - - INIT_LIST_HEAD(&msgheader->submsglist); - msgheader->msgsize = msgsize; - - gpadl_header = (struct vmbus_channel_gpadl_header *) - msgheader->msg; - gpadl_header->rangecount = 1; - gpadl_header->range_buflen = sizeof(struct gpa_range) + - pagecount * sizeof(u64); - gpadl_header->range[0].byte_offset = 0; - gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); - for (i = 0; i < pagecount; i++) - gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( - type, kbuffer, size, send_offset, i); - - *msginfo = msgheader; + + msgbody->msgsize = msgsize; + gpadl_body = (struct vmbus_channel_gpadl_body *)msgbody->msg; + + /* + * Gpadl is u32 and we are using a pointer which could + * be 64-bit + * This is governed by the guest/host protocol and + * so the hypervisor guarantees that this is ok. + */ + for (i = 0; i < pfncurr; i++) + gpadl_body->pfn[i] = hv_gpadl_hvpfn(type, + kbuffer, size, send_offset, pfnsum + i); + + /* add to msg header */ + list_add_tail(&msgbody->msglistentry, &msgheader->submsglist); + pfnsum += pfncurr; + pfnleft -= pfncurr; } return 0; -nomem: - kfree(msgheader); - kfree(msgbody); - return -ENOMEM; } /* diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 42aec2c5606a..9c97c4065fe7 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -296,6 +296,11 @@ static struct { spinlock_t lock; } host_ts; +static bool timesync_implicit; + +module_param(timesync_implicit, bool, 0644); +MODULE_PARM_DESC(timesync_implicit, "If set treat SAMPLE as SYNC when clock is behind"); + static inline u64 reftime_to_ns(u64 reftime) { return (reftime - WLTIMEDELTA) * 100; @@ -345,6 +350,29 @@ static void hv_set_host_time(struct work_struct *work) } /* + * Due to a bug on Hyper-V hosts, the sync flag may not always be sent on resume. + * Force a sync if the guest is behind. + */ +static inline bool hv_implicit_sync(u64 host_time) +{ + struct timespec64 new_ts; + struct timespec64 threshold_ts; + + new_ts = ns_to_timespec64(reftime_to_ns(host_time)); + ktime_get_real_ts64(&threshold_ts); + + threshold_ts.tv_sec += 5; + + /* + * If guest behind the host by 5 or more seconds. + */ + if (timespec64_compare(&new_ts, &threshold_ts) >= 0) + return true; + + return false; +} + +/* * Synchronize time with host after reboot, restore, etc. * * ICTIMESYNCFLAG_SYNC flag bit indicates reboot, restore events of the VM. @@ -384,7 +412,8 @@ static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags) spin_unlock_irqrestore(&host_ts.lock, flags); /* Schedule work to do do_settimeofday64() */ - if (adj_flags & ICTIMESYNCFLAG_SYNC) + if ((adj_flags & ICTIMESYNCFLAG_SYNC) || + (timesync_implicit && hv_implicit_sync(host_ts.host_time))) schedule_work(&adj_time_work); } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index b33d5abd9beb..7f7965f3d187 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -988,7 +988,7 @@ static const struct dev_pm_ops vmbus_pm = { }; /* The one and only one */ -static struct bus_type hv_bus = { +static const struct bus_type hv_bus = { .name = "vmbus", .match = vmbus_match, .shutdown = vmbus_shutdown, diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index b8fc8d1ef20d..b0991dde2e59 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -782,7 +782,7 @@ static int __init coretemp_init(void) if (!x86_match_cpu(coretemp_ids)) return -ENODEV; - max_zones = topology_max_packages() * topology_max_die_per_package(); + max_zones = topology_max_packages() * topology_max_dies_per_package(); zone_devices = kcalloc(max_zones, sizeof(struct platform_device *), GFP_KERNEL); if (!zone_devices) diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c index 6307112c2c0c..9ed2c4b6734e 100644 --- a/drivers/hwmon/fam15h_power.c +++ b/drivers/hwmon/fam15h_power.c @@ -209,7 +209,7 @@ static ssize_t power1_average_show(struct device *dev, * With the new x86 topology modelling, x86_max_cores is the * compute unit number. */ - cu_num = boot_cpu_data.x86_max_cores; + cu_num = topology_num_cores_per_package(); ret = read_registers(data); if (ret) diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index 5511fd46a65e..ce8c4846b7fa 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -445,6 +445,7 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status) irq_status); irq_handled |= (irq_status & ASPEED_I2CD_INTR_MASTER_ERRORS); if (bus->master_state != ASPEED_I2C_MASTER_INACTIVE) { + irq_handled = irq_status; bus->cmd_err = ret; bus->master_state = ASPEED_I2C_MASTER_INACTIVE; goto out_complete; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 2c36b36d7d51..274e987e4cfa 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1416,7 +1416,6 @@ static void i801_add_mux(struct i801_priv *priv) lookup->table[i] = GPIO_LOOKUP(mux_config->gpio_chip, mux_config->gpios[i], "mux", 0); gpiod_add_lookup_table(lookup); - priv->lookup = lookup; /* * Register the mux device, we use PLATFORM_DEVID_NONE here @@ -1430,7 +1429,10 @@ static void i801_add_mux(struct i801_priv *priv) sizeof(struct i2c_mux_gpio_platform_data)); if (IS_ERR(priv->mux_pdev)) { gpiod_remove_lookup_table(lookup); + devm_kfree(dev, lookup); dev_err(dev, "Failed to register i2c-mux-gpio device\n"); + } else { + priv->lookup = lookup; } } @@ -1742,9 +1744,9 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) i801_enable_host_notify(&priv->adapter); - i801_probe_optional_slaves(priv); /* We ignore errors - multiplexing is optional */ i801_add_mux(priv); + i801_probe_optional_slaves(priv); pci_set_drvdata(dev, priv); diff --git a/drivers/i2c/busses/i2c-wmt.c b/drivers/i2c/busses/i2c-wmt.c index ec2a8da134e5..198afee5233c 100644 --- a/drivers/i2c/busses/i2c-wmt.c +++ b/drivers/i2c/busses/i2c-wmt.c @@ -378,11 +378,15 @@ static int wmt_i2c_probe(struct platform_device *pdev) err = i2c_add_adapter(adap); if (err) - return err; + goto err_disable_clk; platform_set_drvdata(pdev, i2c_dev); return 0; + +err_disable_clk: + clk_disable_unprepare(i2c_dev->clk); + return err; } static void wmt_i2c_remove(struct platform_device *pdev) diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c index 90b7ae6d42b7..484fe2e9fb17 100644 --- a/drivers/iio/accel/adxl367.c +++ b/drivers/iio/accel/adxl367.c @@ -1429,9 +1429,11 @@ static int adxl367_verify_devid(struct adxl367_state *st) unsigned int val; int ret; - ret = regmap_read_poll_timeout(st->regmap, ADXL367_REG_DEVID, val, - val == ADXL367_DEVID_AD, 1000, 10000); + ret = regmap_read(st->regmap, ADXL367_REG_DEVID, &val); if (ret) + return dev_err_probe(st->dev, ret, "Failed to read dev id\n"); + + if (val != ADXL367_DEVID_AD) return dev_err_probe(st->dev, -ENODEV, "Invalid dev id 0x%02X, expected 0x%02X\n", val, ADXL367_DEVID_AD); @@ -1510,6 +1512,8 @@ int adxl367_probe(struct device *dev, const struct adxl367_ops *ops, if (ret) return ret; + fsleep(15000); + ret = adxl367_verify_devid(st); if (ret) return ret; diff --git a/drivers/iio/accel/adxl367_i2c.c b/drivers/iio/accel/adxl367_i2c.c index b595fe94f3a3..62c74bdc0d77 100644 --- a/drivers/iio/accel/adxl367_i2c.c +++ b/drivers/iio/accel/adxl367_i2c.c @@ -11,7 +11,7 @@ #include "adxl367.h" -#define ADXL367_I2C_FIFO_DATA 0x42 +#define ADXL367_I2C_FIFO_DATA 0x18 struct adxl367_i2c_state { struct regmap *regmap; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index 66d4ba088e70..d4f9b5d8d28d 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -109,6 +109,8 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) /* compute and process only all complete datum */ nb = fifo_count / bytes_per_datum; fifo_count = nb * bytes_per_datum; + if (nb == 0) + goto end_session; /* Each FIFO data contains all sensors, so same number for FIFO and sensor data */ fifo_period = NSEC_PER_SEC / INV_MPU6050_DIVIDER_TO_FIFO_RATE(st->chip_config.divider); inv_sensors_timestamp_interrupt(&st->timestamp, fifo_period, nb, nb, pf->timestamp); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c index 676704f9151f..e6e6e94452a3 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c @@ -111,6 +111,7 @@ int inv_mpu6050_prepare_fifo(struct inv_mpu6050_state *st, bool enable) if (enable) { /* reset timestamping */ inv_sensors_timestamp_reset(&st->timestamp); + inv_sensors_timestamp_apply_odr(&st->timestamp, 0, 0, 0); /* reset FIFO */ d = st->chip_config.user_ctrl | INV_MPU6050_BIT_FIFO_RST; ret = regmap_write(st->map, st->reg->user_ctrl, d); @@ -184,6 +185,10 @@ static int inv_mpu6050_set_enable(struct iio_dev *indio_dev, bool enable) if (result) goto error_power_off; } else { + st->chip_config.gyro_fifo_enable = 0; + st->chip_config.accl_fifo_enable = 0; + st->chip_config.temp_fifo_enable = 0; + st->chip_config.magn_fifo_enable = 0; result = inv_mpu6050_prepare_fifo(st, false); if (result) goto error_power_off; diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c index e8a5fed07e88..a444d4b2978b 100644 --- a/drivers/iio/pressure/bmp280-spi.c +++ b/drivers/iio/pressure/bmp280-spi.c @@ -4,6 +4,7 @@ * * Inspired by the older BMP085 driver drivers/misc/bmp085-spi.c */ +#include <linux/bits.h> #include <linux/module.h> #include <linux/spi/spi.h> #include <linux/err.h> @@ -35,6 +36,34 @@ static int bmp280_regmap_spi_read(void *context, const void *reg, return spi_write_then_read(spi, reg, reg_size, val, val_size); } +static int bmp380_regmap_spi_read(void *context, const void *reg, + size_t reg_size, void *val, size_t val_size) +{ + struct spi_device *spi = to_spi_device(context); + u8 rx_buf[4]; + ssize_t status; + + /* + * Maximum number of consecutive bytes read for a temperature or + * pressure measurement is 3. + */ + if (val_size > 3) + return -EINVAL; + + /* + * According to the BMP3xx datasheets, for a basic SPI read opertion, + * the first byte needs to be dropped and the rest are the requested + * data. + */ + status = spi_write_then_read(spi, reg, 1, rx_buf, val_size + 1); + if (status) + return status; + + memcpy(val, rx_buf + 1, val_size); + + return 0; +} + static struct regmap_bus bmp280_regmap_bus = { .write = bmp280_regmap_spi_write, .read = bmp280_regmap_spi_read, @@ -42,10 +71,19 @@ static struct regmap_bus bmp280_regmap_bus = { .val_format_endian_default = REGMAP_ENDIAN_BIG, }; +static struct regmap_bus bmp380_regmap_bus = { + .write = bmp280_regmap_spi_write, + .read = bmp380_regmap_spi_read, + .read_flag_mask = BIT(7), + .reg_format_endian_default = REGMAP_ENDIAN_BIG, + .val_format_endian_default = REGMAP_ENDIAN_BIG, +}; + static int bmp280_spi_probe(struct spi_device *spi) { const struct spi_device_id *id = spi_get_device_id(spi); const struct bmp280_chip_info *chip_info; + struct regmap_bus *bmp_regmap_bus; struct regmap *regmap; int ret; @@ -58,8 +96,18 @@ static int bmp280_spi_probe(struct spi_device *spi) chip_info = spi_get_device_match_data(spi); + switch (chip_info->chip_id[0]) { + case BMP380_CHIP_ID: + case BMP390_CHIP_ID: + bmp_regmap_bus = &bmp380_regmap_bus; + break; + default: + bmp_regmap_bus = &bmp280_regmap_bus; + break; + } + regmap = devm_regmap_init(&spi->dev, - &bmp280_regmap_bus, + bmp_regmap_bus, &spi->dev, chip_info->regmap_config); if (IS_ERR(regmap)) { diff --git a/drivers/iio/pressure/dlhl60d.c b/drivers/iio/pressure/dlhl60d.c index 28c8269ba65d..0bba4c5a8d40 100644 --- a/drivers/iio/pressure/dlhl60d.c +++ b/drivers/iio/pressure/dlhl60d.c @@ -250,18 +250,17 @@ static irqreturn_t dlh_trigger_handler(int irq, void *private) struct dlh_state *st = iio_priv(indio_dev); int ret; unsigned int chn, i = 0; - __be32 tmp_buf[2]; + __be32 tmp_buf[2] = { }; ret = dlh_start_capture_and_read(st); if (ret) goto out; for_each_set_bit(chn, indio_dev->active_scan_mask, - indio_dev->masklength) { - memcpy(tmp_buf + i, + indio_dev->masklength) { + memcpy(&tmp_buf[i++], &st->rx_buf[1] + chn * DLH_NUM_DATA_BYTES, DLH_NUM_DATA_BYTES); - i++; } iio_push_to_buffers(indio_dev, tmp_buf); diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 7c4b2a5cc1b5..14c828adebf7 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -130,7 +130,12 @@ static const struct xpad_device { { 0x0079, 0x18d4, "GPD Win 2 X-Box Controller", 0, XTYPE_XBOX360 }, { 0x03eb, 0xff01, "Wooting One (Legacy)", 0, XTYPE_XBOX360 }, { 0x03eb, 0xff02, "Wooting Two (Legacy)", 0, XTYPE_XBOX360 }, + { 0x03f0, 0x038D, "HyperX Clutch", 0, XTYPE_XBOX360 }, /* wired */ + { 0x03f0, 0x048D, "HyperX Clutch", 0, XTYPE_XBOX360 }, /* wireless */ { 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE }, + { 0x03f0, 0x07A0, "HyperX Clutch Gladiate RGB", 0, XTYPE_XBOXONE }, + { 0x03f0, 0x08B6, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE }, /* v2 */ + { 0x03f0, 0x09B4, "HyperX Clutch Tanto", 0, XTYPE_XBOXONE }, { 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX }, { 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX }, { 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX }, @@ -463,6 +468,7 @@ static const struct usb_device_id xpad_table[] = { { USB_INTERFACE_INFO('X', 'B', 0) }, /* Xbox USB-IF not-approved class */ XPAD_XBOX360_VENDOR(0x0079), /* GPD Win 2 controller */ XPAD_XBOX360_VENDOR(0x03eb), /* Wooting Keyboards (Legacy) */ + XPAD_XBOX360_VENDOR(0x03f0), /* HP HyperX Xbox 360 controllers */ XPAD_XBOXONE_VENDOR(0x03f0), /* HP HyperX Xbox One controllers */ XPAD_XBOX360_VENDOR(0x044f), /* Thrustmaster Xbox 360 controllers */ XPAD_XBOX360_VENDOR(0x045e), /* Microsoft Xbox 360 controllers */ diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c index ba00ecfbd343..b41fd1240f43 100644 --- a/drivers/input/keyboard/gpio_keys_polled.c +++ b/drivers/input/keyboard/gpio_keys_polled.c @@ -315,12 +315,10 @@ static int gpio_keys_polled_probe(struct platform_device *pdev) error = devm_gpio_request_one(dev, button->gpio, flags, button->desc ? : DRV_NAME); - if (error) { - dev_err(dev, - "unable to claim gpio %u, err=%d\n", - button->gpio, error); - return error; - } + if (error) + return dev_err_probe(dev, error, + "unable to claim gpio %u\n", + button->gpio); bdata->gpiod = gpio_to_desc(button->gpio); if (!bdata->gpiod) { diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c index 953992b458e9..ca150618d32f 100644 --- a/drivers/input/mouse/bcm5974.c +++ b/drivers/input/mouse/bcm5974.c @@ -19,7 +19,6 @@ * Copyright (C) 2006 Nicolas Boichat (nicolas@boichat.ch) */ -#include "linux/usb.h" #include <linux/kernel.h> #include <linux/errno.h> #include <linux/slab.h> @@ -194,8 +193,6 @@ enum tp_type { /* list of device capability bits */ #define HAS_INTEGRATED_BUTTON 1 -/* maximum number of supported endpoints (currently trackpad and button) */ -#define MAX_ENDPOINTS 2 /* trackpad finger data block size */ #define FSIZE_TYPE1 (14 * sizeof(__le16)) @@ -894,18 +891,6 @@ static int bcm5974_resume(struct usb_interface *iface) return error; } -static bool bcm5974_check_endpoints(struct usb_interface *iface, - const struct bcm5974_config *cfg) -{ - u8 ep_addr[MAX_ENDPOINTS + 1] = {0}; - - ep_addr[0] = cfg->tp_ep; - if (cfg->tp_type == TYPE1) - ep_addr[1] = cfg->bt_ep; - - return usb_check_int_endpoints(iface, ep_addr); -} - static int bcm5974_probe(struct usb_interface *iface, const struct usb_device_id *id) { @@ -918,11 +903,6 @@ static int bcm5974_probe(struct usb_interface *iface, /* find the product index */ cfg = bcm5974_get_config(udev); - if (!bcm5974_check_endpoints(iface, cfg)) { - dev_err(&iface->dev, "Unexpected non-int endpoint\n"); - return -ENODEV; - } - /* allocate memory for our device state and initialize it */ dev = kzalloc(sizeof(struct bcm5974), GFP_KERNEL); input_dev = input_allocate_device(); diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index 258d5fe3d395..42eaebb3bf5c 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -978,12 +978,12 @@ static int rmi_driver_remove(struct device *dev) rmi_disable_irq(rmi_dev, false); - irq_domain_remove(data->irqdomain); - data->irqdomain = NULL; - rmi_f34_remove_sysfs(rmi_dev); rmi_free_function_list(rmi_dev); + irq_domain_remove(data->irqdomain); + data->irqdomain = NULL; + return 0; } diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 8b3601f285fd..c970eae2313d 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -164,5 +164,4 @@ void amd_iommu_domain_set_pgtable(struct protection_domain *domain, u64 *root, int mode); struct dev_table_entry *get_dev_table(struct amd_iommu *iommu); -extern bool amd_iommu_snp_en; #endif diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index c83bd0c2a1c9..480e7681f4f3 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -30,6 +30,7 @@ #include <asm/io_apic.h> #include <asm/irq_remapping.h> #include <asm/set_memory.h> +#include <asm/sev.h> #include <linux/crash_dump.h> @@ -3221,6 +3222,36 @@ out: return true; } +static void iommu_snp_enable(void) +{ +#ifdef CONFIG_KVM_AMD_SEV + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return; + /* + * The SNP support requires that IOMMU must be enabled, and is + * not configured in the passthrough mode. + */ + if (no_iommu || iommu_default_passthrough()) { + pr_err("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n"); + return; + } + + amd_iommu_snp_en = check_feature(FEATURE_SNP); + if (!amd_iommu_snp_en) { + pr_err("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n"); + return; + } + + pr_info("IOMMU SNP support enabled.\n"); + + /* Enforce IOMMU v1 pagetable when SNP is enabled. */ + if (amd_iommu_pgtable != AMD_IOMMU_V1) { + pr_warn("Forcing use of AMD IOMMU v1 page table due to SNP.\n"); + amd_iommu_pgtable = AMD_IOMMU_V1; + } +#endif +} + /**************************************************************************** * * AMD IOMMU Initialization State Machine @@ -3256,6 +3287,7 @@ static int __init state_next(void) break; case IOMMU_ENABLED: register_syscore_ops(&amd_iommu_syscore_ops); + iommu_snp_enable(); ret = amd_iommu_init_pci(); init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT; break; @@ -3767,40 +3799,85 @@ int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true); } -#ifdef CONFIG_AMD_MEM_ENCRYPT -int amd_iommu_snp_enable(void) +#ifdef CONFIG_KVM_AMD_SEV +static int iommu_page_make_shared(void *page) { - /* - * The SNP support requires that IOMMU must be enabled, and is - * not configured in the passthrough mode. - */ - if (no_iommu || iommu_default_passthrough()) { - pr_err("SNP: IOMMU is disabled or configured in passthrough mode, SNP cannot be supported"); - return -EINVAL; + unsigned long paddr, pfn; + + paddr = iommu_virt_to_phys(page); + /* Cbit maybe set in the paddr */ + pfn = __sme_clr(paddr) >> PAGE_SHIFT; + + if (!(pfn % PTRS_PER_PMD)) { + int ret, level; + bool assigned; + + ret = snp_lookup_rmpentry(pfn, &assigned, &level); + if (ret) { + pr_warn("IOMMU PFN %lx RMP lookup failed, ret %d\n", pfn, ret); + return ret; + } + + if (!assigned) { + pr_warn("IOMMU PFN %lx not assigned in RMP table\n", pfn); + return -EINVAL; + } + + if (level > PG_LEVEL_4K) { + ret = psmash(pfn); + if (!ret) + goto done; + + pr_warn("PSMASH failed for IOMMU PFN %lx huge RMP entry, ret: %d, level: %d\n", + pfn, ret, level); + return ret; + } } - /* - * Prevent enabling SNP after IOMMU_ENABLED state because this process - * affect how IOMMU driver sets up data structures and configures - * IOMMU hardware. - */ - if (init_state > IOMMU_ENABLED) { - pr_err("SNP: Too late to enable SNP for IOMMU.\n"); - return -EINVAL; +done: + return rmp_make_shared(pfn, PG_LEVEL_4K); +} + +static int iommu_make_shared(void *va, size_t size) +{ + void *page; + int ret; + + if (!va) + return 0; + + for (page = va; page < (va + size); page += PAGE_SIZE) { + ret = iommu_page_make_shared(page); + if (ret) + return ret; } - amd_iommu_snp_en = check_feature(FEATURE_SNP); + return 0; +} + +int amd_iommu_snp_disable(void) +{ + struct amd_iommu *iommu; + int ret; + if (!amd_iommu_snp_en) - return -EINVAL; + return 0; + + for_each_iommu(iommu) { + ret = iommu_make_shared(iommu->evt_buf, EVT_BUFFER_SIZE); + if (ret) + return ret; - pr_info("SNP enabled\n"); + ret = iommu_make_shared(iommu->ppr_log, PPR_LOG_SIZE); + if (ret) + return ret; - /* Enforce IOMMU v1 pagetable when SNP is enabled. */ - if (amd_iommu_pgtable != AMD_IOMMU_V1) { - pr_warn("Force to using AMD IOMMU v1 page table due to SNP\n"); - amd_iommu_pgtable = AMD_IOMMU_V1; + ret = iommu_make_shared((void *)iommu->cmd_sem, PAGE_SIZE); + if (ret) + return ret; } return 0; } +EXPORT_SYMBOL_GPL(amd_iommu_snp_disable); #endif diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 0ffb1cf17e0b..a74a509bcd63 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3125,7 +3125,8 @@ static int arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr) static void arm_smmu_free_msis(void *data) { struct device *dev = data; - platform_msi_domain_free_irqs(dev); + + platform_device_msi_free_irqs_all(dev); } static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) @@ -3166,7 +3167,7 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) } /* Allocate MSIs for evtq, gerror and priq. Ignore cmdq */ - ret = platform_msi_domain_alloc_irqs(dev, nvec, arm_smmu_write_msi_msg); + ret = platform_device_msi_init_and_alloc_irqs(dev, nvec, arm_smmu_write_msi_msg); if (ret) { dev_warn(dev, "failed to allocate MSIs - falling back to wired irqs\n"); return; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index f7149d0f3d45..72c07a12f5e1 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -546,6 +546,17 @@ config SIFIVE_PLIC select IRQ_DOMAIN_HIERARCHY select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP +config STARFIVE_JH8100_INTC + bool "StarFive JH8100 External Interrupt Controller" + depends on ARCH_STARFIVE || COMPILE_TEST + default ARCH_STARFIVE + select IRQ_DOMAIN_HIERARCHY + help + This enables support for the INTC chip found in StarFive JH8100 + SoC. + + If you don't know what to do here, say Y. + config EXYNOS_IRQ_COMBINER bool "Samsung Exynos IRQ combiner support" if COMPILE_TEST depends on (ARCH_EXYNOS && ARM) || COMPILE_TEST diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index ffd945fe71aa..ec4a18380998 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -96,6 +96,7 @@ obj-$(CONFIG_CSKY_MPINTC) += irq-csky-mpintc.o obj-$(CONFIG_CSKY_APB_INTC) += irq-csky-apb-intc.o obj-$(CONFIG_RISCV_INTC) += irq-riscv-intc.o obj-$(CONFIG_SIFIVE_PLIC) += irq-sifive-plic.o +obj-$(CONFIG_STARFIVE_JH8100_INTC) += irq-starfive-jh8100-intc.o obj-$(CONFIG_IMX_IRQSTEER) += irq-imx-irqsteer.o obj-$(CONFIG_IMX_INTMUX) += irq-imx-intmux.o obj-$(CONFIG_IMX_MU_MSI) += irq-imx-mu-msi.o diff --git a/drivers/irqchip/irq-bcm6345-l1.c b/drivers/irqchip/irq-bcm6345-l1.c index 9745a119d0e6..eb02d203c963 100644 --- a/drivers/irqchip/irq-bcm6345-l1.c +++ b/drivers/irqchip/irq-bcm6345-l1.c @@ -242,7 +242,7 @@ static int __init bcm6345_l1_init_one(struct device_node *dn, else if (intc->n_words != n_words) return -EINVAL; - cpu = intc->cpus[idx] = kzalloc(sizeof(*cpu) + n_words * sizeof(u32), + cpu = intc->cpus[idx] = kzalloc(struct_size(cpu, enable_cache, n_words), GFP_KERNEL); if (!cpu) return -ENOMEM; diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c index 24ca1d656adc..36e71af054e9 100644 --- a/drivers/irqchip/irq-bcm7038-l1.c +++ b/drivers/irqchip/irq-bcm7038-l1.c @@ -249,7 +249,7 @@ static int __init bcm7038_l1_init_one(struct device_node *dn, return -EINVAL; } - cpu = intc->cpus[idx] = kzalloc(sizeof(*cpu) + n_words * sizeof(u32), + cpu = intc->cpus[idx] = kzalloc(struct_size(cpu, mask_cache, n_words), GFP_KERNEL); if (!cpu) return -ENOMEM; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index b822752c4261..fca888b36680 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -4436,12 +4436,12 @@ static const struct irq_domain_ops its_sgi_domain_ops = { static int its_vpe_id_alloc(void) { - return ida_simple_get(&its_vpeid_ida, 0, ITS_MAX_VPEID, GFP_KERNEL); + return ida_alloc_max(&its_vpeid_ida, ITS_MAX_VPEID - 1, GFP_KERNEL); } static void its_vpe_id_free(u16 id) { - ida_simple_remove(&its_vpeid_ida, id); + ida_free(&its_vpeid_ida, id); } static int its_vpe_init(struct its_vpe *vpe) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 98b0329b7154..6fb276504bcc 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -19,6 +19,7 @@ #include <linux/percpu.h> #include <linux/refcount.h> #include <linux/slab.h> +#include <linux/iopoll.h> #include <linux/irqchip.h> #include <linux/irqchip/arm-gic-common.h> @@ -180,11 +181,6 @@ static enum gic_intid_range get_intid_range(struct irq_data *d) return __get_intid_range(d->hwirq); } -static inline unsigned int gic_irq(struct irq_data *d) -{ - return d->hwirq; -} - static inline bool gic_irq_in_rdist(struct irq_data *d) { switch (get_intid_range(d)) { @@ -251,17 +247,13 @@ static inline void __iomem *gic_dist_base(struct irq_data *d) static void gic_do_wait_for_rwp(void __iomem *base, u32 bit) { - u32 count = 1000000; /* 1s! */ + u32 val; + int ret; - while (readl_relaxed(base + GICD_CTLR) & bit) { - count--; - if (!count) { - pr_err_ratelimited("RWP timeout, gone fishing\n"); - return; - } - cpu_relax(); - udelay(1); - } + ret = readl_relaxed_poll_timeout_atomic(base + GICD_CTLR, val, !(val & bit), + 1, USEC_PER_SEC); + if (ret == -ETIMEDOUT) + pr_err_ratelimited("RWP timeout, gone fishing\n"); } /* Wait for completion of a distributor change */ @@ -279,8 +271,8 @@ static void gic_redist_wait_for_rwp(void) static void gic_enable_redist(bool enable) { void __iomem *rbase; - u32 count = 1000000; /* 1s! */ u32 val; + int ret; if (gic_data.flags & FLAGS_WORKAROUND_GICR_WAKER_MSM8996) return; @@ -301,16 +293,13 @@ static void gic_enable_redist(bool enable) return; /* No PM support in this redistributor */ } - while (--count) { - val = readl_relaxed(rbase + GICR_WAKER); - if (enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep)) - break; - cpu_relax(); - udelay(1); - } - if (!count) + ret = readl_relaxed_poll_timeout_atomic(rbase + GICR_WAKER, val, + enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep), + 1, USEC_PER_SEC); + if (ret == -ETIMEDOUT) { pr_err_ratelimited("redistributor failed to %s...\n", enable ? "wakeup" : "sleep"); + } } /* @@ -548,7 +537,7 @@ static int gic_irq_nmi_setup(struct irq_data *d) * A secondary irq_chip should be in charge of LPI request, * it should not be possible to get there */ - if (WARN_ON(gic_irq(d) >= 8192)) + if (WARN_ON(irqd_to_hwirq(d) >= 8192)) return -EINVAL; /* desc lock should already be held */ @@ -588,7 +577,7 @@ static void gic_irq_nmi_teardown(struct irq_data *d) * A secondary irq_chip should be in charge of LPI request, * it should not be possible to get there */ - if (WARN_ON(gic_irq(d) >= 8192)) + if (WARN_ON(irqd_to_hwirq(d) >= 8192)) return; /* desc lock should already be held */ @@ -626,7 +615,7 @@ static bool gic_arm64_erratum_2941627_needed(struct irq_data *d) static void gic_eoi_irq(struct irq_data *d) { - write_gicreg(gic_irq(d), ICC_EOIR1_EL1); + write_gicreg(irqd_to_hwirq(d), ICC_EOIR1_EL1); isb(); if (gic_arm64_erratum_2941627_needed(d)) { @@ -646,19 +635,19 @@ static void gic_eoimode1_eoi_irq(struct irq_data *d) * No need to deactivate an LPI, or an interrupt that * is is getting forwarded to a vcpu. */ - if (gic_irq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d)) + if (irqd_to_hwirq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d)) return; if (!gic_arm64_erratum_2941627_needed(d)) - gic_write_dir(gic_irq(d)); + gic_write_dir(irqd_to_hwirq(d)); else gic_poke_irq(d, GICD_ICACTIVER); } static int gic_set_type(struct irq_data *d, unsigned int type) { + irq_hw_number_t irq = irqd_to_hwirq(d); enum gic_intid_range range; - unsigned int irq = gic_irq(d); void __iomem *base; u32 offset, index; int ret; @@ -684,7 +673,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) ret = gic_configure_irq(index, type, base + offset, NULL); if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) { /* Misconfigured PPIs are usually not fatal */ - pr_warn("GIC: PPI INTID%d is secure or misconfigured\n", irq); + pr_warn("GIC: PPI INTID%ld is secure or misconfigured\n", irq); ret = 0; } @@ -1702,9 +1691,13 @@ static int gic_irq_domain_select(struct irq_domain *d, irq_hw_number_t hwirq; /* Not for us */ - if (fwspec->fwnode != d->fwnode) + if (fwspec->fwnode != d->fwnode) return 0; + /* Handle pure domain searches */ + if (!fwspec->param_count) + return d->bus_token == bus_token; + /* If this is not DT, then we have a single domain */ if (!is_of_node(fwspec->fwnode)) return 1; diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 412196a7dad5..98aa383e39db 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -162,11 +162,6 @@ static inline void __iomem *gic_cpu_base(struct irq_data *d) return gic_data_cpu_base(gic_data); } -static inline unsigned int gic_irq(struct irq_data *d) -{ - return d->hwirq; -} - static inline bool cascading_gic_irq(struct irq_data *d) { void *data = irq_data_get_irq_handler_data(d); @@ -183,14 +178,16 @@ static inline bool cascading_gic_irq(struct irq_data *d) */ static void gic_poke_irq(struct irq_data *d, u32 offset) { - u32 mask = 1 << (gic_irq(d) % 32); - writel_relaxed(mask, gic_dist_base(d) + offset + (gic_irq(d) / 32) * 4); + u32 mask = 1 << (irqd_to_hwirq(d) % 32); + + writel_relaxed(mask, gic_dist_base(d) + offset + (irqd_to_hwirq(d) / 32) * 4); } static int gic_peek_irq(struct irq_data *d, u32 offset) { - u32 mask = 1 << (gic_irq(d) % 32); - return !!(readl_relaxed(gic_dist_base(d) + offset + (gic_irq(d) / 32) * 4) & mask); + u32 mask = 1 << (irqd_to_hwirq(d) % 32); + + return !!(readl_relaxed(gic_dist_base(d) + offset + (irqd_to_hwirq(d) / 32) * 4) & mask); } static void gic_mask_irq(struct irq_data *d) @@ -220,7 +217,7 @@ static void gic_unmask_irq(struct irq_data *d) static void gic_eoi_irq(struct irq_data *d) { - u32 hwirq = gic_irq(d); + irq_hw_number_t hwirq = irqd_to_hwirq(d); if (hwirq < 16) hwirq = this_cpu_read(sgi_intid); @@ -230,7 +227,7 @@ static void gic_eoi_irq(struct irq_data *d) static void gic_eoimode1_eoi_irq(struct irq_data *d) { - u32 hwirq = gic_irq(d); + irq_hw_number_t hwirq = irqd_to_hwirq(d); /* Do not deactivate an IRQ forwarded to a vcpu. */ if (irqd_is_forwarded_to_vcpu(d)) @@ -293,8 +290,8 @@ static int gic_irq_get_irqchip_state(struct irq_data *d, static int gic_set_type(struct irq_data *d, unsigned int type) { + irq_hw_number_t gicirq = irqd_to_hwirq(d); void __iomem *base = gic_dist_base(d); - unsigned int gicirq = gic_irq(d); int ret; /* Interrupt configuration for SGIs can't be changed */ @@ -309,7 +306,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) ret = gic_configure_irq(gicirq, type, base + GIC_DIST_CONFIG, NULL); if (ret && gicirq < 32) { /* Misconfigured PPIs are usually not fatal */ - pr_warn("GIC: PPI%d is secure or misconfigured\n", gicirq - 16); + pr_warn("GIC: PPI%ld is secure or misconfigured\n", gicirq - 16); ret = 0; } @@ -319,7 +316,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) { /* Only interrupts on the primary GIC can be forwarded to a vcpu. */ - if (cascading_gic_irq(d) || gic_irq(d) < 16) + if (cascading_gic_irq(d) || irqd_to_hwirq(d) < 16) return -EINVAL; if (vcpu) @@ -796,7 +793,7 @@ static void rmw_writeb(u8 bval, void __iomem *addr) static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { - void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d); + void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + irqd_to_hwirq(d); struct gic_chip_data *gic = irq_data_get_irq_chip_data(d); unsigned int cpu; diff --git a/drivers/irqchip/irq-imgpdc.c b/drivers/irqchip/irq-imgpdc.c index 5831be454673..b42ed68acfa6 100644 --- a/drivers/irqchip/irq-imgpdc.c +++ b/drivers/irqchip/irq-imgpdc.c @@ -461,12 +461,11 @@ err_generic: return ret; } -static int pdc_intc_remove(struct platform_device *pdev) +static void pdc_intc_remove(struct platform_device *pdev) { struct pdc_intc_priv *priv = platform_get_drvdata(pdev); irq_domain_remove(priv->domain); - return 0; } static const struct of_device_id pdc_intc_match[] = { @@ -479,8 +478,8 @@ static struct platform_driver pdc_intc_driver = { .name = "pdc-intc", .of_match_table = pdc_intc_match, }, - .probe = pdc_intc_probe, - .remove = pdc_intc_remove, + .probe = pdc_intc_probe, + .remove_new = pdc_intc_remove, }; static int __init pdc_intc_init(void) diff --git a/drivers/irqchip/irq-imx-intmux.c b/drivers/irqchip/irq-imx-intmux.c index aa041e4dfee0..511adfaeec82 100644 --- a/drivers/irqchip/irq-imx-intmux.c +++ b/drivers/irqchip/irq-imx-intmux.c @@ -166,6 +166,10 @@ static int imx_intmux_irq_select(struct irq_domain *d, struct irq_fwspec *fwspec if (fwspec->fwnode != d->fwnode) return false; + /* Handle pure domain searches */ + if (!fwspec->param_count) + return d->bus_token == bus_token; + return irqchip_data->chanidx == fwspec->param[1]; } @@ -282,7 +286,7 @@ out: return ret; } -static int imx_intmux_remove(struct platform_device *pdev) +static void imx_intmux_remove(struct platform_device *pdev) { struct intmux_data *data = platform_get_drvdata(pdev); int i; @@ -298,8 +302,6 @@ static int imx_intmux_remove(struct platform_device *pdev) } pm_runtime_disable(&pdev->dev); - - return 0; } #ifdef CONFIG_PM @@ -354,11 +356,11 @@ static const struct of_device_id imx_intmux_id[] = { static struct platform_driver imx_intmux_driver = { .driver = { - .name = "imx-intmux", - .of_match_table = imx_intmux_id, - .pm = &imx_intmux_pm_ops, + .name = "imx-intmux", + .of_match_table = imx_intmux_id, + .pm = &imx_intmux_pm_ops, }, - .probe = imx_intmux_probe, - .remove = imx_intmux_remove, + .probe = imx_intmux_probe, + .remove_new = imx_intmux_remove, }; builtin_platform_driver(imx_intmux_driver); diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c index bd9543314539..20cf7a9e9ece 100644 --- a/drivers/irqchip/irq-imx-irqsteer.c +++ b/drivers/irqchip/irq-imx-irqsteer.c @@ -231,7 +231,7 @@ out: return ret; } -static int imx_irqsteer_remove(struct platform_device *pdev) +static void imx_irqsteer_remove(struct platform_device *pdev) { struct irqsteer_data *irqsteer_data = platform_get_drvdata(pdev); int i; @@ -243,8 +243,6 @@ static int imx_irqsteer_remove(struct platform_device *pdev) irq_domain_remove(irqsteer_data->domain); clk_disable_unprepare(irqsteer_data->ipg_clk); - - return 0; } #ifdef CONFIG_PM @@ -307,11 +305,11 @@ static const struct of_device_id imx_irqsteer_dt_ids[] = { static struct platform_driver imx_irqsteer_driver = { .driver = { - .name = "imx-irqsteer", - .of_match_table = imx_irqsteer_dt_ids, - .pm = &imx_irqsteer_pm_ops, + .name = "imx-irqsteer", + .of_match_table = imx_irqsteer_dt_ids, + .pm = &imx_irqsteer_pm_ops, }, - .probe = imx_irqsteer_probe, - .remove = imx_irqsteer_remove, + .probe = imx_irqsteer_probe, + .remove_new = imx_irqsteer_remove, }; builtin_platform_driver(imx_irqsteer_driver); diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c index a36396db4b08..30f1979fa124 100644 --- a/drivers/irqchip/irq-keystone.c +++ b/drivers/irqchip/irq-keystone.c @@ -190,7 +190,7 @@ static int keystone_irq_probe(struct platform_device *pdev) return 0; } -static int keystone_irq_remove(struct platform_device *pdev) +static void keystone_irq_remove(struct platform_device *pdev) { struct keystone_irq_device *kirq = platform_get_drvdata(pdev); int hwirq; @@ -201,7 +201,6 @@ static int keystone_irq_remove(struct platform_device *pdev) irq_dispose_mapping(irq_find_mapping(kirq->irqd, hwirq)); irq_domain_remove(kirq->irqd); - return 0; } static const struct of_device_id keystone_irq_dt_ids[] = { @@ -212,7 +211,7 @@ MODULE_DEVICE_TABLE(of, keystone_irq_dt_ids); static struct platform_driver keystone_irq_device_driver = { .probe = keystone_irq_probe, - .remove = keystone_irq_remove, + .remove_new = keystone_irq_remove, .driver = { .name = "keystone_irq", .of_match_table = of_match_ptr(keystone_irq_dt_ids), diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index b3736bdd4b9f..b64cbe3052e8 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -198,6 +198,12 @@ static void eiointc_irq_dispatch(struct irq_desc *desc) for (i = 0; i < eiointc_priv[0]->vec_count / VEC_COUNT_PER_REG; i++) { pending = iocsr_read64(EIOINTC_REG_ISR + (i << 3)); + + /* Skip handling if pending bitmap is zero */ + if (!pending) + continue; + + /* Clear the IRQs */ iocsr_write64(pending, EIOINTC_REG_ISR + (i << 3)); while (pending) { int bit = __ffs(pending); @@ -304,23 +310,7 @@ static int eiointc_suspend(void) static void eiointc_resume(void) { - int i, j; - struct irq_desc *desc; - struct irq_data *irq_data; - eiointc_router_init(0); - - for (i = 0; i < nr_pics; i++) { - for (j = 0; j < eiointc_priv[0]->vec_count; j++) { - desc = irq_resolve_mapping(eiointc_priv[i]->eiointc_domain, j); - if (desc && desc->handle_irq && desc->handle_irq != handle_bad_irq) { - raw_spin_lock(&desc->lock); - irq_data = irq_domain_get_irq_data(eiointc_priv[i]->eiointc_domain, irq_desc_get_irq(desc)); - eiointc_set_irq_affinity(irq_data, irq_data->common->affinity, 0); - raw_spin_unlock(&desc->lock); - } - } - } } static struct syscore_ops eiointc_syscore_ops = { diff --git a/drivers/irqchip/irq-ls-scfg-msi.c b/drivers/irqchip/irq-ls-scfg-msi.c index 15cf80b46322..1aef5c4d27c6 100644 --- a/drivers/irqchip/irq-ls-scfg-msi.c +++ b/drivers/irqchip/irq-ls-scfg-msi.c @@ -398,7 +398,7 @@ static int ls_scfg_msi_probe(struct platform_device *pdev) return 0; } -static int ls_scfg_msi_remove(struct platform_device *pdev) +static void ls_scfg_msi_remove(struct platform_device *pdev) { struct ls_scfg_msi *msi_data = platform_get_drvdata(pdev); int i; @@ -410,17 +410,15 @@ static int ls_scfg_msi_remove(struct platform_device *pdev) irq_domain_remove(msi_data->parent); platform_set_drvdata(pdev, NULL); - - return 0; } static struct platform_driver ls_scfg_msi_driver = { .driver = { - .name = "ls-scfg-msi", - .of_match_table = ls_scfg_msi_id, + .name = "ls-scfg-msi", + .of_match_table = ls_scfg_msi_id, }, - .probe = ls_scfg_msi_probe, - .remove = ls_scfg_msi_remove, + .probe = ls_scfg_msi_probe, + .remove_new = ls_scfg_msi_remove, }; module_platform_driver(ls_scfg_msi_driver); diff --git a/drivers/irqchip/irq-madera.c b/drivers/irqchip/irq-madera.c index 3eb1f8cdf674..acceb6e7fa95 100644 --- a/drivers/irqchip/irq-madera.c +++ b/drivers/irqchip/irq-madera.c @@ -222,7 +222,7 @@ static int madera_irq_probe(struct platform_device *pdev) return 0; } -static int madera_irq_remove(struct platform_device *pdev) +static void madera_irq_remove(struct platform_device *pdev) { struct madera *madera = dev_get_drvdata(pdev->dev.parent); @@ -232,13 +232,11 @@ static int madera_irq_remove(struct platform_device *pdev) */ madera->irq_dev = NULL; regmap_del_irq_chip(madera->irq, madera->irq_data); - - return 0; } static struct platform_driver madera_irq_driver = { - .probe = &madera_irq_probe, - .remove = &madera_irq_remove, + .probe = madera_irq_probe, + .remove_new = madera_irq_remove, .driver = { .name = "madera-irq", .pm = &madera_irq_pm_ops, diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index f88df39f4129..9a1791908598 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -154,6 +154,10 @@ static const struct meson_gpio_irq_params c3_params = { INIT_MESON_S4_COMMON_DATA(55) }; +static const struct meson_gpio_irq_params t7_params = { + INIT_MESON_S4_COMMON_DATA(157) +}; + static const struct of_device_id meson_irq_gpio_matches[] __maybe_unused = { { .compatible = "amlogic,meson8-gpio-intc", .data = &meson8_params }, { .compatible = "amlogic,meson8b-gpio-intc", .data = &meson8b_params }, @@ -165,6 +169,7 @@ static const struct of_device_id meson_irq_gpio_matches[] __maybe_unused = { { .compatible = "amlogic,meson-a1-gpio-intc", .data = &a1_params }, { .compatible = "amlogic,meson-s4-gpio-intc", .data = &s4_params }, { .compatible = "amlogic,c3-gpio-intc", .data = &c3_params }, + { .compatible = "amlogic,t7-gpio-intc", .data = &t7_params }, { } }; diff --git a/drivers/irqchip/irq-mvebu-pic.c b/drivers/irqchip/irq-mvebu-pic.c index ef3d3646ccc2..d17d9c0e2880 100644 --- a/drivers/irqchip/irq-mvebu-pic.c +++ b/drivers/irqchip/irq-mvebu-pic.c @@ -167,14 +167,12 @@ static int mvebu_pic_probe(struct platform_device *pdev) return 0; } -static int mvebu_pic_remove(struct platform_device *pdev) +static void mvebu_pic_remove(struct platform_device *pdev) { struct mvebu_pic *pic = platform_get_drvdata(pdev); on_each_cpu(mvebu_pic_disable_percpu_irq, pic, 1); irq_domain_remove(pic->domain); - - return 0; } static const struct of_device_id mvebu_pic_of_match[] = { @@ -184,11 +182,11 @@ static const struct of_device_id mvebu_pic_of_match[] = { MODULE_DEVICE_TABLE(of, mvebu_pic_of_match); static struct platform_driver mvebu_pic_driver = { - .probe = mvebu_pic_probe, - .remove = mvebu_pic_remove, + .probe = mvebu_pic_probe, + .remove_new = mvebu_pic_remove, .driver = { - .name = "mvebu-pic", - .of_match_table = mvebu_pic_of_match, + .name = "mvebu-pic", + .of_match_table = mvebu_pic_of_match, }, }; module_platform_driver(mvebu_pic_driver); diff --git a/drivers/irqchip/irq-pruss-intc.c b/drivers/irqchip/irq-pruss-intc.c index 0f64ecb9b1f4..060eb000e9d3 100644 --- a/drivers/irqchip/irq-pruss-intc.c +++ b/drivers/irqchip/irq-pruss-intc.c @@ -599,7 +599,7 @@ fail_irq: return ret; } -static int pruss_intc_remove(struct platform_device *pdev) +static void pruss_intc_remove(struct platform_device *pdev) { struct pruss_intc *intc = platform_get_drvdata(pdev); u8 max_system_events = intc->soc_config->num_system_events; @@ -616,8 +616,6 @@ static int pruss_intc_remove(struct platform_device *pdev) irq_dispose_mapping(irq_find_mapping(intc->domain, hwirq)); irq_domain_remove(intc->domain); - - return 0; } static const struct pruss_intc_match_data pruss_intc_data = { @@ -645,12 +643,12 @@ MODULE_DEVICE_TABLE(of, pruss_intc_of_match); static struct platform_driver pruss_intc_driver = { .driver = { - .name = "pruss-intc", - .of_match_table = pruss_intc_of_match, - .suppress_bind_attrs = true, + .name = "pruss-intc", + .of_match_table = pruss_intc_of_match, + .suppress_bind_attrs = true, }, - .probe = pruss_intc_probe, - .remove = pruss_intc_remove, + .probe = pruss_intc_probe, + .remove_new = pruss_intc_remove, }; module_platform_driver(pruss_intc_driver); diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c index fa19585f3dee..9ad37237ba95 100644 --- a/drivers/irqchip/irq-renesas-intc-irqpin.c +++ b/drivers/irqchip/irq-renesas-intc-irqpin.c @@ -561,14 +561,13 @@ err0: return ret; } -static int intc_irqpin_remove(struct platform_device *pdev) +static void intc_irqpin_remove(struct platform_device *pdev) { struct intc_irqpin_priv *p = platform_get_drvdata(pdev); irq_domain_remove(p->irq_domain); pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); - return 0; } static int __maybe_unused intc_irqpin_suspend(struct device *dev) @@ -585,11 +584,11 @@ static SIMPLE_DEV_PM_OPS(intc_irqpin_pm_ops, intc_irqpin_suspend, NULL); static struct platform_driver intc_irqpin_device_driver = { .probe = intc_irqpin_probe, - .remove = intc_irqpin_remove, + .remove_new = intc_irqpin_remove, .driver = { - .name = "renesas_intc_irqpin", - .of_match_table = intc_irqpin_dt_ids, - .pm = &intc_irqpin_pm_ops, + .name = "renesas_intc_irqpin", + .of_match_table = intc_irqpin_dt_ids, + .pm = &intc_irqpin_pm_ops, } }; diff --git a/drivers/irqchip/irq-renesas-irqc.c b/drivers/irqchip/irq-renesas-irqc.c index 49b446b396f9..76026e0b8e20 100644 --- a/drivers/irqchip/irq-renesas-irqc.c +++ b/drivers/irqchip/irq-renesas-irqc.c @@ -218,14 +218,13 @@ err_runtime_pm_disable: return ret; } -static int irqc_remove(struct platform_device *pdev) +static void irqc_remove(struct platform_device *pdev) { struct irqc_priv *p = platform_get_drvdata(pdev); irq_domain_remove(p->irq_domain); pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); - return 0; } static int __maybe_unused irqc_suspend(struct device *dev) @@ -248,11 +247,11 @@ MODULE_DEVICE_TABLE(of, irqc_dt_ids); static struct platform_driver irqc_device_driver = { .probe = irqc_probe, - .remove = irqc_remove, + .remove_new = irqc_remove, .driver = { - .name = "renesas_irqc", + .name = "renesas_irqc", .of_match_table = irqc_dt_ids, - .pm = &irqc_pm_ops, + .pm = &irqc_pm_ops, } }; diff --git a/drivers/irqchip/irq-renesas-rza1.c b/drivers/irqchip/irq-renesas-rza1.c index e4c99c2e0373..f05afe82db4d 100644 --- a/drivers/irqchip/irq-renesas-rza1.c +++ b/drivers/irqchip/irq-renesas-rza1.c @@ -244,12 +244,11 @@ out_put_node: return ret; } -static int rza1_irqc_remove(struct platform_device *pdev) +static void rza1_irqc_remove(struct platform_device *pdev) { struct rza1_irqc_priv *priv = platform_get_drvdata(pdev); irq_domain_remove(priv->irq_domain); - return 0; } static const struct of_device_id rza1_irqc_dt_ids[] = { @@ -260,9 +259,9 @@ MODULE_DEVICE_TABLE(of, rza1_irqc_dt_ids); static struct platform_driver rza1_irqc_device_driver = { .probe = rza1_irqc_probe, - .remove = rza1_irqc_remove, + .remove_new = rza1_irqc_remove, .driver = { - .name = "renesas_rza1_irqc", + .name = "renesas_rza1_irqc", .of_match_table = rza1_irqc_dt_ids, } }; diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c index e8d01b14ccdd..f87aeab460eb 100644 --- a/drivers/irqchip/irq-riscv-intc.c +++ b/drivers/irqchip/irq-riscv-intc.c @@ -17,17 +17,29 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/smp.h> +#include <linux/soc/andes/irq.h> + +#include <asm/hwcap.h> static struct irq_domain *intc_domain; +static unsigned int riscv_intc_nr_irqs __ro_after_init = BITS_PER_LONG; +static unsigned int riscv_intc_custom_base __ro_after_init = BITS_PER_LONG; +static unsigned int riscv_intc_custom_nr_irqs __ro_after_init; static asmlinkage void riscv_intc_irq(struct pt_regs *regs) { unsigned long cause = regs->cause & ~CAUSE_IRQ_FLAG; - if (unlikely(cause >= BITS_PER_LONG)) - panic("unexpected interrupt cause"); + if (generic_handle_domain_irq(intc_domain, cause)) + pr_warn_ratelimited("Failed to handle interrupt (cause: %ld)\n", cause); +} + +static asmlinkage void riscv_intc_aia_irq(struct pt_regs *regs) +{ + unsigned long topi; - generic_handle_domain_irq(intc_domain, cause); + while ((topi = csr_read(CSR_TOPI))) + generic_handle_domain_irq(intc_domain, topi >> TOPI_IID_SHIFT); } /* @@ -39,12 +51,43 @@ static asmlinkage void riscv_intc_irq(struct pt_regs *regs) static void riscv_intc_irq_mask(struct irq_data *d) { - csr_clear(CSR_IE, BIT(d->hwirq)); + if (IS_ENABLED(CONFIG_32BIT) && d->hwirq >= BITS_PER_LONG) + csr_clear(CSR_IEH, BIT(d->hwirq - BITS_PER_LONG)); + else + csr_clear(CSR_IE, BIT(d->hwirq)); } static void riscv_intc_irq_unmask(struct irq_data *d) { - csr_set(CSR_IE, BIT(d->hwirq)); + if (IS_ENABLED(CONFIG_32BIT) && d->hwirq >= BITS_PER_LONG) + csr_set(CSR_IEH, BIT(d->hwirq - BITS_PER_LONG)); + else + csr_set(CSR_IE, BIT(d->hwirq)); +} + +static void andes_intc_irq_mask(struct irq_data *d) +{ + /* + * Andes specific S-mode local interrupt causes (hwirq) + * are defined as (256 + n) and controlled by n-th bit + * of SLIE. + */ + unsigned int mask = BIT(d->hwirq % BITS_PER_LONG); + + if (d->hwirq < ANDES_SLI_CAUSE_BASE) + csr_clear(CSR_IE, mask); + else + csr_clear(ANDES_CSR_SLIE, mask); +} + +static void andes_intc_irq_unmask(struct irq_data *d) +{ + unsigned int mask = BIT(d->hwirq % BITS_PER_LONG); + + if (d->hwirq < ANDES_SLI_CAUSE_BASE) + csr_set(CSR_IE, mask); + else + csr_set(ANDES_CSR_SLIE, mask); } static void riscv_intc_irq_eoi(struct irq_data *d) @@ -70,12 +113,21 @@ static struct irq_chip riscv_intc_chip = { .irq_eoi = riscv_intc_irq_eoi, }; +static struct irq_chip andes_intc_chip = { + .name = "RISC-V INTC", + .irq_mask = andes_intc_irq_mask, + .irq_unmask = andes_intc_irq_unmask, + .irq_eoi = riscv_intc_irq_eoi, +}; + static int riscv_intc_domain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq) { + struct irq_chip *chip = d->host_data; + irq_set_percpu_devid(irq); - irq_domain_set_info(d, irq, hwirq, &riscv_intc_chip, d->host_data, - handle_percpu_devid_irq, NULL, NULL); + irq_domain_set_info(d, irq, hwirq, chip, NULL, handle_percpu_devid_irq, + NULL, NULL); return 0; } @@ -93,6 +145,14 @@ static int riscv_intc_domain_alloc(struct irq_domain *domain, if (ret) return ret; + /* + * Only allow hwirq for which we have corresponding standard or + * custom interrupt enable register. + */ + if ((hwirq >= riscv_intc_nr_irqs && hwirq < riscv_intc_custom_base) || + (hwirq >= riscv_intc_custom_base + riscv_intc_custom_nr_irqs)) + return -EINVAL; + for (i = 0; i < nr_irqs; i++) { ret = riscv_intc_domain_map(domain, virq + i, hwirq + i); if (ret) @@ -113,18 +173,20 @@ static struct fwnode_handle *riscv_intc_hwnode(void) return intc_domain->fwnode; } -static int __init riscv_intc_init_common(struct fwnode_handle *fn) +static int __init riscv_intc_init_common(struct fwnode_handle *fn, struct irq_chip *chip) { int rc; - intc_domain = irq_domain_create_linear(fn, BITS_PER_LONG, - &riscv_intc_domain_ops, NULL); + intc_domain = irq_domain_create_tree(fn, &riscv_intc_domain_ops, chip); if (!intc_domain) { pr_err("unable to add IRQ domain\n"); return -ENXIO; } - rc = set_handle_irq(&riscv_intc_irq); + if (riscv_isa_extension_available(NULL, SxAIA)) + rc = set_handle_irq(&riscv_intc_aia_irq); + else + rc = set_handle_irq(&riscv_intc_irq); if (rc) { pr_err("failed to set irq handler\n"); return rc; @@ -132,7 +194,11 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn) riscv_set_intc_hwnode_fn(riscv_intc_hwnode); - pr_info("%d local interrupts mapped\n", BITS_PER_LONG); + pr_info("%d local interrupts mapped%s\n", + riscv_isa_extension_available(NULL, SxAIA) ? 64 : riscv_intc_nr_irqs, + riscv_isa_extension_available(NULL, SxAIA) ? " using AIA" : ""); + if (riscv_intc_custom_nr_irqs) + pr_info("%d custom local interrupts mapped\n", riscv_intc_custom_nr_irqs); return 0; } @@ -140,8 +206,9 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn) static int __init riscv_intc_init(struct device_node *node, struct device_node *parent) { - int rc; + struct irq_chip *chip = &riscv_intc_chip; unsigned long hartid; + int rc; rc = riscv_of_parent_hartid(node, &hartid); if (rc < 0) { @@ -166,10 +233,17 @@ static int __init riscv_intc_init(struct device_node *node, return 0; } - return riscv_intc_init_common(of_node_to_fwnode(node)); + if (of_device_is_compatible(node, "andestech,cpu-intc")) { + riscv_intc_custom_base = ANDES_SLI_CAUSE_BASE; + riscv_intc_custom_nr_irqs = ANDES_RV_IRQ_LAST; + chip = &andes_intc_chip; + } + + return riscv_intc_init_common(of_node_to_fwnode(node), chip); } IRQCHIP_DECLARE(riscv, "riscv,cpu-intc", riscv_intc_init); +IRQCHIP_DECLARE(andes, "andestech,cpu-intc", riscv_intc_init); #ifdef CONFIG_ACPI @@ -196,7 +270,7 @@ static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, return -ENOMEM; } - return riscv_intc_init_common(fn); + return riscv_intc_init_common(fn, &riscv_intc_chip); } IRQCHIP_ACPI_DECLARE(riscv_intc, ACPI_MADT_TYPE_RINTC, NULL, diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index bf0b40b0fad4..f3d4cb9e34f7 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -3,7 +3,6 @@ * Copyright (C) 2017 SiFive * Copyright (C) 2018 Christoph Hellwig */ -#define pr_fmt(fmt) "plic: " fmt #include <linux/cpu.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -64,6 +63,7 @@ #define PLIC_QUIRK_EDGE_INTERRUPT 0 struct plic_priv { + struct device *dev; struct cpumask lmask; struct irq_domain *irqdomain; void __iomem *regs; @@ -103,9 +103,11 @@ static void __plic_toggle(void __iomem *enable_base, int hwirq, int enable) static void plic_toggle(struct plic_handler *handler, int hwirq, int enable) { - raw_spin_lock(&handler->enable_lock); + unsigned long flags; + + raw_spin_lock_irqsave(&handler->enable_lock, flags); __plic_toggle(handler->enable_base, hwirq, enable); - raw_spin_unlock(&handler->enable_lock); + raw_spin_unlock_irqrestore(&handler->enable_lock, flags); } static inline void plic_irq_toggle(const struct cpumask *mask, @@ -242,6 +244,7 @@ static int plic_irq_set_type(struct irq_data *d, unsigned int type) static int plic_irq_suspend(void) { unsigned int i, cpu; + unsigned long flags; u32 __iomem *reg; struct plic_priv *priv; @@ -259,12 +262,12 @@ static int plic_irq_suspend(void) if (!handler->present) continue; - raw_spin_lock(&handler->enable_lock); + raw_spin_lock_irqsave(&handler->enable_lock, flags); for (i = 0; i < DIV_ROUND_UP(priv->nr_irqs, 32); i++) { reg = handler->enable_base + i * sizeof(u32); handler->enable_save[i] = readl(reg); } - raw_spin_unlock(&handler->enable_lock); + raw_spin_unlock_irqrestore(&handler->enable_lock, flags); } return 0; @@ -273,6 +276,7 @@ static int plic_irq_suspend(void) static void plic_irq_resume(void) { unsigned int i, index, cpu; + unsigned long flags; u32 __iomem *reg; struct plic_priv *priv; @@ -290,12 +294,12 @@ static void plic_irq_resume(void) if (!handler->present) continue; - raw_spin_lock(&handler->enable_lock); + raw_spin_lock_irqsave(&handler->enable_lock, flags); for (i = 0; i < DIV_ROUND_UP(priv->nr_irqs, 32); i++) { reg = handler->enable_base + i * sizeof(u32); writel(handler->enable_save[i], reg); } - raw_spin_unlock(&handler->enable_lock); + raw_spin_unlock_irqrestore(&handler->enable_lock, flags); } } @@ -376,9 +380,10 @@ static void plic_handle_irq(struct irq_desc *desc) while ((hwirq = readl(claim))) { int err = generic_handle_domain_irq(handler->priv->irqdomain, hwirq); - if (unlikely(err)) - pr_warn_ratelimited("can't find mapping for hwirq %lu\n", - hwirq); + if (unlikely(err)) { + dev_warn_ratelimited(handler->priv->dev, + "can't find mapping for hwirq %lu\n", hwirq); + } } chained_irq_exit(chip, desc); @@ -406,63 +411,122 @@ static int plic_starting_cpu(unsigned int cpu) enable_percpu_irq(plic_parent_irq, irq_get_trigger_type(plic_parent_irq)); else - pr_warn("cpu%d: parent irq not available\n", cpu); + dev_warn(handler->priv->dev, "cpu%d: parent irq not available\n", cpu); plic_set_threshold(handler, PLIC_ENABLE_THRESHOLD); return 0; } -static int __init __plic_init(struct device_node *node, - struct device_node *parent, - unsigned long plic_quirks) +static const struct of_device_id plic_match[] = { + { .compatible = "sifive,plic-1.0.0" }, + { .compatible = "riscv,plic0" }, + { .compatible = "andestech,nceplic100", + .data = (const void *)BIT(PLIC_QUIRK_EDGE_INTERRUPT) }, + { .compatible = "thead,c900-plic", + .data = (const void *)BIT(PLIC_QUIRK_EDGE_INTERRUPT) }, + {} +}; + +static int plic_parse_nr_irqs_and_contexts(struct platform_device *pdev, + u32 *nr_irqs, u32 *nr_contexts) { - int error = 0, nr_contexts, nr_handlers = 0, i; - u32 nr_irqs; - struct plic_priv *priv; - struct plic_handler *handler; - unsigned int cpu; + struct device *dev = &pdev->dev; + int rc; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + /* + * Currently, only OF fwnode is supported so extend this + * function for ACPI support. + */ + if (!is_of_node(dev->fwnode)) + return -EINVAL; - priv->plic_quirks = plic_quirks; + rc = of_property_read_u32(to_of_node(dev->fwnode), "riscv,ndev", nr_irqs); + if (rc) { + dev_err(dev, "riscv,ndev property not available\n"); + return rc; + } - priv->regs = of_iomap(node, 0); - if (WARN_ON(!priv->regs)) { - error = -EIO; - goto out_free_priv; + *nr_contexts = of_irq_count(to_of_node(dev->fwnode)); + if (WARN_ON(!(*nr_contexts))) { + dev_err(dev, "no PLIC context available\n"); + return -EINVAL; } - error = -EINVAL; - of_property_read_u32(node, "riscv,ndev", &nr_irqs); - if (WARN_ON(!nr_irqs)) - goto out_iounmap; + return 0; +} + +static int plic_parse_context_parent(struct platform_device *pdev, u32 context, + u32 *parent_hwirq, int *parent_cpu) +{ + struct device *dev = &pdev->dev; + struct of_phandle_args parent; + unsigned long hartid; + int rc; - priv->nr_irqs = nr_irqs; + /* + * Currently, only OF fwnode is supported so extend this + * function for ACPI support. + */ + if (!is_of_node(dev->fwnode)) + return -EINVAL; - priv->prio_save = bitmap_alloc(nr_irqs, GFP_KERNEL); - if (!priv->prio_save) - goto out_free_priority_reg; + rc = of_irq_parse_one(to_of_node(dev->fwnode), context, &parent); + if (rc) + return rc; - nr_contexts = of_irq_count(node); - if (WARN_ON(!nr_contexts)) - goto out_free_priority_reg; + rc = riscv_of_parent_hartid(parent.np, &hartid); + if (rc) + return rc; - error = -ENOMEM; - priv->irqdomain = irq_domain_add_linear(node, nr_irqs + 1, - &plic_irqdomain_ops, priv); - if (WARN_ON(!priv->irqdomain)) - goto out_free_priority_reg; + *parent_hwirq = parent.args[0]; + *parent_cpu = riscv_hartid_to_cpuid(hartid); + return 0; +} - for (i = 0; i < nr_contexts; i++) { - struct of_phandle_args parent; - irq_hw_number_t hwirq; - int cpu; - unsigned long hartid; +static int plic_probe(struct platform_device *pdev) +{ + int error = 0, nr_contexts, nr_handlers = 0, cpu, i; + struct device *dev = &pdev->dev; + unsigned long plic_quirks = 0; + struct plic_handler *handler; + u32 nr_irqs, parent_hwirq; + struct irq_domain *domain; + struct plic_priv *priv; + irq_hw_number_t hwirq; + bool cpuhp_setup; + + if (is_of_node(dev->fwnode)) { + const struct of_device_id *id; + + id = of_match_node(plic_match, to_of_node(dev->fwnode)); + if (id) + plic_quirks = (unsigned long)id->data; + } + + error = plic_parse_nr_irqs_and_contexts(pdev, &nr_irqs, &nr_contexts); + if (error) + return error; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = dev; + priv->plic_quirks = plic_quirks; + priv->nr_irqs = nr_irqs; + + priv->regs = devm_platform_ioremap_resource(pdev, 0); + if (WARN_ON(!priv->regs)) + return -EIO; - if (of_irq_parse_one(node, i, &parent)) { - pr_err("failed to parse parent for context %d.\n", i); + priv->prio_save = devm_bitmap_zalloc(dev, nr_irqs, GFP_KERNEL); + if (!priv->prio_save) + return -ENOMEM; + + for (i = 0; i < nr_contexts; i++) { + error = plic_parse_context_parent(pdev, i, &parent_hwirq, &cpu); + if (error) { + dev_warn(dev, "hwirq for context%d not found\n", i); continue; } @@ -470,7 +534,7 @@ static int __init __plic_init(struct device_node *node, * Skip contexts other than external interrupts for our * privilege level. */ - if (parent.args[0] != RV_IRQ_EXT) { + if (parent_hwirq != RV_IRQ_EXT) { /* Disable S-mode enable bits if running in M-mode. */ if (IS_ENABLED(CONFIG_RISCV_M_MODE)) { void __iomem *enable_base = priv->regs + @@ -483,24 +547,17 @@ static int __init __plic_init(struct device_node *node, continue; } - error = riscv_of_parent_hartid(parent.np, &hartid); - if (error < 0) { - pr_warn("failed to parse hart ID for context %d.\n", i); - continue; - } - - cpu = riscv_hartid_to_cpuid(hartid); if (cpu < 0) { - pr_warn("Invalid cpuid for context %d\n", i); + dev_warn(dev, "Invalid cpuid for context %d\n", i); continue; } /* Find parent domain and register chained handler */ - if (!plic_parent_irq && irq_find_host(parent.np)) { - plic_parent_irq = irq_of_parse_and_map(node, i); + domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), DOMAIN_BUS_ANY); + if (!plic_parent_irq && domain) { + plic_parent_irq = irq_create_mapping(domain, RV_IRQ_EXT); if (plic_parent_irq) - irq_set_chained_handler(plic_parent_irq, - plic_handle_irq); + irq_set_chained_handler(plic_parent_irq, plic_handle_irq); } /* @@ -510,7 +567,7 @@ static int __init __plic_init(struct device_node *node, */ handler = per_cpu_ptr(&plic_handlers, cpu); if (handler->present) { - pr_warn("handler already present for context %d.\n", i); + dev_warn(dev, "handler already present for context %d.\n", i); plic_set_threshold(handler, PLIC_DISABLE_THRESHOLD); goto done; } @@ -524,10 +581,10 @@ static int __init __plic_init(struct device_node *node, i * CONTEXT_ENABLE_SIZE; handler->priv = priv; - handler->enable_save = kcalloc(DIV_ROUND_UP(nr_irqs, 32), - sizeof(*handler->enable_save), GFP_KERNEL); + handler->enable_save = devm_kcalloc(dev, DIV_ROUND_UP(nr_irqs, 32), + sizeof(*handler->enable_save), GFP_KERNEL); if (!handler->enable_save) - goto out_free_enable_reg; + goto fail_cleanup_contexts; done: for (hwirq = 1; hwirq <= nr_irqs; hwirq++) { plic_toggle(handler, hwirq, 0); @@ -537,52 +594,60 @@ done: nr_handlers++; } + priv->irqdomain = irq_domain_add_linear(to_of_node(dev->fwnode), nr_irqs + 1, + &plic_irqdomain_ops, priv); + if (WARN_ON(!priv->irqdomain)) + goto fail_cleanup_contexts; + /* * We can have multiple PLIC instances so setup cpuhp state - * and register syscore operations only when context handler - * for current/boot CPU is present. + * and register syscore operations only once after context + * handlers of all online CPUs are initialized. */ - handler = this_cpu_ptr(&plic_handlers); - if (handler->present && !plic_cpuhp_setup_done) { - cpuhp_setup_state(CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, - "irqchip/sifive/plic:starting", - plic_starting_cpu, plic_dying_cpu); - register_syscore_ops(&plic_irq_syscore_ops); - plic_cpuhp_setup_done = true; + if (!plic_cpuhp_setup_done) { + cpuhp_setup = true; + for_each_online_cpu(cpu) { + handler = per_cpu_ptr(&plic_handlers, cpu); + if (!handler->present) { + cpuhp_setup = false; + break; + } + } + if (cpuhp_setup) { + cpuhp_setup_state(CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, + "irqchip/sifive/plic:starting", + plic_starting_cpu, plic_dying_cpu); + register_syscore_ops(&plic_irq_syscore_ops); + plic_cpuhp_setup_done = true; + } } - pr_info("%pOFP: mapped %d interrupts with %d handlers for" - " %d contexts.\n", node, nr_irqs, nr_handlers, nr_contexts); + dev_info(dev, "mapped %d interrupts with %d handlers for %d contexts.\n", + nr_irqs, nr_handlers, nr_contexts); return 0; -out_free_enable_reg: - for_each_cpu(cpu, cpu_present_mask) { +fail_cleanup_contexts: + for (i = 0; i < nr_contexts; i++) { + if (plic_parse_context_parent(pdev, i, &parent_hwirq, &cpu)) + continue; + if (parent_hwirq != RV_IRQ_EXT || cpu < 0) + continue; + handler = per_cpu_ptr(&plic_handlers, cpu); - kfree(handler->enable_save); + handler->present = false; + handler->hart_base = NULL; + handler->enable_base = NULL; + handler->enable_save = NULL; + handler->priv = NULL; } -out_free_priority_reg: - kfree(priv->prio_save); -out_iounmap: - iounmap(priv->regs); -out_free_priv: - kfree(priv); - return error; + return -ENOMEM; } -static int __init plic_init(struct device_node *node, - struct device_node *parent) -{ - return __plic_init(node, parent, 0); -} - -IRQCHIP_DECLARE(sifive_plic, "sifive,plic-1.0.0", plic_init); -IRQCHIP_DECLARE(riscv_plic0, "riscv,plic0", plic_init); /* for legacy systems */ - -static int __init plic_edge_init(struct device_node *node, - struct device_node *parent) -{ - return __plic_init(node, parent, BIT(PLIC_QUIRK_EDGE_INTERRUPT)); -} - -IRQCHIP_DECLARE(andestech_nceplic100, "andestech,nceplic100", plic_edge_init); -IRQCHIP_DECLARE(thead_c900_plic, "thead,c900-plic", plic_edge_init); +static struct platform_driver plic_driver = { + .driver = { + .name = "riscv-plic", + .of_match_table = plic_match, + }, + .probe = plic_probe, +}; +builtin_platform_driver(plic_driver); diff --git a/drivers/irqchip/irq-starfive-jh8100-intc.c b/drivers/irqchip/irq-starfive-jh8100-intc.c new file mode 100644 index 000000000000..0f5837176e53 --- /dev/null +++ b/drivers/irqchip/irq-starfive-jh8100-intc.c @@ -0,0 +1,207 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * StarFive JH8100 External Interrupt Controller driver + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Changhuang Liang <changhuang.liang@starfivetech.com> + */ + +#define pr_fmt(fmt) "irq-starfive-jh8100: " fmt + +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/irq.h> +#include <linux/irqchip.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/reset.h> +#include <linux/spinlock.h> + +#define STARFIVE_INTC_SRC0_CLEAR 0x10 +#define STARFIVE_INTC_SRC0_MASK 0x14 +#define STARFIVE_INTC_SRC0_INT 0x1c + +#define STARFIVE_INTC_SRC_IRQ_NUM 32 + +struct starfive_irq_chip { + void __iomem *base; + struct irq_domain *domain; + raw_spinlock_t lock; +}; + +static void starfive_intc_bit_set(struct starfive_irq_chip *irqc, + u32 reg, u32 bit_mask) +{ + u32 value; + + value = ioread32(irqc->base + reg); + value |= bit_mask; + iowrite32(value, irqc->base + reg); +} + +static void starfive_intc_bit_clear(struct starfive_irq_chip *irqc, + u32 reg, u32 bit_mask) +{ + u32 value; + + value = ioread32(irqc->base + reg); + value &= ~bit_mask; + iowrite32(value, irqc->base + reg); +} + +static void starfive_intc_unmask(struct irq_data *d) +{ + struct starfive_irq_chip *irqc = irq_data_get_irq_chip_data(d); + + raw_spin_lock(&irqc->lock); + starfive_intc_bit_clear(irqc, STARFIVE_INTC_SRC0_MASK, BIT(d->hwirq)); + raw_spin_unlock(&irqc->lock); +} + +static void starfive_intc_mask(struct irq_data *d) +{ + struct starfive_irq_chip *irqc = irq_data_get_irq_chip_data(d); + + raw_spin_lock(&irqc->lock); + starfive_intc_bit_set(irqc, STARFIVE_INTC_SRC0_MASK, BIT(d->hwirq)); + raw_spin_unlock(&irqc->lock); +} + +static struct irq_chip intc_dev = { + .name = "StarFive JH8100 INTC", + .irq_unmask = starfive_intc_unmask, + .irq_mask = starfive_intc_mask, +}; + +static int starfive_intc_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_domain_set_info(d, irq, hwirq, &intc_dev, d->host_data, + handle_level_irq, NULL, NULL); + + return 0; +} + +static const struct irq_domain_ops starfive_intc_domain_ops = { + .xlate = irq_domain_xlate_onecell, + .map = starfive_intc_map, +}; + +static void starfive_intc_irq_handler(struct irq_desc *desc) +{ + struct starfive_irq_chip *irqc = irq_data_get_irq_handler_data(&desc->irq_data); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long value; + int hwirq; + + chained_irq_enter(chip, desc); + + value = ioread32(irqc->base + STARFIVE_INTC_SRC0_INT); + while (value) { + hwirq = ffs(value) - 1; + + generic_handle_domain_irq(irqc->domain, hwirq); + + starfive_intc_bit_set(irqc, STARFIVE_INTC_SRC0_CLEAR, BIT(hwirq)); + starfive_intc_bit_clear(irqc, STARFIVE_INTC_SRC0_CLEAR, BIT(hwirq)); + + __clear_bit(hwirq, &value); + } + + chained_irq_exit(chip, desc); +} + +static int __init starfive_intc_init(struct device_node *intc, + struct device_node *parent) +{ + struct starfive_irq_chip *irqc; + struct reset_control *rst; + struct clk *clk; + int parent_irq; + int ret; + + irqc = kzalloc(sizeof(*irqc), GFP_KERNEL); + if (!irqc) + return -ENOMEM; + + irqc->base = of_iomap(intc, 0); + if (!irqc->base) { + pr_err("Unable to map registers\n"); + ret = -ENXIO; + goto err_free; + } + + rst = of_reset_control_get_exclusive(intc, NULL); + if (IS_ERR(rst)) { + pr_err("Unable to get reset control %pe\n", rst); + ret = PTR_ERR(rst); + goto err_unmap; + } + + clk = of_clk_get(intc, 0); + if (IS_ERR(clk)) { + pr_err("Unable to get clock %pe\n", clk); + ret = PTR_ERR(clk); + goto err_reset_put; + } + + ret = reset_control_deassert(rst); + if (ret) + goto err_clk_put; + + ret = clk_prepare_enable(clk); + if (ret) + goto err_reset_assert; + + raw_spin_lock_init(&irqc->lock); + + irqc->domain = irq_domain_add_linear(intc, STARFIVE_INTC_SRC_IRQ_NUM, + &starfive_intc_domain_ops, irqc); + if (!irqc->domain) { + pr_err("Unable to create IRQ domain\n"); + ret = -EINVAL; + goto err_clk_disable; + } + + parent_irq = of_irq_get(intc, 0); + if (parent_irq < 0) { + pr_err("Failed to get main IRQ: %d\n", parent_irq); + ret = parent_irq; + goto err_remove_domain; + } + + irq_set_chained_handler_and_data(parent_irq, starfive_intc_irq_handler, + irqc); + + pr_info("Interrupt controller register, nr_irqs %d\n", + STARFIVE_INTC_SRC_IRQ_NUM); + + return 0; + +err_remove_domain: + irq_domain_remove(irqc->domain); +err_clk_disable: + clk_disable_unprepare(clk); +err_reset_assert: + reset_control_assert(rst); +err_clk_put: + clk_put(clk); +err_reset_put: + reset_control_put(rst); +err_unmap: + iounmap(irqc->base); +err_free: + kfree(irqc); + return ret; +} + +IRQCHIP_PLATFORM_DRIVER_BEGIN(starfive_intc) +IRQCHIP_MATCH("starfive,jh8100-intc", starfive_intc_init) +IRQCHIP_PLATFORM_DRIVER_END(starfive_intc) + +MODULE_DESCRIPTION("StarFive JH8100 External Interrupt Controller"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Changhuang Liang <changhuang.liang@starfivetech.com>"); diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 971240e2e31b..26a5193d0ae4 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -898,10 +898,9 @@ static void stm32_exti_remove_irq(void *data) irq_domain_remove(domain); } -static int stm32_exti_remove(struct platform_device *pdev) +static void stm32_exti_remove(struct platform_device *pdev) { stm32_exti_h_syscore_deinit(); - return 0; } static int stm32_exti_probe(struct platform_device *pdev) @@ -991,10 +990,10 @@ MODULE_DEVICE_TABLE(of, stm32_exti_ids); static struct platform_driver stm32_exti_driver = { .probe = stm32_exti_probe, - .remove = stm32_exti_remove, + .remove_new = stm32_exti_remove, .driver = { - .name = "stm32_exti", - .of_match_table = stm32_exti_ids, + .name = "stm32_exti", + .of_match_table = stm32_exti_ids, }, }; diff --git a/drivers/irqchip/irq-ts4800.c b/drivers/irqchip/irq-ts4800.c index b2d61d4f6fe6..57f610dab6b8 100644 --- a/drivers/irqchip/irq-ts4800.c +++ b/drivers/irqchip/irq-ts4800.c @@ -139,13 +139,11 @@ static int ts4800_ic_probe(struct platform_device *pdev) return 0; } -static int ts4800_ic_remove(struct platform_device *pdev) +static void ts4800_ic_remove(struct platform_device *pdev) { struct ts4800_irq_data *data = platform_get_drvdata(pdev); irq_domain_remove(data->domain); - - return 0; } static const struct of_device_id ts4800_ic_of_match[] = { @@ -155,11 +153,11 @@ static const struct of_device_id ts4800_ic_of_match[] = { MODULE_DEVICE_TABLE(of, ts4800_ic_of_match); static struct platform_driver ts4800_ic_driver = { - .probe = ts4800_ic_probe, - .remove = ts4800_ic_remove, + .probe = ts4800_ic_probe, + .remove_new = ts4800_ic_remove, .driver = { - .name = "ts4800-irqc", - .of_match_table = ts4800_ic_of_match, + .name = "ts4800-irqc", + .of_match_table = ts4800_ic_of_match, }, }; module_platform_driver(ts4800_ic_driver); diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c index 9e3d5561e04e..ea93e7236c4a 100644 --- a/drivers/irqchip/irq-vic.c +++ b/drivers/irqchip/irq-vic.c @@ -47,9 +47,8 @@ /** * struct vic_device - VIC PM device - * @parent_irq: The parent IRQ number of the VIC if cascaded, or 0. - * @irq: The IRQ number for the base of the VIC. * @base: The register base for the VIC. + * @irq: The IRQ number for the base of the VIC. * @valid_sources: A bitmask of valid interrupts * @resume_sources: A bitmask of interrupts for resume. * @resume_irqs: The IRQs enabled for resume. diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c index e3e28a4f7d01..b1abc2a0c971 100644 --- a/drivers/mailbox/bcm-flexrm-mailbox.c +++ b/drivers/mailbox/bcm-flexrm-mailbox.c @@ -1587,8 +1587,8 @@ static int flexrm_mbox_probe(struct platform_device *pdev) } /* Allocate platform MSIs for each ring */ - ret = platform_msi_domain_alloc_irqs(dev, mbox->num_rings, - flexrm_mbox_msi_write); + ret = platform_device_msi_init_and_alloc_irqs(dev, mbox->num_rings, + flexrm_mbox_msi_write); if (ret) goto fail_destroy_cmpl_pool; @@ -1641,7 +1641,7 @@ skip_debugfs: fail_free_debugfs_root: debugfs_remove_recursive(mbox->root); - platform_msi_domain_free_irqs(dev); + platform_device_msi_free_irqs_all(dev); fail_destroy_cmpl_pool: dma_pool_destroy(mbox->cmpl_pool); fail_destroy_bd_pool: @@ -1657,7 +1657,7 @@ static void flexrm_mbox_remove(struct platform_device *pdev) debugfs_remove_recursive(mbox->root); - platform_msi_domain_free_irqs(dev); + platform_device_msi_free_irqs_all(dev); dma_pool_destroy(mbox->cmpl_pool); dma_pool_destroy(mbox->bd_pool); diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 6ae2329052c9..4e6afa89921f 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -300,7 +300,7 @@ struct cached_dev { struct list_head list; struct bcache_device disk; struct block_device *bdev; - struct bdev_handle *bdev_handle; + struct file *bdev_file; struct cache_sb sb; struct cache_sb_disk *sb_disk; @@ -423,7 +423,7 @@ struct cache { struct kobject kobj; struct block_device *bdev; - struct bdev_handle *bdev_handle; + struct file *bdev_file; struct task_struct *alloc_thread; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index dc3f50f69714..330bcd9ea4a9 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -900,9 +900,23 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, struct request_queue *q; const size_t max_stripes = min_t(size_t, INT_MAX, SIZE_MAX / sizeof(atomic_t)); + struct queue_limits lim = { + .max_hw_sectors = UINT_MAX, + .max_sectors = UINT_MAX, + .max_segment_size = UINT_MAX, + .max_segments = BIO_MAX_VECS, + .max_hw_discard_sectors = UINT_MAX, + .io_min = block_size, + .logical_block_size = block_size, + .physical_block_size = block_size, + }; uint64_t n; int idx; + if (cached_bdev) { + d->stripe_size = bdev_io_opt(cached_bdev) >> SECTOR_SHIFT; + lim.io_opt = umax(block_size, bdev_io_opt(cached_bdev)); + } if (!d->stripe_size) d->stripe_size = 1 << 31; else if (d->stripe_size < BCH_MIN_STRIPE_SZ) @@ -935,8 +949,21 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER)) goto out_ida_remove; - d->disk = blk_alloc_disk(NUMA_NO_NODE); - if (!d->disk) + if (lim.logical_block_size > PAGE_SIZE && cached_bdev) { + /* + * This should only happen with BCACHE_SB_VERSION_BDEV. + * Block/page size is checked for BCACHE_SB_VERSION_CDEV. + */ + pr_info("bcache%i: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n", + idx, lim.logical_block_size, + PAGE_SIZE, bdev_logical_block_size(cached_bdev)); + + /* This also adjusts physical block size/min io size if needed */ + lim.logical_block_size = bdev_logical_block_size(cached_bdev); + } + + d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(d->disk)) goto out_bioset_exit; set_capacity(d->disk, sectors); @@ -949,27 +976,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, d->disk->private_data = d; q = d->disk->queue; - q->limits.max_hw_sectors = UINT_MAX; - q->limits.max_sectors = UINT_MAX; - q->limits.max_segment_size = UINT_MAX; - q->limits.max_segments = BIO_MAX_VECS; - blk_queue_max_discard_sectors(q, UINT_MAX); - q->limits.io_min = block_size; - q->limits.logical_block_size = block_size; - q->limits.physical_block_size = block_size; - - if (q->limits.logical_block_size > PAGE_SIZE && cached_bdev) { - /* - * This should only happen with BCACHE_SB_VERSION_BDEV. - * Block/page size is checked for BCACHE_SB_VERSION_CDEV. - */ - pr_info("%s: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n", - d->disk->disk_name, q->limits.logical_block_size, - PAGE_SIZE, bdev_logical_block_size(cached_bdev)); - - /* This also adjusts physical block size/min io size if needed */ - blk_queue_logical_block_size(q, bdev_logical_block_size(cached_bdev)); - } blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue); @@ -1369,8 +1375,8 @@ static CLOSURE_CALLBACK(cached_dev_free) if (dc->sb_disk) put_page(virt_to_page(dc->sb_disk)); - if (dc->bdev_handle) - bdev_release(dc->bdev_handle); + if (dc->bdev_file) + fput(dc->bdev_file); wake_up(&unregister_wait); @@ -1416,9 +1422,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) hlist_add_head(&io->hash, dc->io_hash + RECENT_IO); } - dc->disk.stripe_size = q->limits.io_opt >> 9; - - if (dc->disk.stripe_size) + if (bdev_io_opt(dc->bdev)) dc->partial_stripes_expensive = q->limits.raid_partial_stripes_expensive; @@ -1428,9 +1432,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) if (ret) return ret; - blk_queue_io_opt(dc->disk.disk->queue, - max(queue_io_opt(dc->disk.disk->queue), queue_io_opt(q))); - atomic_set(&dc->io_errors, 0); dc->io_disable = false; dc->error_limit = DEFAULT_CACHED_DEV_ERROR_LIMIT; @@ -1445,7 +1446,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) /* Cached device - bcache superblock */ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk, - struct bdev_handle *bdev_handle, + struct file *bdev_file, struct cached_dev *dc) { const char *err = "cannot allocate memory"; @@ -1453,8 +1454,8 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk, int ret = -ENOMEM; memcpy(&dc->sb, sb, sizeof(struct cache_sb)); - dc->bdev_handle = bdev_handle; - dc->bdev = bdev_handle->bdev; + dc->bdev_file = bdev_file; + dc->bdev = file_bdev(bdev_file); dc->sb_disk = sb_disk; if (cached_dev_init(dc, sb->block_size << 9)) @@ -2218,8 +2219,8 @@ void bch_cache_release(struct kobject *kobj) if (ca->sb_disk) put_page(virt_to_page(ca->sb_disk)); - if (ca->bdev_handle) - bdev_release(ca->bdev_handle); + if (ca->bdev_file) + fput(ca->bdev_file); kfree(ca); module_put(THIS_MODULE); @@ -2339,18 +2340,18 @@ err_free: } static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, - struct bdev_handle *bdev_handle, + struct file *bdev_file, struct cache *ca) { const char *err = NULL; /* must be set for any error case */ int ret = 0; memcpy(&ca->sb, sb, sizeof(struct cache_sb)); - ca->bdev_handle = bdev_handle; - ca->bdev = bdev_handle->bdev; + ca->bdev_file = bdev_file; + ca->bdev = file_bdev(bdev_file); ca->sb_disk = sb_disk; - if (bdev_max_discard_sectors((bdev_handle->bdev))) + if (bdev_max_discard_sectors(file_bdev(bdev_file))) ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); @@ -2361,20 +2362,20 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, err = "cache_alloc(): cache device is too small"; else err = "cache_alloc(): unknown error"; - pr_notice("error %pg: %s\n", bdev_handle->bdev, err); + pr_notice("error %pg: %s\n", file_bdev(bdev_file), err); /* * If we failed here, it means ca->kobj is not initialized yet, * kobject_put() won't be called and there is no chance to - * call bdev_release() to bdev in bch_cache_release(). So - * we explicitly call bdev_release() here. + * call fput() to bdev in bch_cache_release(). So + * we explicitly call fput() on the block device here. */ - bdev_release(bdev_handle); + fput(bdev_file); return ret; } - if (kobject_add(&ca->kobj, bdev_kobj(bdev_handle->bdev), "bcache")) { + if (kobject_add(&ca->kobj, bdev_kobj(file_bdev(bdev_file)), "bcache")) { pr_notice("error %pg: error calling kobject_add\n", - bdev_handle->bdev); + file_bdev(bdev_file)); ret = -ENOMEM; goto out; } @@ -2388,7 +2389,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, goto out; } - pr_info("registered cache device %pg\n", ca->bdev_handle->bdev); + pr_info("registered cache device %pg\n", file_bdev(ca->bdev_file)); out: kobject_put(&ca->kobj); @@ -2446,7 +2447,7 @@ struct async_reg_args { char *path; struct cache_sb *sb; struct cache_sb_disk *sb_disk; - struct bdev_handle *bdev_handle; + struct file *bdev_file; void *holder; }; @@ -2457,7 +2458,7 @@ static void register_bdev_worker(struct work_struct *work) container_of(work, struct async_reg_args, reg_work.work); mutex_lock(&bch_register_lock); - if (register_bdev(args->sb, args->sb_disk, args->bdev_handle, + if (register_bdev(args->sb, args->sb_disk, args->bdev_file, args->holder) < 0) fail = true; mutex_unlock(&bch_register_lock); @@ -2478,7 +2479,7 @@ static void register_cache_worker(struct work_struct *work) container_of(work, struct async_reg_args, reg_work.work); /* blkdev_put() will be called in bch_cache_release() */ - if (register_cache(args->sb, args->sb_disk, args->bdev_handle, + if (register_cache(args->sb, args->sb_disk, args->bdev_file, args->holder)) fail = true; @@ -2516,7 +2517,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, char *path = NULL; struct cache_sb *sb; struct cache_sb_disk *sb_disk; - struct bdev_handle *bdev_handle, *bdev_handle2; + struct file *bdev_file, *bdev_file2; void *holder = NULL; ssize_t ret; bool async_registration = false; @@ -2549,15 +2550,15 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, ret = -EINVAL; err = "failed to open device"; - bdev_handle = bdev_open_by_path(strim(path), BLK_OPEN_READ, NULL, NULL); - if (IS_ERR(bdev_handle)) + bdev_file = bdev_file_open_by_path(strim(path), BLK_OPEN_READ, NULL, NULL); + if (IS_ERR(bdev_file)) goto out_free_sb; err = "failed to set blocksize"; - if (set_blocksize(bdev_handle->bdev, 4096)) + if (set_blocksize(file_bdev(bdev_file), 4096)) goto out_blkdev_put; - err = read_super(sb, bdev_handle->bdev, &sb_disk); + err = read_super(sb, file_bdev(bdev_file), &sb_disk); if (err) goto out_blkdev_put; @@ -2569,13 +2570,13 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, } /* Now reopen in exclusive mode with proper holder */ - bdev_handle2 = bdev_open_by_dev(bdev_handle->bdev->bd_dev, + bdev_file2 = bdev_file_open_by_dev(file_bdev(bdev_file)->bd_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, holder, NULL); - bdev_release(bdev_handle); - bdev_handle = bdev_handle2; - if (IS_ERR(bdev_handle)) { - ret = PTR_ERR(bdev_handle); - bdev_handle = NULL; + fput(bdev_file); + bdev_file = bdev_file2; + if (IS_ERR(bdev_file)) { + ret = PTR_ERR(bdev_file); + bdev_file = NULL; if (ret == -EBUSY) { dev_t dev; @@ -2610,7 +2611,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, args->path = path; args->sb = sb; args->sb_disk = sb_disk; - args->bdev_handle = bdev_handle; + args->bdev_file = bdev_file; args->holder = holder; register_device_async(args); /* No wait and returns to user space */ @@ -2619,14 +2620,14 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, if (SB_IS_BDEV(sb)) { mutex_lock(&bch_register_lock); - ret = register_bdev(sb, sb_disk, bdev_handle, holder); + ret = register_bdev(sb, sb_disk, bdev_file, holder); mutex_unlock(&bch_register_lock); /* blkdev_put() will be called in cached_dev_free() */ if (ret < 0) goto out_free_sb; } else { /* blkdev_put() will be called in bch_cache_release() */ - ret = register_cache(sb, sb_disk, bdev_handle, holder); + ret = register_cache(sb, sb_disk, bdev_file, holder); if (ret) goto out_free_sb; } @@ -2642,8 +2643,8 @@ out_free_holder: out_put_sb_page: put_page(virt_to_page(sb_disk)); out_blkdev_put: - if (bdev_handle) - bdev_release(bdev_handle); + if (bdev_file) + fput(bdev_file); out_free_sb: kfree(sb); out_free_path: diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index eb009d6bb03a..17e9af60bbf7 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -213,6 +213,7 @@ struct raid_dev { #define RT_FLAG_RS_IN_SYNC 6 #define RT_FLAG_RS_RESYNCING 7 #define RT_FLAG_RS_GROW 8 +#define RT_FLAG_RS_FROZEN 9 /* Array elements of 64 bit needed for rebuild/failed disk bits */ #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8) @@ -3240,11 +3241,12 @@ size_check: rs->md.ro = 1; rs->md.in_sync = 1; - /* Keep array frozen until resume. */ - set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery); - /* Has to be held on running the array */ mddev_suspend_and_lock_nointr(&rs->md); + + /* Keep array frozen until resume. */ + md_frozen_sync_thread(&rs->md); + r = md_run(&rs->md); rs->md.in_sync = 0; /* Assume already marked dirty */ if (r) { @@ -3339,7 +3341,8 @@ static int raid_map(struct dm_target *ti, struct bio *bio) if (unlikely(bio_end_sector(bio) > mddev->array_sectors)) return DM_MAPIO_REQUEUE; - md_handle_request(mddev, bio); + if (unlikely(!md_handle_request(mddev, bio))) + return DM_MAPIO_REQUEUE; return DM_MAPIO_SUBMITTED; } @@ -3718,21 +3721,33 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv, { struct raid_set *rs = ti->private; struct mddev *mddev = &rs->md; + int ret = 0; if (!mddev->pers || !mddev->pers->sync_request) return -EINVAL; - if (!strcasecmp(argv[0], "frozen")) - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - else - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + if (test_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags) || + test_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags)) + return -EBUSY; - if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) { - if (mddev->sync_thread) { - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_reap_sync_thread(mddev); - } - } else if (decipher_sync_action(mddev, mddev->recovery) != st_idle) + if (!strcasecmp(argv[0], "frozen")) { + ret = mddev_lock(mddev); + if (ret) + return ret; + + md_frozen_sync_thread(mddev); + mddev_unlock(mddev); + } else if (!strcasecmp(argv[0], "idle")) { + ret = mddev_lock(mddev); + if (ret) + return ret; + + md_idle_sync_thread(mddev); + mddev_unlock(mddev); + } + + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + if (decipher_sync_action(mddev, mddev->recovery) != st_idle) return -EBUSY; else if (!strcasecmp(argv[0], "resync")) ; /* MD_RECOVERY_NEEDED set below */ @@ -3791,15 +3806,46 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs)); } +static void raid_presuspend(struct dm_target *ti) +{ + struct raid_set *rs = ti->private; + struct mddev *mddev = &rs->md; + + /* + * From now on, disallow raid_message() to change sync_thread until + * resume, raid_postsuspend() is too late. + */ + set_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags); + + if (!reshape_interrupted(mddev)) + return; + + /* + * For raid456, if reshape is interrupted, IO across reshape position + * will never make progress, while caller will wait for IO to be done. + * Inform raid456 to handle those IO to prevent deadlock. + */ + if (mddev->pers && mddev->pers->prepare_suspend) + mddev->pers->prepare_suspend(mddev); +} + +static void raid_presuspend_undo(struct dm_target *ti) +{ + struct raid_set *rs = ti->private; + + clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags); +} + static void raid_postsuspend(struct dm_target *ti) { struct raid_set *rs = ti->private; if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) { - /* Writes have to be stopped before suspending to avoid deadlocks. */ - if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery)) - md_stop_writes(&rs->md); - + /* + * sync_thread must be stopped during suspend, and writes have + * to be stopped before suspending to avoid deadlocks. + */ + md_stop_writes(&rs->md); mddev_suspend(&rs->md, false); } } @@ -4012,8 +4058,6 @@ static int raid_preresume(struct dm_target *ti) } /* Check for any resize/reshape on @rs and adjust/initiate */ - /* Be prepared for mddev_resume() in raid_resume() */ - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) { set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); mddev->resync_min = mddev->recovery_cp; @@ -4047,7 +4091,9 @@ static void raid_resume(struct dm_target *ti) * Take this opportunity to check whether any failed * devices are reachable again. */ + mddev_lock_nointr(mddev); attempt_restore_of_faulty_devices(rs); + mddev_unlock(mddev); } if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) { @@ -4055,10 +4101,13 @@ static void raid_resume(struct dm_target *ti) if (mddev->delta_disks < 0) rs_set_capacity(rs); + WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)); + WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)); + clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags); mddev_lock_nointr(mddev); - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); mddev->ro = 0; mddev->in_sync = 0; + md_unfrozen_sync_thread(mddev); mddev_unlock_and_resume(mddev); } } @@ -4074,6 +4123,8 @@ static struct target_type raid_target = { .message = raid_message, .iterate_devices = raid_iterate_devices, .io_hints = raid_io_hints, + .presuspend = raid_presuspend, + .presuspend_undo = raid_presuspend_undo, .postsuspend = raid_postsuspend, .preresume = raid_preresume, .resume = raid_resume, diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index fdfe30f7b697..8156881a31de 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1655,10 +1655,13 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone) if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) { struct dmz_dev *dev = zone->dev; + unsigned int noio_flag; + noio_flag = memalloc_noio_save(); ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET, dmz_start_sect(zmd, zone), - zmd->zone_nr_sectors, GFP_NOIO); + zmd->zone_nr_sectors); + memalloc_noio_restore(noio_flag); if (ret) { dmz_dev_err(dev, "Reset zone %u failed %d", zone->id, ret); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 8dcabf84d866..447e132d09b5 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -726,7 +726,8 @@ static struct table_device *open_table_device(struct mapped_device *md, dev_t dev, blk_mode_t mode) { struct table_device *td; - struct bdev_handle *bdev_handle; + struct file *bdev_file; + struct block_device *bdev; u64 part_off; int r; @@ -735,34 +736,36 @@ static struct table_device *open_table_device(struct mapped_device *md, return ERR_PTR(-ENOMEM); refcount_set(&td->count, 1); - bdev_handle = bdev_open_by_dev(dev, mode, _dm_claim_ptr, NULL); - if (IS_ERR(bdev_handle)) { - r = PTR_ERR(bdev_handle); + bdev_file = bdev_file_open_by_dev(dev, mode, _dm_claim_ptr, NULL); + if (IS_ERR(bdev_file)) { + r = PTR_ERR(bdev_file); goto out_free_td; } + bdev = file_bdev(bdev_file); + /* * We can be called before the dm disk is added. In that case we can't * register the holder relation here. It will be done once add_disk was * called. */ if (md->disk->slave_dir) { - r = bd_link_disk_holder(bdev_handle->bdev, md->disk); + r = bd_link_disk_holder(bdev, md->disk); if (r) goto out_blkdev_put; } td->dm_dev.mode = mode; - td->dm_dev.bdev = bdev_handle->bdev; - td->dm_dev.bdev_handle = bdev_handle; - td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev_handle->bdev, &part_off, + td->dm_dev.bdev = bdev; + td->dm_dev.bdev_file = bdev_file; + td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off, NULL, NULL); format_dev_t(td->dm_dev.name, dev); list_add(&td->list, &md->table_devices); return td; out_blkdev_put: - bdev_release(bdev_handle); + fput(bdev_file); out_free_td: kfree(td); return ERR_PTR(r); @@ -775,7 +778,7 @@ static void close_table_device(struct table_device *td, struct mapped_device *md { if (md->disk->slave_dir) bd_unlink_disk_holder(td->dm_dev.bdev, md->disk); - bdev_release(td->dm_dev.bdev_handle); + fput(td->dm_dev.bdev_file); put_dax(td->dm_dev.dax_dev); list_del(&td->list); kfree(td); @@ -2098,8 +2101,8 @@ static struct mapped_device *alloc_dev(int minor) * established. If request-based table is loaded: blk-mq will * override accordingly. */ - md->disk = blk_alloc_disk(md->numa_node_id); - if (!md->disk) + md->disk = blk_alloc_disk(NULL, md->numa_node_id); + if (IS_ERR(md->disk)) goto bad; md->queue = md->disk->queue; diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 9672f75c3050..059afc24c08b 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -234,7 +234,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, sector_t doff; bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev; - if (pg_index == store->file_pages - 1) { + /* we compare length (page numbers), not page offset. */ + if ((pg_index - store->sb_index) == store->file_pages - 1) { unsigned int last_page_size = store->bytes & (PAGE_SIZE - 1); if (last_page_size == 0) @@ -438,8 +439,8 @@ static void filemap_write_page(struct bitmap *bitmap, unsigned long pg_index, struct page *page = store->filemap[pg_index]; if (mddev_is_clustered(bitmap->mddev)) { - pg_index += bitmap->cluster_slot * - DIV_ROUND_UP(store->bytes, PAGE_SIZE); + /* go to node bitmap area starting point */ + pg_index += store->sb_index; } if (store->file) @@ -952,6 +953,7 @@ static void md_bitmap_file_set_bit(struct bitmap *bitmap, sector_t block) unsigned long index = file_page_index(store, chunk); unsigned long node_offset = 0; + index += store->sb_index; if (mddev_is_clustered(bitmap->mddev)) node_offset = bitmap->cluster_slot * store->file_pages; @@ -982,6 +984,7 @@ static void md_bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block) unsigned long index = file_page_index(store, chunk); unsigned long node_offset = 0; + index += store->sb_index; if (mddev_is_clustered(bitmap->mddev)) node_offset = bitmap->cluster_slot * store->file_pages; @@ -1043,9 +1046,8 @@ void md_bitmap_unplug(struct bitmap *bitmap) if (dirty || need_write) { if (!writing) { md_bitmap_wait_writes(bitmap); - if (bitmap->mddev->queue) - blk_add_trace_msg(bitmap->mddev->queue, - "md bitmap_unplug"); + mddev_add_trace_msg(bitmap->mddev, + "md bitmap_unplug"); } clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING); filemap_write_page(bitmap, i, false); @@ -1316,9 +1318,7 @@ void md_bitmap_daemon_work(struct mddev *mddev) } bitmap->allclean = 1; - if (bitmap->mddev->queue) - blk_add_trace_msg(bitmap->mddev->queue, - "md bitmap_daemon_work"); + mddev_add_trace_msg(bitmap->mddev, "md bitmap_daemon_work"); /* Any file-page which is PENDING now needs to be written. * So set NEEDWRITE now, then after we make any last-minute changes diff --git a/drivers/md/md-linear.h b/drivers/md/md-linear.h deleted file mode 100644 index 5587eeedb882..000000000000 --- a/drivers/md/md-linear.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINEAR_H -#define _LINEAR_H - -struct dev_info { - struct md_rdev *rdev; - sector_t end_sector; -}; - -struct linear_conf -{ - struct rcu_head rcu; - sector_t array_sectors; - int raid_disks; /* a copy of mddev->raid_disks */ - struct dev_info disks[] __counted_by(raid_disks); -}; -#endif diff --git a/drivers/md/md-multipath.h b/drivers/md/md-multipath.h deleted file mode 100644 index b3099e5fc4d7..000000000000 --- a/drivers/md/md-multipath.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _MULTIPATH_H -#define _MULTIPATH_H - -struct multipath_info { - struct md_rdev *rdev; -}; - -struct mpconf { - struct mddev *mddev; - struct multipath_info *multipaths; - int raid_disks; - spinlock_t device_lock; - struct list_head retry_list; - - mempool_t pool; -}; - -/* - * this is our 'private' 'collective' MULTIPATH buffer head. - * it contains information about what kind of IO operations were started - * for this MULTIPATH operation, and about their status: - */ - -struct multipath_bh { - struct mddev *mddev; - struct bio *master_bio; - struct bio bio; - int path; - struct list_head retry_list; -}; -#endif diff --git a/drivers/md/md.c b/drivers/md/md.c index 9e41a9aaba8b..e575e74aabf5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -65,7 +65,6 @@ #include <linux/percpu-refcount.h> #include <linux/part_stat.h> -#include <trace/events/block.h> #include "md.h" #include "md-bitmap.h" #include "md-cluster.h" @@ -99,18 +98,6 @@ static void mddev_detach(struct mddev *mddev); static void export_rdev(struct md_rdev *rdev, struct mddev *mddev); static void md_wakeup_thread_directly(struct md_thread __rcu *thread); -enum md_ro_state { - MD_RDWR, - MD_RDONLY, - MD_AUTO_READ, - MD_MAX_STATE -}; - -static bool md_is_rdwr(struct mddev *mddev) -{ - return (mddev->ro == MD_RDWR); -} - /* * Default number of read corrections we'll attempt on an rdev * before ejecting it from the array. We divide the read error @@ -378,7 +365,7 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio) return true; } -void md_handle_request(struct mddev *mddev, struct bio *bio) +bool md_handle_request(struct mddev *mddev, struct bio *bio) { check_suspended: if (is_suspended(mddev, bio)) { @@ -386,7 +373,7 @@ check_suspended: /* Bail out if REQ_NOWAIT is set for the bio */ if (bio->bi_opf & REQ_NOWAIT) { bio_wouldblock_error(bio); - return; + return true; } for (;;) { prepare_to_wait(&mddev->sb_wait, &__wait, @@ -402,10 +389,13 @@ check_suspended: if (!mddev->pers->make_request(mddev, bio)) { percpu_ref_put(&mddev->active_io); + if (!mddev->gendisk && mddev->pers->prepare_suspend) + return false; goto check_suspended; } percpu_ref_put(&mddev->active_io); + return true; } EXPORT_SYMBOL(md_handle_request); @@ -529,6 +519,24 @@ void mddev_resume(struct mddev *mddev) } EXPORT_SYMBOL_GPL(mddev_resume); +/* sync bdev before setting device to readonly or stopping raid*/ +static int mddev_set_closing_and_sync_blockdev(struct mddev *mddev, int opener_num) +{ + mutex_lock(&mddev->open_mutex); + if (mddev->pers && atomic_read(&mddev->openers) > opener_num) { + mutex_unlock(&mddev->open_mutex); + return -EBUSY; + } + if (test_and_set_bit(MD_CLOSING, &mddev->flags)) { + mutex_unlock(&mddev->open_mutex); + return -EBUSY; + } + mutex_unlock(&mddev->open_mutex); + + sync_blockdev(mddev->gendisk->part0); + return 0; +} + /* * Generic flush handling for md */ @@ -2406,7 +2414,7 @@ int md_integrity_register(struct mddev *mddev) if (list_empty(&mddev->disks)) return 0; /* nothing to do */ - if (!mddev->gendisk || blk_get_integrity(mddev->gendisk)) + if (mddev_is_dm(mddev) || blk_get_integrity(mddev->gendisk)) return 0; /* shouldn't register, or already is */ rdev_for_each(rdev, mddev) { /* skip spares and non-functional disks */ @@ -2459,7 +2467,7 @@ int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) { struct blk_integrity *bi_mddev; - if (!mddev->gendisk) + if (mddev_is_dm(mddev)) return 0; bi_mddev = blk_get_integrity(mddev->gendisk); @@ -2566,6 +2574,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) fail: pr_warn("md: failed to register dev-%s for %s\n", b, mdname(mddev)); + mddev_destroy_serial_pool(mddev, rdev); return err; } @@ -2582,7 +2591,7 @@ static void export_rdev(struct md_rdev *rdev, struct mddev *mddev) if (test_bit(AutoDetected, &rdev->flags)) md_autodetect_dev(rdev->bdev->bd_dev); #endif - bdev_release(rdev->bdev_handle); + fput(rdev->bdev_file); rdev->bdev = NULL; kobject_put(&rdev->kobj); } @@ -2595,7 +2604,7 @@ static void md_kick_rdev_from_array(struct md_rdev *rdev) list_del_rcu(&rdev->same_set); pr_debug("md: unbind<%pg>\n", rdev->bdev); mddev_destroy_serial_pool(rdev->mddev, rdev); - rdev->mddev = NULL; + WRITE_ONCE(rdev->mddev, NULL); sysfs_remove_link(&rdev->kobj, "block"); sysfs_put(rdev->sysfs_state); sysfs_put(rdev->sysfs_unack_badblocks); @@ -2851,8 +2860,7 @@ repeat: pr_debug("md: updating %s RAID superblock on device (in sync %d)\n", mdname(mddev), mddev->in_sync); - if (mddev->queue) - blk_add_trace_msg(mddev->queue, "md md_update_sb"); + mddev_add_trace_msg(mddev, "md md_update_sb"); rewrite: md_bitmap_update_sb(mddev->bitmap); rdev_for_each(rdev, mddev) { @@ -2933,7 +2941,6 @@ static int add_bound_rdev(struct md_rdev *rdev) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_new_event(); - md_wakeup_thread(mddev->thread); return 0; } @@ -3048,10 +3055,8 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) if (err == 0) { md_kick_rdev_from_array(rdev); - if (mddev->pers) { + if (mddev->pers) set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); - md_wakeup_thread(mddev->thread); - } md_new_event(); } } @@ -3081,7 +3086,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) clear_bit(BlockedBadBlocks, &rdev->flags); wake_up(&rdev->blocked_wait); set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); - md_wakeup_thread(rdev->mddev->thread); err = 0; } else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) { @@ -3119,7 +3123,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) !test_bit(Replacement, &rdev->flags)) set_bit(WantReplacement, &rdev->flags); set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); - md_wakeup_thread(rdev->mddev->thread); err = 0; } else if (cmd_match(buf, "-want_replacement")) { /* Clearing 'want_replacement' is always allowed. @@ -3249,7 +3252,6 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) if (rdev->raid_disk >= 0) return -EBUSY; set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); - md_wakeup_thread(rdev->mddev->thread); } else if (rdev->mddev->pers) { /* Activating a spare .. or possibly reactivating * if we ever get bitmaps working here. @@ -3343,8 +3345,7 @@ static ssize_t new_offset_store(struct md_rdev *rdev, if (kstrtoull(buf, 10, &new_offset) < 0) return -EINVAL; - if (mddev->sync_thread || - test_bit(MD_RECOVERY_RUNNING,&mddev->recovery)) + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; if (new_offset == rdev->data_offset) /* reset is always permitted */ @@ -3675,7 +3676,7 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, struct kernfs_node *kn = NULL; bool suspend = false; ssize_t rv; - struct mddev *mddev = rdev->mddev; + struct mddev *mddev = READ_ONCE(rdev->mddev); if (!entry->store) return -EIO; @@ -3777,16 +3778,16 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe if (err) goto out_clear_rdev; - rdev->bdev_handle = bdev_open_by_dev(newdev, + rdev->bdev_file = bdev_file_open_by_dev(newdev, BLK_OPEN_READ | BLK_OPEN_WRITE, super_format == -2 ? &claim_rdev : rdev, NULL); - if (IS_ERR(rdev->bdev_handle)) { + if (IS_ERR(rdev->bdev_file)) { pr_warn("md: could not open device unknown-block(%u,%u).\n", MAJOR(newdev), MINOR(newdev)); - err = PTR_ERR(rdev->bdev_handle); + err = PTR_ERR(rdev->bdev_file); goto out_clear_rdev; } - rdev->bdev = rdev->bdev_handle->bdev; + rdev->bdev = file_bdev(rdev->bdev_file); kobject_init(&rdev->kobj, &rdev_ktype); @@ -3817,7 +3818,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe return rdev; out_blkdev_put: - bdev_release(rdev->bdev_handle); + fput(rdev->bdev_file); out_clear_rdev: md_rdev_clear(rdev); out_free_rdev: @@ -4017,8 +4018,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len) */ rv = -EBUSY; - if (mddev->sync_thread || - test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || mddev->reshape_position != MaxSector || mddev->sysfs_active) goto out_unlock; @@ -4168,7 +4168,6 @@ level_store(struct mddev *mddev, const char *buf, size_t len) mddev->in_sync = 1; del_timer_sync(&mddev->safemode_timer); } - blk_set_stacking_limits(&mddev->queue->limits); pers->run(mddev); set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); if (!mddev->thread) @@ -4475,8 +4474,8 @@ array_state_show(struct mddev *mddev, char *page) return sprintf(page, "%s\n", array_states[st]); } -static int do_md_stop(struct mddev *mddev, int ro, struct block_device *bdev); -static int md_set_readonly(struct mddev *mddev, struct block_device *bdev); +static int do_md_stop(struct mddev *mddev, int ro); +static int md_set_readonly(struct mddev *mddev); static int restart_array(struct mddev *mddev); static ssize_t @@ -4493,6 +4492,17 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) case broken: /* cannot be set */ case bad_word: return -EINVAL; + case clear: + case readonly: + case inactive: + case read_auto: + if (!mddev->pers || !md_is_rdwr(mddev)) + break; + /* write sysfs will not open mddev and opener should be 0 */ + err = mddev_set_closing_and_sync_blockdev(mddev, 0); + if (err) + return err; + break; default: break; } @@ -4526,14 +4536,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) case inactive: /* stop an active array, return 0 otherwise */ if (mddev->pers) - err = do_md_stop(mddev, 2, NULL); + err = do_md_stop(mddev, 2); break; case clear: - err = do_md_stop(mddev, 0, NULL); + err = do_md_stop(mddev, 0); break; case readonly: if (mddev->pers) - err = md_set_readonly(mddev, NULL); + err = md_set_readonly(mddev); else { mddev->ro = MD_RDONLY; set_disk_ro(mddev->gendisk, 1); @@ -4543,7 +4553,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) case read_auto: if (mddev->pers) { if (md_is_rdwr(mddev)) - err = md_set_readonly(mddev, NULL); + err = md_set_readonly(mddev); else if (mddev->ro == MD_RDONLY) err = restart_array(mddev); if (err == 0) { @@ -4592,6 +4602,11 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) sysfs_notify_dirent_safe(mddev->sysfs_state); } mddev_unlock(mddev); + + if (st == readonly || st == read_auto || st == inactive || + (err && st == clear)) + clear_bit(MD_CLOSING, &mddev->flags); + return err ?: len; } static struct md_sysfs_entry md_array_state = @@ -4919,6 +4934,35 @@ static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq) mddev_lock_nointr(mddev); } +void md_idle_sync_thread(struct mddev *mddev) +{ + lockdep_assert_held(&mddev->reconfig_mutex); + + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + stop_sync_thread(mddev, true, true); +} +EXPORT_SYMBOL_GPL(md_idle_sync_thread); + +void md_frozen_sync_thread(struct mddev *mddev) +{ + lockdep_assert_held(&mddev->reconfig_mutex); + + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + stop_sync_thread(mddev, true, false); +} +EXPORT_SYMBOL_GPL(md_frozen_sync_thread); + +void md_unfrozen_sync_thread(struct mddev *mddev) +{ + lockdep_assert_held(&mddev->reconfig_mutex); + + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); + sysfs_notify_dirent_safe(mddev->sysfs_action); +} +EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread); + static void idle_sync_thread(struct mddev *mddev) { mutex_lock(&mddev->sync_mutex); @@ -5710,6 +5754,51 @@ static const struct kobj_type md_ktype = { int mdp_major = 0; +/* stack the limit for all rdevs into lim */ +void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim) +{ + struct md_rdev *rdev; + + rdev_for_each(rdev, mddev) { + queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset, + mddev->gendisk->disk_name); + } +} +EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits); + +/* apply the extra stacking limits from a new rdev into mddev */ +int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev) +{ + struct queue_limits lim; + + if (mddev_is_dm(mddev)) + return 0; + + lim = queue_limits_start_update(mddev->gendisk->queue); + queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset, + mddev->gendisk->disk_name); + return queue_limits_commit_update(mddev->gendisk->queue, &lim); +} +EXPORT_SYMBOL_GPL(mddev_stack_new_rdev); + +/* update the optimal I/O size after a reshape */ +void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes) +{ + struct queue_limits lim; + + if (mddev_is_dm(mddev)) + return; + + /* don't bother updating io_opt if we can't suspend the array */ + if (mddev_suspend(mddev, false) < 0) + return; + lim = queue_limits_start_update(mddev->gendisk->queue); + lim.io_opt = lim.io_min * nr_stripes; + queue_limits_commit_update(mddev->gendisk->queue, &lim); + mddev_resume(mddev); +} +EXPORT_SYMBOL_GPL(mddev_update_io_opt); + static void mddev_delayed_delete(struct work_struct *ws) { struct mddev *mddev = container_of(ws, struct mddev, del_work); @@ -5774,10 +5863,11 @@ struct mddev *md_alloc(dev_t dev, char *name) */ mddev->hold_active = UNTIL_STOP; - error = -ENOMEM; - disk = blk_alloc_disk(NUMA_NO_NODE); - if (!disk) + disk = blk_alloc_disk(NULL, NUMA_NO_NODE); + if (IS_ERR(disk)) { + error = PTR_ERR(disk); goto out_free_mddev; + } disk->major = MAJOR(mddev->unit); disk->first_minor = unit << shift; @@ -5791,9 +5881,7 @@ struct mddev *md_alloc(dev_t dev, char *name) disk->fops = &md_fops; disk->private_data = mddev; - mddev->queue = disk->queue; - blk_set_stacking_limits(&mddev->queue->limits); - blk_queue_write_cache(mddev->queue, true, true); + blk_queue_write_cache(disk->queue, true, true); disk->events |= DISK_EVENT_MEDIA_CHANGE; mddev->gendisk = disk; error = add_disk(disk); @@ -5935,7 +6023,7 @@ int md_run(struct mddev *mddev) invalidate_bdev(rdev->bdev); if (mddev->ro != MD_RDONLY && rdev_read_only(rdev)) { mddev->ro = MD_RDONLY; - if (mddev->gendisk) + if (!mddev_is_dm(mddev)) set_disk_ro(mddev->gendisk, 1); } @@ -6038,7 +6126,10 @@ int md_run(struct mddev *mddev) pr_warn("True protection against single-disk failure might be compromised.\n"); } - mddev->recovery = 0; + /* dm-raid expect sync_thread to be frozen until resume */ + if (mddev->gendisk) + mddev->recovery = 0; + /* may be over-ridden by personality */ mddev->resync_max_sectors = mddev->dev_sectors; @@ -6094,7 +6185,8 @@ int md_run(struct mddev *mddev) } } - if (mddev->queue) { + if (!mddev_is_dm(mddev)) { + struct request_queue *q = mddev->gendisk->queue; bool nonrot = true; rdev_for_each(rdev, mddev) { @@ -6106,14 +6198,14 @@ int md_run(struct mddev *mddev) if (mddev->degraded) nonrot = false; if (nonrot) - blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue); + blk_queue_flag_set(QUEUE_FLAG_NONROT, q); else - blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue); - blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue); + blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); + blk_queue_flag_set(QUEUE_FLAG_IO_STAT, q); /* Set the NOWAIT flags if all underlying devices support it */ if (nowait) - blk_queue_flag_set(QUEUE_FLAG_NOWAIT, mddev->queue); + blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q); } if (pers->sync_request) { if (mddev->kobj.sd && @@ -6192,7 +6284,6 @@ int do_md_run(struct mddev *mddev) /* run start up tasks that require md_thread */ md_start(mddev); - md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); @@ -6213,7 +6304,6 @@ int md_start(struct mddev *mddev) if (mddev->pers->start) { set_bit(MD_RECOVERY_WAIT, &mddev->recovery); - md_wakeup_thread(mddev->thread); ret = mddev->pers->start(mddev); clear_bit(MD_RECOVERY_WAIT, &mddev->recovery); md_wakeup_thread(mddev->sync_thread); @@ -6258,7 +6348,6 @@ static int restart_array(struct mddev *mddev) pr_debug("md: %s switched to read-write mode.\n", mdname(mddev)); /* Kick recovery or resync if necessary */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); sysfs_notify_dirent_safe(mddev->sysfs_state); return 0; @@ -6278,7 +6367,15 @@ static void md_clean(struct mddev *mddev) mddev->persistent = 0; mddev->level = LEVEL_NONE; mddev->clevel[0] = 0; - mddev->flags = 0; + /* + * Don't clear MD_CLOSING, or mddev can be opened again. + * 'hold_active != 0' means mddev is still in the creation + * process and will be used later. + */ + if (mddev->hold_active) + mddev->flags = 0; + else + mddev->flags &= BIT_ULL_MASK(MD_CLOSING); mddev->sb_flags = 0; mddev->ro = MD_RDWR; mddev->metadata_type[0] = 0; @@ -6315,7 +6412,6 @@ static void md_clean(struct mddev *mddev) static void __md_stop_writes(struct mddev *mddev) { - stop_sync_thread(mddev, true, false); del_timer_sync(&mddev->safemode_timer); if (mddev->pers && mddev->pers->quiesce) { @@ -6340,6 +6436,8 @@ static void __md_stop_writes(struct mddev *mddev) void md_stop_writes(struct mddev *mddev) { mddev_lock_nointr(mddev); + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + stop_sync_thread(mddev, true, false); __md_stop_writes(mddev); mddev_unlock(mddev); } @@ -6353,8 +6451,10 @@ static void mddev_detach(struct mddev *mddev) mddev->pers->quiesce(mddev, 0); } md_unregister_thread(mddev, &mddev->thread); - if (mddev->queue) - blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/ + + /* the unplug fn references 'conf' */ + if (!mddev_is_dm(mddev)) + blk_sync_queue(mddev->gendisk->queue); } static void __md_stop(struct mddev *mddev) @@ -6391,7 +6491,8 @@ void md_stop(struct mddev *mddev) EXPORT_SYMBOL_GPL(md_stop); -static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) +/* ensure 'mddev->pers' exist before calling md_set_readonly() */ +static int md_set_readonly(struct mddev *mddev) { int err = 0; int did_freeze = 0; @@ -6402,7 +6503,6 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) { did_freeze = 1; set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - md_wakeup_thread(mddev->thread); } stop_sync_thread(mddev, false, false); @@ -6410,36 +6510,29 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); mddev_lock_nointr(mddev); - mutex_lock(&mddev->open_mutex); - if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) || - mddev->sync_thread || - test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { pr_warn("md: %s still in use.\n",mdname(mddev)); err = -EBUSY; goto out; } - if (mddev->pers) { - __md_stop_writes(mddev); - - if (mddev->ro == MD_RDONLY) { - err = -ENXIO; - goto out; - } + __md_stop_writes(mddev); - mddev->ro = MD_RDONLY; - set_disk_ro(mddev->gendisk, 1); + if (mddev->ro == MD_RDONLY) { + err = -ENXIO; + goto out; } + mddev->ro = MD_RDONLY; + set_disk_ro(mddev->gendisk, 1); + out: - if ((mddev->pers && !err) || did_freeze) { + if (!err || did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_wakeup_thread(mddev->thread); sysfs_notify_dirent_safe(mddev->sysfs_state); } - mutex_unlock(&mddev->open_mutex); return err; } @@ -6447,8 +6540,7 @@ out: * 0 - completely stop and dis-assemble array * 2 - stop but do not disassemble array */ -static int do_md_stop(struct mddev *mddev, int mode, - struct block_device *bdev) +static int do_md_stop(struct mddev *mddev, int mode) { struct gendisk *disk = mddev->gendisk; struct md_rdev *rdev; @@ -6457,22 +6549,16 @@ static int do_md_stop(struct mddev *mddev, int mode, if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) { did_freeze = 1; set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - md_wakeup_thread(mddev->thread); } stop_sync_thread(mddev, true, false); - mutex_lock(&mddev->open_mutex); - if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) || - mddev->sysfs_active || - mddev->sync_thread || + if (mddev->sysfs_active || test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { pr_warn("md: %s still in use.\n",mdname(mddev)); - mutex_unlock(&mddev->open_mutex); if (did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_wakeup_thread(mddev->thread); } return -EBUSY; } @@ -6491,13 +6577,11 @@ static int do_md_stop(struct mddev *mddev, int mode, sysfs_unlink_rdev(mddev, rdev); set_capacity_and_notify(disk, 0); - mutex_unlock(&mddev->open_mutex); mddev->changed = 1; if (!md_is_rdwr(mddev)) mddev->ro = MD_RDWR; - } else - mutex_unlock(&mddev->open_mutex); + } /* * Free resources if final stop */ @@ -6543,7 +6627,7 @@ static void autorun_array(struct mddev *mddev) err = do_md_run(mddev); if (err) { pr_warn("md: do_md_run() returned %d\n", err); - do_md_stop(mddev, 0, NULL); + do_md_stop(mddev, 0); } } @@ -7013,9 +7097,7 @@ kick_rdev: md_kick_rdev_from_array(rdev); set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); - if (mddev->thread) - md_wakeup_thread(mddev->thread); - else + if (!mddev->thread) md_update_sb(mddev, 1); md_new_event(); @@ -7090,14 +7172,13 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) if (!bdev_nowait(rdev->bdev)) { pr_info("%s: Disabling nowait because %pg does not support nowait\n", mdname(mddev), rdev->bdev); - blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->queue); + blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->gendisk->queue); } /* * Kick recovery, maybe this spare has to be added to the * array immediately. */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_wakeup_thread(mddev->thread); md_new_event(); return 0; @@ -7311,8 +7392,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors) * of each device. If num_sectors is zero, we find the largest size * that fits. */ - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || - mddev->sync_thread) + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; if (!md_is_rdwr(mddev)) return -EROFS; @@ -7329,10 +7409,9 @@ static int update_size(struct mddev *mddev, sector_t num_sectors) if (!rv) { if (mddev_is_clustered(mddev)) md_cluster_ops->update_size(mddev, old_dev_sectors); - else if (mddev->queue) { + else if (!mddev_is_dm(mddev)) set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); - } } return rv; } @@ -7349,8 +7428,7 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks) if (raid_disks <= 0 || (mddev->max_disks && raid_disks >= mddev->max_disks)) return -EINVAL; - if (mddev->sync_thread || - test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) || mddev->reshape_position != MaxSector) return -EBUSY; @@ -7546,16 +7624,17 @@ static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static inline bool md_ioctl_valid(unsigned int cmd) +static inline int md_ioctl_valid(unsigned int cmd) { switch (cmd) { - case ADD_NEW_DISK: case GET_ARRAY_INFO: - case GET_BITMAP_FILE: case GET_DISK_INFO: + case RAID_VERSION: + return 0; + case ADD_NEW_DISK: + case GET_BITMAP_FILE: case HOT_ADD_DISK: case HOT_REMOVE_DISK: - case RAID_VERSION: case RESTART_ARRAY_RW: case RUN_ARRAY: case SET_ARRAY_INFO: @@ -7564,9 +7643,11 @@ static inline bool md_ioctl_valid(unsigned int cmd) case STOP_ARRAY: case STOP_ARRAY_RO: case CLUSTERED_DISK_NACK: - return true; + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + return 0; default: - return false; + return -ENOTTY; } } @@ -7624,31 +7705,17 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode, int err = 0; void __user *argp = (void __user *)arg; struct mddev *mddev = NULL; - bool did_set_md_closing = false; - if (!md_ioctl_valid(cmd)) - return -ENOTTY; - - switch (cmd) { - case RAID_VERSION: - case GET_ARRAY_INFO: - case GET_DISK_INFO: - break; - default: - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - } + err = md_ioctl_valid(cmd); + if (err) + return err; /* * Commands dealing with the RAID driver but not any * particular array: */ - switch (cmd) { - case RAID_VERSION: - err = get_version(argp); - goto out; - default:; - } + if (cmd == RAID_VERSION) + return get_version(argp); /* * Commands creating/starting a new array: @@ -7656,35 +7723,23 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode, mddev = bdev->bd_disk->private_data; - if (!mddev) { - BUG(); - goto out; - } - /* Some actions do not requires the mutex */ switch (cmd) { case GET_ARRAY_INFO: if (!mddev->raid_disks && !mddev->external) - err = -ENODEV; - else - err = get_array_info(mddev, argp); - goto out; + return -ENODEV; + return get_array_info(mddev, argp); case GET_DISK_INFO: if (!mddev->raid_disks && !mddev->external) - err = -ENODEV; - else - err = get_disk_info(mddev, argp); - goto out; + return -ENODEV; + return get_disk_info(mddev, argp); case SET_DISK_FAULTY: - err = set_disk_faulty(mddev, new_decode_dev(arg)); - goto out; + return set_disk_faulty(mddev, new_decode_dev(arg)); case GET_BITMAP_FILE: - err = get_bitmap_file(mddev, argp); - goto out; - + return get_bitmap_file(mddev, argp); } if (cmd == HOT_REMOVE_DISK) @@ -7697,20 +7752,9 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode, /* Need to flush page cache, and ensure no-one else opens * and writes */ - mutex_lock(&mddev->open_mutex); - if (mddev->pers && atomic_read(&mddev->openers) > 1) { - mutex_unlock(&mddev->open_mutex); - err = -EBUSY; - goto out; - } - if (test_and_set_bit(MD_CLOSING, &mddev->flags)) { - mutex_unlock(&mddev->open_mutex); - err = -EBUSY; - goto out; - } - did_set_md_closing = true; - mutex_unlock(&mddev->open_mutex); - sync_blockdev(bdev); + err = mddev_set_closing_and_sync_blockdev(mddev, 1); + if (err) + return err; } if (!md_is_rdwr(mddev)) @@ -7751,11 +7795,12 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode, goto unlock; case STOP_ARRAY: - err = do_md_stop(mddev, 0, bdev); + err = do_md_stop(mddev, 0); goto unlock; case STOP_ARRAY_RO: - err = md_set_readonly(mddev, bdev); + if (mddev->pers) + err = md_set_readonly(mddev); goto unlock; case HOT_REMOVE_DISK: @@ -7850,7 +7895,7 @@ unlock: mddev_unlock(mddev); out: - if(did_set_md_closing) + if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY)) clear_bit(MD_CLOSING, &mddev->flags); return err; } @@ -8687,10 +8732,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, bio_chain(discard_bio, bio); bio_clone_blkg_association(discard_bio, bio); - if (mddev->gendisk) - trace_block_bio_remap(discard_bio, - disk_devt(mddev->gendisk), - bio->bi_iter.bi_sector); + mddev_trace_remap(mddev, discard_bio, bio->bi_iter.bi_sector); submit_bio_noacct(discard_bio); } EXPORT_SYMBOL_GPL(md_submit_discard_bio); @@ -8737,6 +8779,23 @@ void md_account_bio(struct mddev *mddev, struct bio **bio) } EXPORT_SYMBOL_GPL(md_account_bio); +void md_free_cloned_bio(struct bio *bio) +{ + struct md_io_clone *md_io_clone = bio->bi_private; + struct bio *orig_bio = md_io_clone->orig_bio; + struct mddev *mddev = md_io_clone->mddev; + + if (bio->bi_status && !orig_bio->bi_status) + orig_bio->bi_status = bio->bi_status; + + if (md_io_clone->start_time) + bio_end_io_acct(orig_bio, md_io_clone->start_time); + + bio_put(bio); + percpu_ref_put(&mddev->active_io); +} +EXPORT_SYMBOL_GPL(md_free_cloned_bio); + /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before @@ -9170,7 +9229,7 @@ void md_do_sync(struct md_thread *thread) mddev->delta_disks > 0 && mddev->pers->finish_reshape && mddev->pers->size && - mddev->queue) { + !mddev_is_dm(mddev)) { mddev_lock_nointr(mddev); md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0)); mddev_unlock(mddev); @@ -9270,9 +9329,14 @@ static bool md_spares_need_change(struct mddev *mddev) { struct md_rdev *rdev; - rdev_for_each(rdev, mddev) - if (rdev_removeable(rdev) || rdev_addable(rdev)) + rcu_read_lock(); + rdev_for_each_rcu(rdev, mddev) { + if (rdev_removeable(rdev) || rdev_addable(rdev)) { + rcu_read_unlock(); return true; + } + } + rcu_read_unlock(); return false; } diff --git a/drivers/md/md.h b/drivers/md/md.h index 8d881cc59799..097d9dbd69b8 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -18,6 +18,7 @@ #include <linux/timer.h> #include <linux/wait.h> #include <linux/workqueue.h> +#include <trace/events/block.h> #include "md-cluster.h" #define MaxSector (~(sector_t)0) @@ -59,7 +60,7 @@ struct md_rdev { */ struct block_device *meta_bdev; struct block_device *bdev; /* block device handle */ - struct bdev_handle *bdev_handle; /* Handle from open for bdev */ + struct file *bdev_file; /* Handle from open for bdev */ struct page *sb_page, *bb_page; int sb_loaded; @@ -207,6 +208,7 @@ enum flag_bits { * check if there is collision between raid1 * serial bios. */ + Nonrot, /* non-rotational device (SSD) */ }; static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors, @@ -222,6 +224,16 @@ static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors, } return 0; } + +static inline int rdev_has_badblock(struct md_rdev *rdev, sector_t s, + int sectors) +{ + sector_t first_bad; + int bad_sectors; + + return is_badblock(rdev, s, sectors, &first_bad, &bad_sectors); +} + extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, @@ -468,7 +480,6 @@ struct mddev { struct timer_list safemode_timer; struct percpu_ref writes_pending; int sync_checkers; /* # of threads checking writes_pending */ - struct request_queue *queue; /* for plugging ... */ struct bitmap *bitmap; /* the bitmap for the device */ struct { @@ -558,6 +569,37 @@ enum recovery_flags { MD_RESYNCING_REMOTE, /* remote node is running resync thread */ }; +enum md_ro_state { + MD_RDWR, + MD_RDONLY, + MD_AUTO_READ, + MD_MAX_STATE +}; + +static inline bool md_is_rdwr(struct mddev *mddev) +{ + return (mddev->ro == MD_RDWR); +} + +static inline bool reshape_interrupted(struct mddev *mddev) +{ + /* reshape never start */ + if (mddev->reshape_position == MaxSector) + return false; + + /* interrupted */ + if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + return true; + + /* running reshape will be interrupted soon. */ + if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) || + test_bit(MD_RECOVERY_INTR, &mddev->recovery) || + test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) + return true; + + return false; +} + static inline int __must_check mddev_lock(struct mddev *mddev) { return mutex_lock_interruptible(&mddev->reconfig_mutex); @@ -617,6 +659,7 @@ struct md_personality int (*start_reshape) (struct mddev *mddev); void (*finish_reshape) (struct mddev *mddev); void (*update_reshape_pos) (struct mddev *mddev); + void (*prepare_suspend) (struct mddev *mddev); /* quiesce suspends or resumes internal processing. * 1 - stop new actions and wait for action io to complete * 0 - return to normal behaviour @@ -750,6 +793,7 @@ extern void md_finish_reshape(struct mddev *mddev); void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio, sector_t start, sector_t size); void md_account_bio(struct mddev *mddev, struct bio **bio); +void md_free_cloned_bio(struct bio *bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, @@ -778,9 +822,12 @@ extern void md_stop_writes(struct mddev *mddev); extern int md_rdev_init(struct md_rdev *rdev); extern void md_rdev_clear(struct md_rdev *rdev); -extern void md_handle_request(struct mddev *mddev, struct bio *bio); +extern bool md_handle_request(struct mddev *mddev, struct bio *bio); extern int mddev_suspend(struct mddev *mddev, bool interruptible); extern void mddev_resume(struct mddev *mddev); +extern void md_idle_sync_thread(struct mddev *mddev); +extern void md_frozen_sync_thread(struct mddev *mddev); +extern void md_unfrozen_sync_thread(struct mddev *mddev); extern void md_reload_sb(struct mddev *mddev, int raid_disk); extern void md_update_sb(struct mddev *mddev, int force); @@ -821,7 +868,7 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio { if (bio_op(bio) == REQ_OP_WRITE_ZEROES && !bio->bi_bdev->bd_disk->queue->limits.max_write_zeroes_sectors) - mddev->queue->limits.max_write_zeroes_sectors = 0; + mddev->gendisk->queue->limits.max_write_zeroes_sectors = 0; } static inline int mddev_suspend_and_lock(struct mddev *mddev) @@ -860,7 +907,31 @@ void md_autostart_arrays(int part); int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info); int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info); int do_md_run(struct mddev *mddev); +void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim); +int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev); +void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes); extern const struct block_device_operations md_fops; +/* + * MD devices can be used undeneath by DM, in which case ->gendisk is NULL. + */ +static inline bool mddev_is_dm(struct mddev *mddev) +{ + return !mddev->gendisk; +} + +static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio, + sector_t sector) +{ + if (!mddev_is_dm(mddev)) + trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector); +} + +#define mddev_add_trace_msg(mddev, fmt, args...) \ +do { \ + if (!mddev_is_dm(mddev)) \ + blk_add_trace_msg((mddev)->gendisk->queue, fmt, ##args); \ +} while (0) + #endif /* _MD_MD_H */ diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index c50a7abda744..c5d4aeb68404 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -379,6 +379,19 @@ static void raid0_free(struct mddev *mddev, void *priv) free_conf(mddev, conf); } +static int raid0_set_limits(struct mddev *mddev) +{ + struct queue_limits lim; + + blk_set_stacking_limits(&lim); + lim.max_hw_sectors = mddev->chunk_sectors; + lim.max_write_zeroes_sectors = mddev->chunk_sectors; + lim.io_min = mddev->chunk_sectors << 9; + lim.io_opt = lim.io_min * mddev->raid_disks; + mddev_stack_rdev_limits(mddev, &lim); + return queue_limits_set(mddev->gendisk->queue, &lim); +} + static int raid0_run(struct mddev *mddev) { struct r0conf *conf; @@ -399,20 +412,10 @@ static int raid0_run(struct mddev *mddev) mddev->private = conf; } conf = mddev->private; - if (mddev->queue) { - struct md_rdev *rdev; - - blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors); - - blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); - blk_queue_io_opt(mddev->queue, - (mddev->chunk_sectors << 9) * mddev->raid_disks); - - rdev_for_each(rdev, mddev) { - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - } + if (!mddev_is_dm(mddev)) { + ret = raid0_set_limits(mddev); + if (ret) + goto out_free_conf; } /* calculate array device size */ @@ -426,8 +429,10 @@ static int raid0_run(struct mddev *mddev) ret = md_integrity_register(mddev); if (ret) - free_conf(mddev, conf); - + goto out_free_conf; + return 0; +out_free_conf: + free_conf(mddev, conf); return ret; } @@ -578,10 +583,7 @@ static void raid0_map_submit_bio(struct mddev *mddev, struct bio *bio) bio_set_dev(bio, tmp_dev->bdev); bio->bi_iter.bi_sector = sector + zone->dev_start + tmp_dev->data_offset; - - if (mddev->gendisk) - trace_block_bio_remap(bio, disk_devt(mddev->gendisk), - bio_sector); + mddev_trace_remap(mddev, bio, bio_sector); mddev_check_write_zeroes(mddev, bio); submit_bio_noacct(bio); } diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index 512746551f36..2ea1710a3b70 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -227,3 +227,72 @@ static inline bool exceed_read_errors(struct mddev *mddev, struct md_rdev *rdev) return false; } + +/** + * raid1_check_read_range() - check a given read range for bad blocks, + * available read length is returned; + * @rdev: the rdev to read; + * @this_sector: read position; + * @len: read length; + * + * helper function for read_balance() + * + * 1) If there are no bad blocks in the range, @len is returned; + * 2) If the range are all bad blocks, 0 is returned; + * 3) If there are partial bad blocks: + * - If the bad block range starts after @this_sector, the length of first + * good region is returned; + * - If the bad block range starts before @this_sector, 0 is returned and + * the @len is updated to the offset into the region before we get to the + * good blocks; + */ +static inline int raid1_check_read_range(struct md_rdev *rdev, + sector_t this_sector, int *len) +{ + sector_t first_bad; + int bad_sectors; + + /* no bad block overlap */ + if (!is_badblock(rdev, this_sector, *len, &first_bad, &bad_sectors)) + return *len; + + /* + * bad block range starts offset into our range so we can return the + * number of sectors before the bad blocks start. + */ + if (first_bad > this_sector) + return first_bad - this_sector; + + /* read range is fully consumed by bad blocks. */ + if (this_sector + *len <= first_bad + bad_sectors) + return 0; + + /* + * final case, bad block range starts before or at the start of our + * range but does not cover our entire range so we still return 0 but + * update the length with the number of sectors before we get to the + * good ones. + */ + *len = first_bad + bad_sectors - this_sector; + return 0; +} + +/* + * Check if read should choose the first rdev. + * + * Balance on the whole device if no resync is going on (recovery is ok) or + * below the resync window. Otherwise, take the first readable disk. + */ +static inline bool raid1_should_read_first(struct mddev *mddev, + sector_t this_sector, int len) +{ + if ((mddev->recovery_cp < this_sector + len)) + return true; + + if (mddev_is_clustered(mddev) && + md_cluster_ops->area_resyncing(mddev, READ, this_sector, + this_sector + len)) + return true; + + return false; +} diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 286f8b16c7bd..be8ac24f50b6 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -46,9 +46,6 @@ static void allow_barrier(struct r1conf *conf, sector_t sector_nr); static void lower_barrier(struct r1conf *conf, sector_t sector_nr); -#define raid1_log(md, fmt, args...) \ - do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0) - #define RAID_1_10_NAME "raid1" #include "raid1-10.c" @@ -498,9 +495,6 @@ static void raid1_end_write_request(struct bio *bio) * to user-side. So if something waits for IO, then it * will wait for the 'master' bio. */ - sector_t first_bad; - int bad_sectors; - r1_bio->bios[mirror] = NULL; to_put = bio; /* @@ -516,8 +510,8 @@ static void raid1_end_write_request(struct bio *bio) set_bit(R1BIO_Uptodate, &r1_bio->state); /* Maybe we can clear some bad blocks. */ - if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors, - &first_bad, &bad_sectors) && !discard_error) { + if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) && + !discard_error) { r1_bio->bios[mirror] = IO_MADE_GOOD; set_bit(R1BIO_MadeGood, &r1_bio->state); } @@ -582,211 +576,312 @@ static sector_t align_to_barrier_unit_end(sector_t start_sector, return len; } -/* - * This routine returns the disk from which the requested read should - * be done. There is a per-array 'next expected sequential IO' sector - * number - if this matches on the next IO then we use the last disk. - * There is also a per-disk 'last know head position' sector that is - * maintained from IRQ contexts, both the normal and the resync IO - * completion handlers update this position correctly. If there is no - * perfect sequential match then we pick the disk whose head is closest. - * - * If there are 2 mirrors in the same 2 devices, performance degrades - * because position is mirror, not device based. - * - * The rdev for the device selected will have nr_pending incremented. - */ -static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors) +static void update_read_sectors(struct r1conf *conf, int disk, + sector_t this_sector, int len) { - const sector_t this_sector = r1_bio->sector; - int sectors; - int best_good_sectors; - int best_disk, best_dist_disk, best_pending_disk; - int has_nonrot_disk; + struct raid1_info *info = &conf->mirrors[disk]; + + atomic_inc(&info->rdev->nr_pending); + if (info->next_seq_sect != this_sector) + info->seq_start = this_sector; + info->next_seq_sect = this_sector + len; +} + +static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio, + int *max_sectors) +{ + sector_t this_sector = r1_bio->sector; + int len = r1_bio->sectors; int disk; - sector_t best_dist; - unsigned int min_pending; - struct md_rdev *rdev; - int choose_first; - int choose_next_idle; - /* - * Check if we can balance. We can balance on the whole - * device if no resync is going on, or below the resync window. - * We take the first readable disk when above the resync window. - */ - retry: - sectors = r1_bio->sectors; - best_disk = -1; - best_dist_disk = -1; - best_dist = MaxSector; - best_pending_disk = -1; - min_pending = UINT_MAX; - best_good_sectors = 0; - has_nonrot_disk = 0; - choose_next_idle = 0; - clear_bit(R1BIO_FailFast, &r1_bio->state); + for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { + struct md_rdev *rdev; + int read_len; - if ((conf->mddev->recovery_cp < this_sector + sectors) || - (mddev_is_clustered(conf->mddev) && - md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector, - this_sector + sectors))) - choose_first = 1; - else - choose_first = 0; + if (r1_bio->bios[disk] == IO_BLOCKED) + continue; + + rdev = conf->mirrors[disk].rdev; + if (!rdev || test_bit(Faulty, &rdev->flags)) + continue; + + /* choose the first disk even if it has some bad blocks. */ + read_len = raid1_check_read_range(rdev, this_sector, &len); + if (read_len > 0) { + update_read_sectors(conf, disk, this_sector, read_len); + *max_sectors = read_len; + return disk; + } + } + + return -1; +} + +static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio, + int *max_sectors) +{ + sector_t this_sector = r1_bio->sector; + int best_disk = -1; + int best_len = 0; + int disk; for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { - sector_t dist; - sector_t first_bad; - int bad_sectors; - unsigned int pending; - bool nonrot; + struct md_rdev *rdev; + int len; + int read_len; + + if (r1_bio->bios[disk] == IO_BLOCKED) + continue; rdev = conf->mirrors[disk].rdev; - if (r1_bio->bios[disk] == IO_BLOCKED - || rdev == NULL - || test_bit(Faulty, &rdev->flags)) + if (!rdev || test_bit(Faulty, &rdev->flags) || + test_bit(WriteMostly, &rdev->flags)) continue; - if (!test_bit(In_sync, &rdev->flags) && - rdev->recovery_offset < this_sector + sectors) + + /* keep track of the disk with the most readable sectors. */ + len = r1_bio->sectors; + read_len = raid1_check_read_range(rdev, this_sector, &len); + if (read_len > best_len) { + best_disk = disk; + best_len = read_len; + } + } + + if (best_disk != -1) { + *max_sectors = best_len; + update_read_sectors(conf, best_disk, this_sector, best_len); + } + + return best_disk; +} + +static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio, + int *max_sectors) +{ + sector_t this_sector = r1_bio->sector; + int bb_disk = -1; + int bb_read_len = 0; + int disk; + + for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { + struct md_rdev *rdev; + int len; + int read_len; + + if (r1_bio->bios[disk] == IO_BLOCKED) continue; - if (test_bit(WriteMostly, &rdev->flags)) { - /* Don't balance among write-mostly, just - * use the first as a last resort */ - if (best_dist_disk < 0) { - if (is_badblock(rdev, this_sector, sectors, - &first_bad, &bad_sectors)) { - if (first_bad <= this_sector) - /* Cannot use this */ - continue; - best_good_sectors = first_bad - this_sector; - } else - best_good_sectors = sectors; - best_dist_disk = disk; - best_pending_disk = disk; - } + + rdev = conf->mirrors[disk].rdev; + if (!rdev || test_bit(Faulty, &rdev->flags) || + !test_bit(WriteMostly, &rdev->flags)) continue; + + /* there are no bad blocks, we can use this disk */ + len = r1_bio->sectors; + read_len = raid1_check_read_range(rdev, this_sector, &len); + if (read_len == r1_bio->sectors) { + update_read_sectors(conf, disk, this_sector, read_len); + return disk; } - /* This is a reasonable device to use. It might - * even be best. + + /* + * there are partial bad blocks, choose the rdev with largest + * read length. */ - if (is_badblock(rdev, this_sector, sectors, - &first_bad, &bad_sectors)) { - if (best_dist < MaxSector) - /* already have a better device */ - continue; - if (first_bad <= this_sector) { - /* cannot read here. If this is the 'primary' - * device, then we must not read beyond - * bad_sectors from another device.. - */ - bad_sectors -= (this_sector - first_bad); - if (choose_first && sectors > bad_sectors) - sectors = bad_sectors; - if (best_good_sectors > sectors) - best_good_sectors = sectors; - - } else { - sector_t good_sectors = first_bad - this_sector; - if (good_sectors > best_good_sectors) { - best_good_sectors = good_sectors; - best_disk = disk; - } - if (choose_first) - break; - } - continue; - } else { - if ((sectors > best_good_sectors) && (best_disk >= 0)) - best_disk = -1; - best_good_sectors = sectors; + if (read_len > bb_read_len) { + bb_disk = disk; + bb_read_len = read_len; } + } + + if (bb_disk != -1) { + *max_sectors = bb_read_len; + update_read_sectors(conf, bb_disk, this_sector, bb_read_len); + } + + return bb_disk; +} + +static bool is_sequential(struct r1conf *conf, int disk, struct r1bio *r1_bio) +{ + /* TODO: address issues with this check and concurrency. */ + return conf->mirrors[disk].next_seq_sect == r1_bio->sector || + conf->mirrors[disk].head_position == r1_bio->sector; +} + +/* + * If buffered sequential IO size exceeds optimal iosize, check if there is idle + * disk. If yes, choose the idle disk. + */ +static bool should_choose_next(struct r1conf *conf, int disk) +{ + struct raid1_info *mirror = &conf->mirrors[disk]; + int opt_iosize; + + if (!test_bit(Nonrot, &mirror->rdev->flags)) + return false; + + opt_iosize = bdev_io_opt(mirror->rdev->bdev) >> 9; + return opt_iosize > 0 && mirror->seq_start != MaxSector && + mirror->next_seq_sect > opt_iosize && + mirror->next_seq_sect - opt_iosize >= mirror->seq_start; +} + +static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio) +{ + if (!rdev || test_bit(Faulty, &rdev->flags)) + return false; + + /* still in recovery */ + if (!test_bit(In_sync, &rdev->flags) && + rdev->recovery_offset < r1_bio->sector + r1_bio->sectors) + return false; + + /* don't read from slow disk unless have to */ + if (test_bit(WriteMostly, &rdev->flags)) + return false; + + /* don't split IO for bad blocks unless have to */ + if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors)) + return false; + + return true; +} + +struct read_balance_ctl { + sector_t closest_dist; + int closest_dist_disk; + int min_pending; + int min_pending_disk; + int sequential_disk; + int readable_disks; +}; + +static int choose_best_rdev(struct r1conf *conf, struct r1bio *r1_bio) +{ + int disk; + struct read_balance_ctl ctl = { + .closest_dist_disk = -1, + .closest_dist = MaxSector, + .min_pending_disk = -1, + .min_pending = UINT_MAX, + .sequential_disk = -1, + }; + + for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { + struct md_rdev *rdev; + sector_t dist; + unsigned int pending; - if (best_disk >= 0) - /* At least two disks to choose from so failfast is OK */ + if (r1_bio->bios[disk] == IO_BLOCKED) + continue; + + rdev = conf->mirrors[disk].rdev; + if (!rdev_readable(rdev, r1_bio)) + continue; + + /* At least two disks to choose from so failfast is OK */ + if (ctl.readable_disks++ == 1) set_bit(R1BIO_FailFast, &r1_bio->state); - nonrot = bdev_nonrot(rdev->bdev); - has_nonrot_disk |= nonrot; pending = atomic_read(&rdev->nr_pending); - dist = abs(this_sector - conf->mirrors[disk].head_position); - if (choose_first) { - best_disk = disk; - break; - } + dist = abs(r1_bio->sector - conf->mirrors[disk].head_position); + /* Don't change to another disk for sequential reads */ - if (conf->mirrors[disk].next_seq_sect == this_sector - || dist == 0) { - int opt_iosize = bdev_io_opt(rdev->bdev) >> 9; - struct raid1_info *mirror = &conf->mirrors[disk]; + if (is_sequential(conf, disk, r1_bio)) { + if (!should_choose_next(conf, disk)) + return disk; - best_disk = disk; /* - * If buffered sequential IO size exceeds optimal - * iosize, check if there is idle disk. If yes, choose - * the idle disk. read_balance could already choose an - * idle disk before noticing it's a sequential IO in - * this disk. This doesn't matter because this disk - * will idle, next time it will be utilized after the - * first disk has IO size exceeds optimal iosize. In - * this way, iosize of the first disk will be optimal - * iosize at least. iosize of the second disk might be - * small, but not a big deal since when the second disk - * starts IO, the first disk is likely still busy. + * Add 'pending' to avoid choosing this disk if + * there is other idle disk. */ - if (nonrot && opt_iosize > 0 && - mirror->seq_start != MaxSector && - mirror->next_seq_sect > opt_iosize && - mirror->next_seq_sect - opt_iosize >= - mirror->seq_start) { - choose_next_idle = 1; - continue; - } - break; + pending++; + /* + * If there is no other idle disk, this disk + * will be chosen. + */ + ctl.sequential_disk = disk; } - if (choose_next_idle) - continue; - - if (min_pending > pending) { - min_pending = pending; - best_pending_disk = disk; + if (ctl.min_pending > pending) { + ctl.min_pending = pending; + ctl.min_pending_disk = disk; } - if (dist < best_dist) { - best_dist = dist; - best_dist_disk = disk; + if (ctl.closest_dist > dist) { + ctl.closest_dist = dist; + ctl.closest_dist_disk = disk; } } /* + * sequential IO size exceeds optimal iosize, however, there is no other + * idle disk, so choose the sequential disk. + */ + if (ctl.sequential_disk != -1 && ctl.min_pending != 0) + return ctl.sequential_disk; + + /* * If all disks are rotational, choose the closest disk. If any disk is * non-rotational, choose the disk with less pending request even the * disk is rotational, which might/might not be optimal for raids with * mixed ratation/non-rotational disks depending on workload. */ - if (best_disk == -1) { - if (has_nonrot_disk || min_pending == 0) - best_disk = best_pending_disk; - else - best_disk = best_dist_disk; - } + if (ctl.min_pending_disk != -1 && + (READ_ONCE(conf->nonrot_disks) || ctl.min_pending == 0)) + return ctl.min_pending_disk; + else + return ctl.closest_dist_disk; +} - if (best_disk >= 0) { - rdev = conf->mirrors[best_disk].rdev; - if (!rdev) - goto retry; - atomic_inc(&rdev->nr_pending); - sectors = best_good_sectors; +/* + * This routine returns the disk from which the requested read should be done. + * + * 1) If resync is in progress, find the first usable disk and use it even if it + * has some bad blocks. + * + * 2) Now that there is no resync, loop through all disks and skipping slow + * disks and disks with bad blocks for now. Only pay attention to key disk + * choice. + * + * 3) If we've made it this far, now look for disks with bad blocks and choose + * the one with most number of sectors. + * + * 4) If we are all the way at the end, we have no choice but to use a disk even + * if it is write mostly. + * + * The rdev for the device selected will have nr_pending incremented. + */ +static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, + int *max_sectors) +{ + int disk; - if (conf->mirrors[best_disk].next_seq_sect != this_sector) - conf->mirrors[best_disk].seq_start = this_sector; + clear_bit(R1BIO_FailFast, &r1_bio->state); + + if (raid1_should_read_first(conf->mddev, r1_bio->sector, + r1_bio->sectors)) + return choose_first_rdev(conf, r1_bio, max_sectors); - conf->mirrors[best_disk].next_seq_sect = this_sector + sectors; + disk = choose_best_rdev(conf, r1_bio); + if (disk >= 0) { + *max_sectors = r1_bio->sectors; + update_read_sectors(conf, disk, r1_bio->sector, + r1_bio->sectors); + return disk; } - *max_sectors = sectors; - return best_disk; + /* + * If we are here it means we didn't find a perfectly good disk so + * now spend a bit more time trying to find one with the most good + * sectors. + */ + disk = choose_bb_rdev(conf, r1_bio, max_sectors); + if (disk >= 0) + return disk; + + return choose_slow_rdev(conf, r1_bio, max_sectors); } static void wake_up_barrier(struct r1conf *conf) @@ -1098,7 +1193,7 @@ static void freeze_array(struct r1conf *conf, int extra) */ spin_lock_irq(&conf->resync_lock); conf->array_frozen = 1; - raid1_log(conf->mddev, "wait freeze"); + mddev_add_trace_msg(conf->mddev, "raid1 wait freeze"); wait_event_lock_irq_cmd( conf->wait_barrier, get_unqueued_pending(conf) == extra, @@ -1287,7 +1382,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, * Reading from a write-mostly device must take care not to * over-take any writes that are 'behind' */ - raid1_log(mddev, "wait behind writes"); + mddev_add_trace_msg(mddev, "raid1 wait behind writes"); wait_event(bitmap->behind_wait, atomic_read(&bitmap->behind_writes) == 0); } @@ -1320,11 +1415,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, test_bit(R1BIO_FailFast, &r1_bio->state)) read_bio->bi_opf |= MD_FAILFAST; read_bio->bi_private = r1_bio; - - if (mddev->gendisk) - trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk), - r1_bio->sector); - + mddev_trace_remap(mddev, read_bio, r1_bio->sector); submit_bio_noacct(read_bio); } @@ -1474,7 +1565,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, bio_wouldblock_error(bio); return; } - raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk); + mddev_add_trace_msg(mddev, "raid1 wait rdev %d blocked", + blocked_rdev->raid_disk); md_wait_for_blocked_rdev(blocked_rdev, mddev); wait_barrier(conf, bio->bi_iter.bi_sector, false); goto retry_write; @@ -1557,10 +1649,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, mbio->bi_private = r1_bio; atomic_inc(&r1_bio->remaining); - - if (mddev->gendisk) - trace_block_bio_remap(mbio, disk_devt(mddev->gendisk), - r1_bio->sector); + mddev_trace_remap(mddev, mbio, r1_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_bdev = (void *)rdev; if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) { @@ -1760,6 +1849,52 @@ static int raid1_spare_active(struct mddev *mddev) return count; } +static bool raid1_add_conf(struct r1conf *conf, struct md_rdev *rdev, int disk, + bool replacement) +{ + struct raid1_info *info = conf->mirrors + disk; + + if (replacement) + info += conf->raid_disks; + + if (info->rdev) + return false; + + if (bdev_nonrot(rdev->bdev)) { + set_bit(Nonrot, &rdev->flags); + WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks + 1); + } + + rdev->raid_disk = disk; + info->head_position = 0; + info->seq_start = MaxSector; + WRITE_ONCE(info->rdev, rdev); + + return true; +} + +static bool raid1_remove_conf(struct r1conf *conf, int disk) +{ + struct raid1_info *info = conf->mirrors + disk; + struct md_rdev *rdev = info->rdev; + + if (!rdev || test_bit(In_sync, &rdev->flags) || + atomic_read(&rdev->nr_pending)) + return false; + + /* Only remove non-faulty devices if recovery is not possible. */ + if (!test_bit(Faulty, &rdev->flags) && + rdev->mddev->recovery_disabled != conf->recovery_disabled && + rdev->mddev->degraded < conf->raid_disks) + return false; + + if (test_and_clear_bit(Nonrot, &rdev->flags)) + WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks - 1); + + WRITE_ONCE(info->rdev, NULL); + return true; +} + static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) { struct r1conf *conf = mddev->private; @@ -1791,19 +1926,16 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) for (mirror = first; mirror <= last; mirror++) { p = conf->mirrors + mirror; if (!p->rdev) { - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); + err = mddev_stack_new_rdev(mddev, rdev); + if (err) + return err; - p->head_position = 0; - rdev->raid_disk = mirror; - err = 0; + raid1_add_conf(conf, rdev, mirror, false); /* As all devices are equivalent, we don't need a full recovery * if this was recently any drive of the array */ if (rdev->saved_raid_disk < 0) conf->fullsync = 1; - WRITE_ONCE(p->rdev, rdev); break; } if (test_bit(WantReplacement, &p->rdev->flags) && @@ -1813,13 +1945,11 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (err && repl_slot >= 0) { /* Add this device as a replacement */ - p = conf->mirrors + repl_slot; clear_bit(In_sync, &rdev->flags); set_bit(Replacement, &rdev->flags); - rdev->raid_disk = repl_slot; + raid1_add_conf(conf, rdev, repl_slot, true); err = 0; conf->fullsync = 1; - WRITE_ONCE(p[conf->raid_disks].rdev, rdev); } print_conf(conf); @@ -1836,27 +1966,20 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) if (unlikely(number >= conf->raid_disks)) goto abort; - if (rdev != p->rdev) - p = conf->mirrors + conf->raid_disks + number; + if (rdev != p->rdev) { + number += conf->raid_disks; + p = conf->mirrors + number; + } print_conf(conf); if (rdev == p->rdev) { - if (test_bit(In_sync, &rdev->flags) || - atomic_read(&rdev->nr_pending)) { + if (!raid1_remove_conf(conf, number)) { err = -EBUSY; goto abort; } - /* Only remove non-faulty devices if recovery - * is not possible. - */ - if (!test_bit(Faulty, &rdev->flags) && - mddev->recovery_disabled != conf->recovery_disabled && - mddev->degraded < conf->raid_disks) { - err = -EBUSY; - goto abort; - } - WRITE_ONCE(p->rdev, NULL); - if (conf->mirrors[conf->raid_disks + number].rdev) { + + if (number < conf->raid_disks && + conf->mirrors[conf->raid_disks + number].rdev) { /* We just removed a device that is being replaced. * Move down the replacement. We drain all IO before * doing this to avoid confusion. @@ -1944,8 +2067,6 @@ static void end_sync_write(struct bio *bio) struct r1bio *r1_bio = get_resync_r1bio(bio); struct mddev *mddev = r1_bio->mddev; struct r1conf *conf = mddev->private; - sector_t first_bad; - int bad_sectors; struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev; if (!uptodate) { @@ -1955,14 +2076,11 @@ static void end_sync_write(struct bio *bio) set_bit(MD_RECOVERY_NEEDED, & mddev->recovery); set_bit(R1BIO_WriteError, &r1_bio->state); - } else if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors, - &first_bad, &bad_sectors) && - !is_badblock(conf->mirrors[r1_bio->read_disk].rdev, - r1_bio->sector, - r1_bio->sectors, - &first_bad, &bad_sectors) - ) + } else if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) && + !rdev_has_badblock(conf->mirrors[r1_bio->read_disk].rdev, + r1_bio->sector, r1_bio->sectors)) { set_bit(R1BIO_MadeGood, &r1_bio->state); + } put_sync_write_buf(r1_bio, uptodate); } @@ -2279,16 +2397,12 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio) s = PAGE_SIZE >> 9; do { - sector_t first_bad; - int bad_sectors; - rdev = conf->mirrors[d].rdev; if (rdev && (test_bit(In_sync, &rdev->flags) || (!test_bit(Faulty, &rdev->flags) && rdev->recovery_offset >= sect + s)) && - is_badblock(rdev, sect, s, - &first_bad, &bad_sectors) == 0) { + rdev_has_badblock(rdev, sect, s) == 0) { atomic_inc(&rdev->nr_pending); if (sync_page_io(rdev, sect, s<<9, conf->tmppage, REQ_OP_READ, false)) @@ -3006,23 +3120,17 @@ static struct r1conf *setup_conf(struct mddev *mddev) err = -EINVAL; spin_lock_init(&conf->device_lock); + conf->raid_disks = mddev->raid_disks; rdev_for_each(rdev, mddev) { int disk_idx = rdev->raid_disk; - if (disk_idx >= mddev->raid_disks - || disk_idx < 0) + + if (disk_idx >= conf->raid_disks || disk_idx < 0) continue; - if (test_bit(Replacement, &rdev->flags)) - disk = conf->mirrors + mddev->raid_disks + disk_idx; - else - disk = conf->mirrors + disk_idx; - if (disk->rdev) + if (!raid1_add_conf(conf, rdev, disk_idx, + test_bit(Replacement, &rdev->flags))) goto abort; - disk->rdev = rdev; - disk->head_position = 0; - disk->seq_start = MaxSector; } - conf->raid_disks = mddev->raid_disks; conf->mddev = mddev; INIT_LIST_HEAD(&conf->retry_list); INIT_LIST_HEAD(&conf->bio_end_io_list); @@ -3086,12 +3194,21 @@ static struct r1conf *setup_conf(struct mddev *mddev) return ERR_PTR(err); } +static int raid1_set_limits(struct mddev *mddev) +{ + struct queue_limits lim; + + blk_set_stacking_limits(&lim); + lim.max_write_zeroes_sectors = 0; + mddev_stack_rdev_limits(mddev, &lim); + return queue_limits_set(mddev->gendisk->queue, &lim); +} + static void raid1_free(struct mddev *mddev, void *priv); static int raid1_run(struct mddev *mddev) { struct r1conf *conf; int i; - struct md_rdev *rdev; int ret; if (mddev->level != 1) { @@ -3118,14 +3235,10 @@ static int raid1_run(struct mddev *mddev) if (IS_ERR(conf)) return PTR_ERR(conf); - if (mddev->queue) - blk_queue_max_write_zeroes_sectors(mddev->queue, 0); - - rdev_for_each(rdev, mddev) { - if (!mddev->gendisk) - continue; - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); + if (!mddev_is_dm(mddev)) { + ret = raid1_set_limits(mddev); + if (ret) + goto abort; } mddev->degraded = 0; diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index 14d4211a123a..5300cbaa58a4 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -71,6 +71,7 @@ struct r1conf { * allow for replacements. */ int raid_disks; + int nonrot_disks; spinlock_t device_lock; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index a5f8419e2df1..a4556d2e46bf 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -76,9 +76,6 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio); static void end_reshape_write(struct bio *bio); static void end_reshape(struct r10conf *conf); -#define raid10_log(md, fmt, args...) \ - do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0) - #include "raid1-10.c" #define NULL_CMD @@ -518,11 +515,7 @@ static void raid10_end_write_request(struct bio *bio) * The 'master' represents the composite IO operation to * user-side. So if something waits for IO, then it will * wait for the 'master' bio. - */ - sector_t first_bad; - int bad_sectors; - - /* + * * Do not set R10BIO_Uptodate if the current device is * rebuilding or Faulty. This is because we cannot use * such device for properly reading the data back (we could @@ -535,10 +528,9 @@ static void raid10_end_write_request(struct bio *bio) set_bit(R10BIO_Uptodate, &r10_bio->state); /* Maybe we can clear some bad blocks. */ - if (is_badblock(rdev, - r10_bio->devs[slot].addr, - r10_bio->sectors, - &first_bad, &bad_sectors) && !discard_error) { + if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr, + r10_bio->sectors) && + !discard_error) { bio_put(bio); if (repl) r10_bio->devs[slot].repl_bio = IO_MADE_GOOD; @@ -753,17 +745,8 @@ static struct md_rdev *read_balance(struct r10conf *conf, best_good_sectors = 0; do_balance = 1; clear_bit(R10BIO_FailFast, &r10_bio->state); - /* - * Check if we can balance. We can balance on the whole - * device if no resync is going on (recovery is ok), or below - * the resync window. We take the first readable disk when - * above the resync window. - */ - if ((conf->mddev->recovery_cp < MaxSector - && (this_sector + sectors >= conf->next_resync)) || - (mddev_is_clustered(conf->mddev) && - md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector, - this_sector + sectors))) + + if (raid1_should_read_first(conf->mddev, this_sector, sectors)) do_balance = 0; for (slot = 0; slot < conf->copies ; slot++) { @@ -1033,7 +1016,7 @@ static bool wait_barrier(struct r10conf *conf, bool nowait) ret = false; } else { conf->nr_waiting++; - raid10_log(conf->mddev, "wait barrier"); + mddev_add_trace_msg(conf->mddev, "raid10 wait barrier"); wait_event_barrier(conf, stop_waiting_barrier(conf)); conf->nr_waiting--; } @@ -1152,7 +1135,7 @@ static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf, bio_wouldblock_error(bio); return false; } - raid10_log(conf->mddev, "wait reshape"); + mddev_add_trace_msg(conf->mddev, "raid10 wait reshape"); wait_event(conf->wait_barrier, conf->reshape_progress <= bio->bi_iter.bi_sector || conf->reshape_progress >= bio->bi_iter.bi_sector + @@ -1249,10 +1232,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, test_bit(R10BIO_FailFast, &r10_bio->state)) read_bio->bi_opf |= MD_FAILFAST; read_bio->bi_private = r10_bio; - - if (mddev->gendisk) - trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk), - r10_bio->sector); + mddev_trace_remap(mddev, read_bio, r10_bio->sector); submit_bio_noacct(read_bio); return; } @@ -1288,10 +1268,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, && enough(conf, devnum)) mbio->bi_opf |= MD_FAILFAST; mbio->bi_private = r10_bio; - - if (conf->mddev->gendisk) - trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk), - r10_bio->sector); + mddev_trace_remap(mddev, mbio, r10_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_bdev = (void *)rdev; @@ -1330,10 +1307,7 @@ retry_wait: } if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) { - sector_t first_bad; sector_t dev_sector = r10_bio->devs[i].addr; - int bad_sectors; - int is_bad; /* * Discard request doesn't care the write result @@ -1342,9 +1316,8 @@ retry_wait: if (!r10_bio->sectors) continue; - is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors, - &first_bad, &bad_sectors); - if (is_bad < 0) { + if (rdev_has_badblock(rdev, dev_sector, + r10_bio->sectors) < 0) { /* * Mustn't write here until the bad block * is acknowledged @@ -1360,8 +1333,9 @@ retry_wait: if (unlikely(blocked_rdev)) { /* Have to wait for this device to get unblocked, then retry */ allow_barrier(conf); - raid10_log(conf->mddev, "%s wait rdev %d blocked", - __func__, blocked_rdev->raid_disk); + mddev_add_trace_msg(conf->mddev, + "raid10 %s wait rdev %d blocked", + __func__, blocked_rdev->raid_disk); md_wait_for_blocked_rdev(blocked_rdev, mddev); wait_barrier(conf, false); goto retry_wait; @@ -1416,7 +1390,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, bio_wouldblock_error(bio); return; } - raid10_log(conf->mddev, "wait reshape metadata"); + mddev_add_trace_msg(conf->mddev, + "raid10 wait reshape metadata"); wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); @@ -2131,10 +2106,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) continue; } - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - + err = mddev_stack_new_rdev(mddev, rdev); + if (err) + return err; p->head_position = 0; p->recovery_disabled = mddev->recovery_disabled - 1; rdev->raid_disk = mirror; @@ -2150,10 +2124,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) clear_bit(In_sync, &rdev->flags); set_bit(Replacement, &rdev->flags); rdev->raid_disk = repl_slot; - err = 0; - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); + err = mddev_stack_new_rdev(mddev, rdev); + if (err) + return err; conf->fullsync = 1; WRITE_ONCE(p->replacement, rdev); } @@ -2290,8 +2263,6 @@ static void end_sync_write(struct bio *bio) struct mddev *mddev = r10_bio->mddev; struct r10conf *conf = mddev->private; int d; - sector_t first_bad; - int bad_sectors; int slot; int repl; struct md_rdev *rdev = NULL; @@ -2312,11 +2283,10 @@ static void end_sync_write(struct bio *bio) &rdev->mddev->recovery); set_bit(R10BIO_WriteError, &r10_bio->state); } - } else if (is_badblock(rdev, - r10_bio->devs[slot].addr, - r10_bio->sectors, - &first_bad, &bad_sectors)) + } else if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr, + r10_bio->sectors)) { set_bit(R10BIO_MadeGood, &r10_bio->state); + } rdev_dec_pending(rdev, mddev); @@ -2597,11 +2567,8 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector, int sectors, struct page *page, enum req_op op) { - sector_t first_bad; - int bad_sectors; - - if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors) - && (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags))) + if (rdev_has_badblock(rdev, sector, sectors) && + (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags))) return -1; if (sync_page_io(rdev, sector, sectors << 9, page, op, false)) /* success */ @@ -2658,16 +2625,14 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 s = PAGE_SIZE >> 9; do { - sector_t first_bad; - int bad_sectors; - d = r10_bio->devs[sl].devnum; rdev = conf->mirrors[d].rdev; if (rdev && test_bit(In_sync, &rdev->flags) && !test_bit(Faulty, &rdev->flags) && - is_badblock(rdev, r10_bio->devs[sl].addr + sect, s, - &first_bad, &bad_sectors) == 0) { + rdev_has_badblock(rdev, + r10_bio->devs[sl].addr + sect, + s) == 0) { atomic_inc(&rdev->nr_pending); success = sync_page_io(rdev, r10_bio->devs[sl].addr + @@ -4002,14 +3967,26 @@ static struct r10conf *setup_conf(struct mddev *mddev) return ERR_PTR(err); } -static void raid10_set_io_opt(struct r10conf *conf) +static unsigned int raid10_nr_stripes(struct r10conf *conf) { - int raid_disks = conf->geo.raid_disks; + unsigned int raid_disks = conf->geo.raid_disks; - if (!(conf->geo.raid_disks % conf->geo.near_copies)) - raid_disks /= conf->geo.near_copies; - blk_queue_io_opt(conf->mddev->queue, (conf->mddev->chunk_sectors << 9) * - raid_disks); + if (conf->geo.raid_disks % conf->geo.near_copies) + return raid_disks; + return raid_disks / conf->geo.near_copies; +} + +static int raid10_set_queue_limits(struct mddev *mddev) +{ + struct r10conf *conf = mddev->private; + struct queue_limits lim; + + blk_set_stacking_limits(&lim); + lim.max_write_zeroes_sectors = 0; + lim.io_min = mddev->chunk_sectors << 9; + lim.io_opt = lim.io_min * raid10_nr_stripes(conf); + mddev_stack_rdev_limits(mddev, &lim); + return queue_limits_set(mddev->gendisk->queue, &lim); } static int raid10_run(struct mddev *mddev) @@ -4021,6 +3998,7 @@ static int raid10_run(struct mddev *mddev) sector_t size; sector_t min_offset_diff = 0; int first = 1; + int ret = -EIO; if (mddev->private == NULL) { conf = setup_conf(mddev); @@ -4047,12 +4025,6 @@ static int raid10_run(struct mddev *mddev) } } - if (mddev->queue) { - blk_queue_max_write_zeroes_sectors(mddev->queue, 0); - blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); - raid10_set_io_opt(conf); - } - rdev_for_each(rdev, mddev) { long long diff; @@ -4081,14 +4053,16 @@ static int raid10_run(struct mddev *mddev) if (first || diff < min_offset_diff) min_offset_diff = diff; - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - disk->head_position = 0; first = 0; } + if (!mddev_is_dm(conf->mddev)) { + ret = raid10_set_queue_limits(mddev); + if (ret) + goto out_free_conf; + } + /* need to check that every block has at least one working mirror */ if (!enough(conf, -1)) { pr_err("md/raid10:%s: not enough operational mirrors.\n", @@ -4185,7 +4159,7 @@ out_free_conf: raid10_free_conf(conf); mddev->private = NULL; out: - return -EIO; + return ret; } static void raid10_free(struct mddev *mddev, void *priv) @@ -4954,8 +4928,7 @@ static void end_reshape(struct r10conf *conf) conf->reshape_safe = MaxSector; spin_unlock_irq(&conf->device_lock); - if (conf->mddev->queue) - raid10_set_io_opt(conf); + mddev_update_io_opt(conf->mddev, raid10_nr_stripes(conf)); conf->fullsync = 0; } diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index da4ba736c4f0..a70cbec12ed0 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1393,7 +1393,8 @@ int ppl_init_log(struct r5conf *conf) ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid)); ppl_conf->block_size = 512; } else { - ppl_conf->block_size = queue_logical_block_size(mddev->queue); + ppl_conf->block_size = + queue_logical_block_size(mddev->gendisk->queue); } for (i = 0; i < ppl_conf->count; i++) { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 6a7a32f7fb91..d874abfc1836 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -36,6 +36,7 @@ */ #include <linux/blkdev.h> +#include <linux/delay.h> #include <linux/kthread.h> #include <linux/raid/pq.h> #include <linux/async_tx.h> @@ -760,6 +761,7 @@ enum stripe_result { STRIPE_RETRY, STRIPE_SCHEDULE_AND_RETRY, STRIPE_FAIL, + STRIPE_WAIT_RESHAPE, }; struct stripe_request_ctx { @@ -1210,10 +1212,8 @@ again: */ while (op_is_write(op) && rdev && test_bit(WriteErrorSeen, &rdev->flags)) { - sector_t first_bad; - int bad_sectors; - int bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), - &first_bad, &bad_sectors); + int bad = rdev_has_badblock(rdev, sh->sector, + RAID5_STRIPE_SECTORS(conf)); if (!bad) break; @@ -1295,10 +1295,7 @@ again: if (rrdev) set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags); - if (conf->mddev->gendisk) - trace_block_bio_remap(bi, - disk_devt(conf->mddev->gendisk), - sh->dev[i].sector); + mddev_trace_remap(conf->mddev, bi, sh->dev[i].sector); if (should_defer && op_is_write(op)) bio_list_add(&pending_bios, bi); else @@ -1342,10 +1339,7 @@ again: */ if (op == REQ_OP_DISCARD) rbi->bi_vcnt = 0; - if (conf->mddev->gendisk) - trace_block_bio_remap(rbi, - disk_devt(conf->mddev->gendisk), - sh->dev[i].sector); + mddev_trace_remap(conf->mddev, rbi, sh->dev[i].sector); if (should_defer && op_is_write(op)) bio_list_add(&pending_bios, rbi); else @@ -2412,7 +2406,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp) atomic_inc(&conf->active_stripes); raid5_release_stripe(sh); - conf->max_nr_stripes++; + WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes + 1); return 1; } @@ -2422,12 +2416,12 @@ static int grow_stripes(struct r5conf *conf, int num) size_t namelen = sizeof(conf->cache_name[0]); int devs = max(conf->raid_disks, conf->previous_raid_disks); - if (conf->mddev->gendisk) + if (mddev_is_dm(conf->mddev)) snprintf(conf->cache_name[0], namelen, - "raid%d-%s", conf->level, mdname(conf->mddev)); + "raid%d-%p", conf->level, conf->mddev); else snprintf(conf->cache_name[0], namelen, - "raid%d-%p", conf->level, conf->mddev); + "raid%d-%s", conf->level, mdname(conf->mddev)); snprintf(conf->cache_name[1], namelen, "%.27s-alt", conf->cache_name[0]); conf->active_name = 0; @@ -2707,7 +2701,7 @@ static int drop_one_stripe(struct r5conf *conf) shrink_buffers(sh); free_stripe(conf->slab_cache, sh); atomic_dec(&conf->active_stripes); - conf->max_nr_stripes--; + WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes - 1); return 1; } @@ -2855,8 +2849,6 @@ static void raid5_end_write_request(struct bio *bi) struct r5conf *conf = sh->raid_conf; int disks = sh->disks, i; struct md_rdev *rdev; - sector_t first_bad; - int bad_sectors; int replacement = 0; for (i = 0 ; i < disks; i++) { @@ -2888,9 +2880,8 @@ static void raid5_end_write_request(struct bio *bi) if (replacement) { if (bi->bi_status) md_error(conf->mddev, rdev); - else if (is_badblock(rdev, sh->sector, - RAID5_STRIPE_SECTORS(conf), - &first_bad, &bad_sectors)) + else if (rdev_has_badblock(rdev, sh->sector, + RAID5_STRIPE_SECTORS(conf))) set_bit(R5_MadeGoodRepl, &sh->dev[i].flags); } else { if (bi->bi_status) { @@ -2900,9 +2891,8 @@ static void raid5_end_write_request(struct bio *bi) if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); - } else if (is_badblock(rdev, sh->sector, - RAID5_STRIPE_SECTORS(conf), - &first_bad, &bad_sectors)) { + } else if (rdev_has_badblock(rdev, sh->sector, + RAID5_STRIPE_SECTORS(conf))) { set_bit(R5_MadeGood, &sh->dev[i].flags); if (test_bit(R5_ReadError, &sh->dev[i].flags)) /* That was a successful write so make @@ -4205,10 +4195,9 @@ static int handle_stripe_dirtying(struct r5conf *conf, set_bit(STRIPE_HANDLE, &sh->state); if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_PREFER_RMW)) && rmw > 0) { /* prefer read-modify-write, but need to get some data */ - if (conf->mddev->queue) - blk_add_trace_msg(conf->mddev->queue, - "raid5 rmw %llu %d", - (unsigned long long)sh->sector, rmw); + mddev_add_trace_msg(conf->mddev, "raid5 rmw %llu %d", + sh->sector, rmw); + for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (test_bit(R5_InJournal, &dev->flags) && @@ -4285,10 +4274,11 @@ static int handle_stripe_dirtying(struct r5conf *conf, set_bit(STRIPE_DELAYED, &sh->state); } } - if (rcw && conf->mddev->queue) - blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d", - (unsigned long long)sh->sector, - rcw, qread, test_bit(STRIPE_DELAYED, &sh->state)); + if (rcw && !mddev_is_dm(conf->mddev)) + blk_add_trace_msg(conf->mddev->gendisk->queue, + "raid5 rcw %llu %d %d %d", + (unsigned long long)sh->sector, rcw, qread, + test_bit(STRIPE_DELAYED, &sh->state)); } if (rcw > disks && rmw > disks && @@ -4674,8 +4664,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) /* Now to look around and see what can be done */ for (i=disks; i--; ) { struct md_rdev *rdev; - sector_t first_bad; - int bad_sectors; int is_bad = 0; dev = &sh->dev[i]; @@ -4719,8 +4707,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) rdev = conf->disks[i].replacement; if (rdev && !test_bit(Faulty, &rdev->flags) && rdev->recovery_offset >= sh->sector + RAID5_STRIPE_SECTORS(conf) && - !is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), - &first_bad, &bad_sectors)) + !rdev_has_badblock(rdev, sh->sector, + RAID5_STRIPE_SECTORS(conf))) set_bit(R5_ReadRepl, &dev->flags); else { if (rdev && !test_bit(Faulty, &rdev->flags)) @@ -4733,8 +4721,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) if (rdev && test_bit(Faulty, &rdev->flags)) rdev = NULL; if (rdev) { - is_bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), - &first_bad, &bad_sectors); + is_bad = rdev_has_badblock(rdev, sh->sector, + RAID5_STRIPE_SECTORS(conf)); if (s->blocked_rdev == NULL && (test_bit(Blocked, &rdev->flags) || is_bad < 0)) { @@ -5463,8 +5451,8 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) struct r5conf *conf = mddev->private; struct bio *align_bio; struct md_rdev *rdev; - sector_t sector, end_sector, first_bad; - int bad_sectors, dd_idx; + sector_t sector, end_sector; + int dd_idx; bool did_inc; if (!in_chunk_boundary(mddev, raid_bio)) { @@ -5493,8 +5481,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) atomic_inc(&rdev->nr_pending); - if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad, - &bad_sectors)) { + if (rdev_has_badblock(rdev, sector, bio_sectors(raid_bio))) { rdev_dec_pending(rdev, mddev); return 0; } @@ -5530,9 +5517,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) spin_unlock_irq(&conf->device_lock); } - if (mddev->gendisk) - trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk), - raid_bio->bi_iter.bi_sector); + mddev_trace_remap(mddev, align_bio, raid_bio->bi_iter.bi_sector); submit_bio_noacct(align_bio); return 1; } @@ -5701,8 +5686,8 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule) } release_inactive_stripe_list(conf, cb->temp_inactive_list, NR_STRIPE_HASH_LOCKS); - if (mddev->queue) - trace_block_unplug(mddev->queue, cnt, !from_schedule); + if (!mddev_is_dm(mddev)) + trace_block_unplug(mddev->gendisk->queue, cnt, !from_schedule); kfree(cb); } @@ -5946,7 +5931,8 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, if (ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) { spin_unlock_irq(&conf->device_lock); - return STRIPE_SCHEDULE_AND_RETRY; + ret = STRIPE_SCHEDULE_AND_RETRY; + goto out; } } spin_unlock_irq(&conf->device_lock); @@ -6025,6 +6011,12 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, out_release: raid5_release_stripe(sh); +out: + if (ret == STRIPE_SCHEDULE_AND_RETRY && reshape_interrupted(mddev)) { + bi->bi_status = BLK_STS_RESOURCE; + ret = STRIPE_WAIT_RESHAPE; + pr_err_ratelimited("dm-raid456: io across reshape position while reshape can't make progress"); + } return ret; } @@ -6146,7 +6138,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) while (1) { res = make_stripe_request(mddev, conf, &ctx, logical_sector, bi); - if (res == STRIPE_FAIL) + if (res == STRIPE_FAIL || res == STRIPE_WAIT_RESHAPE) break; if (res == STRIPE_RETRY) @@ -6184,6 +6176,11 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) if (rw == WRITE) md_write_end(mddev); + if (res == STRIPE_WAIT_RESHAPE) { + md_free_cloned_bio(bi); + return false; + } + bio_endio(bi); return true; } @@ -6773,7 +6770,18 @@ static void raid5d(struct md_thread *thread) spin_unlock_irq(&conf->device_lock); md_check_recovery(mddev); spin_lock_irq(&conf->device_lock); + + /* + * Waiting on MD_SB_CHANGE_PENDING below may deadlock + * seeing md_check_recovery() is needed to clear + * the flag when using mdmon. + */ + continue; } + + wait_event_lock_irq(mddev->sb_wait, + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags), + conf->device_lock); } pr_debug("%d stripes handled\n", handled); @@ -6820,7 +6828,7 @@ raid5_set_cache_size(struct mddev *mddev, int size) if (size <= 16 || size > 32768) return -EINVAL; - conf->min_nr_stripes = size; + WRITE_ONCE(conf->min_nr_stripes, size); mutex_lock(&conf->cache_size_mutex); while (size < conf->max_nr_stripes && drop_one_stripe(conf)) @@ -6832,7 +6840,7 @@ raid5_set_cache_size(struct mddev *mddev, int size) mutex_lock(&conf->cache_size_mutex); while (size > conf->max_nr_stripes) if (!grow_one_stripe(conf, GFP_KERNEL)) { - conf->min_nr_stripes = conf->max_nr_stripes; + WRITE_ONCE(conf->min_nr_stripes, conf->max_nr_stripes); result = -ENOMEM; break; } @@ -6967,10 +6975,8 @@ raid5_store_stripe_size(struct mddev *mddev, const char *page, size_t len) pr_debug("md/raid: change stripe_size from %lu to %lu\n", conf->stripe_size, new); - if (mddev->sync_thread || - test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || - mddev->reshape_position != MaxSector || - mddev->sysfs_active) { + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || + mddev->reshape_position != MaxSector || mddev->sysfs_active) { err = -EBUSY; goto out_unlock; } @@ -7084,7 +7090,7 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len) if (!conf) err = -ENODEV; else if (new != conf->skip_copy) { - struct request_queue *q = mddev->queue; + struct request_queue *q = mddev->gendisk->queue; conf->skip_copy = new; if (new) @@ -7390,11 +7396,13 @@ static unsigned long raid5_cache_count(struct shrinker *shrink, struct shrink_control *sc) { struct r5conf *conf = shrink->private_data; + int max_stripes = READ_ONCE(conf->max_nr_stripes); + int min_stripes = READ_ONCE(conf->min_nr_stripes); - if (conf->max_nr_stripes < conf->min_nr_stripes) + if (max_stripes < min_stripes) /* unlikely, but not impossible */ return 0; - return conf->max_nr_stripes - conf->min_nr_stripes; + return max_stripes - min_stripes; } static struct r5conf *setup_conf(struct mddev *mddev) @@ -7684,10 +7692,65 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded return 0; } -static void raid5_set_io_opt(struct r5conf *conf) +static int raid5_set_limits(struct mddev *mddev) { - blk_queue_io_opt(conf->mddev->queue, (conf->chunk_sectors << 9) * - (conf->raid_disks - conf->max_degraded)); + struct r5conf *conf = mddev->private; + struct queue_limits lim; + int data_disks, stripe; + struct md_rdev *rdev; + + /* + * The read-ahead size must cover two whole stripes, which is + * 2 * (datadisks) * chunksize where 'n' is the number of raid devices. + */ + data_disks = conf->previous_raid_disks - conf->max_degraded; + + /* + * We can only discard a whole stripe. It doesn't make sense to + * discard data disk but write parity disk + */ + stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9)); + + blk_set_stacking_limits(&lim); + lim.io_min = mddev->chunk_sectors << 9; + lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded); + lim.raid_partial_stripes_expensive = 1; + lim.discard_granularity = stripe; + lim.max_write_zeroes_sectors = 0; + mddev_stack_rdev_limits(mddev, &lim); + rdev_for_each(rdev, mddev) + queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset, + mddev->gendisk->disk_name); + + /* + * Zeroing is required for discard, otherwise data could be lost. + * + * Consider a scenario: discard a stripe (the stripe could be + * inconsistent if discard_zeroes_data is 0); write one disk of the + * stripe (the stripe could be inconsistent again depending on which + * disks are used to calculate parity); the disk is broken; The stripe + * data of this disk is lost. + * + * We only allow DISCARD if the sysadmin has confirmed that only safe + * devices are in use by setting a module parameter. A better idea + * might be to turn DISCARD into WRITE_ZEROES requests, as that is + * required to be safe. + */ + if (!devices_handle_discard_safely || + lim.max_discard_sectors < (stripe >> 9) || + lim.discard_granularity < stripe) + lim.max_hw_discard_sectors = 0; + + /* + * Requests require having a bitmap for each stripe. + * Limit the max sectors based on this. + */ + lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf); + + /* No restrictions on the number of segments in the request */ + lim.max_segments = USHRT_MAX; + + return queue_limits_set(mddev->gendisk->queue, &lim); } static int raid5_run(struct mddev *mddev) @@ -7700,6 +7763,7 @@ static int raid5_run(struct mddev *mddev) int i; long long min_offset_diff = 0; int first = 1; + int ret = -EIO; if (mddev->recovery_cp != MaxSector) pr_notice("md/raid:%s: not clean -- starting background reconstruction\n", @@ -7948,66 +8012,10 @@ static int raid5_run(struct mddev *mddev) mdname(mddev)); md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); - if (mddev->queue) { - int chunk_size; - /* read-ahead size must cover two whole stripes, which - * is 2 * (datadisks) * chunksize where 'n' is the - * number of raid devices - */ - int data_disks = conf->previous_raid_disks - conf->max_degraded; - int stripe = data_disks * - ((mddev->chunk_sectors << 9) / PAGE_SIZE); - - chunk_size = mddev->chunk_sectors << 9; - blk_queue_io_min(mddev->queue, chunk_size); - raid5_set_io_opt(conf); - mddev->queue->limits.raid_partial_stripes_expensive = 1; - /* - * We can only discard a whole stripe. It doesn't make sense to - * discard data disk but write parity disk - */ - stripe = stripe * PAGE_SIZE; - stripe = roundup_pow_of_two(stripe); - mddev->queue->limits.discard_granularity = stripe; - - blk_queue_max_write_zeroes_sectors(mddev->queue, 0); - - rdev_for_each(rdev, mddev) { - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->new_data_offset << 9); - } - - /* - * zeroing is required, otherwise data - * could be lost. Consider a scenario: discard a stripe - * (the stripe could be inconsistent if - * discard_zeroes_data is 0); write one disk of the - * stripe (the stripe could be inconsistent again - * depending on which disks are used to calculate - * parity); the disk is broken; The stripe data of this - * disk is lost. - * - * We only allow DISCARD if the sysadmin has confirmed that - * only safe devices are in use by setting a module parameter. - * A better idea might be to turn DISCARD into WRITE_ZEROES - * requests, as that is required to be safe. - */ - if (!devices_handle_discard_safely || - mddev->queue->limits.max_discard_sectors < (stripe >> 9) || - mddev->queue->limits.discard_granularity < stripe) - blk_queue_max_discard_sectors(mddev->queue, 0); - - /* - * Requests require having a bitmap for each stripe. - * Limit the max sectors based on this. - */ - blk_queue_max_hw_sectors(mddev->queue, - RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf)); - - /* No restrictions on the number of segments in the request */ - blk_queue_max_segments(mddev->queue, USHRT_MAX); + if (!mddev_is_dm(mddev)) { + ret = raid5_set_limits(mddev); + if (ret) + goto abort; } if (log_init(conf, journal_dev, raid5_has_ppl(conf))) @@ -8020,7 +8028,7 @@ abort: free_conf(conf); mddev->private = NULL; pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev)); - return -EIO; + return ret; } static void raid5_free(struct mddev *mddev, void *priv) @@ -8531,8 +8539,8 @@ static void end_reshape(struct r5conf *conf) spin_unlock_irq(&conf->device_lock); wake_up(&conf->wait_for_overlap); - if (conf->mddev->queue) - raid5_set_io_opt(conf); + mddev_update_io_opt(conf->mddev, + conf->raid_disks - conf->max_degraded); } } @@ -8909,6 +8917,18 @@ static int raid5_start(struct mddev *mddev) return r5l_start(conf->log); } +/* + * This is only used for dm-raid456, caller already frozen sync_thread, hence + * if rehsape is still in progress, io that is waiting for reshape can never be + * done now, hence wake up and handle those IO. + */ +static void raid5_prepare_suspend(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + + wake_up(&conf->wait_for_overlap); +} + static struct md_personality raid6_personality = { .name = "raid6", @@ -8932,6 +8952,7 @@ static struct md_personality raid6_personality = .quiesce = raid5_quiesce, .takeover = raid6_takeover, .change_consistency_policy = raid5_change_consistency_policy, + .prepare_suspend = raid5_prepare_suspend, }; static struct md_personality raid5_personality = { @@ -8956,6 +8977,7 @@ static struct md_personality raid5_personality = .quiesce = raid5_quiesce, .takeover = raid5_takeover, .change_consistency_policy = raid5_change_consistency_policy, + .prepare_suspend = raid5_prepare_suspend, }; static struct md_personality raid4_personality = @@ -8981,6 +9003,7 @@ static struct md_personality raid4_personality = .quiesce = raid5_quiesce, .takeover = raid4_takeover, .change_consistency_policy = raid5_change_consistency_policy, + .prepare_suspend = raid5_prepare_suspend, }; static int __init raid5_init(void) diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c index 04115cd92433..47a314a4eb6f 100644 --- a/drivers/memstick/core/ms_block.c +++ b/drivers/memstick/core/ms_block.c @@ -2078,6 +2078,12 @@ static const struct blk_mq_ops msb_mq_ops = { static int msb_init_disk(struct memstick_dev *card) { struct msb_data *msb = memstick_get_drvdata(card); + struct queue_limits lim = { + .logical_block_size = msb->page_size, + .max_hw_sectors = MS_BLOCK_MAX_PAGES, + .max_segments = MS_BLOCK_MAX_SEGS, + .max_segment_size = MS_BLOCK_MAX_PAGES * msb->page_size, + }; int rc; unsigned long capacity; @@ -2093,19 +2099,13 @@ static int msb_init_disk(struct memstick_dev *card) if (rc) goto out_release_id; - msb->disk = blk_mq_alloc_disk(&msb->tag_set, card); + msb->disk = blk_mq_alloc_disk(&msb->tag_set, &lim, card); if (IS_ERR(msb->disk)) { rc = PTR_ERR(msb->disk); goto out_free_tag_set; } msb->queue = msb->disk->queue; - blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES); - blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS); - blk_queue_max_segment_size(msb->queue, - MS_BLOCK_MAX_PAGES * msb->page_size); - blk_queue_logical_block_size(msb->queue, msb->page_size); - sprintf(msb->disk->disk_name, "msblk%d", msb->disk_id); msb->disk->fops = &msb_bdops; msb->disk->private_data = msb; diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index 5a69ed33999b..49accfdc89d6 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -1103,6 +1103,12 @@ static const struct blk_mq_ops mspro_mq_ops = { static int mspro_block_init_disk(struct memstick_dev *card) { struct mspro_block_data *msb = memstick_get_drvdata(card); + struct queue_limits lim = { + .logical_block_size = msb->page_size, + .max_hw_sectors = MSPRO_BLOCK_MAX_PAGES, + .max_segments = MSPRO_BLOCK_MAX_SEGS, + .max_segment_size = MSPRO_BLOCK_MAX_PAGES * msb->page_size, + }; struct mspro_devinfo *dev_info = NULL; struct mspro_sys_info *sys_info = NULL; struct mspro_sys_attr *s_attr = NULL; @@ -1138,18 +1144,13 @@ static int mspro_block_init_disk(struct memstick_dev *card) if (rc) goto out_release_id; - msb->disk = blk_mq_alloc_disk(&msb->tag_set, card); + msb->disk = blk_mq_alloc_disk(&msb->tag_set, &lim, card); if (IS_ERR(msb->disk)) { rc = PTR_ERR(msb->disk); goto out_free_tag_set; } msb->queue = msb->disk->queue; - blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES); - blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS); - blk_queue_max_segment_size(msb->queue, - MSPRO_BLOCK_MAX_PAGES * msb->page_size); - msb->disk->major = major; msb->disk->first_minor = disk_id << MSPRO_BLOCK_PART_SHIFT; msb->disk->minors = 1 << MSPRO_BLOCK_PART_SHIFT; @@ -1158,8 +1159,6 @@ static int mspro_block_init_disk(struct memstick_dev *card) sprintf(msb->disk->disk_name, "mspblk%d", disk_id); - blk_queue_logical_block_size(msb->queue, msb->page_size); - capacity = be16_to_cpu(sys_info->user_block_count); capacity *= be16_to_cpu(sys_info->block_size); capacity *= msb->page_size >> 9; diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 03319a1fa97f..dbd26c3b245b 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -263,7 +263,6 @@ struct fastrpc_channel_ctx { int domain_id; int sesscount; int vmcount; - u64 perms; struct qcom_scm_vmperm vmperms[FASTRPC_MAX_VMIDS]; struct rpmsg_device *rpdev; struct fastrpc_session_ctx session[FASTRPC_MAX_SESSIONS]; @@ -1279,9 +1278,11 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl, /* Map if we have any heap VMIDs associated with this ADSP Static Process. */ if (fl->cctx->vmcount) { + u64 src_perms = BIT(QCOM_SCM_VMID_HLOS); + err = qcom_scm_assign_mem(fl->cctx->remote_heap->phys, (u64)fl->cctx->remote_heap->size, - &fl->cctx->perms, + &src_perms, fl->cctx->vmperms, fl->cctx->vmcount); if (err) { dev_err(fl->sctx->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d", @@ -1915,8 +1916,10 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp) /* Add memory to static PD pool, protection thru hypervisor */ if (req.flags == ADSP_MMAP_REMOTE_HEAP_ADDR && fl->cctx->vmcount) { + u64 src_perms = BIT(QCOM_SCM_VMID_HLOS); + err = qcom_scm_assign_mem(buf->phys, (u64)buf->size, - &fl->cctx->perms, fl->cctx->vmperms, fl->cctx->vmcount); + &src_perms, fl->cctx->vmperms, fl->cctx->vmcount); if (err) { dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d", buf->phys, buf->size, err); @@ -2290,7 +2293,6 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev) if (vmcount) { data->vmcount = vmcount; - data->perms = BIT(QCOM_SCM_VMID_HLOS); for (i = 0; i < data->vmcount; i++) { data->vmperms[i].vmid = vmids[i]; data->vmperms[i].perm = QCOM_SCM_PERM_RWX; diff --git a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c index c6eb27d46cb0..15119584473c 100644 --- a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c +++ b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c @@ -198,8 +198,14 @@ static int lis3lv02d_i2c_suspend(struct device *dev) struct i2c_client *client = to_i2c_client(dev); struct lis3lv02d *lis3 = i2c_get_clientdata(client); - if (!lis3->pdata || !lis3->pdata->wakeup_flags) + /* Turn on for wakeup if turned off by runtime suspend */ + if (lis3->pdata && lis3->pdata->wakeup_flags) { + if (pm_runtime_suspended(dev)) + lis3lv02d_poweron(lis3); + /* For non wakeup turn off if not already turned off by runtime suspend */ + } else if (!pm_runtime_suspended(dev)) lis3lv02d_poweroff(lis3); + return 0; } @@ -208,13 +214,12 @@ static int lis3lv02d_i2c_resume(struct device *dev) struct i2c_client *client = to_i2c_client(dev); struct lis3lv02d *lis3 = i2c_get_clientdata(client); - /* - * pm_runtime documentation says that devices should always - * be powered on at resume. Pm_runtime turns them off after system - * wide resume is complete. - */ - if (!lis3->pdata || !lis3->pdata->wakeup_flags || - pm_runtime_suspended(dev)) + /* Turn back off if turned on for wakeup and runtime suspended*/ + if (lis3->pdata && lis3->pdata->wakeup_flags) { + if (pm_runtime_suspended(dev)) + lis3lv02d_poweroff(lis3); + /* For non wakeup turn back on if not runtime suspended */ + } else if (!pm_runtime_suspended(dev)) lis3lv02d_poweron(lis3); return 0; diff --git a/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c b/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c index be52b113aea9..89364bdbb129 100644 --- a/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c +++ b/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c @@ -96,7 +96,8 @@ static const struct component_master_ops mei_component_master_ops = { * * The function checks if the device is pci device and * Intel VGA adapter, the subcomponent is SW Proxy - * and the parent of MEI PCI and the parent of VGA are the same PCH device. + * and the VGA is on the bus 0 reserved for built-in devices + * to reject discrete GFX. * * @dev: master device * @subcomponent: subcomponent to match (I915_COMPONENT_SWPROXY) @@ -123,7 +124,8 @@ static int mei_gsc_proxy_component_match(struct device *dev, int subcomponent, if (subcomponent != I915_COMPONENT_GSC_PROXY) return 0; - return component_compare_dev(dev->parent, ((struct device *)data)->parent); + /* Only built-in GFX */ + return (pdev->bus->number == 0); } static int mei_gsc_proxy_probe(struct mei_cl_device *cldev, @@ -146,7 +148,7 @@ static int mei_gsc_proxy_probe(struct mei_cl_device *cldev, } component_match_add_typed(&cldev->dev, &master_match, - mei_gsc_proxy_component_match, cldev->dev.parent); + mei_gsc_proxy_component_match, NULL); if (IS_ERR_OR_NULL(master_match)) { ret = -ENOMEM; goto err_exit; diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 961e5d53a27a..aac36750d2c5 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -112,6 +112,8 @@ #define MEI_DEV_ID_RPL_S 0x7A68 /* Raptor Lake Point S */ #define MEI_DEV_ID_MTL_M 0x7E70 /* Meteor Lake Point M */ +#define MEI_DEV_ID_ARL_S 0x7F68 /* Arrow Lake Point S */ +#define MEI_DEV_ID_ARL_H 0x7770 /* Arrow Lake Point H */ /* * MEI HW Section diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 676d566f38dd..8cf636c54032 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -119,6 +119,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_H, MEI_ME_PCH15_CFG)}, /* required last entry */ {0, } diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c index 6f4a4be6ccb5..55f7db490d3b 100644 --- a/drivers/misc/mei/vsc-tp.c +++ b/drivers/misc/mei/vsc-tp.c @@ -535,6 +535,7 @@ static const struct acpi_device_id vsc_tp_acpi_ids[] = { { "INTC1009" }, /* Raptor Lake */ { "INTC1058" }, /* Tiger Lake */ { "INTC1094" }, /* Alder Lake */ + { "INTC10D0" }, /* Meteor Lake */ {} }; MODULE_DEVICE_TABLE(acpi, vsc_tp_acpi_ids); diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index a0a2412f62a7..2ae60d208cdf 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -174,8 +174,8 @@ static struct scatterlist *mmc_alloc_sg(unsigned short sg_len, gfp_t gfp) return sg; } -static void mmc_queue_setup_discard(struct request_queue *q, - struct mmc_card *card) +static void mmc_queue_setup_discard(struct mmc_card *card, + struct queue_limits *lim) { unsigned max_discard; @@ -183,15 +183,17 @@ static void mmc_queue_setup_discard(struct request_queue *q, if (!max_discard) return; - blk_queue_max_discard_sectors(q, max_discard); - q->limits.discard_granularity = card->pref_erase << 9; - /* granularity must not be greater than max. discard */ - if (card->pref_erase > max_discard) - q->limits.discard_granularity = SECTOR_SIZE; + lim->max_hw_discard_sectors = max_discard; if (mmc_can_secure_erase_trim(card)) - blk_queue_max_secure_erase_sectors(q, max_discard); + lim->max_secure_erase_sectors = max_discard; if (mmc_can_trim(card) && card->erased_byte == 0) - blk_queue_max_write_zeroes_sectors(q, max_discard); + lim->max_write_zeroes_sectors = max_discard; + + /* granularity must not be greater than max. discard */ + if (card->pref_erase > max_discard) + lim->discard_granularity = SECTOR_SIZE; + else + lim->discard_granularity = card->pref_erase << 9; } static unsigned short mmc_get_max_segments(struct mmc_host *host) @@ -341,40 +343,53 @@ static const struct blk_mq_ops mmc_mq_ops = { .timeout = mmc_mq_timed_out, }; -static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card) +static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq, + struct mmc_card *card) { struct mmc_host *host = card->host; - unsigned block_size = 512; + struct queue_limits lim = { }; + struct gendisk *disk; - blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue); if (mmc_can_erase(card)) - mmc_queue_setup_discard(mq->queue, card); + mmc_queue_setup_discard(card, &lim); if (!mmc_dev(host)->dma_mask || !*mmc_dev(host)->dma_mask) - blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_HIGH); - blk_queue_max_hw_sectors(mq->queue, - min(host->max_blk_count, host->max_req_size / 512)); - if (host->can_dma_map_merge) - WARN(!blk_queue_can_use_dma_map_merging(mq->queue, - mmc_dev(host)), - "merging was advertised but not possible"); - blk_queue_max_segments(mq->queue, mmc_get_max_segments(host)); - - if (mmc_card_mmc(card) && card->ext_csd.data_sector_size) { - block_size = card->ext_csd.data_sector_size; - WARN_ON(block_size != 512 && block_size != 4096); - } + lim.bounce = BLK_BOUNCE_HIGH; + + lim.max_hw_sectors = min(host->max_blk_count, host->max_req_size / 512); + + if (mmc_card_mmc(card) && card->ext_csd.data_sector_size) + lim.logical_block_size = card->ext_csd.data_sector_size; + else + lim.logical_block_size = 512; + + WARN_ON_ONCE(lim.logical_block_size != 512 && + lim.logical_block_size != 4096); - blk_queue_logical_block_size(mq->queue, block_size); /* - * After blk_queue_can_use_dma_map_merging() was called with succeed, - * since it calls blk_queue_virt_boundary(), the mmc should not call - * both blk_queue_max_segment_size(). + * Setting a virt_boundary implicity sets a max_segment_size, so try + * to set the hardware one here. */ - if (!host->can_dma_map_merge) - blk_queue_max_segment_size(mq->queue, - round_down(host->max_seg_size, block_size)); + if (host->can_dma_map_merge) { + lim.virt_boundary_mask = dma_get_merge_boundary(mmc_dev(host)); + lim.max_segments = MMC_DMA_MAP_MERGE_SEGMENTS; + } else { + lim.max_segment_size = + round_down(host->max_seg_size, lim.logical_block_size); + lim.max_segments = host->max_segs; + } + + disk = blk_mq_alloc_disk(&mq->tag_set, &lim, mq); + if (IS_ERR(disk)) + return disk; + mq->queue = disk->queue; + + if (mmc_host_is_spi(host) && host->use_spi_crc) + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue); + blk_queue_rq_timeout(mq->queue, 60 * HZ); + + blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue); + blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue); dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue)); @@ -386,6 +401,7 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card) init_waitqueue_head(&mq->wait); mmc_crypto_setup_queue(mq->queue, host); + return disk; } static inline bool mmc_merge_capable(struct mmc_host *host) @@ -447,18 +463,9 @@ struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card) return ERR_PTR(ret); - disk = blk_mq_alloc_disk(&mq->tag_set, mq); - if (IS_ERR(disk)) { + disk = mmc_alloc_disk(mq, card); + if (IS_ERR(disk)) blk_mq_free_tag_set(&mq->tag_set); - return disk; - } - mq->queue = disk->queue; - - if (mmc_host_is_spi(host) && host->use_spi_crc) - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue); - blk_queue_rq_timeout(mq->queue, 60 * HZ); - - mmc_setup_queue(mq, card); return disk; } diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index aa44a23ec045..97a00ec9a4d4 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -37,7 +37,7 @@ /* Info for the block device */ struct block2mtd_dev { struct list_head list; - struct bdev_handle *bdev_handle; + struct file *bdev_file; struct mtd_info mtd; struct mutex write_mutex; }; @@ -55,8 +55,7 @@ static struct page *page_read(struct address_space *mapping, pgoff_t index) /* erase a specified part of the device */ static int _block2mtd_erase(struct block2mtd_dev *dev, loff_t to, size_t len) { - struct address_space *mapping = - dev->bdev_handle->bdev->bd_inode->i_mapping; + struct address_space *mapping = dev->bdev_file->f_mapping; struct page *page; pgoff_t index = to >> PAGE_SHIFT; // page index int pages = len >> PAGE_SHIFT; @@ -106,8 +105,7 @@ static int block2mtd_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct block2mtd_dev *dev = mtd->priv; - struct address_space *mapping = - dev->bdev_handle->bdev->bd_inode->i_mapping; + struct address_space *mapping = dev->bdev_file->f_mapping; struct page *page; pgoff_t index = from >> PAGE_SHIFT; int offset = from & (PAGE_SIZE-1); @@ -142,8 +140,7 @@ static int _block2mtd_write(struct block2mtd_dev *dev, const u_char *buf, loff_t to, size_t len, size_t *retlen) { struct page *page; - struct address_space *mapping = - dev->bdev_handle->bdev->bd_inode->i_mapping; + struct address_space *mapping = dev->bdev_file->f_mapping; pgoff_t index = to >> PAGE_SHIFT; // page index int offset = to & ~PAGE_MASK; // page offset int cpylen; @@ -198,7 +195,7 @@ static int block2mtd_write(struct mtd_info *mtd, loff_t to, size_t len, static void block2mtd_sync(struct mtd_info *mtd) { struct block2mtd_dev *dev = mtd->priv; - sync_blockdev(dev->bdev_handle->bdev); + sync_blockdev(file_bdev(dev->bdev_file)); return; } @@ -210,10 +207,9 @@ static void block2mtd_free_device(struct block2mtd_dev *dev) kfree(dev->mtd.name); - if (dev->bdev_handle) { - invalidate_mapping_pages( - dev->bdev_handle->bdev->bd_inode->i_mapping, 0, -1); - bdev_release(dev->bdev_handle); + if (dev->bdev_file) { + invalidate_mapping_pages(dev->bdev_file->f_mapping, 0, -1); + fput(dev->bdev_file); } kfree(dev); @@ -223,10 +219,10 @@ static void block2mtd_free_device(struct block2mtd_dev *dev) * This function is marked __ref because it calls the __init marked * early_lookup_bdev when called from the early boot code. */ -static struct bdev_handle __ref *mdtblock_early_get_bdev(const char *devname, +static struct file __ref *mdtblock_early_get_bdev(const char *devname, blk_mode_t mode, int timeout, struct block2mtd_dev *dev) { - struct bdev_handle *bdev_handle = ERR_PTR(-ENODEV); + struct file *bdev_file = ERR_PTR(-ENODEV); #ifndef MODULE int i; @@ -234,7 +230,7 @@ static struct bdev_handle __ref *mdtblock_early_get_bdev(const char *devname, * We can't use early_lookup_bdev from a running system. */ if (system_state >= SYSTEM_RUNNING) - return bdev_handle; + return bdev_file; /* * We might not have the root device mounted at this point. @@ -253,20 +249,20 @@ static struct bdev_handle __ref *mdtblock_early_get_bdev(const char *devname, wait_for_device_probe(); if (!early_lookup_bdev(devname, &devt)) { - bdev_handle = bdev_open_by_dev(devt, mode, dev, NULL); - if (!IS_ERR(bdev_handle)) + bdev_file = bdev_file_open_by_dev(devt, mode, dev, NULL); + if (!IS_ERR(bdev_file)) break; } } #endif - return bdev_handle; + return bdev_file; } static struct block2mtd_dev *add_device(char *devname, int erase_size, char *label, int timeout) { const blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE; - struct bdev_handle *bdev_handle; + struct file *bdev_file; struct block_device *bdev; struct block2mtd_dev *dev; char *name; @@ -279,16 +275,16 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size, return NULL; /* Get a handle on the device */ - bdev_handle = bdev_open_by_path(devname, mode, dev, NULL); - if (IS_ERR(bdev_handle)) - bdev_handle = mdtblock_early_get_bdev(devname, mode, timeout, + bdev_file = bdev_file_open_by_path(devname, mode, dev, NULL); + if (IS_ERR(bdev_file)) + bdev_file = mdtblock_early_get_bdev(devname, mode, timeout, dev); - if (IS_ERR(bdev_handle)) { + if (IS_ERR(bdev_file)) { pr_err("error: cannot open device %s\n", devname); goto err_free_block2mtd; } - dev->bdev_handle = bdev_handle; - bdev = bdev_handle->bdev; + dev->bdev_file = bdev_file; + bdev = file_bdev(bdev_file); if (MAJOR(bdev->bd_dev) == MTD_BLOCK_MAJOR) { pr_err("attempting to use an MTD device as a block device\n"); diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index f0526dcc2162..3caa0717d46c 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -277,6 +277,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) { struct mtd_blktrans_ops *tr = new->tr; struct mtd_blktrans_dev *d; + struct queue_limits lim = { }; int last_devnum = -1; struct gendisk *gd; int ret; @@ -331,9 +332,13 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); if (ret) goto out_kfree_tag_set; + + lim.logical_block_size = tr->blksize; + if (tr->discard) + lim.max_hw_discard_sectors = UINT_MAX; /* Create gendisk */ - gd = blk_mq_alloc_disk(new->tag_set, new); + gd = blk_mq_alloc_disk(new->tag_set, &lim, new); if (IS_ERR(gd)) { ret = PTR_ERR(gd); goto out_free_tag_set; @@ -371,14 +376,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) if (tr->flush) blk_queue_write_cache(new->rq, true, false); - blk_queue_logical_block_size(new->rq, tr->blksize); - blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq); - if (tr->discard) - blk_queue_max_discard_sectors(new->rq, UINT_MAX); - gd->queue = new->rq; if (new->readonly) diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 654bd7372cd8..5c8fdcc088a0 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -348,6 +348,9 @@ static int calc_disk_capacity(struct ubi_volume_info *vi, u64 *disk_capacity) int ubiblock_create(struct ubi_volume_info *vi) { + struct queue_limits lim = { + .max_segments = UBI_MAX_SG_COUNT, + }; struct ubiblock *dev; struct gendisk *gd; u64 disk_capacity; @@ -393,7 +396,7 @@ int ubiblock_create(struct ubi_volume_info *vi) /* Initialize the gendisk of this ubiblock device */ - gd = blk_mq_alloc_disk(&dev->tag_set, dev); + gd = blk_mq_alloc_disk(&dev->tag_set, &lim, dev); if (IS_ERR(gd)) { ret = PTR_ERR(gd); goto out_free_tags; @@ -416,7 +419,6 @@ int ubiblock_create(struct ubi_volume_info *vi) dev->gd = gd; dev->rq = gd->queue; - blk_queue_max_segments(dev->rq, UBI_MAX_SG_COUNT); list_add_tail(&dev->list, &ubiblock_devices); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a11748b8d69b..cd0683bcca03 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1811,7 +1811,7 @@ void bond_xdp_set_features(struct net_device *bond_dev) ASSERT_RTNL(); - if (!bond_xdp_check(bond)) { + if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) { xdp_clear_features_flag(bond_dev); return; } diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 61b71bcfe396..c3da97abce20 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -49,9 +49,9 @@ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data) mutex_lock(&dev->alu_mutex); ctrl_addr = IND_ACC_TABLE(table) | addr; - ret = ksz_write8(dev, regs[REG_IND_BYTE], data); + ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); if (!ret) - ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); + ret = ksz_write8(dev, regs[REG_IND_BYTE], data); mutex_unlock(&dev->alu_mutex); diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c index 11c23a7f3172..fd1a5149c003 100644 --- a/drivers/net/ethernet/amd/pds_core/auxbus.c +++ b/drivers/net/ethernet/amd/pds_core/auxbus.c @@ -160,23 +160,19 @@ static struct pds_auxiliary_dev *pdsc_auxbus_dev_register(struct pdsc *cf, if (err < 0) { dev_warn(cf->dev, "auxiliary_device_init of %s failed: %pe\n", name, ERR_PTR(err)); - goto err_out; + kfree(padev); + return ERR_PTR(err); } err = auxiliary_device_add(aux_dev); if (err) { dev_warn(cf->dev, "auxiliary_device_add of %s failed: %pe\n", name, ERR_PTR(err)); - goto err_out_uninit; + auxiliary_device_uninit(aux_dev); + return ERR_PTR(err); } return padev; - -err_out_uninit: - auxiliary_device_uninit(aux_dev); -err_out: - kfree(padev); - return ERR_PTR(err); } int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf) diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index a2788fd5f8bb..19e450a5bd31 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -2559,7 +2559,7 @@ void e1000_copy_rx_addrs_to_phy_ich8lan(struct e1000_hw *hw) hw->phy.ops.write_reg_page(hw, BM_RAR_H(i), (u16)(mac_reg & 0xFFFF)); hw->phy.ops.write_reg_page(hw, BM_RAR_CTRL(i), - FIELD_GET(E1000_RAH_AV, mac_reg)); + (u16)((mac_reg & E1000_RAH_AV) >> 16)); } e1000_disable_phy_wakeup_reg_access_bm(hw, &phy_reg); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 54eb55464e31..89a3401d20ab 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13560,9 +13560,9 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) return err; i40e_queue_pair_disable_irq(vsi, queue_pair); + i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); - i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index af4269330581..ce1f11b8ad65 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -567,8 +567,7 @@ static inline bool i40e_is_fw_ver_lt(struct i40e_hw *hw, u16 maj, u16 min) **/ static inline bool i40e_is_fw_ver_eq(struct i40e_hw *hw, u16 maj, u16 min) { - return (hw->aq.fw_maj_ver > maj || - (hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min)); + return (hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min); } #endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index adfa1f2a80a6..bd9b1fed74ab 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -1597,7 +1597,7 @@ static void ice_dpll_deinit_rclk_pin(struct ice_pf *pf) } if (WARN_ON_ONCE(!vsi || !vsi->netdev)) return; - netdev_dpll_pin_clear(vsi->netdev); + dpll_netdev_pin_clear(vsi->netdev); dpll_pin_put(rclk->pin); } @@ -1641,7 +1641,7 @@ ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin, } if (WARN_ON((!vsi || !vsi->netdev))) return -EINVAL; - netdev_dpll_pin_set(vsi->netdev, pf->dplls.rclk.pin); + dpll_netdev_pin_set(vsi->netdev, pf->dplls.rclk.pin); return 0; @@ -2120,6 +2120,7 @@ void ice_dpll_init(struct ice_pf *pf) struct ice_dplls *d = &pf->dplls; int err = 0; + mutex_init(&d->lock); err = ice_dpll_init_info(pf, cgu); if (err) goto err_exit; @@ -2132,7 +2133,6 @@ void ice_dpll_init(struct ice_pf *pf) err = ice_dpll_init_pins(pf, cgu); if (err) goto deinit_pps; - mutex_init(&d->lock); if (cgu) { err = ice_dpll_init_worker(pf); if (err) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 097bf8fd6bf0..fc23dbe302b4 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -3192,7 +3192,7 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi) } } - tx_ring_stats = vsi_stat->rx_ring_stats; + tx_ring_stats = vsi_stat->tx_ring_stats; vsi_stat->tx_ring_stats = krealloc_array(vsi_stat->tx_ring_stats, req_txq, sizeof(*vsi_stat->tx_ring_stats), diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 59c7e37f175f..df6a68ab747e 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -8013,6 +8013,8 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, pf_sw = pf->first_sw; /* find the attribute in the netlink message */ br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; nla_for_each_nested(attr, br_spec, rem) { __u16 mode; diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index a94a1c48c3de..b0f78c2f2790 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1068,6 +1068,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) struct ice_pf *pf = pci_get_drvdata(pdev); u16 prev_msix, prev_queues, queues; bool needs_rebuild = false; + struct ice_vsi *vsi; struct ice_vf *vf; int id; @@ -1102,6 +1103,10 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) if (!vf) return -ENOENT; + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return -ENOENT; + prev_msix = vf->num_msix; prev_queues = vf->num_vf_qs; @@ -1122,7 +1127,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) if (vf->first_vector_idx < 0) goto unroll; - if (ice_vf_reconfig_vsi(vf)) { + if (ice_vf_reconfig_vsi(vf) || ice_vf_init_host_cfg(vf, vsi)) { /* Try to rebuild with previous values */ needs_rebuild = true; goto unroll; @@ -1148,8 +1153,10 @@ unroll: if (vf->first_vector_idx < 0) return -EINVAL; - if (needs_rebuild) + if (needs_rebuild) { ice_vf_reconfig_vsi(vf); + ice_vf_init_host_cfg(vf, vsi); + } ice_ena_vf_mappings(vf); ice_put_vf(vf); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index c925813ec9ca..6f2328a049bf 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -440,7 +440,6 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vf->driver_caps = *(u32 *)msg; else vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | - VIRTCHNL_VF_OFFLOAD_RSS_REG | VIRTCHNL_VF_OFFLOAD_VLAN; vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; @@ -453,14 +452,8 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vf_cap_flags |= ice_vc_get_vlan_caps(hw, vf, vsi, vf->driver_caps); - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; - } else { - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; - else - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; - } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index 5e19d48a05b4..d796dbd2a440 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -13,8 +13,6 @@ * - opcodes needed by VF when caps are activated * * Caps that don't use new opcodes (no opcodes should be allowed): - * - VIRTCHNL_VF_OFFLOAD_RSS_AQ - * - VIRTCHNL_VF_OFFLOAD_RSS_REG * - VIRTCHNL_VF_OFFLOAD_WB_ON_ITR * - VIRTCHNL_VF_OFFLOAD_CRC * - VIRTCHNL_VF_OFFLOAD_RX_POLLING diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 8b81a1677045..2eecd0f39aa6 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -179,6 +179,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) return -EBUSY; usleep_range(1000, 2000); } + + ice_qvec_dis_irq(vsi, rx_ring, q_vector); + ice_qvec_toggle_napi(vsi, q_vector, false); + netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); ice_fill_txq_meta(vsi, tx_ring, &txq_meta); @@ -195,13 +199,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } - ice_qvec_dis_irq(vsi, rx_ring, q_vector); - err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; - ice_qvec_toggle_napi(vsi, q_vector, false); ice_qp_clean_rings(vsi, q_idx); ice_qp_reset_stats(vsi, q_idx); @@ -259,11 +260,11 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) return err; - clear_bit(ICE_CFG_BUSY, vsi->state); ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + clear_bit(ICE_CFG_BUSY, vsi->state); return 0; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index d0cdd63b3d5b..390977a76de2 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -2087,8 +2087,10 @@ int idpf_send_disable_queues_msg(struct idpf_vport *vport) set_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags); /* schedule the napi to receive all the marker packets */ + local_bh_disable(); for (i = 0; i < vport->num_q_vectors; i++) napi_schedule(&vport->q_vectors[i].napi); + local_bh_enable(); return idpf_wait_for_marker_event(vport); } diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index ba8d3fe186ae..81c21a893ede 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6487,7 +6487,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, int cpu = smp_processor_id(); struct netdev_queue *nq; struct igc_ring *ring; - int i, drops; + int i, nxmit; if (unlikely(!netif_carrier_ok(dev))) return -ENETDOWN; @@ -6503,16 +6503,15 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, /* Avoid transmit queue timeout since we share it with the slow path */ txq_trans_cond_update(nq); - drops = 0; + nxmit = 0; for (i = 0; i < num_frames; i++) { int err; struct xdp_frame *xdpf = frames[i]; err = igc_xdp_init_tx_descriptor(ring, xdpf); - if (err) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err) + break; + nxmit++; } if (flags & XDP_XMIT_FLUSH) @@ -6520,7 +6519,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, __netif_tx_unlock(nq); - return num_frames - drops; + return nxmit; } static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index bd541527c8c7..99876b765b08 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2939,8 +2939,8 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter) static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, u64 qmask) { - u32 mask; struct ixgbe_hw *hw = &adapter->hw; + u32 mask; switch (hw->mac.type) { case ixgbe_mac_82598EB: @@ -10525,6 +10525,44 @@ static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring) } /** + * ixgbe_irq_disable_single - Disable single IRQ vector + * @adapter: adapter structure + * @ring: ring index + **/ +static void ixgbe_irq_disable_single(struct ixgbe_adapter *adapter, u32 ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 qmask = BIT_ULL(ring); + u32 mask; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + mask = qmask & IXGBE_EIMC_RTX_QUEUE; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + mask = (qmask & 0xFFFFFFFF); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); + mask = (qmask >> 32); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); + break; + default: + break; + } + IXGBE_WRITE_FLUSH(&adapter->hw); + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + synchronize_irq(adapter->msix_entries[ring].vector); + else + synchronize_irq(adapter->pdev->irq); +} + +/** * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings * @adapter: adapter structure * @ring: ring index @@ -10540,6 +10578,11 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; + ixgbe_irq_disable_single(adapter, ring); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + ixgbe_disable_txr(adapter, tx_ring); if (xdp_ring) ixgbe_disable_txr(adapter, xdp_ring); @@ -10548,9 +10591,6 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) if (xdp_ring) synchronize_rcu(); - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_disable(&rx_ring->q_vector->napi); - ixgbe_clean_tx_ring(tx_ring); if (xdp_ring) ixgbe_clean_tx_ring(xdp_ring); @@ -10578,9 +10618,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_enable(&rx_ring->q_vector->napi); - ixgbe_configure_tx_ring(adapter, tx_ring); if (xdp_ring) ixgbe_configure_tx_ring(adapter, xdp_ring); @@ -10589,6 +10626,11 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); if (xdp_ring) clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); + ixgbe_irq_enable_queues(adapter, BIT_ULL(ring)); + IXGBE_WRITE_FLUSH(&adapter->hw); } /** diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 3e064234f6fe..98d4306929f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -157,6 +157,12 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, return -EOPNOTSUPP; } + if (action == DEVLINK_RELOAD_ACTION_FW_ACTIVATE && + !dev->priv.fw_reset) { + NL_SET_ERR_MSG_MOD(extack, "FW activate is unsupported for this function"); + return -EOPNOTSUPP; + } + if (mlx5_core_is_pf(dev) && pci_num_vf(pdev)) NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c index 928bf24d4b12..d74a5aaf4268 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c @@ -261,7 +261,7 @@ static void mlx5_dpll_netdev_dpll_pin_set(struct mlx5_dpll *mdpll, { if (mdpll->tracking_netdev) return; - netdev_dpll_pin_set(netdev, mdpll->dpll_pin); + dpll_netdev_pin_set(netdev, mdpll->dpll_pin); mdpll->tracking_netdev = netdev; } @@ -269,7 +269,7 @@ static void mlx5_dpll_netdev_dpll_pin_clear(struct mlx5_dpll *mdpll) { if (!mdpll->tracking_netdev) return; - netdev_dpll_pin_clear(mdpll->tracking_netdev); + dpll_netdev_pin_clear(mdpll->tracking_netdev); mdpll->tracking_netdev = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 078f56a3cbb2..ca05b3252a1b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -42,9 +42,9 @@ mlx5e_ptp_port_ts_cqe_list_add(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metad WARN_ON_ONCE(tracker->inuse); tracker->inuse = true; - spin_lock(&list->tracker_list_lock); + spin_lock_bh(&list->tracker_list_lock); list_add_tail(&tracker->entry, &list->tracker_list_head); - spin_unlock(&list->tracker_list_lock); + spin_unlock_bh(&list->tracker_list_lock); } static void @@ -54,9 +54,9 @@ mlx5e_ptp_port_ts_cqe_list_remove(struct mlx5e_ptp_port_ts_cqe_list *list, u8 me WARN_ON_ONCE(!tracker->inuse); tracker->inuse = false; - spin_lock(&list->tracker_list_lock); + spin_lock_bh(&list->tracker_list_lock); list_del(&tracker->entry); - spin_unlock(&list->tracker_list_lock); + spin_unlock_bh(&list->tracker_list_lock); } void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata) @@ -155,7 +155,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map; struct mlx5e_ptp_port_ts_cqe_tracker *pos, *n; - spin_lock(&cqe_list->tracker_list_lock); + spin_lock_bh(&cqe_list->tracker_list_lock); list_for_each_entry_safe(pos, n, &cqe_list->tracker_list_head, entry) { struct sk_buff *skb = mlx5e_ptp_metadata_map_lookup(metadata_map, pos->metadata_id); @@ -170,7 +170,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, pos->inuse = false; list_del(&pos->entry); } - spin_unlock(&cqe_list->tracker_list_lock); + spin_unlock_bh(&cqe_list->tracker_list_lock); } #define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 86bf007fd05b..b500cc2c9689 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -37,7 +37,7 @@ mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ignore_flow_level, table_type)) { if (priv->mdev->coredev_type == MLX5_COREDEV_PF) - mlx5_core_warn(priv->mdev, "firmware level support is missing\n"); + mlx5_core_dbg(priv->mdev, "firmware flow level support is missing\n"); err = -EOPNOTSUPP; goto err_check; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index d4ebd8743114..b2cabd6ab86c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -310,9 +310,9 @@ static void mlx5e_macsec_destroy_object(struct mlx5_core_dev *mdev, u32 macsec_o mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); } -static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, - struct mlx5e_macsec_sa *sa, - bool is_tx, struct net_device *netdev, u32 fs_id) +static void mlx5e_macsec_cleanup_sa_fs(struct mlx5e_macsec *macsec, + struct mlx5e_macsec_sa *sa, bool is_tx, + struct net_device *netdev, u32 fs_id) { int action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : MLX5_ACCEL_MACSEC_ACTION_DECRYPT; @@ -322,20 +322,49 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action, netdev, fs_id); - mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id); sa->macsec_rule = NULL; } +static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, + struct mlx5e_macsec_sa *sa, bool is_tx, + struct net_device *netdev, u32 fs_id) +{ + mlx5e_macsec_cleanup_sa_fs(macsec, sa, is_tx, netdev, fs_id); + mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id); +} + +static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx, + struct mlx5e_macsec_sa *sa, bool encrypt, + bool is_tx, u32 *fs_id) +{ + struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); + struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs; + struct mlx5_macsec_rule_attrs rule_attrs; + union mlx5_macsec_rule *macsec_rule; + + rule_attrs.macsec_obj_id = sa->macsec_obj_id; + rule_attrs.sci = sa->sci; + rule_attrs.assoc_num = sa->assoc_num; + rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : + MLX5_ACCEL_MACSEC_ACTION_DECRYPT; + + macsec_rule = mlx5_macsec_fs_add_rule(macsec_fs, ctx, &rule_attrs, fs_id); + if (!macsec_rule) + return -ENOMEM; + + sa->macsec_rule = macsec_rule; + + return 0; +} + static int mlx5e_macsec_init_sa(struct macsec_context *ctx, struct mlx5e_macsec_sa *sa, bool encrypt, bool is_tx, u32 *fs_id) { struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); struct mlx5e_macsec *macsec = priv->macsec; - struct mlx5_macsec_rule_attrs rule_attrs; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_macsec_obj_attrs obj_attrs; - union mlx5_macsec_rule *macsec_rule; int err; obj_attrs.next_pn = sa->next_pn; @@ -357,20 +386,12 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, if (err) return err; - rule_attrs.macsec_obj_id = sa->macsec_obj_id; - rule_attrs.sci = sa->sci; - rule_attrs.assoc_num = sa->assoc_num; - rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : - MLX5_ACCEL_MACSEC_ACTION_DECRYPT; - - macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, fs_id); - if (!macsec_rule) { - err = -ENOMEM; - goto destroy_macsec_object; + if (sa->active) { + err = mlx5e_macsec_init_sa_fs(ctx, sa, encrypt, is_tx, fs_id); + if (err) + goto destroy_macsec_object; } - sa->macsec_rule = macsec_rule; - return 0; destroy_macsec_object: @@ -526,9 +547,7 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx) goto destroy_sa; macsec_device->tx_sa[assoc_num] = tx_sa; - if (!secy->operational || - assoc_num != tx_sc->encoding_sa || - !tx_sa->active) + if (!secy->operational) goto out; err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); @@ -595,7 +614,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) goto out; if (ctx_tx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); + err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL); if (err) goto out; } else { @@ -604,7 +623,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) goto out; } - mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0); + mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0); } out: mutex_unlock(&macsec->lock); @@ -1030,8 +1049,9 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx) goto out; } - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, - rx_sc->sc_xarray_element->fs_id); + if (rx_sa->active) + mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, + rx_sc->sc_xarray_element->fs_id); mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id); kfree(rx_sa); rx_sc->rx_sa[assoc_num] = NULL; @@ -1112,8 +1132,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, if (!rx_sa || !rx_sa->macsec_rule) continue; - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, - rx_sc->sc_xarray_element->fs_id); + mlx5e_macsec_cleanup_sa_fs(macsec, rx_sa, false, ctx->secy->netdev, + rx_sc->sc_xarray_element->fs_id); } } @@ -1124,8 +1144,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, continue; if (rx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false, - &rx_sc->sc_xarray_element->fs_id); + err = mlx5e_macsec_init_sa_fs(ctx, rx_sa, true, false, + &rx_sc->sc_xarray_element->fs_id); if (err) goto out; } @@ -1178,7 +1198,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx) if (!tx_sa) continue; - mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0); + mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0); } for (i = 0; i < MACSEC_NUM_AN; ++i) { @@ -1187,7 +1207,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx) continue; if (tx_sa->assoc_num == tx_sc->encoding_sa && tx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); + err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL); if (err) goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 5c166d9d2dca..2fa076b23fbe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -401,6 +401,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, mlx5e_skb_cb_hwtstamp_init(skb); mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb, metadata_index); + /* ensure skb is put on metadata_map before tracking the index */ + wmb(); mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); if (!netif_tx_queue_stopped(sq->txq) && mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 190f10aba170..5a0047bdcb51 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -152,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) xa_for_each(&esw->offloads.vport_reps, i, rep) { rpriv = rep->rep_data[REP_ETH].priv; - if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems)) + if (!rpriv || !rpriv->netdev) continue; rhashtable_walk_enter(&rpriv->tc_ht, &iter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b0455134c98e..baaae628b0a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -535,21 +535,26 @@ esw_src_port_rewrite_supported(struct mlx5_eswitch *esw) } static bool -esw_dests_to_vf_pf_vports(struct mlx5_flow_destination *dests, int max_dest) +esw_dests_to_int_external(struct mlx5_flow_destination *dests, int max_dest) { - bool vf_dest = false, pf_dest = false; + bool internal_dest = false, external_dest = false; int i; for (i = 0; i < max_dest; i++) { - if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT) + if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT && + dests[i].type != MLX5_FLOW_DESTINATION_TYPE_UPLINK) continue; - if (dests[i].vport.num == MLX5_VPORT_UPLINK) - pf_dest = true; + /* Uplink dest is external, but considered as internal + * if there is reformat because firmware uses LB+hairpin to support it. + */ + if (dests[i].vport.num == MLX5_VPORT_UPLINK && + !(dests[i].vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID)) + external_dest = true; else - vf_dest = true; + internal_dest = true; - if (vf_dest && pf_dest) + if (internal_dest && external_dest) return true; } @@ -695,9 +700,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, /* Header rewrite with combined wire+loopback in FDB is not allowed */ if ((flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) && - esw_dests_to_vf_pf_vports(dest, i)) { + esw_dests_to_int_external(dest, i)) { esw_warn(esw->dev, - "FDB: Header rewrite with forwarding to both PF and VF is not allowed\n"); + "FDB: Header rewrite with forwarding to both internal and external dests is not allowed\n"); rule = ERR_PTR(-EINVAL); goto err_esw_get; } @@ -3658,22 +3663,6 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode) return 0; } -static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - struct net *devl_net, *netdev_net; - bool ret = false; - - mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); - if (dev->mlx5e_res.uplink_netdev) { - netdev_net = dev_net(dev->mlx5e_res.uplink_netdev); - devl_net = devlink_net(devlink); - ret = net_eq(devl_net, netdev_net); - } - mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); - return ret; -} - int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) { struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -3718,13 +3707,6 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && - !esw_offloads_devlink_ns_eq_netdev_ns(devlink)) { - NL_SET_ERR_MSG_MOD(extack, - "Can't change E-Switch mode to switchdev when netdev net namespace has diverged from the devlink's."); - return -EPERM; - } - mlx5_lag_disable_change(esw->dev); err = mlx5_esw_try_lock(esw); if (err < 0) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index f27eab6e4929..2911aa34a5be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -703,19 +703,30 @@ void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT); mlx5_eq_notifier_register(dev, &fw_reset->nb); } void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev) { - mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb); + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + if (!fw_reset) + return; + + mlx5_eq_notifier_unregister(dev, &fw_reset->nb); } void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags); cancel_work_sync(&fw_reset->fw_live_patch_work); cancel_work_sync(&fw_reset->reset_request_work); @@ -733,9 +744,13 @@ static const struct devlink_param mlx5_fw_reset_devlink_params[] = { int mlx5_fw_reset_init(struct mlx5_core_dev *dev) { - struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); + struct mlx5_fw_reset *fw_reset; int err; + if (!MLX5_CAP_MCAM_REG(dev, mfrl)) + return 0; + + fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); if (!fw_reset) return -ENOMEM; fw_reset->wq = create_singlethread_workqueue("mlx5_fw_reset_events"); @@ -771,6 +786,9 @@ void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + devl_params_unregister(priv_to_devlink(dev), mlx5_fw_reset_devlink_params, ARRAY_SIZE(mlx5_fw_reset_devlink_params)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 8ff6dc9bc803..b5c709bba155 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -452,10 +452,10 @@ mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct health_buffer __iomem *h = health->health; u8 synd = ioread8(&h->synd); + devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); if (!synd) return 0; - devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd)); return 0; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c index 4af285918ea2..75868b3f548e 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c @@ -347,10 +347,10 @@ int sparx5_del_mact_entry(struct sparx5 *sparx5, list) { if ((vid == 0 || mact_entry->vid == vid) && ether_addr_equal(addr, mact_entry->mac)) { + sparx5_mact_forget(sparx5, addr, mact_entry->vid); + list_del(&mact_entry->list); devm_kfree(sparx5->dev, mact_entry); - - sparx5_mact_forget(sparx5, addr, mact_entry->vid); } } mutex_unlock(&sparx5->mact_lock); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 9d2f4ac783e4..2939a21ca74f 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -294,7 +294,7 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev, txqueue, netif_tx_queue_stopped(netif_txq), jiffies_to_msecs(jiffies - trans_start), - dql_avail(&netif_txq->dql), + netdev_queue_dql_avail(netif_txq), k3_cppi_desc_pool_avail(tx_chn->desc_pool)); if (netif_tx_queue_stopped(netif_txq)) { diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 32c51c244153..c4ed36c71897 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -221,7 +221,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct genevehdr *gnvh = geneve_hdr(skb); struct metadata_dst *tun_dst = NULL; unsigned int len; - int err = 0; + int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { @@ -272,9 +272,23 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, skb->pkt_type = PACKET_HOST; } - oiph = skb_network_header(skb); + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(geneve->dev, rx_length_errors); + DEV_STATS_INC(geneve->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + oiph = skb->head + nh; + if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index ba6c8ac2a736..d2aa2c5b1989 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3135,7 +3135,8 @@ static int lan78xx_open(struct net_device *net) done: mutex_unlock(&dev->dev_mutex); - usb_autopm_put_interface(dev->intf); + if (ret < 0) + usb_autopm_put_interface(dev->intf); return ret; } diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index bb3726b622ad..4d0c527e8576 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1496,19 +1496,21 @@ static int btt_blk_init(struct btt *btt) { struct nd_btt *nd_btt = btt->nd_btt; struct nd_namespace_common *ndns = nd_btt->ndns; - int rc = -ENOMEM; + struct queue_limits lim = { + .logical_block_size = btt->sector_size, + .max_hw_sectors = UINT_MAX, + }; + int rc; - btt->btt_disk = blk_alloc_disk(NUMA_NO_NODE); - if (!btt->btt_disk) - return -ENOMEM; + btt->btt_disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(btt->btt_disk)) + return PTR_ERR(btt->btt_disk); nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name); btt->btt_disk->first_minor = 0; btt->btt_disk->fops = &btt_fops; btt->btt_disk->private_data = btt; - blk_queue_logical_block_size(btt->btt_disk->queue, btt->sector_size); - blk_queue_max_hw_sectors(btt->btt_disk->queue, UINT_MAX); blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue); blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, btt->btt_disk->queue); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 4e8fdcb3f1c8..8dcc10b6db5b 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -451,6 +451,11 @@ static int pmem_attach_disk(struct device *dev, { struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); struct nd_region *nd_region = to_nd_region(dev->parent); + struct queue_limits lim = { + .logical_block_size = pmem_sector_size(ndns), + .physical_block_size = PAGE_SIZE, + .max_hw_sectors = UINT_MAX, + }; int nid = dev_to_node(dev), fua; struct resource *res = &nsio->res; struct range bb_range; @@ -497,9 +502,9 @@ static int pmem_attach_disk(struct device *dev, return -EBUSY; } - disk = blk_alloc_disk(nid); - if (!disk) - return -ENOMEM; + disk = blk_alloc_disk(&lim, nid); + if (IS_ERR(disk)) + return PTR_ERR(disk); q = disk->queue; pmem->disk = disk; @@ -539,9 +544,6 @@ static int pmem_attach_disk(struct device *dev, pmem->virt_addr = addr; blk_queue_write_cache(q, true, fua); - blk_queue_physical_block_size(q, PAGE_SIZE); - blk_queue_logical_block_size(q, pmem_sector_size(ndns)); - blk_queue_max_hw_sectors(q, UINT_MAX); blk_queue_flag_set(QUEUE_FLAG_NONROT, q); blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, q); if (pmem->pfn_flags & PFN_MAP) diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index c727cd1f264b..a480cdeac288 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1516,7 +1516,7 @@ static int apple_nvme_probe(struct platform_device *pdev) goto put_dev; } - anv->ctrl.admin_q = blk_mq_init_queue(&anv->admin_tagset); + anv->ctrl.admin_q = blk_mq_alloc_queue(&anv->admin_tagset, NULL, NULL); if (IS_ERR(anv->ctrl.admin_q)) { ret = -ENOMEM; goto put_dev; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0a96362912ce..00864a634470 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -114,12 +114,21 @@ static DEFINE_MUTEX(nvme_subsystems_lock); static DEFINE_IDA(nvme_instance_ida); static dev_t nvme_ctrl_base_chr_devt; -static struct class *nvme_class; -static struct class *nvme_subsys_class; +static int nvme_class_uevent(const struct device *dev, struct kobj_uevent_env *env); +static const struct class nvme_class = { + .name = "nvme", + .dev_uevent = nvme_class_uevent, +}; + +static const struct class nvme_subsys_class = { + .name = "nvme-subsystem", +}; static DEFINE_IDA(nvme_ns_chr_minor_ida); static dev_t nvme_ns_chr_devt; -static struct class *nvme_ns_chr_class; +static const struct class nvme_ns_chr_class = { + .name = "nvme-generic", +}; static void nvme_put_subsystem(struct nvme_subsystem *subsys); static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, @@ -1398,8 +1407,10 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) error = nvme_submit_sync_cmd(dev->admin_q, &c, *id, sizeof(struct nvme_id_ctrl)); - if (error) + if (error) { kfree(*id); + *id = NULL; + } return error; } @@ -1528,6 +1539,7 @@ int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, if (error) { dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error); kfree(*id); + *id = NULL; } return error; } @@ -1727,12 +1739,23 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -#ifdef CONFIG_BLK_DEV_INTEGRITY -static void nvme_init_integrity(struct gendisk *disk, - struct nvme_ns_head *head, u32 max_integrity_segments) +static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head) { struct blk_integrity integrity = { }; + blk_integrity_unregister(disk); + + if (!head->ms) + return true; + + /* + * PI can always be supported as we can ask the controller to simply + * insert/strip it, which is not possible for other kinds of metadata. + */ + if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) || + !(head->features & NVME_NS_METADATA_SUPPORTED)) + return nvme_ns_has_pi(head); + switch (head->pi_type) { case NVME_NS_DPS_PI_TYPE3: switch (head->guard_type) { @@ -1775,53 +1798,32 @@ static void nvme_init_integrity(struct gendisk *disk, } integrity.tuple_size = head->ms; + integrity.pi_offset = head->pi_offset; blk_integrity_register(disk, &integrity); - blk_queue_max_integrity_segments(disk->queue, max_integrity_segments); -} -#else -static void nvme_init_integrity(struct gendisk *disk, - struct nvme_ns_head *head, u32 max_integrity_segments) -{ + return true; } -#endif /* CONFIG_BLK_DEV_INTEGRITY */ -static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk, - struct nvme_ns_head *head) +static void nvme_config_discard(struct nvme_ns *ns, struct queue_limits *lim) { - struct request_queue *queue = disk->queue; - u32 max_discard_sectors; - - if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) { - max_discard_sectors = nvme_lba_to_sect(head, ctrl->dmrsl); - } else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) { - max_discard_sectors = UINT_MAX; - } else { - blk_queue_max_discard_sectors(queue, 0); - return; - } + struct nvme_ctrl *ctrl = ns->ctrl; BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < NVME_DSM_MAX_RANGES); - /* - * If discard is already enabled, don't reset queue limits. - * - * This works around the fact that the block layer can't cope well with - * updating the hardware limits when overridden through sysfs. This is - * harmless because discard limits in NVMe are purely advisory. - */ - if (queue->limits.max_discard_sectors) - return; + if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns->head, UINT_MAX)) + lim->max_hw_discard_sectors = + nvme_lba_to_sect(ns->head, ctrl->dmrsl); + else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) + lim->max_hw_discard_sectors = UINT_MAX; + else + lim->max_hw_discard_sectors = 0; + + lim->discard_granularity = lim->logical_block_size; - blk_queue_max_discard_sectors(queue, max_discard_sectors); if (ctrl->dmrl) - blk_queue_max_discard_segments(queue, ctrl->dmrl); + lim->max_discard_segments = ctrl->dmrl; else - blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES); - queue->limits.discard_granularity = queue_logical_block_size(queue); - - if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) - blk_queue_max_write_zeroes_sectors(queue, UINT_MAX); + lim->max_discard_segments = NVME_DSM_MAX_RANGES; } static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) @@ -1832,42 +1834,38 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) a->csi == b->csi; } -static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head, - struct nvme_id_ns *id) +static int nvme_identify_ns_nvm(struct nvme_ctrl *ctrl, unsigned int nsid, + struct nvme_id_ns_nvm **nvmp) { - bool first = id->dps & NVME_NS_DPS_PI_FIRST; - unsigned lbaf = nvme_lbaf_index(id->flbas); - struct nvme_command c = { }; + struct nvme_command c = { + .identify.opcode = nvme_admin_identify, + .identify.nsid = cpu_to_le32(nsid), + .identify.cns = NVME_ID_CNS_CS_NS, + .identify.csi = NVME_CSI_NVM, + }; struct nvme_id_ns_nvm *nvm; - int ret = 0; - u32 elbaf; - - head->pi_size = 0; - head->ms = le16_to_cpu(id->lbaf[lbaf].ms); - if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) { - head->pi_size = sizeof(struct t10_pi_tuple); - head->guard_type = NVME_NVM_NS_16B_GUARD; - goto set_pi; - } + int ret; nvm = kzalloc(sizeof(*nvm), GFP_KERNEL); if (!nvm) return -ENOMEM; - c.identify.opcode = nvme_admin_identify; - c.identify.nsid = cpu_to_le32(head->ns_id); - c.identify.cns = NVME_ID_CNS_CS_NS; - c.identify.csi = NVME_CSI_NVM; - ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, nvm, sizeof(*nvm)); if (ret) - goto free_data; + kfree(nvm); + else + *nvmp = nvm; + return ret; +} - elbaf = le32_to_cpu(nvm->elbaf[lbaf]); +static void nvme_configure_pi_elbas(struct nvme_ns_head *head, + struct nvme_id_ns *id, struct nvme_id_ns_nvm *nvm) +{ + u32 elbaf = le32_to_cpu(nvm->elbaf[nvme_lbaf_index(id->flbas)]); /* no support for storage tag formats right now */ if (nvme_elbaf_sts(elbaf)) - goto free_data; + return; head->guard_type = nvme_elbaf_guard_type(elbaf); switch (head->guard_type) { @@ -1880,30 +1878,31 @@ static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head, default: break; } - -free_data: - kfree(nvm); -set_pi: - if (head->pi_size && (first || head->ms == head->pi_size)) - head->pi_type = id->dps & NVME_NS_DPS_PI_MASK; - else - head->pi_type = 0; - - return ret; } -static int nvme_configure_metadata(struct nvme_ctrl *ctrl, - struct nvme_ns_head *head, struct nvme_id_ns *id) +static void nvme_configure_metadata(struct nvme_ctrl *ctrl, + struct nvme_ns_head *head, struct nvme_id_ns *id, + struct nvme_id_ns_nvm *nvm) { - int ret; - - ret = nvme_init_ms(ctrl, head, id); - if (ret) - return ret; - head->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS); + head->pi_type = 0; + head->pi_size = 0; + head->pi_offset = 0; + head->ms = le16_to_cpu(id->lbaf[nvme_lbaf_index(id->flbas)].ms); if (!head->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)) - return 0; + return; + + if (nvm && (ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) { + nvme_configure_pi_elbas(head, id, nvm); + } else { + head->pi_size = sizeof(struct t10_pi_tuple); + head->guard_type = NVME_NVM_NS_16B_GUARD; + } + + if (head->pi_size && head->ms >= head->pi_size) + head->pi_type = id->dps & NVME_NS_DPS_PI_MASK; + if (!(id->dps & NVME_NS_DPS_PI_FIRST)) + head->pi_offset = head->ms - head->pi_size; if (ctrl->ops->flags & NVME_F_FABRICS) { /* @@ -1912,7 +1911,7 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl, * remap the separate metadata buffer from the block layer. */ if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT))) - return 0; + return; head->features |= NVME_NS_EXT_LBAS; @@ -1939,33 +1938,32 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl, else head->features |= NVME_NS_METADATA_SUPPORTED; } - return 0; } -static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, - struct request_queue *q) +static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl) { - bool vwc = ctrl->vwc & NVME_CTRL_VWC_PRESENT; - - if (ctrl->max_hw_sectors) { - u32 max_segments = - (ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> 9)) + 1; + return ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> SECTOR_SHIFT) + 1; +} - max_segments = min_not_zero(max_segments, ctrl->max_segments); - blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors); - blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); - } - blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1); - blk_queue_dma_alignment(q, 3); - blk_queue_write_cache(q, vwc, vwc); +static void nvme_set_ctrl_limits(struct nvme_ctrl *ctrl, + struct queue_limits *lim) +{ + lim->max_hw_sectors = ctrl->max_hw_sectors; + lim->max_segments = min_t(u32, USHRT_MAX, + min_not_zero(nvme_max_drv_segments(ctrl), ctrl->max_segments)); + lim->max_integrity_segments = ctrl->max_integrity_segments; + lim->virt_boundary_mask = NVME_CTRL_PAGE_SIZE - 1; + lim->max_segment_size = UINT_MAX; + lim->dma_alignment = 3; } -static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk, - struct nvme_ns_head *head, struct nvme_id_ns *id) +static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, + struct queue_limits *lim) { - sector_t capacity = nvme_lba_to_sect(head, le64_to_cpu(id->nsze)); + struct nvme_ns_head *head = ns->head; u32 bs = 1U << head->lba_shift; u32 atomic_bs, phys_bs, io_opt = 0; + bool valid = true; /* * The block layer can't support LBA sizes larger than the page size @@ -1973,12 +1971,10 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk, * allow block I/O. */ if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) { - capacity = 0; bs = (1 << 9); + valid = false; } - blk_integrity_unregister(disk); - atomic_bs = phys_bs = bs; if (id->nabo == 0) { /* @@ -1989,7 +1985,7 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk, if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; else - atomic_bs = (1 + ctrl->subsys->awupf) * bs; + atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs; } if (id->nsfeat & NVME_NS_FEAT_IO_OPT) { @@ -1999,36 +1995,20 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk, io_opt = bs * (1 + le16_to_cpu(id->nows)); } - blk_queue_logical_block_size(disk->queue, bs); /* * Linux filesystems assume writing a single physical block is * an atomic operation. Hence limit the physical block size to the * value of the Atomic Write Unit Power Fail parameter. */ - blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs)); - blk_queue_io_min(disk->queue, phys_bs); - blk_queue_io_opt(disk->queue, io_opt); - - /* - * Register a metadata profile for PI, or the plain non-integrity NVMe - * metadata masquerading as Type 0 if supported, otherwise reject block - * I/O to namespaces with metadata except when the namespace supports - * PI, as it can strip/insert in that case. - */ - if (head->ms) { - if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && - (head->features & NVME_NS_METADATA_SUPPORTED)) - nvme_init_integrity(disk, head, - ctrl->max_integrity_segments); - else if (!nvme_ns_has_pi(head)) - capacity = 0; - } - - set_capacity_and_notify(disk, capacity); - - nvme_config_discard(ctrl, disk, head); - blk_queue_max_write_zeroes_sectors(disk->queue, - ctrl->max_zeroes_sectors); + lim->logical_block_size = bs; + lim->physical_block_size = min(phys_bs, atomic_bs); + lim->io_min = phys_bs; + lim->io_opt = io_opt; + if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) + lim->max_write_zeroes_sectors = UINT_MAX; + else + lim->max_write_zeroes_sectors = ns->ctrl->max_zeroes_sectors; + return valid; } static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info) @@ -2042,7 +2022,8 @@ static inline bool nvme_first_scan(struct gendisk *disk) return !disk_live(disk); } -static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id) +static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id, + struct queue_limits *lim) { struct nvme_ctrl *ctrl = ns->ctrl; u32 iob; @@ -2070,38 +2051,36 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id) return; } - blk_queue_chunk_sectors(ns->queue, iob); + lim->chunk_sectors = iob; } static int nvme_update_ns_info_generic(struct nvme_ns *ns, struct nvme_ns_info *info) { + struct queue_limits lim; + int ret; + blk_mq_freeze_queue(ns->disk->queue); - nvme_set_queue_limits(ns->ctrl, ns->queue); + lim = queue_limits_start_update(ns->disk->queue); + nvme_set_ctrl_limits(ns->ctrl, &lim); + ret = queue_limits_commit_update(ns->disk->queue, &lim); set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); blk_mq_unfreeze_queue(ns->disk->queue); - if (nvme_ns_head_multipath(ns->head)) { - blk_mq_freeze_queue(ns->head->disk->queue); - set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); - nvme_mpath_revalidate_paths(ns); - blk_stack_limits(&ns->head->disk->queue->limits, - &ns->queue->limits, 0); - ns->head->disk->flags |= GENHD_FL_HIDDEN; - blk_mq_unfreeze_queue(ns->head->disk->queue); - } - /* Hide the block-interface for these devices */ - ns->disk->flags |= GENHD_FL_HIDDEN; - set_bit(NVME_NS_READY, &ns->flags); - - return 0; + if (!ret) + ret = -ENODEV; + return ret; } static int nvme_update_ns_info_block(struct nvme_ns *ns, struct nvme_ns_info *info) { + bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT; + struct queue_limits lim; + struct nvme_id_ns_nvm *nvm = NULL; struct nvme_id_ns *id; + sector_t capacity; unsigned lbaf; int ret; @@ -2113,30 +2092,52 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, /* namespace not allocated or attached */ info->is_removed = true; ret = -ENODEV; - goto error; + goto out; + } + + if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) { + ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm); + if (ret < 0) + goto out; } blk_mq_freeze_queue(ns->disk->queue); lbaf = nvme_lbaf_index(id->flbas); ns->head->lba_shift = id->lbaf[lbaf].ds; ns->head->nuse = le64_to_cpu(id->nuse); - nvme_set_queue_limits(ns->ctrl, ns->queue); - - ret = nvme_configure_metadata(ns->ctrl, ns->head, id); - if (ret < 0) { - blk_mq_unfreeze_queue(ns->disk->queue); - goto out; - } - nvme_set_chunk_sectors(ns, id); - nvme_update_disk_info(ns->ctrl, ns->disk, ns->head, id); + capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze)); - if (ns->head->ids.csi == NVME_CSI_ZNS) { - ret = nvme_update_zone_info(ns, lbaf); + lim = queue_limits_start_update(ns->disk->queue); + nvme_set_ctrl_limits(ns->ctrl, &lim); + nvme_configure_metadata(ns->ctrl, ns->head, id, nvm); + nvme_set_chunk_sectors(ns, id, &lim); + if (!nvme_update_disk_info(ns, id, &lim)) + capacity = 0; + nvme_config_discard(ns, &lim); + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + ns->head->ids.csi == NVME_CSI_ZNS) { + ret = nvme_update_zone_info(ns, lbaf, &lim); if (ret) { blk_mq_unfreeze_queue(ns->disk->queue); goto out; } } + ret = queue_limits_commit_update(ns->disk->queue, &lim); + if (ret) { + blk_mq_unfreeze_queue(ns->disk->queue); + goto out; + } + + /* + * Register a metadata profile for PI, or the plain non-integrity NVMe + * metadata masquerading as Type 0 if supported, otherwise reject block + * I/O to namespaces with metadata except when the namespace supports + * PI, as it can strip/insert in that case. + */ + if (!nvme_init_integrity(ns->disk, ns->head)) + capacity = 0; + + set_capacity_and_notify(ns->disk, capacity); /* * Only set the DEAC bit if the device guarantees that reads from @@ -2147,62 +2148,81 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3))) ns->head->features |= NVME_NS_DEAC; set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); + blk_queue_write_cache(ns->disk->queue, vwc, vwc); set_bit(NVME_NS_READY, &ns->flags); blk_mq_unfreeze_queue(ns->disk->queue); if (blk_queue_is_zoned(ns->queue)) { - ret = nvme_revalidate_zones(ns); + ret = blk_revalidate_disk_zones(ns->disk, NULL); if (ret && !nvme_first_scan(ns->disk)) goto out; } - if (nvme_ns_head_multipath(ns->head)) { - blk_mq_freeze_queue(ns->head->disk->queue); - nvme_update_disk_info(ns->ctrl, ns->head->disk, ns->head, id); - set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); - nvme_mpath_revalidate_paths(ns); - blk_stack_limits(&ns->head->disk->queue->limits, - &ns->queue->limits, 0); - disk_update_readahead(ns->head->disk); - blk_mq_unfreeze_queue(ns->head->disk->queue); - } - ret = 0; out: - /* - * If probing fails due an unsupported feature, hide the block device, - * but still allow other access. - */ - if (ret == -ENODEV) { - ns->disk->flags |= GENHD_FL_HIDDEN; - set_bit(NVME_NS_READY, &ns->flags); - ret = 0; - } - -error: + kfree(nvm); kfree(id); return ret; } static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) { + bool unsupported = false; + int ret; + switch (info->ids.csi) { case NVME_CSI_ZNS: if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { dev_info(ns->ctrl->device, "block device for nsid %u not supported without CONFIG_BLK_DEV_ZONED\n", info->nsid); - return nvme_update_ns_info_generic(ns, info); + ret = nvme_update_ns_info_generic(ns, info); + break; } - return nvme_update_ns_info_block(ns, info); + ret = nvme_update_ns_info_block(ns, info); + break; case NVME_CSI_NVM: - return nvme_update_ns_info_block(ns, info); + ret = nvme_update_ns_info_block(ns, info); + break; default: dev_info(ns->ctrl->device, "block device for nsid %u not supported (csi %u)\n", info->nsid, info->ids.csi); - return nvme_update_ns_info_generic(ns, info); + ret = nvme_update_ns_info_generic(ns, info); + break; + } + + /* + * If probing fails due an unsupported feature, hide the block device, + * but still allow other access. + */ + if (ret == -ENODEV) { + ns->disk->flags |= GENHD_FL_HIDDEN; + set_bit(NVME_NS_READY, &ns->flags); + unsupported = true; + ret = 0; } + + if (!ret && nvme_ns_head_multipath(ns->head)) { + struct queue_limits lim; + + blk_mq_freeze_queue(ns->head->disk->queue); + if (unsupported) + ns->head->disk->flags |= GENHD_FL_HIDDEN; + else + nvme_init_integrity(ns->head->disk, ns->head); + set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk)); + set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); + nvme_mpath_revalidate_paths(ns); + + lim = queue_limits_start_update(ns->head->disk->queue); + queue_limits_stack_bdev(&lim, ns->disk->part0, 0, + ns->head->disk->disk_name); + ret = queue_limits_commit_update(ns->head->disk->queue, &lim); + blk_mq_unfreeze_queue(ns->head->disk->queue); + } + + return ret; } #ifdef CONFIG_BLK_SED_OPAL @@ -2877,7 +2897,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) subsys->awupf = le16_to_cpu(id->awupf); nvme_mpath_default_iopolicy(subsys); - subsys->dev.class = nvme_subsys_class; + subsys->dev.class = &nvme_subsys_class; subsys->dev.release = nvme_release_subsystem; subsys->dev.groups = nvme_subsys_attrs_groups; dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance); @@ -3117,11 +3137,17 @@ static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ct return -EINVAL; } + if (!ctrl->maxcmd) { + dev_err(ctrl->device, "Maximum outstanding commands is 0\n"); + return -EINVAL; + } + return 0; } static int nvme_init_identify(struct nvme_ctrl *ctrl) { + struct queue_limits lim; struct nvme_id_ctrl *id; u32 max_hw_sectors; bool prev_apst_enabled; @@ -3188,7 +3214,12 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->max_hw_sectors = min_not_zero(ctrl->max_hw_sectors, max_hw_sectors); - nvme_set_queue_limits(ctrl, ctrl->admin_q); + lim = queue_limits_start_update(ctrl->admin_q); + nvme_set_ctrl_limits(ctrl, &lim); + ret = queue_limits_commit_update(ctrl->admin_q, &lim); + if (ret) + goto out_free; + ctrl->sgls = le32_to_cpu(id->sgls); ctrl->kas = le16_to_cpu(id->kas); ctrl->max_namespaces = le32_to_cpu(id->mnan); @@ -3420,7 +3451,7 @@ int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device, if (minor < 0) return minor; cdev_device->devt = MKDEV(MAJOR(nvme_ns_chr_devt), minor); - cdev_device->class = nvme_ns_chr_class; + cdev_device->class = &nvme_ns_chr_class; cdev_device->release = nvme_cdev_rel; device_initialize(cdev_device); cdev_init(cdev, fops); @@ -3692,7 +3723,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) if (!ns) return; - disk = blk_mq_alloc_disk(ctrl->tagset, ns); + disk = blk_mq_alloc_disk(ctrl->tagset, NULL, ns); if (IS_ERR(disk)) goto out_free_ns; disk->fops = &nvme_bdev_ops; @@ -4353,6 +4384,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event); int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int cmd_size) { + struct queue_limits lim = {}; int ret; memset(set, 0, sizeof(*set)); @@ -4372,14 +4404,14 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, if (ret) return ret; - ctrl->admin_q = blk_mq_init_queue(set); + ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL); if (IS_ERR(ctrl->admin_q)) { ret = PTR_ERR(ctrl->admin_q); goto out_free_tagset; } if (ctrl->ops->flags & NVME_F_FABRICS) { - ctrl->fabrics_q = blk_mq_init_queue(set); + ctrl->fabrics_q = blk_mq_alloc_queue(set, NULL, NULL); if (IS_ERR(ctrl->fabrics_q)) { ret = PTR_ERR(ctrl->fabrics_q); goto out_cleanup_admin_q; @@ -4443,7 +4475,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, return ret; if (ctrl->ops->flags & NVME_F_FABRICS) { - ctrl->connect_q = blk_mq_init_queue(set); + ctrl->connect_q = blk_mq_alloc_queue(set, NULL, NULL); if (IS_ERR(ctrl->connect_q)) { ret = PTR_ERR(ctrl->connect_q); goto out_free_tag_set; @@ -4613,7 +4645,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->device = &ctrl->ctrl_device; ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt), ctrl->instance); - ctrl->device->class = nvme_class; + ctrl->device->class = &nvme_class; ctrl->device->parent = ctrl->dev; if (ops->dev_attr_groups) ctrl->device->groups = ops->dev_attr_groups; @@ -4846,42 +4878,36 @@ static int __init nvme_core_init(void) if (result < 0) goto destroy_delete_wq; - nvme_class = class_create("nvme"); - if (IS_ERR(nvme_class)) { - result = PTR_ERR(nvme_class); + result = class_register(&nvme_class); + if (result) goto unregister_chrdev; - } - nvme_class->dev_uevent = nvme_class_uevent; - nvme_subsys_class = class_create("nvme-subsystem"); - if (IS_ERR(nvme_subsys_class)) { - result = PTR_ERR(nvme_subsys_class); + result = class_register(&nvme_subsys_class); + if (result) goto destroy_class; - } result = alloc_chrdev_region(&nvme_ns_chr_devt, 0, NVME_MINORS, "nvme-generic"); if (result < 0) goto destroy_subsys_class; - nvme_ns_chr_class = class_create("nvme-generic"); - if (IS_ERR(nvme_ns_chr_class)) { - result = PTR_ERR(nvme_ns_chr_class); + result = class_register(&nvme_ns_chr_class); + if (result) goto unregister_generic_ns; - } + result = nvme_init_auth(); if (result) goto destroy_ns_chr; return 0; destroy_ns_chr: - class_destroy(nvme_ns_chr_class); + class_unregister(&nvme_ns_chr_class); unregister_generic_ns: unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS); destroy_subsys_class: - class_destroy(nvme_subsys_class); + class_unregister(&nvme_subsys_class); destroy_class: - class_destroy(nvme_class); + class_unregister(&nvme_class); unregister_chrdev: unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS); destroy_delete_wq: @@ -4897,9 +4923,9 @@ out: static void __exit nvme_core_exit(void) { nvme_exit_auth(); - class_destroy(nvme_ns_chr_class); - class_destroy(nvme_subsys_class); - class_destroy(nvme_class); + class_unregister(&nvme_ns_chr_class); + class_unregister(&nvme_subsys_class); + class_unregister(&nvme_class); unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS); unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS); destroy_workqueue(nvme_delete_wq); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 495c171daead..1f0ea1f32d22 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -638,7 +638,7 @@ static struct key *nvmf_parse_key(int key_id) } key = key_lookup(key_id); - if (!IS_ERR(key)) + if (IS_ERR(key)) pr_err("key id %08x not found\n", key_id); else pr_debug("Using key id %08x\n", key_id); @@ -1319,7 +1319,10 @@ out_free_opts: return ERR_PTR(ret); } -static struct class *nvmf_class; +static const struct class nvmf_class = { + .name = "nvme-fabrics", +}; + static struct device *nvmf_device; static DEFINE_MUTEX(nvmf_dev_mutex); @@ -1439,15 +1442,14 @@ static int __init nvmf_init(void) if (!nvmf_default_host) return -ENOMEM; - nvmf_class = class_create("nvme-fabrics"); - if (IS_ERR(nvmf_class)) { + ret = class_register(&nvmf_class); + if (ret) { pr_err("couldn't register class nvme-fabrics\n"); - ret = PTR_ERR(nvmf_class); goto out_free_host; } nvmf_device = - device_create(nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl"); + device_create(&nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl"); if (IS_ERR(nvmf_device)) { pr_err("couldn't create nvme-fabrics device!\n"); ret = PTR_ERR(nvmf_device); @@ -1463,9 +1465,9 @@ static int __init nvmf_init(void) return 0; out_destroy_device: - device_destroy(nvmf_class, MKDEV(0, 0)); + device_destroy(&nvmf_class, MKDEV(0, 0)); out_destroy_class: - class_destroy(nvmf_class); + class_unregister(&nvmf_class); out_free_host: nvmf_host_put(nvmf_default_host); return ret; @@ -1474,8 +1476,8 @@ out_free_host: static void __exit nvmf_exit(void) { misc_deregister(&nvmf_misc); - device_destroy(nvmf_class, MKDEV(0, 0)); - class_destroy(nvmf_class); + device_destroy(&nvmf_class, MKDEV(0, 0)); + class_unregister(&nvmf_class); nvmf_host_put(nvmf_default_host); BUILD_BUG_ON(sizeof(struct nvmf_common_command) != 64); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 74de1e64aeea..5397fb428b24 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -516,6 +516,7 @@ static void nvme_requeue_work(struct work_struct *work) int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) { + struct queue_limits lim; bool vwc = false; mutex_init(&head->lock); @@ -532,9 +533,14 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) !nvme_is_unique_nsid(ctrl, head) || !multipath) return 0; - head->disk = blk_alloc_disk(ctrl->numa_node); - if (!head->disk) - return -ENOMEM; + blk_set_stacking_limits(&lim); + lim.dma_alignment = 3; + if (head->ids.csi != NVME_CSI_ZNS) + lim.max_zone_append_sectors = 0; + + head->disk = blk_alloc_disk(&lim, ctrl->numa_node); + if (IS_ERR(head->disk)) + return PTR_ERR(head->disk); head->disk->fops = &nvme_ns_head_ops; head->disk->private_data = head; sprintf(head->disk->disk_name, "nvme%dn%d", @@ -553,11 +559,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues) blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue); - /* set to a default value of 512 until the disk is validated */ - blk_queue_logical_block_size(head->disk->queue, 512); - blk_set_stacking_limits(&head->disk->queue->limits); - blk_queue_dma_alignment(head->disk->queue, 3); - /* we need to propagate up the VMC settings */ if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) vwc = true; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 7b87763e2f8a..24193fcb8bd5 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -464,6 +464,7 @@ struct nvme_ns_head { u16 ms; u16 pi_size; u8 pi_type; + u8 pi_offset; u8 guard_type; u16 sgs; u32 sws; @@ -1035,11 +1036,11 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk) } #endif /* CONFIG_NVME_MULTIPATH */ -int nvme_revalidate_zones(struct nvme_ns *ns); int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); +int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf, + struct queue_limits *lim); #ifdef CONFIG_BLK_DEV_ZONED -int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf); blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd, enum nvme_zone_mgmt_action action); @@ -1050,13 +1051,6 @@ static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, { return BLK_STS_NOTSUPP; } - -static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf) -{ - dev_warn(ns->ctrl->device, - "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n"); - return -EPROTONOSUPPORT; -} #endif static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 20fdd40b1879..366f0bb4ebfc 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1006,6 +1006,7 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) { int ret; bool changed; + u16 max_queue_size; ret = nvme_rdma_configure_admin_queue(ctrl, new); if (ret) @@ -1030,11 +1031,16 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1); } - if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) { + if (ctrl->ctrl.max_integrity_segments) + max_queue_size = NVME_RDMA_MAX_METADATA_QUEUE_SIZE; + else + max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE; + + if (ctrl->ctrl.sqsize + 1 > max_queue_size) { dev_warn(ctrl->ctrl.device, - "ctrl sqsize %u > max queue size %u, clamping down\n", - ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE); - ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1; + "ctrl sqsize %u > max queue size %u, clamping down\n", + ctrl->ctrl.sqsize + 1, max_queue_size); + ctrl->ctrl.sqsize = max_queue_size - 1; } if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) { diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index f2832f70e7e0..09fcaa519e5b 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -221,14 +221,11 @@ static int ns_update_nuse(struct nvme_ns *ns) ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id); if (ret) - goto out_free_id; + return ret; ns->head->nuse = le64_to_cpu(id->nuse); - -out_free_id: kfree(id); - - return ret; + return 0; } static ssize_t nuse_show(struct device *dev, struct device_attribute *attr, diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 499bbb0eee8d..722384bcc765 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -7,16 +7,6 @@ #include <linux/vmalloc.h> #include "nvme.h" -int nvme_revalidate_zones(struct nvme_ns *ns) -{ - struct request_queue *q = ns->queue; - - blk_queue_chunk_sectors(q, ns->head->zsze); - blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append); - - return blk_revalidate_disk_zones(ns->disk, NULL); -} - static int nvme_set_max_append(struct nvme_ctrl *ctrl) { struct nvme_command c = { }; @@ -45,10 +35,10 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl) return 0; } -int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf) +int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf, + struct queue_limits *lim) { struct nvme_effects_log *log = ns->head->effects; - struct request_queue *q = ns->queue; struct nvme_command c = { }; struct nvme_id_ns_zns *id; int status; @@ -109,10 +99,12 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf) goto free_data; } - disk_set_zoned(ns->disk); - blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q); - disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1); - disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1); + blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue); + lim->zoned = 1; + lim->max_open_zones = le32_to_cpu(id->mor) + 1; + lim->max_active_zones = le32_to_cpu(id->mar) + 1; + lim->chunk_sectors = ns->head->zsze; + lim->max_zone_append_sectors = ns->ctrl->max_zone_append; free_data: kfree(id); return status; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 39cb570f833d..f5b7054a4a05 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -428,7 +428,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->cqes = (0x4 << 4) | 0x4; /* no enforcement soft-limit for maxcmd - pick arbitrary high value */ - id->maxcmd = cpu_to_le16(NVMET_MAX_CMD); + id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl)); id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES); id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES); diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 2482a0db2504..77a6e817b315 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -273,6 +273,32 @@ static ssize_t nvmet_param_inline_data_size_store(struct config_item *item, CONFIGFS_ATTR(nvmet_, param_inline_data_size); +static ssize_t nvmet_param_max_queue_size_show(struct config_item *item, + char *page) +{ + struct nvmet_port *port = to_nvmet_port(item); + + return snprintf(page, PAGE_SIZE, "%d\n", port->max_queue_size); +} + +static ssize_t nvmet_param_max_queue_size_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_port *port = to_nvmet_port(item); + int ret; + + if (nvmet_is_port_enabled(port, __func__)) + return -EACCES; + ret = kstrtoint(page, 0, &port->max_queue_size); + if (ret) { + pr_err("Invalid value '%s' for max_queue_size\n", page); + return -EINVAL; + } + return count; +} + +CONFIGFS_ATTR(nvmet_, param_max_queue_size); + #ifdef CONFIG_BLK_DEV_INTEGRITY static ssize_t nvmet_param_pi_enable_show(struct config_item *item, char *page) @@ -1859,6 +1885,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = { &nvmet_attr_addr_trtype, &nvmet_attr_addr_tsas, &nvmet_attr_param_inline_data_size, + &nvmet_attr_param_max_queue_size, #ifdef CONFIG_BLK_DEV_INTEGRITY &nvmet_attr_param_pi_enable, #endif @@ -1917,6 +1944,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group, INIT_LIST_HEAD(&port->subsystems); INIT_LIST_HEAD(&port->referrals); port->inline_data_size = -1; /* < 0 == let the transport choose */ + port->max_queue_size = -1; /* < 0 == let the transport choose */ port->disc_addr.portid = cpu_to_le16(portid); port->disc_addr.adrfam = NVMF_ADDR_FAMILY_MAX; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 8658e9c08534..6bbe4df0166c 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -358,6 +358,18 @@ int nvmet_enable_port(struct nvmet_port *port) if (port->inline_data_size < 0) port->inline_data_size = 0; + /* + * If the transport didn't set the max_queue_size properly, then clamp + * it to the target limits. Also set default values in case the + * transport didn't set it at all. + */ + if (port->max_queue_size < 0) + port->max_queue_size = NVMET_MAX_QUEUE_SIZE; + else + port->max_queue_size = clamp_t(int, port->max_queue_size, + NVMET_MIN_QUEUE_SIZE, + NVMET_MAX_QUEUE_SIZE); + port->enabled = true; port->tr_ops = ops; return 0; @@ -1223,9 +1235,10 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl) ctrl->cap |= (15ULL << 24); /* maximum queue entries supported: */ if (ctrl->ops->get_max_queue_size) - ctrl->cap |= ctrl->ops->get_max_queue_size(ctrl) - 1; + ctrl->cap |= min_t(u16, ctrl->ops->get_max_queue_size(ctrl), + ctrl->port->max_queue_size) - 1; else - ctrl->cap |= NVMET_QUEUE_SIZE - 1; + ctrl->cap |= ctrl->port->max_queue_size - 1; if (nvmet_is_passthru_subsys(ctrl->subsys)) nvmet_passthrough_override_cap(ctrl); @@ -1411,6 +1424,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, kref_init(&ctrl->ref); ctrl->subsys = subsys; + ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support; nvmet_init_cap(ctrl); WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL); diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 68e82ccc0e4e..ce54da8c6b36 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -282,7 +282,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req) id->lpa = (1 << 2); /* no enforcement soft-limit for maxcmd - pick arbitrary high value */ - id->maxcmd = cpu_to_le16(NVMET_MAX_CMD); + id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl)); id->sgls = cpu_to_le32(1 << 0); /* we always support SGLs */ if (ctrl->ops->flags & NVMF_KEYED_SGLS) diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 9964ffe347d2..b23f4cf840bd 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -157,7 +157,8 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR; } - if (sqsize > mqes) { + /* for fabrics, this value applies to only the I/O Submission Queues */ + if (qid && sqsize > mqes) { pr_warn("sqsize %u is larger than MQES supported %u cntlid %d\n", sqsize, mqes, ctrl->cntlid); req->error_loc = offsetof(struct nvmf_connect_command, sqsize); @@ -251,8 +252,6 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) if (status) goto out; - ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support; - uuid_copy(&ctrl->hostid, &d->hostid); ret = nvmet_setup_auth(ctrl); diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 1471af250ea6..913cd2ec7a6f 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -1556,7 +1556,9 @@ static const struct attribute_group *fcloop_dev_attr_groups[] = { NULL, }; -static struct class *fcloop_class; +static const struct class fcloop_class = { + .name = "fcloop", +}; static struct device *fcloop_device; @@ -1564,15 +1566,14 @@ static int __init fcloop_init(void) { int ret; - fcloop_class = class_create("fcloop"); - if (IS_ERR(fcloop_class)) { + ret = class_register(&fcloop_class); + if (ret) { pr_err("couldn't register class fcloop\n"); - ret = PTR_ERR(fcloop_class); return ret; } fcloop_device = device_create_with_groups( - fcloop_class, NULL, MKDEV(0, 0), NULL, + &fcloop_class, NULL, MKDEV(0, 0), NULL, fcloop_dev_attr_groups, "ctl"); if (IS_ERR(fcloop_device)) { pr_err("couldn't create ctl device!\n"); @@ -1585,7 +1586,7 @@ static int __init fcloop_init(void) return 0; out_destroy_class: - class_destroy(fcloop_class); + class_unregister(&fcloop_class); return ret; } @@ -1643,8 +1644,8 @@ static void __exit fcloop_exit(void) put_device(fcloop_device); - device_destroy(fcloop_class, MKDEV(0, 0)); - class_destroy(fcloop_class); + device_destroy(&fcloop_class, MKDEV(0, 0)); + class_unregister(&fcloop_class); } module_init(fcloop_init); diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index f11400a908f2..6426aac2634a 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -50,10 +50,10 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) void nvmet_bdev_ns_disable(struct nvmet_ns *ns) { - if (ns->bdev_handle) { - bdev_release(ns->bdev_handle); + if (ns->bdev_file) { + fput(ns->bdev_file); ns->bdev = NULL; - ns->bdev_handle = NULL; + ns->bdev_file = NULL; } } @@ -85,18 +85,18 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns) if (ns->buffered_io) return -ENOTBLK; - ns->bdev_handle = bdev_open_by_path(ns->device_path, + ns->bdev_file = bdev_file_open_by_path(ns->device_path, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL); - if (IS_ERR(ns->bdev_handle)) { - ret = PTR_ERR(ns->bdev_handle); + if (IS_ERR(ns->bdev_file)) { + ret = PTR_ERR(ns->bdev_file); if (ret != -ENOTBLK) { pr_err("failed to open block device %s: (%d)\n", ns->device_path, ret); } - ns->bdev_handle = NULL; + ns->bdev_file = NULL; return ret; } - ns->bdev = ns->bdev_handle->bdev; + ns->bdev = file_bdev(ns->bdev_file); ns->size = bdev_nr_bytes(ns->bdev); ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev)); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 6c8acebe1a1a..f460728e1df1 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -58,7 +58,7 @@ struct nvmet_ns { struct percpu_ref ref; - struct bdev_handle *bdev_handle; + struct file *bdev_file; struct block_device *bdev; struct file *file; bool readonly; @@ -163,6 +163,7 @@ struct nvmet_port { void *priv; bool enabled; int inline_data_size; + int max_queue_size; const struct nvmet_fabrics_ops *tr_ops; bool pi_enable; }; @@ -543,9 +544,10 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys, void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type, u8 event_info, u8 log_page); -#define NVMET_QUEUE_SIZE 1024 +#define NVMET_MIN_QUEUE_SIZE 16 +#define NVMET_MAX_QUEUE_SIZE 1024 #define NVMET_NR_QUEUES 128 -#define NVMET_MAX_CMD NVMET_QUEUE_SIZE +#define NVMET_MAX_CMD(ctrl) (NVME_CAP_MQES(ctrl->cap) + 1) /* * Nice round number that makes a list of nsids fit into a page. diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index f2d963e1fe94..bb4a69d538fd 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -132,7 +132,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req) id->sqes = min_t(__u8, ((0x6 << 4) | 0x6), id->sqes); id->cqes = min_t(__u8, ((0x4 << 4) | 0x4), id->cqes); - id->maxcmd = cpu_to_le16(NVMET_MAX_CMD); + id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl)); /* don't support fuse commands */ id->fuses = 0; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 3a0f2c170f4c..f2bb9d95ecf4 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1956,6 +1956,14 @@ static int nvmet_rdma_add_port(struct nvmet_port *nport) nport->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE; } + if (nport->max_queue_size < 0) { + nport->max_queue_size = NVME_RDMA_DEFAULT_QUEUE_SIZE; + } else if (nport->max_queue_size > NVME_RDMA_MAX_QUEUE_SIZE) { + pr_warn("max_queue_size %u is too large, reducing to %u\n", + nport->max_queue_size, NVME_RDMA_MAX_QUEUE_SIZE); + nport->max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE; + } + ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr, nport->disc_addr.trsvcid, &port->addr); if (ret) { @@ -2015,6 +2023,8 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl) static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_ctrl *ctrl) { + if (ctrl->pi_support) + return NVME_RDMA_MAX_METADATA_QUEUE_SIZE; return NVME_RDMA_MAX_QUEUE_SIZE; } diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index 5b5c1e481722..3148d9f1bde6 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -456,8 +456,7 @@ static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req) switch (zsa_req_op(req->cmd->zms.zsa)) { case REQ_OP_ZONE_RESET: ret = blkdev_zone_mgmt(req->ns->bdev, REQ_OP_ZONE_RESET, 0, - get_capacity(req->ns->bdev->bd_disk), - GFP_KERNEL); + get_capacity(req->ns->bdev->bd_disk)); if (ret < 0) return blkdev_zone_mgmt_errno_to_nvme_status(ret); break; @@ -508,7 +507,7 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w) goto out; } - ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors, GFP_KERNEL); + ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors); if (ret < 0) status = blkdev_zone_mgmt_errno_to_nvme_status(ret); diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index 6303b82566f9..9e5d7fa647b6 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -716,7 +716,7 @@ static void smmu_pmu_free_msis(void *data) { struct device *dev = data; - platform_msi_domain_free_irqs(dev); + platform_device_msi_free_irqs_all(dev); } static void smmu_pmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) @@ -746,7 +746,7 @@ static void smmu_pmu_setup_msi(struct smmu_pmu *pmu) if (!(readl(pmu->reg_base + SMMU_PMCG_CFGR) & SMMU_PMCG_CFGR_MSI)) return; - ret = platform_msi_domain_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg); + ret = platform_device_msi_init_and_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg); if (ret) { dev_warn(dev, "failed to allocate MSIs\n"); return; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 1ad10110dd25..17c4ad7553a5 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -3562,14 +3562,6 @@ static int qmp_combo_probe(struct platform_device *pdev) if (ret) return ret; - ret = qmp_combo_typec_switch_register(qmp); - if (ret) - return ret; - - ret = drm_aux_bridge_register(dev); - if (ret) - return ret; - /* Check for legacy binding with child nodes. */ usb_np = of_get_child_by_name(dev->of_node, "usb3-phy"); if (usb_np) { @@ -3589,6 +3581,14 @@ static int qmp_combo_probe(struct platform_device *pdev) if (ret) goto err_node_put; + ret = qmp_combo_typec_switch_register(qmp); + if (ret) + goto err_node_put; + + ret = drm_aux_bridge_register(dev); + if (ret) + goto err_node_put; + pm_runtime_set_active(dev); ret = devm_pm_runtime_enable(dev); if (ret) diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index ee56856cb80c..bbcdece83bf4 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -1644,7 +1644,7 @@ static int pinctrl_pins_show(struct seq_file *s, void *what) const struct pinctrl_ops *ops = pctldev->desc->pctlops; unsigned int i, pin; #ifdef CONFIG_GPIOLIB - struct gpio_device *gdev __free(gpio_device_put) = NULL; + struct gpio_device *gdev = NULL; struct pinctrl_gpio_range *range; int gpio_num; #endif diff --git a/drivers/pinctrl/stm32/pinctrl-stm32mp257.c b/drivers/pinctrl/stm32/pinctrl-stm32mp257.c index 73f091cd827e..23aebd4695e9 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32mp257.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32mp257.c @@ -2562,7 +2562,7 @@ static const struct of_device_id stm32mp257_pctrl_match[] = { }; static const struct dev_pm_ops stm32_pinctrl_dev_pm_ops = { - SET_LATE_SYSTEM_SLEEP_PM_OPS(NULL, stm32_pinctrl_resume) + SET_LATE_SYSTEM_SLEEP_PM_OPS(stm32_pinctrl_suspend, stm32_pinctrl_resume) }; static struct platform_driver stm32mp257_pinctrl_driver = { diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c index 8527dca9cf56..dcbe8f85e122 100644 --- a/drivers/platform/x86/amd/pmf/tee-if.c +++ b/drivers/platform/x86/amd/pmf/tee-if.c @@ -458,8 +458,10 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev) amd_pmf_hex_dump_pb(dev); dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL); - if (!dev->prev_data) + if (!dev->prev_data) { + ret = -ENOMEM; goto error; + } ret = amd_pmf_start_policy_engine(dev); if (ret) diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c index a5e0f5c22179..b89c0dda9e5d 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c @@ -242,7 +242,7 @@ static int __init intel_uncore_init(void) return -ENODEV; uncore_max_entries = topology_max_packages() * - topology_max_die_per_package(); + topology_max_dies_per_package(); uncore_instances = kcalloc(uncore_max_entries, sizeof(*uncore_instances), GFP_KERNEL); if (!uncore_instances) diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index 6bd14d0132db..3d66e1d4eb1f 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -20,9 +20,11 @@ #define P2SBC_HIDE BIT(8) #define P2SB_DEVFN_DEFAULT PCI_DEVFN(31, 1) +#define P2SB_DEVFN_GOLDMONT PCI_DEVFN(13, 0) +#define SPI_DEVFN_GOLDMONT PCI_DEVFN(13, 2) static const struct x86_cpu_id p2sb_cpu_ids[] = { - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, PCI_DEVFN(13, 0)), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, P2SB_DEVFN_GOLDMONT), {} }; @@ -98,21 +100,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) { - unsigned int slot, fn; - - if (PCI_FUNC(devfn) == 0) { - /* - * When function number of the P2SB device is zero, scan it and - * other function numbers, and if devices are available, cache - * their BAR0s. - */ - slot = PCI_SLOT(devfn); - for (fn = 0; fn < NR_P2SB_RES_CACHE; fn++) - p2sb_scan_and_cache_devfn(bus, PCI_DEVFN(slot, fn)); - } else { - /* Scan the P2SB device and cache its BAR0 */ - p2sb_scan_and_cache_devfn(bus, devfn); - } + /* Scan the P2SB device and cache its BAR0 */ + p2sb_scan_and_cache_devfn(bus, devfn); + + /* On Goldmont p2sb_bar() also gets called for the SPI controller */ + if (devfn == P2SB_DEVFN_GOLDMONT) + p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT); if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) return -ENOENT; diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 2feed036c1cd..00c861899a47 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1564,7 +1564,7 @@ struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id if (id_is_cpu) { rp->id = topology_logical_die_id(id); rp->lead_cpu = id; - if (topology_max_die_per_package() > 1) + if (topology_max_dies_per_package() > 1) snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, "package-%d-die-%d", topology_physical_package_id(id), topology_die_id(id)); else diff --git a/drivers/ptp/ptp_kvm_common.c b/drivers/ptp/ptp_kvm_common.c index 2418977989be..15ccb7dd2ed0 100644 --- a/drivers/ptp/ptp_kvm_common.c +++ b/drivers/ptp/ptp_kvm_common.c @@ -28,15 +28,15 @@ static int ptp_kvm_get_time_fn(ktime_t *device_time, struct system_counterval_t *system_counter, void *ctx) { - long ret; - u64 cycle; + enum clocksource_ids cs_id; struct timespec64 tspec; - struct clocksource *cs; + u64 cycle; + int ret; spin_lock(&kvm_ptp_lock); preempt_disable_notrace(); - ret = kvm_arch_ptp_get_crosststamp(&cycle, &tspec, &cs); + ret = kvm_arch_ptp_get_crosststamp(&cycle, &tspec, &cs_id); if (ret) { spin_unlock(&kvm_ptp_lock); preempt_enable_notrace(); @@ -46,7 +46,7 @@ static int ptp_kvm_get_time_fn(ktime_t *device_time, preempt_enable_notrace(); system_counter->cycles = cycle; - system_counter->cs = cs; + system_counter->cs_id = cs_id; *device_time = timespec64_to_ktime(tspec); diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c index 902844cc1a17..617c8d6706d3 100644 --- a/drivers/ptp/ptp_kvm_x86.c +++ b/drivers/ptp/ptp_kvm_x86.c @@ -93,7 +93,7 @@ int kvm_arch_ptp_get_clock(struct timespec64 *ts) } int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec, - struct clocksource **cs) + enum clocksource_ids *cs_id) { struct pvclock_vcpu_time_info *src; unsigned int version; @@ -123,7 +123,7 @@ int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec, *cycle = __pvclock_read_cycles(src, clock_pair->tsc); } while (pvclock_read_retry(src, version)); - *cs = &kvm_clock; + *cs_id = CSID_X86_KVM_CLK; return 0; } diff --git a/drivers/ras/Kconfig b/drivers/ras/Kconfig index c2a236f2e846..fc4f4bb94a4c 100644 --- a/drivers/ras/Kconfig +++ b/drivers/ras/Kconfig @@ -32,5 +32,18 @@ menuconfig RAS if RAS source "arch/x86/ras/Kconfig" +source "drivers/ras/amd/atl/Kconfig" + +config RAS_FMPM + tristate "FRU Memory Poison Manager" + default m + depends on AMD_ATL && ACPI_APEI + help + Support saving and restoring memory error information across reboot + using ACPI ERST as persistent storage. Error information is saved with + the UEFI CPER "FRU Memory Poison" section format. + + Memory will be retired during boot time and run time depending on + platform-specific policies. endif diff --git a/drivers/ras/Makefile b/drivers/ras/Makefile index 6f0404f50107..11f95d59d397 100644 --- a/drivers/ras/Makefile +++ b/drivers/ras/Makefile @@ -2,3 +2,6 @@ obj-$(CONFIG_RAS) += ras.o obj-$(CONFIG_DEBUG_FS) += debugfs.o obj-$(CONFIG_RAS_CEC) += cec.o + +obj-$(CONFIG_RAS_FMPM) += amd/fmpm.o +obj-y += amd/atl/ diff --git a/drivers/ras/amd/atl/Kconfig b/drivers/ras/amd/atl/Kconfig new file mode 100644 index 000000000000..df49c23e7f62 --- /dev/null +++ b/drivers/ras/amd/atl/Kconfig @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +# +# AMD Address Translation Library Kconfig +# +# Copyright (c) 2023, Advanced Micro Devices, Inc. +# All Rights Reserved. +# +# Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + +config AMD_ATL + tristate "AMD Address Translation Library" + depends on AMD_NB && X86_64 && RAS + depends on MEMORY_FAILURE + default N + help + This library includes support for implementation-specific + address translation procedures needed for various error + handling cases. + + Enable this option if using DRAM ECC on Zen-based systems + and OS-based error handling. diff --git a/drivers/ras/amd/atl/Makefile b/drivers/ras/amd/atl/Makefile new file mode 100644 index 000000000000..4acd5f05bd9c --- /dev/null +++ b/drivers/ras/amd/atl/Makefile @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +# +# AMD Address Translation Library Makefile +# +# Copyright (c) 2023, Advanced Micro Devices, Inc. +# All Rights Reserved. +# +# Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + +amd_atl-y := access.o +amd_atl-y += core.o +amd_atl-y += dehash.o +amd_atl-y += denormalize.o +amd_atl-y += map.o +amd_atl-y += system.o +amd_atl-y += umc.o + +obj-$(CONFIG_AMD_ATL) += amd_atl.o diff --git a/drivers/ras/amd/atl/access.c b/drivers/ras/amd/atl/access.c new file mode 100644 index 000000000000..ee4661ed28ba --- /dev/null +++ b/drivers/ras/amd/atl/access.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * access.c : DF Indirect Access functions + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +/* Protect the PCI config register pairs used for DF indirect access. */ +static DEFINE_MUTEX(df_indirect_mutex); + +/* + * Data Fabric Indirect Access uses FICAA/FICAD. + * + * Fabric Indirect Configuration Access Address (FICAA): constructed based + * on the device's Instance Id and the PCI function and register offset of + * the desired register. + * + * Fabric Indirect Configuration Access Data (FICAD): there are FICAD + * low and high registers but so far only the low register is needed. + * + * Use Instance Id 0xFF to indicate a broadcast read. + */ +#define DF_BROADCAST 0xFF + +#define DF_FICAA_INST_EN BIT(0) +#define DF_FICAA_REG_NUM GENMASK(10, 1) +#define DF_FICAA_FUNC_NUM GENMASK(13, 11) +#define DF_FICAA_INST_ID GENMASK(23, 16) + +#define DF_FICAA_REG_NUM_LEGACY GENMASK(10, 2) + +static u16 get_accessible_node(u16 node) +{ + /* + * On heterogeneous systems, not all AMD Nodes are accessible + * through software-visible registers. The Node ID needs to be + * adjusted for register accesses. But its value should not be + * changed for the translation methods. + */ + if (df_cfg.flags.heterogeneous) { + /* Only Node 0 is accessible on DF3.5 systems. */ + if (df_cfg.rev == DF3p5) + node = 0; + + /* + * Only the first Node in each Socket is accessible on + * DF4.5 systems, and this is visible to software as one + * Fabric per Socket. The Socket ID can be derived from + * the Node ID and global shift values. + */ + if (df_cfg.rev == DF4p5) + node >>= df_cfg.socket_id_shift - df_cfg.node_id_shift; + } + + return node; +} + +static int __df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) +{ + u32 ficaa_addr = 0x8C, ficad_addr = 0xB8; + struct pci_dev *F4; + int err = -ENODEV; + u32 ficaa = 0; + + node = get_accessible_node(node); + if (node >= amd_nb_num()) + goto out; + + F4 = node_to_amd_nb(node)->link; + if (!F4) + goto out; + + /* Enable instance-specific access. */ + if (instance_id != DF_BROADCAST) { + ficaa |= FIELD_PREP(DF_FICAA_INST_EN, 1); + ficaa |= FIELD_PREP(DF_FICAA_INST_ID, instance_id); + } + + /* + * The two least-significant bits are masked when inputing the + * register offset to FICAA. + */ + reg >>= 2; + + if (df_cfg.flags.legacy_ficaa) { + ficaa_addr = 0x5C; + ficad_addr = 0x98; + + ficaa |= FIELD_PREP(DF_FICAA_REG_NUM_LEGACY, reg); + } else { + ficaa |= FIELD_PREP(DF_FICAA_REG_NUM, reg); + } + + ficaa |= FIELD_PREP(DF_FICAA_FUNC_NUM, func); + + mutex_lock(&df_indirect_mutex); + + err = pci_write_config_dword(F4, ficaa_addr, ficaa); + if (err) { + pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa); + goto out_unlock; + } + + err = pci_read_config_dword(F4, ficad_addr, lo); + if (err) + pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa); + + pr_debug("node=%u inst=0x%x func=0x%x reg=0x%x val=0x%x", + node, instance_id, func, reg << 2, *lo); + +out_unlock: + mutex_unlock(&df_indirect_mutex); + +out: + return err; +} + +int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) +{ + return __df_indirect_read(node, func, reg, instance_id, lo); +} + +int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo) +{ + return __df_indirect_read(node, func, reg, DF_BROADCAST, lo); +} diff --git a/drivers/ras/amd/atl/core.c b/drivers/ras/amd/atl/core.c new file mode 100644 index 000000000000..6dc4e06305f7 --- /dev/null +++ b/drivers/ras/amd/atl/core.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * core.c : Module init and base translation functions + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include <linux/module.h> +#include <asm/cpu_device_id.h> + +#include "internal.h" + +struct df_config df_cfg __read_mostly; + +static int addr_over_limit(struct addr_ctx *ctx) +{ + u64 dram_limit_addr; + + if (df_cfg.rev >= DF4) + dram_limit_addr = FIELD_GET(DF4_DRAM_LIMIT_ADDR, ctx->map.limit); + else + dram_limit_addr = FIELD_GET(DF2_DRAM_LIMIT_ADDR, ctx->map.limit); + + dram_limit_addr <<= DF_DRAM_BASE_LIMIT_LSB; + dram_limit_addr |= GENMASK(DF_DRAM_BASE_LIMIT_LSB - 1, 0); + + /* Is calculated system address above DRAM limit address? */ + if (ctx->ret_addr > dram_limit_addr) { + atl_debug(ctx, "Calculated address (0x%016llx) > DRAM limit (0x%016llx)", + ctx->ret_addr, dram_limit_addr); + return -EINVAL; + } + + return 0; +} + +static bool legacy_hole_en(struct addr_ctx *ctx) +{ + u32 reg = ctx->map.base; + + if (df_cfg.rev >= DF4) + reg = ctx->map.ctl; + + return FIELD_GET(DF_LEGACY_MMIO_HOLE_EN, reg); +} + +static int add_legacy_hole(struct addr_ctx *ctx) +{ + u32 dram_hole_base; + u8 func = 0; + + if (!legacy_hole_en(ctx)) + return 0; + + if (df_cfg.rev >= DF4) + func = 7; + + if (df_indirect_read_broadcast(ctx->node_id, func, 0x104, &dram_hole_base)) + return -EINVAL; + + dram_hole_base &= DF_DRAM_HOLE_BASE_MASK; + + if (ctx->ret_addr >= dram_hole_base) + ctx->ret_addr += (BIT_ULL(32) - dram_hole_base); + + return 0; +} + +static u64 get_base_addr(struct addr_ctx *ctx) +{ + u64 base_addr; + + if (df_cfg.rev >= DF4) + base_addr = FIELD_GET(DF4_BASE_ADDR, ctx->map.base); + else + base_addr = FIELD_GET(DF2_BASE_ADDR, ctx->map.base); + + return base_addr << DF_DRAM_BASE_LIMIT_LSB; +} + +static int add_base_and_hole(struct addr_ctx *ctx) +{ + ctx->ret_addr += get_base_addr(ctx); + + if (add_legacy_hole(ctx)) + return -EINVAL; + + return 0; +} + +static bool late_hole_remove(struct addr_ctx *ctx) +{ + if (df_cfg.rev == DF3p5) + return true; + + if (df_cfg.rev == DF4) + return true; + + if (ctx->map.intlv_mode == DF3_6CHAN) + return true; + + return false; +} + +unsigned long norm_to_sys_addr(u8 socket_id, u8 die_id, u8 coh_st_inst_id, unsigned long addr) +{ + struct addr_ctx ctx; + + if (df_cfg.rev == UNKNOWN) + return -EINVAL; + + memset(&ctx, 0, sizeof(ctx)); + + /* Start from the normalized address */ + ctx.ret_addr = addr; + ctx.inst_id = coh_st_inst_id; + + ctx.inputs.norm_addr = addr; + ctx.inputs.socket_id = socket_id; + ctx.inputs.die_id = die_id; + ctx.inputs.coh_st_inst_id = coh_st_inst_id; + + if (determine_node_id(&ctx, socket_id, die_id)) + return -EINVAL; + + if (get_address_map(&ctx)) + return -EINVAL; + + if (denormalize_address(&ctx)) + return -EINVAL; + + if (!late_hole_remove(&ctx) && add_base_and_hole(&ctx)) + return -EINVAL; + + if (dehash_address(&ctx)) + return -EINVAL; + + if (late_hole_remove(&ctx) && add_base_and_hole(&ctx)) + return -EINVAL; + + if (addr_over_limit(&ctx)) + return -EINVAL; + + return ctx.ret_addr; +} + +static void check_for_legacy_df_access(void) +{ + /* + * All Zen-based systems before Family 19h use the legacy + * DF Indirect Access (FICAA/FICAD) offsets. + */ + if (boot_cpu_data.x86 < 0x19) { + df_cfg.flags.legacy_ficaa = true; + return; + } + + /* All systems after Family 19h use the current offsets. */ + if (boot_cpu_data.x86 > 0x19) + return; + + /* Some Family 19h systems use the legacy offsets. */ + switch (boot_cpu_data.x86_model) { + case 0x00 ... 0x0f: + case 0x20 ... 0x5f: + df_cfg.flags.legacy_ficaa = true; + } +} + +/* + * This library provides functionality for AMD-based systems with a Data Fabric. + * The set of systems with a Data Fabric is equivalent to the set of Zen-based systems + * and the set of systems with the Scalable MCA feature at this time. However, these + * are technically independent things. + * + * It's possible to match on the PCI IDs of the Data Fabric devices, but this will be + * an ever expanding list. Instead, match on the SMCA and Zen features to cover all + * relevant systems. + */ +static const struct x86_cpu_id amd_atl_cpuids[] = { + X86_MATCH_FEATURE(X86_FEATURE_SMCA, NULL), + X86_MATCH_FEATURE(X86_FEATURE_ZEN, NULL), + { } +}; +MODULE_DEVICE_TABLE(x86cpu, amd_atl_cpuids); + +static int __init amd_atl_init(void) +{ + if (!x86_match_cpu(amd_atl_cpuids)) + return -ENODEV; + + if (!amd_nb_num()) + return -ENODEV; + + check_for_legacy_df_access(); + + if (get_df_system_info()) + return -ENODEV; + + /* Increment this module's recount so that it can't be easily unloaded. */ + __module_get(THIS_MODULE); + amd_atl_register_decoder(convert_umc_mca_addr_to_sys_addr); + + pr_info("AMD Address Translation Library initialized"); + return 0; +} + +/* + * Exit function is only needed for testing and debug. Module unload must be + * forced to override refcount check. + */ +static void __exit amd_atl_exit(void) +{ + amd_atl_unregister_decoder(); +} + +module_init(amd_atl_init); +module_exit(amd_atl_exit); + +MODULE_LICENSE("GPL"); diff --git a/drivers/ras/amd/atl/dehash.c b/drivers/ras/amd/atl/dehash.c new file mode 100644 index 000000000000..4ea46262c4f5 --- /dev/null +++ b/drivers/ras/amd/atl/dehash.c @@ -0,0 +1,500 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * dehash.c : Functions to account for hashing bits + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +/* + * Verify the interleave bits are correct in the different interleaving + * settings. + * + * If @num_intlv_dies and/or @num_intlv_sockets are 1, it means the + * respective interleaving is disabled. + */ +static inline bool map_bits_valid(struct addr_ctx *ctx, u8 bit1, u8 bit2, + u8 num_intlv_dies, u8 num_intlv_sockets) +{ + if (!(ctx->map.intlv_bit_pos == bit1 || ctx->map.intlv_bit_pos == bit2)) { + pr_debug("Invalid interleave bit: %u", ctx->map.intlv_bit_pos); + return false; + } + + if (ctx->map.num_intlv_dies > num_intlv_dies) { + pr_debug("Invalid number of interleave dies: %u", ctx->map.num_intlv_dies); + return false; + } + + if (ctx->map.num_intlv_sockets > num_intlv_sockets) { + pr_debug("Invalid number of interleave sockets: %u", ctx->map.num_intlv_sockets); + return false; + } + + return true; +} + +static int df2_dehash_addr(struct addr_ctx *ctx) +{ + u8 hashed_bit, intlv_bit, intlv_bit_pos; + + if (!map_bits_valid(ctx, 8, 9, 1, 1)) + return -EINVAL; + + intlv_bit_pos = ctx->map.intlv_bit_pos; + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(12), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr); + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + return 0; +} + +static int df3_dehash_addr(struct addr_ctx *ctx) +{ + bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G; + u8 hashed_bit, intlv_bit, intlv_bit_pos; + + if (!map_bits_valid(ctx, 8, 9, 1, 1)) + return -EINVAL; + + hash_ctl_64k = FIELD_GET(DF3_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF3_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF3_HASH_CTL_1G, ctx->map.ctl); + + intlv_bit_pos = ctx->map.intlv_bit_pos; + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(14), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + /* Calculation complete for 2 channels. Continue for 4 and 8 channels. */ + if (ctx->map.intlv_mode == DF3_COD4_2CHAN_HASH) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(12), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(12); + + /* Calculation complete for 4 channels. Continue for 8 channels. */ + if (ctx->map.intlv_mode == DF3_COD2_4CHAN_HASH) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(13), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(13); + + return 0; +} + +static int df3_6chan_dehash_addr(struct addr_ctx *ctx) +{ + u8 intlv_bit_pos = ctx->map.intlv_bit_pos; + u8 hashed_bit, intlv_bit, num_intlv_bits; + bool hash_ctl_2M, hash_ctl_1G; + + if (ctx->map.intlv_mode != DF3_6CHAN) { + atl_debug_on_bad_intlv_mode(ctx); + return -EINVAL; + } + + num_intlv_bits = ilog2(ctx->map.num_intlv_chan) + 1; + + hash_ctl_2M = FIELD_GET(DF3_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF3_HASH_CTL_1G, ctx->map.ctl); + + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= !!(BIT_ULL(intlv_bit_pos + num_intlv_bits) & ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + intlv_bit_pos++; + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + intlv_bit_pos++; + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + return 0; +} + +static int df4_dehash_addr(struct addr_ctx *ctx) +{ + bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G; + u8 hashed_bit, intlv_bit; + + if (!map_bits_valid(ctx, 8, 8, 1, 2)) + return -EINVAL; + + hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl); + + intlv_bit = FIELD_GET(BIT_ULL(8), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + + if (ctx->map.num_intlv_sockets == 1) + hashed_bit ^= FIELD_GET(BIT_ULL(14), ctx->ret_addr); + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(8); + + /* + * Hashing is possible with socket interleaving, so check the total number + * of channels in the system rather than DRAM map interleaving mode. + * + * Calculation complete for 2 channels. Continue for 4, 8, and 16 channels. + */ + if (ctx->map.total_intlv_chan <= 2) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(12), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(12); + + /* Calculation complete for 4 channels. Continue for 8 and 16 channels. */ + if (ctx->map.total_intlv_chan <= 4) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(13), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(13); + + /* Calculation complete for 8 channels. Continue for 16 channels. */ + if (ctx->map.total_intlv_chan <= 8) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(14), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(19), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(24), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(33), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(14); + + return 0; +} + +static int df4p5_dehash_addr(struct addr_ctx *ctx) +{ + bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G, hash_ctl_1T; + u8 hashed_bit, intlv_bit; + u64 rehash_vector; + + if (!map_bits_valid(ctx, 8, 8, 1, 2)) + return -EINVAL; + + hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl); + hash_ctl_1T = FIELD_GET(DF4p5_HASH_CTL_1T, ctx->map.ctl); + + /* + * Generate a unique address to determine which bits + * need to be dehashed. + * + * Start with a contiguous bitmask for the total + * number of channels starting at bit 8. + * + * Then make a gap in the proper place based on + * interleave mode. + */ + rehash_vector = ctx->map.total_intlv_chan - 1; + rehash_vector <<= 8; + + if (ctx->map.intlv_mode == DF4p5_NPS2_4CHAN_1K_HASH || + ctx->map.intlv_mode == DF4p5_NPS1_8CHAN_1K_HASH || + ctx->map.intlv_mode == DF4p5_NPS1_16CHAN_1K_HASH) + rehash_vector = expand_bits(10, 2, rehash_vector); + else + rehash_vector = expand_bits(9, 3, rehash_vector); + + if (rehash_vector & BIT_ULL(8)) { + intlv_bit = FIELD_GET(BIT_ULL(8), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(40), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(8); + } + + if (rehash_vector & BIT_ULL(9)) { + intlv_bit = FIELD_GET(BIT_ULL(9), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(41), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(9); + } + + if (rehash_vector & BIT_ULL(12)) { + intlv_bit = FIELD_GET(BIT_ULL(12), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(42), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(12); + } + + if (rehash_vector & BIT_ULL(13)) { + intlv_bit = FIELD_GET(BIT_ULL(13), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(19), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(24), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(33), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(43), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(13); + } + + if (rehash_vector & BIT_ULL(14)) { + intlv_bit = FIELD_GET(BIT_ULL(14), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(20), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(25), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(34), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(44), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(14); + } + + return 0; +} + +/* + * MI300 hash bits + * 4K 64K 2M 1G 1T 1T + * COH_ST_Select[0] = XOR of addr{8, 12, 15, 22, 29, 36, 43} + * COH_ST_Select[1] = XOR of addr{9, 13, 16, 23, 30, 37, 44} + * COH_ST_Select[2] = XOR of addr{10, 14, 17, 24, 31, 38, 45} + * COH_ST_Select[3] = XOR of addr{11, 18, 25, 32, 39, 46} + * COH_ST_Select[4] = XOR of addr{14, 19, 26, 33, 40, 47} aka Stack + * DieID[0] = XOR of addr{12, 20, 27, 34, 41 } + * DieID[1] = XOR of addr{13, 21, 28, 35, 42 } + */ +static int mi300_dehash_addr(struct addr_ctx *ctx) +{ + bool hash_ctl_4k, hash_ctl_64k, hash_ctl_2M, hash_ctl_1G, hash_ctl_1T; + bool hashed_bit, intlv_bit, test_bit; + u8 num_intlv_bits, base_bit, i; + + if (!map_bits_valid(ctx, 8, 8, 4, 1)) + return -EINVAL; + + hash_ctl_4k = FIELD_GET(DF4p5_HASH_CTL_4K, ctx->map.ctl); + hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl); + hash_ctl_1T = FIELD_GET(DF4p5_HASH_CTL_1T, ctx->map.ctl); + + /* Channel bits */ + num_intlv_bits = ilog2(ctx->map.num_intlv_chan); + + for (i = 0; i < num_intlv_bits; i++) { + base_bit = 8 + i; + + /* COH_ST_Select[4] jumps to a base bit of 14. */ + if (i == 4) + base_bit = 14; + + intlv_bit = BIT_ULL(base_bit) & ctx->ret_addr; + + hashed_bit = intlv_bit; + + /* 4k hash bit only applies to the first 3 bits. */ + if (i <= 2) { + test_bit = BIT_ULL(12 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_4k; + } + + /* Use temporary 'test_bit' value to avoid Sparse warnings. */ + test_bit = BIT_ULL(15 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_64k; + test_bit = BIT_ULL(22 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_2M; + test_bit = BIT_ULL(29 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1G; + test_bit = BIT_ULL(36 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1T; + test_bit = BIT_ULL(43 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(base_bit); + } + + /* Die bits */ + num_intlv_bits = ilog2(ctx->map.num_intlv_dies); + + for (i = 0; i < num_intlv_bits; i++) { + base_bit = 12 + i; + + intlv_bit = BIT_ULL(base_bit) & ctx->ret_addr; + + hashed_bit = intlv_bit; + + test_bit = BIT_ULL(20 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_64k; + test_bit = BIT_ULL(27 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_2M; + test_bit = BIT_ULL(34 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1G; + test_bit = BIT_ULL(41 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(base_bit); + } + + return 0; +} + +int dehash_address(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + /* No hashing cases. */ + case NONE: + case NOHASH_2CHAN: + case NOHASH_4CHAN: + case NOHASH_8CHAN: + case NOHASH_16CHAN: + case NOHASH_32CHAN: + /* Hashing bits handled earlier during CS ID calculation. */ + case DF4_NPS4_3CHAN_HASH: + case DF4_NPS2_5CHAN_HASH: + case DF4_NPS2_6CHAN_HASH: + case DF4_NPS1_10CHAN_HASH: + case DF4_NPS1_12CHAN_HASH: + case DF4p5_NPS2_6CHAN_1K_HASH: + case DF4p5_NPS2_6CHAN_2K_HASH: + case DF4p5_NPS1_10CHAN_1K_HASH: + case DF4p5_NPS1_10CHAN_2K_HASH: + case DF4p5_NPS1_12CHAN_1K_HASH: + case DF4p5_NPS1_12CHAN_2K_HASH: + case DF4p5_NPS0_24CHAN_1K_HASH: + case DF4p5_NPS0_24CHAN_2K_HASH: + /* No hash physical address bits, so nothing to do. */ + case DF4p5_NPS4_3CHAN_1K_HASH: + case DF4p5_NPS4_3CHAN_2K_HASH: + case DF4p5_NPS2_5CHAN_1K_HASH: + case DF4p5_NPS2_5CHAN_2K_HASH: + return 0; + + case DF2_2CHAN_HASH: + return df2_dehash_addr(ctx); + + case DF3_COD4_2CHAN_HASH: + case DF3_COD2_4CHAN_HASH: + case DF3_COD1_8CHAN_HASH: + return df3_dehash_addr(ctx); + + case DF3_6CHAN: + return df3_6chan_dehash_addr(ctx); + + case DF4_NPS4_2CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + return df4_dehash_addr(ctx); + + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + case DF4p5_NPS1_16CHAN_1K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return df4p5_dehash_addr(ctx); + + case MI3_HASH_8CHAN: + case MI3_HASH_16CHAN: + case MI3_HASH_32CHAN: + return mi300_dehash_addr(ctx); + + default: + atl_debug_on_bad_intlv_mode(ctx); + return -EINVAL; + } +} diff --git a/drivers/ras/amd/atl/denormalize.c b/drivers/ras/amd/atl/denormalize.c new file mode 100644 index 000000000000..e279224288d6 --- /dev/null +++ b/drivers/ras/amd/atl/denormalize.c @@ -0,0 +1,718 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * denormalize.c : Functions to account for interleaving bits + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +/* + * Returns the Destination Fabric ID. This is the first (lowest) + * COH_ST Fabric ID used within a DRAM Address map. + */ +static u16 get_dst_fabric_id(struct addr_ctx *ctx) +{ + switch (df_cfg.rev) { + case DF2: return FIELD_GET(DF2_DST_FABRIC_ID, ctx->map.limit); + case DF3: return FIELD_GET(DF3_DST_FABRIC_ID, ctx->map.limit); + case DF3p5: return FIELD_GET(DF3p5_DST_FABRIC_ID, ctx->map.limit); + case DF4: return FIELD_GET(DF4_DST_FABRIC_ID, ctx->map.ctl); + case DF4p5: return FIELD_GET(DF4p5_DST_FABRIC_ID, ctx->map.ctl); + default: + atl_debug_on_bad_df_rev(); + return 0; + } +} + +/* + * Make a contiguous gap in address for N bits starting at bit P. + * + * Example: + * address bits: [20:0] + * # of interleave bits (n): 3 + * starting interleave bit (p): 8 + * + * expanded address bits: [20+n : n+p][n+p-1 : p][p-1 : 0] + * [23 : 11][10 : 8][7 : 0] + */ +static u64 make_space_for_coh_st_id_at_intlv_bit(struct addr_ctx *ctx) +{ + return expand_bits(ctx->map.intlv_bit_pos, + ctx->map.total_intlv_bits, + ctx->ret_addr); +} + +/* + * Make two gaps in address for N bits. + * First gap is a single bit at bit P. + * Second gap is the remaining N-1 bits at bit 12. + * + * Example: + * address bits: [20:0] + * # of interleave bits (n): 3 + * starting interleave bit (p): 8 + * + * First gap + * expanded address bits: [20+1 : p+1][p][p-1 : 0] + * [21 : 9][8][7 : 0] + * + * Second gap uses result from first. + * r = n - 1; remaining interleave bits + * expanded address bits: [21+r : 12+r][12+r-1: 12][11 : 0] + * [23 : 14][13 : 12][11 : 0] + */ +static u64 make_space_for_coh_st_id_split_2_1(struct addr_ctx *ctx) +{ + /* Make a single space at the interleave bit. */ + u64 denorm_addr = expand_bits(ctx->map.intlv_bit_pos, 1, ctx->ret_addr); + + /* Done if there's only a single interleave bit. */ + if (ctx->map.total_intlv_bits <= 1) + return denorm_addr; + + /* Make spaces for the remaining interleave bits starting at bit 12. */ + return expand_bits(12, ctx->map.total_intlv_bits - 1, denorm_addr); +} + +/* + * Make space for CS ID at bits [14:8] as follows: + * + * 8 channels -> bits [10:8] + * 16 channels -> bits [11:8] + * 32 channels -> bits [14,11:8] + * + * 1 die -> N/A + * 2 dies -> bit [12] + * 4 dies -> bits [13:12] + */ +static u64 make_space_for_coh_st_id_mi300(struct addr_ctx *ctx) +{ + u8 num_intlv_bits = ilog2(ctx->map.num_intlv_chan); + u64 denorm_addr; + + if (ctx->map.intlv_bit_pos != 8) { + pr_debug("Invalid interleave bit: %u", ctx->map.intlv_bit_pos); + return ~0ULL; + } + + /* Channel bits. Covers up to 4 bits at [11:8]. */ + denorm_addr = expand_bits(8, min(num_intlv_bits, 4), ctx->ret_addr); + + /* Die bits. Always starts at [12]. */ + denorm_addr = expand_bits(12, ilog2(ctx->map.num_intlv_dies), denorm_addr); + + /* Additional channel bit at [14]. */ + if (num_intlv_bits > 4) + denorm_addr = expand_bits(14, 1, denorm_addr); + + return denorm_addr; +} + +/* + * Take the current calculated address and shift enough bits in the middle + * to make a gap where the interleave bits will be inserted. + */ +static u64 make_space_for_coh_st_id(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + case NOHASH_2CHAN: + case NOHASH_4CHAN: + case NOHASH_8CHAN: + case NOHASH_16CHAN: + case NOHASH_32CHAN: + case DF2_2CHAN_HASH: + return make_space_for_coh_st_id_at_intlv_bit(ctx); + + case DF3_COD4_2CHAN_HASH: + case DF3_COD2_4CHAN_HASH: + case DF3_COD1_8CHAN_HASH: + case DF4_NPS4_2CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return make_space_for_coh_st_id_split_2_1(ctx); + + case MI3_HASH_8CHAN: + case MI3_HASH_16CHAN: + case MI3_HASH_32CHAN: + return make_space_for_coh_st_id_mi300(ctx); + + default: + atl_debug_on_bad_intlv_mode(ctx); + return ~0ULL; + } +} + +static u16 get_coh_st_id_df2(struct addr_ctx *ctx) +{ + u8 num_socket_intlv_bits = ilog2(ctx->map.num_intlv_sockets); + u8 num_die_intlv_bits = ilog2(ctx->map.num_intlv_dies); + u8 num_intlv_bits; + u16 coh_st_id, mask; + + coh_st_id = ctx->coh_st_fabric_id - get_dst_fabric_id(ctx); + + /* Channel interleave bits */ + num_intlv_bits = order_base_2(ctx->map.num_intlv_chan); + mask = GENMASK(num_intlv_bits - 1, 0); + coh_st_id &= mask; + + /* Die interleave bits */ + if (num_die_intlv_bits) { + u16 die_bits; + + mask = GENMASK(num_die_intlv_bits - 1, 0); + die_bits = ctx->coh_st_fabric_id & df_cfg.die_id_mask; + die_bits >>= df_cfg.die_id_shift; + + coh_st_id |= (die_bits & mask) << num_intlv_bits; + num_intlv_bits += num_die_intlv_bits; + } + + /* Socket interleave bits */ + if (num_socket_intlv_bits) { + u16 socket_bits; + + mask = GENMASK(num_socket_intlv_bits - 1, 0); + socket_bits = ctx->coh_st_fabric_id & df_cfg.socket_id_mask; + socket_bits >>= df_cfg.socket_id_shift; + + coh_st_id |= (socket_bits & mask) << num_intlv_bits; + } + + return coh_st_id; +} + +static u16 get_coh_st_id_df4(struct addr_ctx *ctx) +{ + /* + * Start with the original component mask and the number of interleave + * bits for the channels in this map. + */ + u8 num_intlv_bits = ilog2(ctx->map.num_intlv_chan); + u16 mask = df_cfg.component_id_mask; + + u16 socket_bits; + + /* Set the derived Coherent Station ID to the input Coherent Station Fabric ID. */ + u16 coh_st_id = ctx->coh_st_fabric_id & mask; + + /* + * Subtract the "base" Destination Fabric ID. + * This accounts for systems with disabled Coherent Stations. + */ + coh_st_id -= get_dst_fabric_id(ctx) & mask; + + /* + * Generate and use a new mask based on the number of bits + * needed for channel interleaving in this map. + */ + mask = GENMASK(num_intlv_bits - 1, 0); + coh_st_id &= mask; + + /* Done if socket interleaving is not enabled. */ + if (ctx->map.num_intlv_sockets <= 1) + return coh_st_id; + + /* + * Figure out how many bits are needed for the number of + * interleaved sockets. And shift the derived Coherent Station ID to account + * for these. + */ + num_intlv_bits = ilog2(ctx->map.num_intlv_sockets); + coh_st_id <<= num_intlv_bits; + + /* Generate a new mask for the socket interleaving bits. */ + mask = GENMASK(num_intlv_bits - 1, 0); + + /* Get the socket interleave bits from the original Coherent Station Fabric ID. */ + socket_bits = (ctx->coh_st_fabric_id & df_cfg.socket_id_mask) >> df_cfg.socket_id_shift; + + /* Apply the appropriate socket bits to the derived Coherent Station ID. */ + coh_st_id |= socket_bits & mask; + + return coh_st_id; +} + +/* + * MI300 hash has: + * (C)hannel[3:0] = coh_st_id[3:0] + * (S)tack[0] = coh_st_id[4] + * (D)ie[1:0] = coh_st_id[6:5] + * + * Hashed coh_st_id is swizzled so that Stack bit is at the end. + * coh_st_id = SDDCCCC + */ +static u16 get_coh_st_id_mi300(struct addr_ctx *ctx) +{ + u8 channel_bits, die_bits, stack_bit; + u16 die_id; + + /* Subtract the "base" Destination Fabric ID. */ + ctx->coh_st_fabric_id -= get_dst_fabric_id(ctx); + + die_id = (ctx->coh_st_fabric_id & df_cfg.die_id_mask) >> df_cfg.die_id_shift; + + channel_bits = FIELD_GET(GENMASK(3, 0), ctx->coh_st_fabric_id); + stack_bit = FIELD_GET(BIT(4), ctx->coh_st_fabric_id) << 6; + die_bits = die_id << 4; + + return stack_bit | die_bits | channel_bits; +} + +/* + * Derive the correct Coherent Station ID that represents the interleave bits + * used within the system physical address. This accounts for the + * interleave mode, number of interleaved channels/dies/sockets, and + * other system/mode-specific bit swizzling. + * + * Returns: Coherent Station ID on success. + * All bits set on error. + */ +static u16 calculate_coh_st_id(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + case NOHASH_2CHAN: + case NOHASH_4CHAN: + case NOHASH_8CHAN: + case NOHASH_16CHAN: + case NOHASH_32CHAN: + case DF3_COD4_2CHAN_HASH: + case DF3_COD2_4CHAN_HASH: + case DF3_COD1_8CHAN_HASH: + case DF2_2CHAN_HASH: + return get_coh_st_id_df2(ctx); + + case DF4_NPS4_2CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return get_coh_st_id_df4(ctx); + + case MI3_HASH_8CHAN: + case MI3_HASH_16CHAN: + case MI3_HASH_32CHAN: + return get_coh_st_id_mi300(ctx); + + /* COH_ST ID is simply the COH_ST Fabric ID adjusted by the Destination Fabric ID. */ + case DF4p5_NPS2_4CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_1K_HASH: + case DF4p5_NPS1_16CHAN_1K_HASH: + return ctx->coh_st_fabric_id - get_dst_fabric_id(ctx); + + default: + atl_debug_on_bad_intlv_mode(ctx); + return ~0; + } +} + +static u64 insert_coh_st_id_at_intlv_bit(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id) +{ + return denorm_addr | (coh_st_id << ctx->map.intlv_bit_pos); +} + +static u64 insert_coh_st_id_split_2_1(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id) +{ + /* Insert coh_st_id[0] at the interleave bit. */ + denorm_addr |= (coh_st_id & BIT(0)) << ctx->map.intlv_bit_pos; + + /* Insert coh_st_id[2:1] at bit 12. */ + denorm_addr |= (coh_st_id & GENMASK(2, 1)) << 11; + + return denorm_addr; +} + +static u64 insert_coh_st_id_split_2_2(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id) +{ + /* Insert coh_st_id[1:0] at bit 8. */ + denorm_addr |= (coh_st_id & GENMASK(1, 0)) << 8; + + /* + * Insert coh_st_id[n:2] at bit 12. 'n' could be 2 or 3. + * Grab both because bit 3 will be clear if unused. + */ + denorm_addr |= (coh_st_id & GENMASK(3, 2)) << 10; + + return denorm_addr; +} + +static u64 insert_coh_st_id(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id) +{ + switch (ctx->map.intlv_mode) { + case NOHASH_2CHAN: + case NOHASH_4CHAN: + case NOHASH_8CHAN: + case NOHASH_16CHAN: + case NOHASH_32CHAN: + case MI3_HASH_8CHAN: + case MI3_HASH_16CHAN: + case MI3_HASH_32CHAN: + case DF2_2CHAN_HASH: + return insert_coh_st_id_at_intlv_bit(ctx, denorm_addr, coh_st_id); + + case DF3_COD4_2CHAN_HASH: + case DF3_COD2_4CHAN_HASH: + case DF3_COD1_8CHAN_HASH: + case DF4_NPS4_2CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return insert_coh_st_id_split_2_1(ctx, denorm_addr, coh_st_id); + + case DF4p5_NPS2_4CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_1K_HASH: + case DF4p5_NPS1_16CHAN_1K_HASH: + return insert_coh_st_id_split_2_2(ctx, denorm_addr, coh_st_id); + + default: + atl_debug_on_bad_intlv_mode(ctx); + return ~0ULL; + } +} + +/* + * MI300 systems have a fixed, hardware-defined physical-to-logical + * Coherent Station mapping. The Remap registers are not used. + */ +static const u16 phy_to_log_coh_st_map_mi300[] = { + 12, 13, 14, 15, + 8, 9, 10, 11, + 4, 5, 6, 7, + 0, 1, 2, 3, + 28, 29, 30, 31, + 24, 25, 26, 27, + 20, 21, 22, 23, + 16, 17, 18, 19, +}; + +static u16 get_logical_coh_st_fabric_id_mi300(struct addr_ctx *ctx) +{ + if (ctx->inst_id >= ARRAY_SIZE(phy_to_log_coh_st_map_mi300)) { + atl_debug(ctx, "Instance ID out of range"); + return ~0; + } + + return phy_to_log_coh_st_map_mi300[ctx->inst_id] | (ctx->node_id << df_cfg.node_id_shift); +} + +static u16 get_logical_coh_st_fabric_id(struct addr_ctx *ctx) +{ + u16 component_id, log_fabric_id; + + /* Start with the physical COH_ST Fabric ID. */ + u16 phys_fabric_id = ctx->coh_st_fabric_id; + + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return get_logical_coh_st_fabric_id_mi300(ctx); + + /* Skip logical ID lookup if remapping is disabled. */ + if (!FIELD_GET(DF4_REMAP_EN, ctx->map.ctl) && + ctx->map.intlv_mode != DF3_6CHAN) + return phys_fabric_id; + + /* Mask off the Node ID bits to get the "local" Component ID. */ + component_id = phys_fabric_id & df_cfg.component_id_mask; + + /* + * Search the list of logical Component IDs for the one that + * matches this physical Component ID. + */ + for (log_fabric_id = 0; log_fabric_id < MAX_COH_ST_CHANNELS; log_fabric_id++) { + if (ctx->map.remap_array[log_fabric_id] == component_id) + break; + } + + if (log_fabric_id == MAX_COH_ST_CHANNELS) + atl_debug(ctx, "COH_ST remap entry not found for 0x%x", + log_fabric_id); + + /* Get the Node ID bits from the physical and apply to the logical. */ + return (phys_fabric_id & df_cfg.node_id_mask) | log_fabric_id; +} + +static int denorm_addr_common(struct addr_ctx *ctx) +{ + u64 denorm_addr; + u16 coh_st_id; + + /* + * Convert the original physical COH_ST Fabric ID to a logical value. + * This is required for non-power-of-two and other interleaving modes. + */ + ctx->coh_st_fabric_id = get_logical_coh_st_fabric_id(ctx); + + denorm_addr = make_space_for_coh_st_id(ctx); + coh_st_id = calculate_coh_st_id(ctx); + ctx->ret_addr = insert_coh_st_id(ctx, denorm_addr, coh_st_id); + return 0; +} + +static int denorm_addr_df3_6chan(struct addr_ctx *ctx) +{ + u16 coh_st_id = ctx->coh_st_fabric_id & df_cfg.component_id_mask; + u8 total_intlv_bits = ctx->map.total_intlv_bits; + u8 low_bit, intlv_bit = ctx->map.intlv_bit_pos; + u64 msb_intlv_bits, temp_addr_a, temp_addr_b; + u8 np2_bits = ctx->map.np2_bits; + + if (ctx->map.intlv_mode != DF3_6CHAN) + return -EINVAL; + + /* + * 'np2_bits' holds the number of bits needed to cover the + * amount of memory (rounded up) in this map using 64K chunks. + * + * Example: + * Total memory in map: 6GB + * Rounded up to next power-of-2: 8GB + * Number of 64K chunks: 0x20000 + * np2_bits = log2(# of chunks): 17 + * + * Get the two most-significant interleave bits from the + * input address based on the following: + * + * [15 + np2_bits - total_intlv_bits : 14 + np2_bits - total_intlv_bits] + */ + low_bit = 14 + np2_bits - total_intlv_bits; + msb_intlv_bits = ctx->ret_addr >> low_bit; + msb_intlv_bits &= 0x3; + + /* + * If MSB are 11b, then logical COH_ST ID is 6 or 7. + * Need to adjust based on the mod3 result. + */ + if (msb_intlv_bits == 3) { + u8 addr_mod, phys_addr_msb, msb_coh_st_id; + + /* Get the remaining interleave bits from the input address. */ + temp_addr_b = GENMASK_ULL(low_bit - 1, intlv_bit) & ctx->ret_addr; + temp_addr_b >>= intlv_bit; + + /* Calculate the logical COH_ST offset based on mod3. */ + addr_mod = temp_addr_b % 3; + + /* Get COH_ST ID bits [2:1]. */ + msb_coh_st_id = (coh_st_id >> 1) & 0x3; + + /* Get the bit that starts the physical address bits. */ + phys_addr_msb = (intlv_bit + np2_bits + 1); + phys_addr_msb &= BIT(0); + phys_addr_msb++; + phys_addr_msb *= 3 - addr_mod + msb_coh_st_id; + phys_addr_msb %= 3; + + /* Move the physical address MSB to the correct place. */ + temp_addr_b |= phys_addr_msb << (low_bit - total_intlv_bits - intlv_bit); + + /* Generate a new COH_ST ID as follows: coh_st_id = [1, 1, coh_st_id[0]] */ + coh_st_id &= BIT(0); + coh_st_id |= GENMASK(2, 1); + } else { + temp_addr_b = GENMASK_ULL(63, intlv_bit) & ctx->ret_addr; + temp_addr_b >>= intlv_bit; + } + + temp_addr_a = GENMASK_ULL(intlv_bit - 1, 0) & ctx->ret_addr; + temp_addr_b <<= intlv_bit + total_intlv_bits; + + ctx->ret_addr = temp_addr_a | temp_addr_b; + ctx->ret_addr |= coh_st_id << intlv_bit; + return 0; +} + +static int denorm_addr_df4_np2(struct addr_ctx *ctx) +{ + bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G; + u16 group, group_offset, log_coh_st_offset; + unsigned int mod_value, shift_value; + u16 mask = df_cfg.component_id_mask; + u64 temp_addr_a, temp_addr_b; + bool hash_pa8, hashed_bit; + + switch (ctx->map.intlv_mode) { + case DF4_NPS4_3CHAN_HASH: + mod_value = 3; + shift_value = 13; + break; + case DF4_NPS2_6CHAN_HASH: + mod_value = 3; + shift_value = 12; + break; + case DF4_NPS1_12CHAN_HASH: + mod_value = 3; + shift_value = 11; + break; + case DF4_NPS2_5CHAN_HASH: + mod_value = 5; + shift_value = 13; + break; + case DF4_NPS1_10CHAN_HASH: + mod_value = 5; + shift_value = 12; + break; + default: + atl_debug_on_bad_intlv_mode(ctx); + return -EINVAL; + }; + + if (ctx->map.num_intlv_sockets == 1) { + hash_pa8 = BIT_ULL(shift_value) & ctx->ret_addr; + temp_addr_a = remove_bits(shift_value, shift_value, ctx->ret_addr); + } else { + hash_pa8 = ctx->coh_st_fabric_id & df_cfg.socket_id_mask; + temp_addr_a = ctx->ret_addr; + } + + /* Make a gap for the real bit [8]. */ + temp_addr_a = expand_bits(8, 1, temp_addr_a); + + /* Make an additional gap for bits [13:12], as appropriate.*/ + if (ctx->map.intlv_mode == DF4_NPS2_6CHAN_HASH || + ctx->map.intlv_mode == DF4_NPS1_10CHAN_HASH) { + temp_addr_a = expand_bits(13, 1, temp_addr_a); + } else if (ctx->map.intlv_mode == DF4_NPS1_12CHAN_HASH) { + temp_addr_a = expand_bits(12, 2, temp_addr_a); + } + + /* Keep bits [13:0]. */ + temp_addr_a &= GENMASK_ULL(13, 0); + + /* Get the appropriate high bits. */ + shift_value += 1 - ilog2(ctx->map.num_intlv_sockets); + temp_addr_b = GENMASK_ULL(63, shift_value) & ctx->ret_addr; + temp_addr_b >>= shift_value; + temp_addr_b *= mod_value; + + /* + * Coherent Stations are divided into groups. + * + * Multiples of 3 (mod3) are divided into quadrants. + * e.g. NP4_3CHAN -> [0, 1, 2] [6, 7, 8] + * [3, 4, 5] [9, 10, 11] + * + * Multiples of 5 (mod5) are divided into sides. + * e.g. NP2_5CHAN -> [0, 1, 2, 3, 4] [5, 6, 7, 8, 9] + */ + + /* + * Calculate the logical offset for the COH_ST within its DRAM Address map. + * e.g. if map includes [5, 6, 7, 8, 9] and target instance is '8', then + * log_coh_st_offset = 8 - 5 = 3 + */ + log_coh_st_offset = (ctx->coh_st_fabric_id & mask) - (get_dst_fabric_id(ctx) & mask); + + /* + * Figure out the group number. + * + * Following above example, + * log_coh_st_offset = 3 + * mod_value = 5 + * group = 3 / 5 = 0 + */ + group = log_coh_st_offset / mod_value; + + /* + * Figure out the offset within the group. + * + * Following above example, + * log_coh_st_offset = 3 + * mod_value = 5 + * group_offset = 3 % 5 = 3 + */ + group_offset = log_coh_st_offset % mod_value; + + /* Adjust group_offset if the hashed bit [8] is set. */ + if (hash_pa8) { + if (!group_offset) + group_offset = mod_value - 1; + else + group_offset--; + } + + /* Add in the group offset to the high bits. */ + temp_addr_b += group_offset; + + /* Shift the high bits to the proper starting position. */ + temp_addr_b <<= 14; + + /* Combine the high and low bits together. */ + ctx->ret_addr = temp_addr_a | temp_addr_b; + + /* Account for hashing here instead of in dehash_address(). */ + hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl); + + hashed_bit = !!hash_pa8; + hashed_bit ^= FIELD_GET(BIT_ULL(14), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + + ctx->ret_addr |= hashed_bit << 8; + + /* Done for 3 and 5 channel. */ + if (ctx->map.intlv_mode == DF4_NPS4_3CHAN_HASH || + ctx->map.intlv_mode == DF4_NPS2_5CHAN_HASH) + return 0; + + /* Select the proper 'group' bit to use for Bit 13. */ + if (ctx->map.intlv_mode == DF4_NPS1_12CHAN_HASH) + hashed_bit = !!(group & BIT(1)); + else + hashed_bit = group & BIT(0); + + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + + ctx->ret_addr |= hashed_bit << 13; + + /* Done for 6 and 10 channel. */ + if (ctx->map.intlv_mode != DF4_NPS1_12CHAN_HASH) + return 0; + + hashed_bit = group & BIT(0); + hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + + ctx->ret_addr |= hashed_bit << 12; + return 0; +} + +int denormalize_address(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + case NONE: + return 0; + case DF4_NPS4_3CHAN_HASH: + case DF4_NPS2_6CHAN_HASH: + case DF4_NPS1_12CHAN_HASH: + case DF4_NPS2_5CHAN_HASH: + case DF4_NPS1_10CHAN_HASH: + return denorm_addr_df4_np2(ctx); + case DF3_6CHAN: + return denorm_addr_df3_6chan(ctx); + default: + return denorm_addr_common(ctx); + } +} diff --git a/drivers/ras/amd/atl/internal.h b/drivers/ras/amd/atl/internal.h new file mode 100644 index 000000000000..5de69e0bb0f9 --- /dev/null +++ b/drivers/ras/amd/atl/internal.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Address Translation Library + * + * internal.h : Helper functions and common defines + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#ifndef __AMD_ATL_INTERNAL_H__ +#define __AMD_ATL_INTERNAL_H__ + +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/ras.h> + +#include <asm/amd_nb.h> + +#include "reg_fields.h" + +/* Maximum possible number of Coherent Stations within a single Data Fabric. */ +#define MAX_COH_ST_CHANNELS 32 + +/* PCI ID for Zen4 Server DF Function 0. */ +#define DF_FUNC0_ID_ZEN4_SERVER 0x14AD1022 + +/* PCI IDs for MI300 DF Function 0. */ +#define DF_FUNC0_ID_MI300 0x15281022 + +/* Shift needed for adjusting register values to true values. */ +#define DF_DRAM_BASE_LIMIT_LSB 28 +#define MI300_DRAM_LIMIT_LSB 20 + +enum df_revisions { + UNKNOWN, + DF2, + DF3, + DF3p5, + DF4, + DF4p5, +}; + +/* These are mapped 1:1 to the hardware values. Special cases are set at > 0x20. */ +enum intlv_modes { + NONE = 0x00, + NOHASH_2CHAN = 0x01, + NOHASH_4CHAN = 0x03, + NOHASH_8CHAN = 0x05, + DF3_6CHAN = 0x06, + NOHASH_16CHAN = 0x07, + NOHASH_32CHAN = 0x08, + DF3_COD4_2CHAN_HASH = 0x0C, + DF3_COD2_4CHAN_HASH = 0x0D, + DF3_COD1_8CHAN_HASH = 0x0E, + DF4_NPS4_2CHAN_HASH = 0x10, + DF4_NPS2_4CHAN_HASH = 0x11, + DF4_NPS1_8CHAN_HASH = 0x12, + DF4_NPS4_3CHAN_HASH = 0x13, + DF4_NPS2_6CHAN_HASH = 0x14, + DF4_NPS1_12CHAN_HASH = 0x15, + DF4_NPS2_5CHAN_HASH = 0x16, + DF4_NPS1_10CHAN_HASH = 0x17, + MI3_HASH_8CHAN = 0x18, + MI3_HASH_16CHAN = 0x19, + MI3_HASH_32CHAN = 0x1A, + DF2_2CHAN_HASH = 0x21, + /* DF4.5 modes are all IntLvNumChan + 0x20 */ + DF4p5_NPS1_16CHAN_1K_HASH = 0x2C, + DF4p5_NPS0_24CHAN_1K_HASH = 0x2E, + DF4p5_NPS4_2CHAN_1K_HASH = 0x30, + DF4p5_NPS2_4CHAN_1K_HASH = 0x31, + DF4p5_NPS1_8CHAN_1K_HASH = 0x32, + DF4p5_NPS4_3CHAN_1K_HASH = 0x33, + DF4p5_NPS2_6CHAN_1K_HASH = 0x34, + DF4p5_NPS1_12CHAN_1K_HASH = 0x35, + DF4p5_NPS2_5CHAN_1K_HASH = 0x36, + DF4p5_NPS1_10CHAN_1K_HASH = 0x37, + DF4p5_NPS4_2CHAN_2K_HASH = 0x40, + DF4p5_NPS2_4CHAN_2K_HASH = 0x41, + DF4p5_NPS1_8CHAN_2K_HASH = 0x42, + DF4p5_NPS1_16CHAN_2K_HASH = 0x43, + DF4p5_NPS4_3CHAN_2K_HASH = 0x44, + DF4p5_NPS2_6CHAN_2K_HASH = 0x45, + DF4p5_NPS1_12CHAN_2K_HASH = 0x46, + DF4p5_NPS0_24CHAN_2K_HASH = 0x47, + DF4p5_NPS2_5CHAN_2K_HASH = 0x48, + DF4p5_NPS1_10CHAN_2K_HASH = 0x49, +}; + +struct df_flags { + __u8 legacy_ficaa : 1, + socket_id_shift_quirk : 1, + heterogeneous : 1, + __reserved_0 : 5; +}; + +struct df_config { + enum df_revisions rev; + + /* + * These masks operate on the 16-bit Coherent Station IDs, + * e.g. Instance, Fabric, Destination, etc. + */ + u16 component_id_mask; + u16 die_id_mask; + u16 node_id_mask; + u16 socket_id_mask; + + /* + * Least-significant bit of Node ID portion of the + * system-wide Coherent Station Fabric ID. + */ + u8 node_id_shift; + + /* + * Least-significant bit of Die portion of the Node ID. + * Adjusted to include the Node ID shift in order to apply + * to the Coherent Station Fabric ID. + */ + u8 die_id_shift; + + /* + * Least-significant bit of Socket portion of the Node ID. + * Adjusted to include the Node ID shift in order to apply + * to the Coherent Station Fabric ID. + */ + u8 socket_id_shift; + + /* Number of DRAM Address maps visible in a Coherent Station. */ + u8 num_coh_st_maps; + + /* Global flags to handle special cases. */ + struct df_flags flags; +}; + +extern struct df_config df_cfg; + +struct dram_addr_map { + /* + * Each DRAM Address Map can operate independently + * in different interleaving modes. + */ + enum intlv_modes intlv_mode; + + /* System-wide number for this address map. */ + u8 num; + + /* Raw register values */ + u32 base; + u32 limit; + u32 ctl; + u32 intlv; + + /* + * Logical to Physical Coherent Station Remapping array + * + * Index: Logical Coherent Station Instance ID + * Value: Physical Coherent Station Instance ID + * + * phys_coh_st_inst_id = remap_array[log_coh_st_inst_id] + */ + u8 remap_array[MAX_COH_ST_CHANNELS]; + + /* + * Number of bits covering DRAM Address map 0 + * when interleaving is non-power-of-2. + * + * Used only for DF3_6CHAN. + */ + u8 np2_bits; + + /* Position of the 'interleave bit'. */ + u8 intlv_bit_pos; + /* Number of channels interleaved in this map. */ + u8 num_intlv_chan; + /* Number of dies interleaved in this map. */ + u8 num_intlv_dies; + /* Number of sockets interleaved in this map. */ + u8 num_intlv_sockets; + /* + * Total number of channels interleaved accounting + * for die and socket interleaving. + */ + u8 total_intlv_chan; + /* Total bits needed to cover 'total_intlv_chan'. */ + u8 total_intlv_bits; +}; + +/* Original input values cached for debug printing. */ +struct addr_ctx_inputs { + u64 norm_addr; + u8 socket_id; + u8 die_id; + u8 coh_st_inst_id; +}; + +struct addr_ctx { + u64 ret_addr; + + struct addr_ctx_inputs inputs; + struct dram_addr_map map; + + /* AMD Node ID calculated from Socket and Die IDs. */ + u8 node_id; + + /* + * Coherent Station Instance ID + * Local ID used within a 'node'. + */ + u16 inst_id; + + /* + * Coherent Station Fabric ID + * System-wide ID that includes 'node' bits. + */ + u16 coh_st_fabric_id; +}; + +int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo); +int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo); + +int get_df_system_info(void); +int determine_node_id(struct addr_ctx *ctx, u8 socket_num, u8 die_num); +int get_addr_hash_mi300(void); + +int get_address_map(struct addr_ctx *ctx); + +int denormalize_address(struct addr_ctx *ctx); +int dehash_address(struct addr_ctx *ctx); + +unsigned long norm_to_sys_addr(u8 socket_id, u8 die_id, u8 coh_st_inst_id, unsigned long addr); +unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err); + +/* + * Make a gap in @data that is @num_bits long starting at @bit_num. + * e.g. data = 11111111'b + * bit_num = 3 + * num_bits = 2 + * result = 1111100111'b + */ +static inline u64 expand_bits(u8 bit_num, u8 num_bits, u64 data) +{ + u64 temp1, temp2; + + if (!num_bits) + return data; + + if (!bit_num) { + WARN_ON_ONCE(num_bits >= BITS_PER_LONG); + return data << num_bits; + } + + WARN_ON_ONCE(bit_num >= BITS_PER_LONG); + + temp1 = data & GENMASK_ULL(bit_num - 1, 0); + + temp2 = data & GENMASK_ULL(63, bit_num); + temp2 <<= num_bits; + + return temp1 | temp2; +} + +/* + * Remove bits in @data between @low_bit and @high_bit inclusive. + * e.g. data = XXXYYZZZ'b + * low_bit = 3 + * high_bit = 4 + * result = XXXZZZ'b + */ +static inline u64 remove_bits(u8 low_bit, u8 high_bit, u64 data) +{ + u64 temp1, temp2; + + WARN_ON_ONCE(high_bit >= BITS_PER_LONG); + WARN_ON_ONCE(low_bit >= BITS_PER_LONG); + WARN_ON_ONCE(low_bit > high_bit); + + if (!low_bit) + return data >> (high_bit++); + + temp1 = GENMASK_ULL(low_bit - 1, 0) & data; + temp2 = GENMASK_ULL(63, high_bit + 1) & data; + temp2 >>= high_bit - low_bit + 1; + + return temp1 | temp2; +} + +#define atl_debug(ctx, fmt, arg...) \ + pr_debug("socket_id=%u die_id=%u coh_st_inst_id=%u norm_addr=0x%016llx: " fmt,\ + (ctx)->inputs.socket_id, (ctx)->inputs.die_id,\ + (ctx)->inputs.coh_st_inst_id, (ctx)->inputs.norm_addr, ##arg) + +static inline void atl_debug_on_bad_df_rev(void) +{ + pr_debug("Unrecognized DF rev: %u", df_cfg.rev); +} + +static inline void atl_debug_on_bad_intlv_mode(struct addr_ctx *ctx) +{ + atl_debug(ctx, "Unrecognized interleave mode: %u", ctx->map.intlv_mode); +} + +#endif /* __AMD_ATL_INTERNAL_H__ */ diff --git a/drivers/ras/amd/atl/map.c b/drivers/ras/amd/atl/map.c new file mode 100644 index 000000000000..8b908e8d7495 --- /dev/null +++ b/drivers/ras/amd/atl/map.c @@ -0,0 +1,682 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * map.c : Functions to read and decode DRAM address maps + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +static int df2_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF2_INTLV_NUM_CHAN, ctx->map.base); + + if (ctx->map.intlv_mode == 8) + ctx->map.intlv_mode = DF2_2CHAN_HASH; + + if (ctx->map.intlv_mode != NONE && + ctx->map.intlv_mode != NOHASH_2CHAN && + ctx->map.intlv_mode != DF2_2CHAN_HASH) + return -EINVAL; + + return 0; +} + +static int df3_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF3_INTLV_NUM_CHAN, ctx->map.base); + return 0; +} + +static int df3p5_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF3p5_INTLV_NUM_CHAN, ctx->map.base); + + if (ctx->map.intlv_mode == DF3_6CHAN) + return -EINVAL; + + return 0; +} + +static int df4_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF4_INTLV_NUM_CHAN, ctx->map.intlv); + + if (ctx->map.intlv_mode == DF3_COD4_2CHAN_HASH || + ctx->map.intlv_mode == DF3_COD2_4CHAN_HASH || + ctx->map.intlv_mode == DF3_COD1_8CHAN_HASH || + ctx->map.intlv_mode == DF3_6CHAN) + return -EINVAL; + + return 0; +} + +static int df4p5_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF4p5_INTLV_NUM_CHAN, ctx->map.intlv); + + if (ctx->map.intlv_mode <= NOHASH_32CHAN) + return 0; + + if (ctx->map.intlv_mode >= MI3_HASH_8CHAN && + ctx->map.intlv_mode <= MI3_HASH_32CHAN) + return 0; + + /* + * Modes matching the ranges above are returned as-is. + * + * All other modes are "fixed up" by adding 20h to make a unique value. + */ + ctx->map.intlv_mode += 0x20; + + return 0; +} + +static int get_intlv_mode(struct addr_ctx *ctx) +{ + int ret; + + switch (df_cfg.rev) { + case DF2: + ret = df2_get_intlv_mode(ctx); + break; + case DF3: + ret = df3_get_intlv_mode(ctx); + break; + case DF3p5: + ret = df3p5_get_intlv_mode(ctx); + break; + case DF4: + ret = df4_get_intlv_mode(ctx); + break; + case DF4p5: + ret = df4p5_get_intlv_mode(ctx); + break; + default: + ret = -EINVAL; + } + + if (ret) + atl_debug_on_bad_df_rev(); + + return ret; +} + +static u64 get_hi_addr_offset(u32 reg_dram_offset) +{ + u8 shift = DF_DRAM_BASE_LIMIT_LSB; + u64 hi_addr_offset; + + switch (df_cfg.rev) { + case DF2: + hi_addr_offset = FIELD_GET(DF2_HI_ADDR_OFFSET, reg_dram_offset); + break; + case DF3: + case DF3p5: + hi_addr_offset = FIELD_GET(DF3_HI_ADDR_OFFSET, reg_dram_offset); + break; + case DF4: + case DF4p5: + hi_addr_offset = FIELD_GET(DF4_HI_ADDR_OFFSET, reg_dram_offset); + break; + default: + hi_addr_offset = 0; + atl_debug_on_bad_df_rev(); + } + + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + shift = MI300_DRAM_LIMIT_LSB; + + return hi_addr_offset << shift; +} + +/* + * Returns: 0 if offset is disabled. + * 1 if offset is enabled. + * -EINVAL on error. + */ +static int get_dram_offset(struct addr_ctx *ctx, u64 *norm_offset) +{ + u32 reg_dram_offset; + u8 map_num; + + /* Should not be called for map 0. */ + if (!ctx->map.num) { + atl_debug(ctx, "Trying to find DRAM offset for map 0"); + return -EINVAL; + } + + /* + * DramOffset registers don't exist for map 0, so the base register + * actually refers to map 1. + * Adjust the map_num for the register offsets. + */ + map_num = ctx->map.num - 1; + + if (df_cfg.rev >= DF4) { + /* Read D18F7x140 (DramOffset) */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x140 + (4 * map_num), + ctx->inst_id, ®_dram_offset)) + return -EINVAL; + + } else { + /* Read D18F0x1B4 (DramOffset) */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x1B4 + (4 * map_num), + ctx->inst_id, ®_dram_offset)) + return -EINVAL; + } + + if (!FIELD_GET(DF_HI_ADDR_OFFSET_EN, reg_dram_offset)) + return 0; + + *norm_offset = get_hi_addr_offset(reg_dram_offset); + + return 1; +} + +static int df3_6ch_get_dram_addr_map(struct addr_ctx *ctx) +{ + u16 dst_fabric_id = FIELD_GET(DF3_DST_FABRIC_ID, ctx->map.limit); + u8 i, j, shift = 4, mask = 0xF; + u32 reg, offset = 0x60; + u16 dst_node_id; + + /* Get Socket 1 register. */ + if (dst_fabric_id & df_cfg.socket_id_mask) + offset = 0x68; + + /* Read D18F0x06{0,8} (DF::Skt0CsTargetRemap0)/(DF::Skt0CsTargetRemap1) */ + if (df_indirect_read_broadcast(ctx->node_id, 0, offset, ®)) + return -EINVAL; + + /* Save 8 remap entries. */ + for (i = 0, j = 0; i < 8; i++, j++) + ctx->map.remap_array[i] = (reg >> (j * shift)) & mask; + + dst_node_id = dst_fabric_id & df_cfg.node_id_mask; + dst_node_id >>= df_cfg.node_id_shift; + + /* Read D18F2x090 (DF::Np2ChannelConfig) */ + if (df_indirect_read_broadcast(dst_node_id, 2, 0x90, ®)) + return -EINVAL; + + ctx->map.np2_bits = FIELD_GET(DF_LOG2_ADDR_64K_SPACE0, reg); + return 0; +} + +static int df2_get_dram_addr_map(struct addr_ctx *ctx) +{ + /* Read D18F0x110 (DramBaseAddress). */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x110 + (8 * ctx->map.num), + ctx->inst_id, &ctx->map.base)) + return -EINVAL; + + /* Read D18F0x114 (DramLimitAddress). */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x114 + (8 * ctx->map.num), + ctx->inst_id, &ctx->map.limit)) + return -EINVAL; + + return 0; +} + +static int df3_get_dram_addr_map(struct addr_ctx *ctx) +{ + if (df2_get_dram_addr_map(ctx)) + return -EINVAL; + + /* Read D18F0x3F8 (DfGlobalCtl). */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x3F8, + ctx->inst_id, &ctx->map.ctl)) + return -EINVAL; + + return 0; +} + +static int df4_get_dram_addr_map(struct addr_ctx *ctx) +{ + u8 remap_sel, i, j, shift = 4, mask = 0xF; + u32 remap_reg; + + /* Read D18F7xE00 (DramBaseAddress). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0xE00 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.base)) + return -EINVAL; + + /* Read D18F7xE04 (DramLimitAddress). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0xE04 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.limit)) + return -EINVAL; + + /* Read D18F7xE08 (DramAddressCtl). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0xE08 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.ctl)) + return -EINVAL; + + /* Read D18F7xE0C (DramAddressIntlv). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0xE0C + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.intlv)) + return -EINVAL; + + /* Check if Remap Enable bit is valid. */ + if (!FIELD_GET(DF4_REMAP_EN, ctx->map.ctl)) + return 0; + + /* Fill with bogus values, because '0' is a valid value. */ + memset(&ctx->map.remap_array, 0xFF, sizeof(ctx->map.remap_array)); + + /* Get Remap registers. */ + remap_sel = FIELD_GET(DF4_REMAP_SEL, ctx->map.ctl); + + /* Read D18F7x180 (CsTargetRemap0A). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x180 + (8 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save first 8 remap entries. */ + for (i = 0, j = 0; i < 8; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + /* Read D18F7x184 (CsTargetRemap0B). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x184 + (8 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save next 8 remap entries. */ + for (i = 8, j = 0; i < 16; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + return 0; +} + +static int df4p5_get_dram_addr_map(struct addr_ctx *ctx) +{ + u8 remap_sel, i, j, shift = 5, mask = 0x1F; + u32 remap_reg; + + /* Read D18F7x200 (DramBaseAddress). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x200 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.base)) + return -EINVAL; + + /* Read D18F7x204 (DramLimitAddress). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x204 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.limit)) + return -EINVAL; + + /* Read D18F7x208 (DramAddressCtl). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x208 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.ctl)) + return -EINVAL; + + /* Read D18F7x20C (DramAddressIntlv). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x20C + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.intlv)) + return -EINVAL; + + /* Check if Remap Enable bit is valid. */ + if (!FIELD_GET(DF4_REMAP_EN, ctx->map.ctl)) + return 0; + + /* Fill with bogus values, because '0' is a valid value. */ + memset(&ctx->map.remap_array, 0xFF, sizeof(ctx->map.remap_array)); + + /* Get Remap registers. */ + remap_sel = FIELD_GET(DF4p5_REMAP_SEL, ctx->map.ctl); + + /* Read D18F7x180 (CsTargetRemap0A). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x180 + (24 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save first 6 remap entries. */ + for (i = 0, j = 0; i < 6; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + /* Read D18F7x184 (CsTargetRemap0B). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x184 + (24 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save next 6 remap entries. */ + for (i = 6, j = 0; i < 12; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + /* Read D18F7x188 (CsTargetRemap0C). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x188 + (24 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save next 6 remap entries. */ + for (i = 12, j = 0; i < 18; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + return 0; +} + +static int get_dram_addr_map(struct addr_ctx *ctx) +{ + switch (df_cfg.rev) { + case DF2: return df2_get_dram_addr_map(ctx); + case DF3: + case DF3p5: return df3_get_dram_addr_map(ctx); + case DF4: return df4_get_dram_addr_map(ctx); + case DF4p5: return df4p5_get_dram_addr_map(ctx); + default: + atl_debug_on_bad_df_rev(); + return -EINVAL; + } +} + +static int get_coh_st_fabric_id(struct addr_ctx *ctx) +{ + u32 reg; + + /* + * On MI300 systems, the Coherent Station Fabric ID is derived + * later. And it does not depend on the register value. + */ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return 0; + + /* Read D18F0x50 (FabricBlockInstanceInformation3). */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x50, ctx->inst_id, ®)) + return -EINVAL; + + if (df_cfg.rev < DF4p5) + ctx->coh_st_fabric_id = FIELD_GET(DF2_COH_ST_FABRIC_ID, reg); + else + ctx->coh_st_fabric_id = FIELD_GET(DF4p5_COH_ST_FABRIC_ID, reg); + + return 0; +} + +static int find_normalized_offset(struct addr_ctx *ctx, u64 *norm_offset) +{ + u64 last_offset = 0; + int ret; + + for (ctx->map.num = 1; ctx->map.num < df_cfg.num_coh_st_maps; ctx->map.num++) { + ret = get_dram_offset(ctx, norm_offset); + if (ret < 0) + return ret; + + /* Continue search if this map's offset is not enabled. */ + if (!ret) + continue; + + /* Enabled offsets should never be 0. */ + if (*norm_offset == 0) { + atl_debug(ctx, "Enabled map %u offset is 0", ctx->map.num); + return -EINVAL; + } + + /* Offsets should always increase from one map to the next. */ + if (*norm_offset <= last_offset) { + atl_debug(ctx, "Map %u offset (0x%016llx) <= previous (0x%016llx)", + ctx->map.num, *norm_offset, last_offset); + return -EINVAL; + } + + /* Match if this map's offset is less than the current calculated address. */ + if (ctx->ret_addr >= *norm_offset) + break; + + last_offset = *norm_offset; + } + + /* + * Finished search without finding a match. + * Reset to map 0 and no offset. + */ + if (ctx->map.num >= df_cfg.num_coh_st_maps) { + ctx->map.num = 0; + *norm_offset = 0; + } + + return 0; +} + +static bool valid_map(struct addr_ctx *ctx) +{ + if (df_cfg.rev >= DF4) + return FIELD_GET(DF_ADDR_RANGE_VAL, ctx->map.ctl); + else + return FIELD_GET(DF_ADDR_RANGE_VAL, ctx->map.base); +} + +static int get_address_map_common(struct addr_ctx *ctx) +{ + u64 norm_offset = 0; + + if (get_coh_st_fabric_id(ctx)) + return -EINVAL; + + if (find_normalized_offset(ctx, &norm_offset)) + return -EINVAL; + + if (get_dram_addr_map(ctx)) + return -EINVAL; + + if (!valid_map(ctx)) + return -EINVAL; + + ctx->ret_addr -= norm_offset; + + return 0; +} + +static u8 get_num_intlv_chan(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + case NONE: + return 1; + case NOHASH_2CHAN: + case DF2_2CHAN_HASH: + case DF3_COD4_2CHAN_HASH: + case DF4_NPS4_2CHAN_HASH: + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + return 2; + case DF4_NPS4_3CHAN_HASH: + case DF4p5_NPS4_3CHAN_1K_HASH: + case DF4p5_NPS4_3CHAN_2K_HASH: + return 3; + case NOHASH_4CHAN: + case DF3_COD2_4CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4p5_NPS2_4CHAN_1K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + return 4; + case DF4_NPS2_5CHAN_HASH: + case DF4p5_NPS2_5CHAN_1K_HASH: + case DF4p5_NPS2_5CHAN_2K_HASH: + return 5; + case DF3_6CHAN: + case DF4_NPS2_6CHAN_HASH: + case DF4p5_NPS2_6CHAN_1K_HASH: + case DF4p5_NPS2_6CHAN_2K_HASH: + return 6; + case NOHASH_8CHAN: + case DF3_COD1_8CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + case MI3_HASH_8CHAN: + case DF4p5_NPS1_8CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + return 8; + case DF4_NPS1_10CHAN_HASH: + case DF4p5_NPS1_10CHAN_1K_HASH: + case DF4p5_NPS1_10CHAN_2K_HASH: + return 10; + case DF4_NPS1_12CHAN_HASH: + case DF4p5_NPS1_12CHAN_1K_HASH: + case DF4p5_NPS1_12CHAN_2K_HASH: + return 12; + case NOHASH_16CHAN: + case MI3_HASH_16CHAN: + case DF4p5_NPS1_16CHAN_1K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return 16; + case DF4p5_NPS0_24CHAN_1K_HASH: + case DF4p5_NPS0_24CHAN_2K_HASH: + return 24; + case NOHASH_32CHAN: + case MI3_HASH_32CHAN: + return 32; + default: + atl_debug_on_bad_intlv_mode(ctx); + return 0; + } +} + +static void calculate_intlv_bits(struct addr_ctx *ctx) +{ + ctx->map.num_intlv_chan = get_num_intlv_chan(ctx); + + ctx->map.total_intlv_chan = ctx->map.num_intlv_chan; + ctx->map.total_intlv_chan *= ctx->map.num_intlv_dies; + ctx->map.total_intlv_chan *= ctx->map.num_intlv_sockets; + + /* + * Get the number of bits needed to cover this many channels. + * order_base_2() rounds up automatically. + */ + ctx->map.total_intlv_bits = order_base_2(ctx->map.total_intlv_chan); +} + +static u8 get_intlv_bit_pos(struct addr_ctx *ctx) +{ + u8 addr_sel = 0; + + switch (df_cfg.rev) { + case DF2: + addr_sel = FIELD_GET(DF2_INTLV_ADDR_SEL, ctx->map.base); + break; + case DF3: + case DF3p5: + addr_sel = FIELD_GET(DF3_INTLV_ADDR_SEL, ctx->map.base); + break; + case DF4: + case DF4p5: + addr_sel = FIELD_GET(DF4_INTLV_ADDR_SEL, ctx->map.intlv); + break; + default: + atl_debug_on_bad_df_rev(); + break; + } + + /* Add '8' to get the 'interleave bit position'. */ + return addr_sel + 8; +} + +static u8 get_num_intlv_dies(struct addr_ctx *ctx) +{ + u8 dies = 0; + + switch (df_cfg.rev) { + case DF2: + dies = FIELD_GET(DF2_INTLV_NUM_DIES, ctx->map.limit); + break; + case DF3: + dies = FIELD_GET(DF3_INTLV_NUM_DIES, ctx->map.base); + break; + case DF3p5: + dies = FIELD_GET(DF3p5_INTLV_NUM_DIES, ctx->map.base); + break; + case DF4: + case DF4p5: + dies = FIELD_GET(DF4_INTLV_NUM_DIES, ctx->map.intlv); + break; + default: + atl_debug_on_bad_df_rev(); + break; + } + + /* Register value is log2, e.g. 0 -> 1 die, 1 -> 2 dies, etc. */ + return 1 << dies; +} + +static u8 get_num_intlv_sockets(struct addr_ctx *ctx) +{ + u8 sockets = 0; + + switch (df_cfg.rev) { + case DF2: + sockets = FIELD_GET(DF2_INTLV_NUM_SOCKETS, ctx->map.limit); + break; + case DF3: + case DF3p5: + sockets = FIELD_GET(DF2_INTLV_NUM_SOCKETS, ctx->map.base); + break; + case DF4: + case DF4p5: + sockets = FIELD_GET(DF4_INTLV_NUM_SOCKETS, ctx->map.intlv); + break; + default: + atl_debug_on_bad_df_rev(); + break; + } + + /* Register value is log2, e.g. 0 -> 1 sockets, 1 -> 2 sockets, etc. */ + return 1 << sockets; +} + +static int get_global_map_data(struct addr_ctx *ctx) +{ + if (get_intlv_mode(ctx)) + return -EINVAL; + + if (ctx->map.intlv_mode == DF3_6CHAN && + df3_6ch_get_dram_addr_map(ctx)) + return -EINVAL; + + ctx->map.intlv_bit_pos = get_intlv_bit_pos(ctx); + ctx->map.num_intlv_dies = get_num_intlv_dies(ctx); + ctx->map.num_intlv_sockets = get_num_intlv_sockets(ctx); + calculate_intlv_bits(ctx); + + return 0; +} + +static void dump_address_map(struct dram_addr_map *map) +{ + u8 i; + + pr_debug("intlv_mode=0x%x", map->intlv_mode); + pr_debug("num=0x%x", map->num); + pr_debug("base=0x%x", map->base); + pr_debug("limit=0x%x", map->limit); + pr_debug("ctl=0x%x", map->ctl); + pr_debug("intlv=0x%x", map->intlv); + + for (i = 0; i < MAX_COH_ST_CHANNELS; i++) + pr_debug("remap_array[%u]=0x%x", i, map->remap_array[i]); + + pr_debug("intlv_bit_pos=%u", map->intlv_bit_pos); + pr_debug("num_intlv_chan=%u", map->num_intlv_chan); + pr_debug("num_intlv_dies=%u", map->num_intlv_dies); + pr_debug("num_intlv_sockets=%u", map->num_intlv_sockets); + pr_debug("total_intlv_chan=%u", map->total_intlv_chan); + pr_debug("total_intlv_bits=%u", map->total_intlv_bits); +} + +int get_address_map(struct addr_ctx *ctx) +{ + int ret; + + ret = get_address_map_common(ctx); + if (ret) + return ret; + + ret = get_global_map_data(ctx); + if (ret) + return ret; + + dump_address_map(&ctx->map); + + return ret; +} diff --git a/drivers/ras/amd/atl/reg_fields.h b/drivers/ras/amd/atl/reg_fields.h new file mode 100644 index 000000000000..9dcdf6e4a856 --- /dev/null +++ b/drivers/ras/amd/atl/reg_fields.h @@ -0,0 +1,606 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Address Translation Library + * + * reg_fields.h : Register field definitions + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +/* + * Notes on naming: + * 1) Use "DF_" prefix for fields that are the same for all revisions. + * 2) Use "DFx_" prefix for fields that differ between revisions. + * a) "x" is the first major revision where the new field appears. + * b) E.g., if DF2 and DF3 have the same field, then call it DF2. + * c) E.g., if DF3p5 and DF4 have the same field, then call it DF4. + */ + +/* + * Coherent Station Fabric ID + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x50 [Fabric Block Instance Information 3] + * DF2 BlockFabricId [19:8] + * DF3 BlockFabricId [19:8] + * DF3p5 BlockFabricId [19:8] + * DF4 BlockFabricId [19:8] + * DF4p5 BlockFabricId [15:8] + */ +#define DF2_COH_ST_FABRIC_ID GENMASK(19, 8) +#define DF4p5_COH_ST_FABRIC_ID GENMASK(15, 8) + +/* + * Component ID Mask + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F1x208 [System Fabric ID Mask 0] + * DF3 ComponentIdMask [9:0] + * + * D18F1x150 [System Fabric ID Mask 0] + * DF3p5 ComponentIdMask [15:0] + * + * D18F4x1B0 [System Fabric ID Mask 0] + * DF4 ComponentIdMask [15:0] + * DF4p5 ComponentIdMask [15:0] + */ +#define DF3_COMPONENT_ID_MASK GENMASK(9, 0) +#define DF4_COMPONENT_ID_MASK GENMASK(15, 0) + +/* + * Destination Fabric ID + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x114 [DRAM Limit Address] + * DF2 DstFabricID [7:0] + * DF3 DstFabricID [9:0] + * DF3 DstFabricID [11:0] + * + * D18F7xE08 [DRAM Address Control] + * DF4 DstFabricID [27:16] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 DstFabricID [23:16] + */ +#define DF2_DST_FABRIC_ID GENMASK(7, 0) +#define DF3_DST_FABRIC_ID GENMASK(9, 0) +#define DF3p5_DST_FABRIC_ID GENMASK(11, 0) +#define DF4_DST_FABRIC_ID GENMASK(27, 16) +#define DF4p5_DST_FABRIC_ID GENMASK(23, 16) + +/* + * Die ID Mask + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F1x208 [System Fabric ID Mask] + * DF2 DieIdMask [15:8] + * + * D18F1x20C [System Fabric ID Mask 1] + * DF3 DieIdMask [18:16] + * + * D18F1x158 [System Fabric ID Mask 2] + * DF3p5 DieIdMask [15:0] + * + * D18F4x1B8 [System Fabric ID Mask 2] + * DF4 DieIdMask [15:0] + * DF4p5 DieIdMask [15:0] + */ +#define DF2_DIE_ID_MASK GENMASK(15, 8) +#define DF3_DIE_ID_MASK GENMASK(18, 16) +#define DF4_DIE_ID_MASK GENMASK(15, 0) + +/* + * Die ID Shift + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F1x208 [System Fabric ID Mask] + * DF2 DieIdShift [27:24] + * + * DF3 N/A + * DF3p5 N/A + * DF4 N/A + * DF4p5 N/A + */ +#define DF2_DIE_ID_SHIFT GENMASK(27, 24) + +/* + * DRAM Address Range Valid + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 AddrRngVal [0] + * DF3 AddrRngVal [0] + * DF3p5 AddrRngVal [0] + * + * D18F7xE08 [DRAM Address Control] + * DF4 AddrRngVal [0] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 AddrRngVal [0] + */ +#define DF_ADDR_RANGE_VAL BIT(0) + +/* + * DRAM Base Address + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 DramBaseAddr [31:12] + * DF3 DramBaseAddr [31:12] + * DF3p5 DramBaseAddr [31:12] + * + * D18F7xE00 [DRAM Base Address] + * DF4 DramBaseAddr [27:0] + * + * D18F7x200 [DRAM Base Address] + * DF4p5 DramBaseAddr [27:0] + */ +#define DF2_BASE_ADDR GENMASK(31, 12) +#define DF4_BASE_ADDR GENMASK(27, 0) + +/* + * DRAM Hole Base + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F0x104 [DRAM Hole Control] + * DF2 DramHoleBase [31:24] + * DF3 DramHoleBase [31:24] + * DF3p5 DramHoleBase [31:24] + * + * D18F7x104 [DRAM Hole Control] + * DF4 DramHoleBase [31:24] + * DF4p5 DramHoleBase [31:24] + */ +#define DF_DRAM_HOLE_BASE_MASK GENMASK(31, 24) + +/* + * DRAM Limit Address + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x114 [DRAM Limit Address] + * DF2 DramLimitAddr [31:12] + * DF3 DramLimitAddr [31:12] + * DF3p5 DramLimitAddr [31:12] + * + * D18F7xE04 [DRAM Limit Address] + * DF4 DramLimitAddr [27:0] + * + * D18F7x204 [DRAM Limit Address] + * DF4p5 DramLimitAddr [27:0] + */ +#define DF2_DRAM_LIMIT_ADDR GENMASK(31, 12) +#define DF4_DRAM_LIMIT_ADDR GENMASK(27, 0) + +/* + * Hash Interleave Controls + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F0x3F8 [DF Global Control] + * DF3 GlbHashIntlvCtl64K [20] + * GlbHashIntlvCtl2M [21] + * GlbHashIntlvCtl1G [22] + * + * DF3p5 GlbHashIntlvCtl64K [20] + * GlbHashIntlvCtl2M [21] + * GlbHashIntlvCtl1G [22] + * + * D18F7xE08 [DRAM Address Control] + * DF4 HashIntlvCtl64K [8] + * HashIntlvCtl2M [9] + * HashIntlvCtl1G [10] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 HashIntlvCtl4K [7] + * HashIntlvCtl64K [8] + * HashIntlvCtl2M [9] + * HashIntlvCtl1G [10] + * HashIntlvCtl1T [15] + */ +#define DF3_HASH_CTL_64K BIT(20) +#define DF3_HASH_CTL_2M BIT(21) +#define DF3_HASH_CTL_1G BIT(22) +#define DF4_HASH_CTL_64K BIT(8) +#define DF4_HASH_CTL_2M BIT(9) +#define DF4_HASH_CTL_1G BIT(10) +#define DF4p5_HASH_CTL_4K BIT(7) +#define DF4p5_HASH_CTL_1T BIT(15) + +/* + * High Address Offset + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x1B4 [DRAM Offset] + * DF2 HiAddrOffset [31:20] + * DF3 HiAddrOffset [31:12] + * DF3p5 HiAddrOffset [31:12] + * + * D18F7x140 [DRAM Offset] + * DF4 HiAddrOffset [24:1] + * DF4p5 HiAddrOffset [24:1] + * MI300 HiAddrOffset [31:1] + */ +#define DF2_HI_ADDR_OFFSET GENMASK(31, 20) +#define DF3_HI_ADDR_OFFSET GENMASK(31, 12) + +/* Follow reference code by including reserved bits for simplicity. */ +#define DF4_HI_ADDR_OFFSET GENMASK(31, 1) + +/* + * High Address Offset Enable + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x1B4 [DRAM Offset] + * DF2 HiAddrOffsetEn [0] + * DF3 HiAddrOffsetEn [0] + * DF3p5 HiAddrOffsetEn [0] + * + * D18F7x140 [DRAM Offset] + * DF4 HiAddrOffsetEn [0] + * DF4p5 HiAddrOffsetEn [0] + */ +#define DF_HI_ADDR_OFFSET_EN BIT(0) + +/* + * Interleave Address Select + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 IntLvAddrSel [10:8] + * DF3 IntLvAddrSel [11:9] + * DF3p5 IntLvAddrSel [11:9] + * + * D18F7xE0C [DRAM Address Interleave] + * DF4 IntLvAddrSel [2:0] + * + * D18F7x20C [DRAM Address Interleave] + * DF4p5 IntLvAddrSel [2:0] + */ +#define DF2_INTLV_ADDR_SEL GENMASK(10, 8) +#define DF3_INTLV_ADDR_SEL GENMASK(11, 9) +#define DF4_INTLV_ADDR_SEL GENMASK(2, 0) + +/* + * Interleave Number of Channels + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 IntLvNumChan [7:4] + * DF3 IntLvNumChan [5:2] + * DF3p5 IntLvNumChan [6:2] + * + * D18F7xE0C [DRAM Address Interleave] + * DF4 IntLvNumChan [8:4] + * + * D18F7x20C [DRAM Address Interleave] + * DF4p5 IntLvNumChan [9:4] + */ +#define DF2_INTLV_NUM_CHAN GENMASK(7, 4) +#define DF3_INTLV_NUM_CHAN GENMASK(5, 2) +#define DF3p5_INTLV_NUM_CHAN GENMASK(6, 2) +#define DF4_INTLV_NUM_CHAN GENMASK(8, 4) +#define DF4p5_INTLV_NUM_CHAN GENMASK(9, 4) + +/* + * Interleave Number of Dies + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x114 [DRAM Limit Address] + * DF2 IntLvNumDies [11:10] + * + * D18F0x110 [DRAM Base Address] + * DF3 IntLvNumDies [7:6] + * DF3p5 IntLvNumDies [7] + * + * D18F7xE0C [DRAM Address Interleave] + * DF4 IntLvNumDies [13:12] + * + * D18F7x20C [DRAM Address Interleave] + * DF4p5 IntLvNumDies [13:12] + */ +#define DF2_INTLV_NUM_DIES GENMASK(11, 10) +#define DF3_INTLV_NUM_DIES GENMASK(7, 6) +#define DF3p5_INTLV_NUM_DIES BIT(7) +#define DF4_INTLV_NUM_DIES GENMASK(13, 12) + +/* + * Interleave Number of Sockets + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x114 [DRAM Limit Address] + * DF2 IntLvNumSockets [8] + * + * D18F0x110 [DRAM Base Address] + * DF3 IntLvNumSockets [8] + * DF3p5 IntLvNumSockets [8] + * + * D18F7xE0C [DRAM Address Interleave] + * DF4 IntLvNumSockets [18] + * + * D18F7x20C [DRAM Address Interleave] + * DF4p5 IntLvNumSockets [18] + */ +#define DF2_INTLV_NUM_SOCKETS BIT(8) +#define DF4_INTLV_NUM_SOCKETS BIT(18) + +/* + * Legacy MMIO Hole Enable + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 LgcyMmioHoleEn [1] + * DF3 LgcyMmioHoleEn [1] + * DF3p5 LgcyMmioHoleEn [1] + * + * D18F7xE08 [DRAM Address Control] + * DF4 LgcyMmioHoleEn [1] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 LgcyMmioHoleEn [1] + */ +#define DF_LEGACY_MMIO_HOLE_EN BIT(1) + +/* + * Log2 Address 64K Space 0 + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F2x90 [Non-power-of-2 channel Configuration Register for COH_ST DRAM Address Maps] + * DF3 Log2Addr64KSpace0 [5:0] + * + * DF3p5 N/A + * DF4 N/A + * DF4p5 N/A + */ +#define DF_LOG2_ADDR_64K_SPACE0 GENMASK(5, 0) + +/* + * Major Revision + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * DF3 N/A + * DF3p5 N/A + * + * D18F0x040 [Fabric Block Instance Count] + * DF4 MajorRevision [27:24] + * DF4p5 MajorRevision [27:24] + */ +#define DF_MAJOR_REVISION GENMASK(27, 24) + +/* + * Minor Revision + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * DF3 N/A + * DF3p5 N/A + * + * D18F0x040 [Fabric Block Instance Count] + * DF4 MinorRevision [23:16] + * DF4p5 MinorRevision [23:16] + */ +#define DF_MINOR_REVISION GENMASK(23, 16) + +/* + * Node ID Mask + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F1x208 [System Fabric ID Mask 0] + * DF3 NodeIdMask [25:16] + * + * D18F1x150 [System Fabric ID Mask 0] + * DF3p5 NodeIdMask [31:16] + * + * D18F4x1B0 [System Fabric ID Mask 0] + * DF4 NodeIdMask [31:16] + * DF4p5 NodeIdMask [31:16] + */ +#define DF3_NODE_ID_MASK GENMASK(25, 16) +#define DF4_NODE_ID_MASK GENMASK(31, 16) + +/* + * Node ID Shift + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F1x20C [System Fabric ID Mask 1] + * DF3 NodeIdShift [3:0] + * + * D18F1x154 [System Fabric ID Mask 1] + * DF3p5 NodeIdShift [3:0] + * + * D18F4x1B4 [System Fabric ID Mask 1] + * DF4 NodeIdShift [3:0] + * DF4p5 NodeIdShift [3:0] + */ +#define DF3_NODE_ID_SHIFT GENMASK(3, 0) + +/* + * Remap Enable + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * DF3 N/A + * DF3p5 N/A + * + * D18F7xE08 [DRAM Address Control] + * DF4 RemapEn [4] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 RemapEn [4] + */ +#define DF4_REMAP_EN BIT(4) + +/* + * Remap Select + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * DF3 N/A + * DF3p5 N/A + * + * D18F7xE08 [DRAM Address Control] + * DF4 RemapSel [7:5] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 RemapSel [6:5] + */ +#define DF4_REMAP_SEL GENMASK(7, 5) +#define DF4p5_REMAP_SEL GENMASK(6, 5) + +/* + * Socket ID Mask + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F1x208 [System Fabric ID Mask] + * DF2 SocketIdMask [23:16] + * + * D18F1x20C [System Fabric ID Mask 1] + * DF3 SocketIdMask [26:24] + * + * D18F1x158 [System Fabric ID Mask 2] + * DF3p5 SocketIdMask [31:16] + * + * D18F4x1B8 [System Fabric ID Mask 2] + * DF4 SocketIdMask [31:16] + * DF4p5 SocketIdMask [31:16] + */ +#define DF2_SOCKET_ID_MASK GENMASK(23, 16) +#define DF3_SOCKET_ID_MASK GENMASK(26, 24) +#define DF4_SOCKET_ID_MASK GENMASK(31, 16) + +/* + * Socket ID Shift + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F1x208 [System Fabric ID Mask] + * DF2 SocketIdShift [31:28] + * + * D18F1x20C [System Fabric ID Mask 1] + * DF3 SocketIdShift [9:8] + * + * D18F1x158 [System Fabric ID Mask 2] + * DF3p5 SocketIdShift [11:8] + * + * D18F4x1B4 [System Fabric ID Mask 1] + * DF4 SocketIdShift [11:8] + * DF4p5 SocketIdShift [11:8] + */ +#define DF2_SOCKET_ID_SHIFT GENMASK(31, 28) +#define DF3_SOCKET_ID_SHIFT GENMASK(9, 8) +#define DF4_SOCKET_ID_SHIFT GENMASK(11, 8) diff --git a/drivers/ras/amd/atl/system.c b/drivers/ras/amd/atl/system.c new file mode 100644 index 000000000000..701349e84942 --- /dev/null +++ b/drivers/ras/amd/atl/system.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * system.c : Functions to read and save system-wide data + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +int determine_node_id(struct addr_ctx *ctx, u8 socket_id, u8 die_id) +{ + u16 socket_id_bits, die_id_bits; + + if (socket_id > 0 && df_cfg.socket_id_mask == 0) { + atl_debug(ctx, "Invalid socket inputs: socket_id=%u socket_id_mask=0x%x", + socket_id, df_cfg.socket_id_mask); + return -EINVAL; + } + + /* Do each step independently to avoid shift out-of-bounds issues. */ + socket_id_bits = socket_id; + socket_id_bits <<= df_cfg.socket_id_shift; + socket_id_bits &= df_cfg.socket_id_mask; + + if (die_id > 0 && df_cfg.die_id_mask == 0) { + atl_debug(ctx, "Invalid die inputs: die_id=%u die_id_mask=0x%x", + die_id, df_cfg.die_id_mask); + return -EINVAL; + } + + /* Do each step independently to avoid shift out-of-bounds issues. */ + die_id_bits = die_id; + die_id_bits <<= df_cfg.die_id_shift; + die_id_bits &= df_cfg.die_id_mask; + + ctx->node_id = (socket_id_bits | die_id_bits) >> df_cfg.node_id_shift; + return 0; +} + +static void df2_get_masks_shifts(u32 mask0) +{ + df_cfg.socket_id_shift = FIELD_GET(DF2_SOCKET_ID_SHIFT, mask0); + df_cfg.socket_id_mask = FIELD_GET(DF2_SOCKET_ID_MASK, mask0); + df_cfg.die_id_shift = FIELD_GET(DF2_DIE_ID_SHIFT, mask0); + df_cfg.die_id_mask = FIELD_GET(DF2_DIE_ID_MASK, mask0); + df_cfg.node_id_shift = df_cfg.die_id_shift; + df_cfg.node_id_mask = df_cfg.socket_id_mask | df_cfg.die_id_mask; + df_cfg.component_id_mask = ~df_cfg.node_id_mask; +} + +static void df3_get_masks_shifts(u32 mask0, u32 mask1) +{ + df_cfg.component_id_mask = FIELD_GET(DF3_COMPONENT_ID_MASK, mask0); + df_cfg.node_id_mask = FIELD_GET(DF3_NODE_ID_MASK, mask0); + + df_cfg.node_id_shift = FIELD_GET(DF3_NODE_ID_SHIFT, mask1); + df_cfg.socket_id_shift = FIELD_GET(DF3_SOCKET_ID_SHIFT, mask1); + df_cfg.socket_id_mask = FIELD_GET(DF3_SOCKET_ID_MASK, mask1); + df_cfg.die_id_mask = FIELD_GET(DF3_DIE_ID_MASK, mask1); +} + +static void df3p5_get_masks_shifts(u32 mask0, u32 mask1, u32 mask2) +{ + df_cfg.component_id_mask = FIELD_GET(DF4_COMPONENT_ID_MASK, mask0); + df_cfg.node_id_mask = FIELD_GET(DF4_NODE_ID_MASK, mask0); + + df_cfg.node_id_shift = FIELD_GET(DF3_NODE_ID_SHIFT, mask1); + df_cfg.socket_id_shift = FIELD_GET(DF4_SOCKET_ID_SHIFT, mask1); + + df_cfg.socket_id_mask = FIELD_GET(DF4_SOCKET_ID_MASK, mask2); + df_cfg.die_id_mask = FIELD_GET(DF4_DIE_ID_MASK, mask2); +} + +static void df4_get_masks_shifts(u32 mask0, u32 mask1, u32 mask2) +{ + df3p5_get_masks_shifts(mask0, mask1, mask2); + + if (!(df_cfg.flags.socket_id_shift_quirk && df_cfg.socket_id_shift == 1)) + return; + + df_cfg.socket_id_shift = 0; + df_cfg.socket_id_mask = 1; + df_cfg.die_id_shift = 0; + df_cfg.die_id_mask = 0; + df_cfg.node_id_shift = 8; + df_cfg.node_id_mask = 0x100; +} + +static int df4_get_fabric_id_mask_registers(void) +{ + u32 mask0, mask1, mask2; + + /* Read D18F4x1B0 (SystemFabricIdMask0) */ + if (df_indirect_read_broadcast(0, 4, 0x1B0, &mask0)) + return -EINVAL; + + /* Read D18F4x1B4 (SystemFabricIdMask1) */ + if (df_indirect_read_broadcast(0, 4, 0x1B4, &mask1)) + return -EINVAL; + + /* Read D18F4x1B8 (SystemFabricIdMask2) */ + if (df_indirect_read_broadcast(0, 4, 0x1B8, &mask2)) + return -EINVAL; + + df4_get_masks_shifts(mask0, mask1, mask2); + return 0; +} + +static int df4_determine_df_rev(u32 reg) +{ + df_cfg.rev = FIELD_GET(DF_MINOR_REVISION, reg) < 5 ? DF4 : DF4p5; + + /* Check for special cases or quirks based on Device/Vendor IDs.*/ + + /* Read D18F0x000 (DeviceVendorId0) */ + if (df_indirect_read_broadcast(0, 0, 0, ®)) + return -EINVAL; + + if (reg == DF_FUNC0_ID_ZEN4_SERVER) + df_cfg.flags.socket_id_shift_quirk = 1; + + if (reg == DF_FUNC0_ID_MI300) { + df_cfg.flags.heterogeneous = 1; + + if (get_addr_hash_mi300()) + return -EINVAL; + } + + return df4_get_fabric_id_mask_registers(); +} + +static int determine_df_rev_legacy(void) +{ + u32 fabric_id_mask0, fabric_id_mask1, fabric_id_mask2; + + /* + * Check for DF3.5. + * + * Component ID Mask must be non-zero. Register D18F1x150 is + * reserved pre-DF3.5, so value will be Read-as-Zero. + */ + + /* Read D18F1x150 (SystemFabricIdMask0). */ + if (df_indirect_read_broadcast(0, 1, 0x150, &fabric_id_mask0)) + return -EINVAL; + + if (FIELD_GET(DF4_COMPONENT_ID_MASK, fabric_id_mask0)) { + df_cfg.rev = DF3p5; + + /* Read D18F1x154 (SystemFabricIdMask1) */ + if (df_indirect_read_broadcast(0, 1, 0x154, &fabric_id_mask1)) + return -EINVAL; + + /* Read D18F1x158 (SystemFabricIdMask2) */ + if (df_indirect_read_broadcast(0, 1, 0x158, &fabric_id_mask2)) + return -EINVAL; + + df3p5_get_masks_shifts(fabric_id_mask0, fabric_id_mask1, fabric_id_mask2); + return 0; + } + + /* + * Check for DF3. + * + * Component ID Mask must be non-zero. Field is Read-as-Zero on DF2. + */ + + /* Read D18F1x208 (SystemFabricIdMask). */ + if (df_indirect_read_broadcast(0, 1, 0x208, &fabric_id_mask0)) + return -EINVAL; + + if (FIELD_GET(DF3_COMPONENT_ID_MASK, fabric_id_mask0)) { + df_cfg.rev = DF3; + + /* Read D18F1x20C (SystemFabricIdMask1) */ + if (df_indirect_read_broadcast(0, 1, 0x20C, &fabric_id_mask1)) + return -EINVAL; + + df3_get_masks_shifts(fabric_id_mask0, fabric_id_mask1); + return 0; + } + + /* Default to DF2. */ + df_cfg.rev = DF2; + df2_get_masks_shifts(fabric_id_mask0); + return 0; +} + +static int determine_df_rev(void) +{ + u32 reg; + u8 rev; + + if (df_cfg.rev != UNKNOWN) + return 0; + + /* Read D18F0x40 (FabricBlockInstanceCount). */ + if (df_indirect_read_broadcast(0, 0, 0x40, ®)) + return -EINVAL; + + /* + * Revision fields added for DF4 and later. + * + * Major revision of '0' is found pre-DF4. Field is Read-as-Zero. + */ + rev = FIELD_GET(DF_MAJOR_REVISION, reg); + if (!rev) + return determine_df_rev_legacy(); + + /* + * Fail out for major revisions other than '4'. + * + * Explicit support should be added for newer systems to avoid issues. + */ + if (rev == 4) + return df4_determine_df_rev(reg); + + return -EINVAL; +} + +static void get_num_maps(void) +{ + switch (df_cfg.rev) { + case DF2: + case DF3: + case DF3p5: + df_cfg.num_coh_st_maps = 2; + break; + case DF4: + case DF4p5: + df_cfg.num_coh_st_maps = 4; + break; + default: + atl_debug_on_bad_df_rev(); + } +} + +static void apply_node_id_shift(void) +{ + if (df_cfg.rev == DF2) + return; + + df_cfg.die_id_shift = df_cfg.node_id_shift; + df_cfg.die_id_mask <<= df_cfg.node_id_shift; + df_cfg.socket_id_mask <<= df_cfg.node_id_shift; + df_cfg.socket_id_shift += df_cfg.node_id_shift; +} + +static void dump_df_cfg(void) +{ + pr_debug("rev=0x%x", df_cfg.rev); + + pr_debug("component_id_mask=0x%x", df_cfg.component_id_mask); + pr_debug("die_id_mask=0x%x", df_cfg.die_id_mask); + pr_debug("node_id_mask=0x%x", df_cfg.node_id_mask); + pr_debug("socket_id_mask=0x%x", df_cfg.socket_id_mask); + + pr_debug("die_id_shift=0x%x", df_cfg.die_id_shift); + pr_debug("node_id_shift=0x%x", df_cfg.node_id_shift); + pr_debug("socket_id_shift=0x%x", df_cfg.socket_id_shift); + + pr_debug("num_coh_st_maps=%u", df_cfg.num_coh_st_maps); + + pr_debug("flags.legacy_ficaa=%u", df_cfg.flags.legacy_ficaa); + pr_debug("flags.socket_id_shift_quirk=%u", df_cfg.flags.socket_id_shift_quirk); +} + +int get_df_system_info(void) +{ + if (determine_df_rev()) { + pr_warn("amd_atl: Failed to determine DF Revision"); + df_cfg.rev = UNKNOWN; + return -EINVAL; + } + + apply_node_id_shift(); + + get_num_maps(); + + dump_df_cfg(); + + return 0; +} diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c new file mode 100644 index 000000000000..59b6169093f7 --- /dev/null +++ b/drivers/ras/amd/atl/umc.c @@ -0,0 +1,341 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * umc.c : Unified Memory Controller (UMC) topology helpers + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +/* + * MI300 has a fixed, model-specific mapping between a UMC instance and + * its related Data Fabric Coherent Station instance. + * + * The MCA_IPID_UMC[InstanceId] field holds a unique identifier for the + * UMC instance within a Node. Use this to find the appropriate Coherent + * Station ID. + * + * Redundant bits were removed from the map below. + */ +static const u16 umc_coh_st_map[32] = { + 0x393, 0x293, 0x193, 0x093, + 0x392, 0x292, 0x192, 0x092, + 0x391, 0x291, 0x191, 0x091, + 0x390, 0x290, 0x190, 0x090, + 0x793, 0x693, 0x593, 0x493, + 0x792, 0x692, 0x592, 0x492, + 0x791, 0x691, 0x591, 0x491, + 0x790, 0x690, 0x590, 0x490, +}; + +#define UMC_ID_MI300 GENMASK(23, 12) +static u8 get_coh_st_inst_id_mi300(struct atl_err *err) +{ + u16 umc_id = FIELD_GET(UMC_ID_MI300, err->ipid); + u8 i; + + for (i = 0; i < ARRAY_SIZE(umc_coh_st_map); i++) { + if (umc_id == umc_coh_st_map[i]) + break; + } + + WARN_ON_ONCE(i >= ARRAY_SIZE(umc_coh_st_map)); + + return i; +} + +/* XOR the bits in @val. */ +static u16 bitwise_xor_bits(u16 val) +{ + u16 tmp = 0; + u8 i; + + for (i = 0; i < 16; i++) + tmp ^= (val >> i) & 0x1; + + return tmp; +} + +struct xor_bits { + bool xor_enable; + u16 col_xor; + u32 row_xor; +}; + +#define NUM_BANK_BITS 4 + +static struct { + /* UMC::CH::AddrHashBank */ + struct xor_bits bank[NUM_BANK_BITS]; + + /* UMC::CH::AddrHashPC */ + struct xor_bits pc; + + /* UMC::CH::AddrHashPC2 */ + u8 bank_xor; +} addr_hash; + +#define MI300_UMC_CH_BASE 0x90000 +#define MI300_ADDR_HASH_BANK0 (MI300_UMC_CH_BASE + 0xC8) +#define MI300_ADDR_HASH_PC (MI300_UMC_CH_BASE + 0xE0) +#define MI300_ADDR_HASH_PC2 (MI300_UMC_CH_BASE + 0xE4) + +#define ADDR_HASH_XOR_EN BIT(0) +#define ADDR_HASH_COL_XOR GENMASK(13, 1) +#define ADDR_HASH_ROW_XOR GENMASK(31, 14) +#define ADDR_HASH_BANK_XOR GENMASK(5, 0) + +/* + * Read UMC::CH::AddrHash{Bank,PC,PC2} registers to get XOR bits used + * for hashing. Do this during module init, since the values will not + * change during run time. + * + * These registers are instantiated for each UMC across each AMD Node. + * However, they should be identically programmed due to the fixed hardware + * design of MI300 systems. So read the values from Node 0 UMC 0 and keep a + * single global structure for simplicity. + */ +int get_addr_hash_mi300(void) +{ + u32 temp; + int ret; + u8 i; + + for (i = 0; i < NUM_BANK_BITS; i++) { + ret = amd_smn_read(0, MI300_ADDR_HASH_BANK0 + (i * 4), &temp); + if (ret) + return ret; + + addr_hash.bank[i].xor_enable = FIELD_GET(ADDR_HASH_XOR_EN, temp); + addr_hash.bank[i].col_xor = FIELD_GET(ADDR_HASH_COL_XOR, temp); + addr_hash.bank[i].row_xor = FIELD_GET(ADDR_HASH_ROW_XOR, temp); + } + + ret = amd_smn_read(0, MI300_ADDR_HASH_PC, &temp); + if (ret) + return ret; + + addr_hash.pc.xor_enable = FIELD_GET(ADDR_HASH_XOR_EN, temp); + addr_hash.pc.col_xor = FIELD_GET(ADDR_HASH_COL_XOR, temp); + addr_hash.pc.row_xor = FIELD_GET(ADDR_HASH_ROW_XOR, temp); + + ret = amd_smn_read(0, MI300_ADDR_HASH_PC2, &temp); + if (ret) + return ret; + + addr_hash.bank_xor = FIELD_GET(ADDR_HASH_BANK_XOR, temp); + + return 0; +} + +/* + * MI300 systems report a DRAM address in MCA_ADDR for DRAM ECC errors. This must + * be converted to the intermediate normalized address (NA) before translating to a + * system physical address. + * + * The DRAM address includes bank, row, and column. Also included are bits for + * pseudochannel (PC) and stack ID (SID). + * + * Abbreviations: (S)tack ID, (P)seudochannel, (R)ow, (B)ank, (C)olumn, (Z)ero + * + * The MCA address format is as follows: + * MCA_ADDR[27:0] = {S[1:0], P[0], R[14:0], B[3:0], C[4:0], Z[0]} + * + * The normalized address format is fixed in hardware and is as follows: + * NA[30:0] = {S[1:0], R[13:0], C4, B[1:0], B[3:2], C[3:2], P, C[1:0], Z[4:0]} + * + * Additionally, the PC and Bank bits may be hashed. This must be accounted for before + * reconstructing the normalized address. + */ +#define MI300_UMC_MCA_COL GENMASK(5, 1) +#define MI300_UMC_MCA_BANK GENMASK(9, 6) +#define MI300_UMC_MCA_ROW GENMASK(24, 10) +#define MI300_UMC_MCA_PC BIT(25) +#define MI300_UMC_MCA_SID GENMASK(27, 26) + +#define MI300_NA_COL_1_0 GENMASK(6, 5) +#define MI300_NA_PC BIT(7) +#define MI300_NA_COL_3_2 GENMASK(9, 8) +#define MI300_NA_BANK_3_2 GENMASK(11, 10) +#define MI300_NA_BANK_1_0 GENMASK(13, 12) +#define MI300_NA_COL_4 BIT(14) +#define MI300_NA_ROW GENMASK(28, 15) +#define MI300_NA_SID GENMASK(30, 29) + +static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr) +{ + u16 i, col, row, bank, pc, sid, temp; + + col = FIELD_GET(MI300_UMC_MCA_COL, addr); + bank = FIELD_GET(MI300_UMC_MCA_BANK, addr); + row = FIELD_GET(MI300_UMC_MCA_ROW, addr); + pc = FIELD_GET(MI300_UMC_MCA_PC, addr); + sid = FIELD_GET(MI300_UMC_MCA_SID, addr); + + /* Calculate hash for each Bank bit. */ + for (i = 0; i < NUM_BANK_BITS; i++) { + if (!addr_hash.bank[i].xor_enable) + continue; + + temp = bitwise_xor_bits(col & addr_hash.bank[i].col_xor); + temp ^= bitwise_xor_bits(row & addr_hash.bank[i].row_xor); + bank ^= temp << i; + } + + /* Calculate hash for PC bit. */ + if (addr_hash.pc.xor_enable) { + /* Bits SID[1:0] act as Bank[6:5] for PC hash, so apply them here. */ + bank |= sid << 5; + + temp = bitwise_xor_bits(col & addr_hash.pc.col_xor); + temp ^= bitwise_xor_bits(row & addr_hash.pc.row_xor); + temp ^= bitwise_xor_bits(bank & addr_hash.bank_xor); + pc ^= temp; + + /* Drop SID bits for the sake of debug printing later. */ + bank &= 0x1F; + } + + /* Reconstruct the normalized address starting with NA[4:0] = 0 */ + addr = 0; + + /* NA[6:5] = Column[1:0] */ + temp = col & 0x3; + addr |= FIELD_PREP(MI300_NA_COL_1_0, temp); + + /* NA[7] = PC */ + addr |= FIELD_PREP(MI300_NA_PC, pc); + + /* NA[9:8] = Column[3:2] */ + temp = (col >> 2) & 0x3; + addr |= FIELD_PREP(MI300_NA_COL_3_2, temp); + + /* NA[11:10] = Bank[3:2] */ + temp = (bank >> 2) & 0x3; + addr |= FIELD_PREP(MI300_NA_BANK_3_2, temp); + + /* NA[13:12] = Bank[1:0] */ + temp = bank & 0x3; + addr |= FIELD_PREP(MI300_NA_BANK_1_0, temp); + + /* NA[14] = Column[4] */ + temp = (col >> 4) & 0x1; + addr |= FIELD_PREP(MI300_NA_COL_4, temp); + + /* NA[28:15] = Row[13:0] */ + addr |= FIELD_PREP(MI300_NA_ROW, row); + + /* NA[30:29] = SID[1:0] */ + addr |= FIELD_PREP(MI300_NA_SID, sid); + + pr_debug("Addr=0x%016lx", addr); + pr_debug("Bank=%u Row=%u Column=%u PC=%u SID=%u", bank, row, col, pc, sid); + + return addr; +} + +/* + * When a DRAM ECC error occurs on MI300 systems, it is recommended to retire + * all memory within that DRAM row. This applies to the memory with a DRAM + * bank. + * + * To find the memory addresses, loop through permutations of the DRAM column + * bits and find the System Physical address of each. The column bits are used + * to calculate the intermediate Normalized address, so all permutations should + * be checked. + * + * See amd_atl::convert_dram_to_norm_addr_mi300() for MI300 address formats. + */ +#define MI300_NUM_COL BIT(HWEIGHT(MI300_UMC_MCA_COL)) +static void retire_row_mi300(struct atl_err *a_err) +{ + unsigned long addr; + struct page *p; + u8 col; + + for (col = 0; col < MI300_NUM_COL; col++) { + a_err->addr &= ~MI300_UMC_MCA_COL; + a_err->addr |= FIELD_PREP(MI300_UMC_MCA_COL, col); + + addr = amd_convert_umc_mca_addr_to_sys_addr(a_err); + if (IS_ERR_VALUE(addr)) + continue; + + addr = PHYS_PFN(addr); + + /* + * Skip invalid or already poisoned pages to avoid unnecessary + * error messages from memory_failure(). + */ + p = pfn_to_online_page(addr); + if (!p) + continue; + + if (PageHWPoison(p)) + continue; + + memory_failure(addr, 0); + } +} + +void amd_retire_dram_row(struct atl_err *a_err) +{ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return retire_row_mi300(a_err); +} +EXPORT_SYMBOL_GPL(amd_retire_dram_row); + +static unsigned long get_addr(unsigned long addr) +{ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return convert_dram_to_norm_addr_mi300(addr); + + return addr; +} + +#define MCA_IPID_INST_ID_HI GENMASK_ULL(47, 44) +static u8 get_die_id(struct atl_err *err) +{ + /* + * AMD Node ID is provided in MCA_IPID[InstanceIdHi], and this + * needs to be divided by 4 to get the internal Die ID. + */ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) { + u8 node_id = FIELD_GET(MCA_IPID_INST_ID_HI, err->ipid); + + return node_id >> 2; + } + + /* + * For CPUs, this is the AMD Node ID modulo the number + * of AMD Nodes per socket. + */ + return topology_amd_node_id(err->cpu) % topology_amd_nodes_per_pkg(); +} + +#define UMC_CHANNEL_NUM GENMASK(31, 20) +static u8 get_coh_st_inst_id(struct atl_err *err) +{ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return get_coh_st_inst_id_mi300(err); + + return FIELD_GET(UMC_CHANNEL_NUM, err->ipid); +} + +unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err) +{ + u8 socket_id = topology_physical_package_id(err->cpu); + u8 coh_st_inst_id = get_coh_st_inst_id(err); + unsigned long addr = get_addr(err->addr); + u8 die_id = get_die_id(err); + + pr_debug("socket_id=0x%x die_id=0x%x coh_st_inst_id=0x%x addr=0x%016lx", + socket_id, die_id, coh_st_inst_id, addr); + + return norm_to_sys_addr(socket_id, die_id, coh_st_inst_id, addr); +} diff --git a/drivers/ras/amd/fmpm.c b/drivers/ras/amd/fmpm.c new file mode 100644 index 000000000000..2f4ac9591c8f --- /dev/null +++ b/drivers/ras/amd/fmpm.c @@ -0,0 +1,1013 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * FRU (Field-Replaceable Unit) Memory Poison Manager + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Authors: + * Naveen Krishna Chatradhi <naveenkrishna.chatradhi@amd.com> + * Muralidhara M K <muralidhara.mk@amd.com> + * Yazen Ghannam <Yazen.Ghannam@amd.com> + * + * Implementation notes, assumptions, and limitations: + * + * - FRU memory poison section and memory poison descriptor definitions are not yet + * included in the UEFI specification. So they are defined here. Afterwards, they + * may be moved to linux/cper.h, if appropriate. + * + * - Platforms based on AMD MI300 systems will be the first to use these structures. + * There are a number of assumptions made here that will need to be generalized + * to support other platforms. + * + * AMD MI300-based platform(s) assumptions: + * - Memory errors are reported through x86 MCA. + * - The entire DRAM row containing a memory error should be retired. + * - There will be (1) FRU memory poison section per CPER. + * - The FRU will be the CPU package (processor socket). + * - The default number of memory poison descriptor entries should be (8). + * - The platform will use ACPI ERST for persistent storage. + * - All FRU records should be saved to persistent storage. Module init will + * fail if any FRU record is not successfully written. + * + * - Boot time memory retirement may occur later than ideal due to dependencies + * on other libraries and drivers. This leaves a gap where bad memory may be + * accessed during early boot stages. + * + * - Enough memory should be pre-allocated for each FRU record to be able to hold + * the expected number of descriptor entries. This, mostly empty, record is + * written to storage during init time. Subsequent writes to the same record + * should allow the Platform to update the stored record in-place. Otherwise, + * if the record is extended, then the Platform may need to perform costly memory + * management operations on the storage. For example, the Platform may spend time + * in Firmware copying and invalidating memory on a relatively slow SPI ROM. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cper.h> +#include <linux/ras.h> +#include <linux/cpu.h> + +#include <acpi/apei.h> + +#include <asm/cpu_device_id.h> +#include <asm/mce.h> + +#include "../debugfs.h" + +#define INVALID_CPU UINT_MAX + +/* Validation Bits */ +#define FMP_VALID_ARCH_TYPE BIT_ULL(0) +#define FMP_VALID_ARCH BIT_ULL(1) +#define FMP_VALID_ID_TYPE BIT_ULL(2) +#define FMP_VALID_ID BIT_ULL(3) +#define FMP_VALID_LIST_ENTRIES BIT_ULL(4) +#define FMP_VALID_LIST BIT_ULL(5) + +/* FRU Architecture Types */ +#define FMP_ARCH_TYPE_X86_CPUID_1_EAX 0 + +/* FRU ID Types */ +#define FMP_ID_TYPE_X86_PPIN 0 + +/* FRU Memory Poison Section */ +struct cper_sec_fru_mem_poison { + u32 checksum; + u64 validation_bits; + u32 fru_arch_type; + u64 fru_arch; + u32 fru_id_type; + u64 fru_id; + u32 nr_entries; +} __packed; + +/* FRU Descriptor ID Types */ +#define FPD_HW_ID_TYPE_MCA_IPID 0 + +/* FRU Descriptor Address Types */ +#define FPD_ADDR_TYPE_MCA_ADDR 0 + +/* Memory Poison Descriptor */ +struct cper_fru_poison_desc { + u64 timestamp; + u32 hw_id_type; + u64 hw_id; + u32 addr_type; + u64 addr; +} __packed; + +/* Collection of headers and sections for easy pointer use. */ +struct fru_rec { + struct cper_record_header hdr; + struct cper_section_descriptor sec_desc; + struct cper_sec_fru_mem_poison fmp; + struct cper_fru_poison_desc entries[]; +} __packed; + +/* + * Pointers to the complete CPER record of each FRU. + * + * Memory allocation will include padded space for descriptor entries. + */ +static struct fru_rec **fru_records; + +/* system physical addresses array */ +static u64 *spa_entries; + +#define INVALID_SPA ~0ULL + +static struct dentry *fmpm_dfs_dir; +static struct dentry *fmpm_dfs_entries; + +#define CPER_CREATOR_FMP \ + GUID_INIT(0xcd5c2993, 0xf4b2, 0x41b2, 0xb5, 0xd4, 0xf9, 0xc3, \ + 0xa0, 0x33, 0x08, 0x75) + +#define CPER_SECTION_TYPE_FMP \ + GUID_INIT(0x5e4706c1, 0x5356, 0x48c6, 0x93, 0x0b, 0x52, 0xf2, \ + 0x12, 0x0a, 0x44, 0x58) + +/** + * DOC: max_nr_entries (byte) + * Maximum number of descriptor entries possible for each FRU. + * + * Values between '1' and '255' are valid. + * No input or '0' will default to FMPM_DEFAULT_MAX_NR_ENTRIES. + */ +static u8 max_nr_entries; +module_param(max_nr_entries, byte, 0644); +MODULE_PARM_DESC(max_nr_entries, + "Maximum number of memory poison descriptor entries per FRU"); + +#define FMPM_DEFAULT_MAX_NR_ENTRIES 8 + +/* Maximum number of FRUs in the system. */ +#define FMPM_MAX_NR_FRU 256 +static unsigned int max_nr_fru; + +/* Total length of record including headers and list of descriptor entries. */ +static size_t max_rec_len; + +/* Total number of SPA entries across all FRUs. */ +static unsigned int spa_nr_entries; + +/* + * Protect the local records cache in fru_records and prevent concurrent + * writes to storage. This is only needed after init once notifier block + * registration is done. + * + * The majority of a record is fixed at module init and will not change + * during run time. The entries within a record will be updated as new + * errors are reported. The mutex should be held whenever the entries are + * accessed during run time. + */ +static DEFINE_MUTEX(fmpm_update_mutex); + +#define for_each_fru(i, rec) \ + for (i = 0; rec = fru_records[i], i < max_nr_fru; i++) + +static inline u32 get_fmp_len(struct fru_rec *rec) +{ + return rec->sec_desc.section_length - sizeof(struct cper_section_descriptor); +} + +static struct fru_rec *get_fru_record(u64 fru_id) +{ + struct fru_rec *rec; + unsigned int i; + + for_each_fru(i, rec) { + if (rec->fmp.fru_id == fru_id) + return rec; + } + + pr_debug("Record not found for FRU 0x%016llx\n", fru_id); + + return NULL; +} + +/* + * Sum up all bytes within the FRU Memory Poison Section including the Memory + * Poison Descriptor entries. + * + * Don't include the old checksum here. It's a u32 value, so summing each of its + * bytes will give the wrong total. + */ +static u32 do_fmp_checksum(struct cper_sec_fru_mem_poison *fmp, u32 len) +{ + u32 checksum = 0; + u8 *buf, *end; + + /* Skip old checksum. */ + buf = (u8 *)fmp + sizeof(u32); + end = buf + len; + + while (buf < end) + checksum += (u8)(*(buf++)); + + return checksum; +} + +static int update_record_on_storage(struct fru_rec *rec) +{ + u32 len, checksum; + int ret; + + /* Calculate a new checksum. */ + len = get_fmp_len(rec); + + /* Get the current total. */ + checksum = do_fmp_checksum(&rec->fmp, len); + + /* Use the complement value. */ + rec->fmp.checksum = -checksum; + + pr_debug("Writing to storage\n"); + + ret = erst_write(&rec->hdr); + if (ret) { + pr_warn("Storage update failed for FRU 0x%016llx\n", rec->fmp.fru_id); + + if (ret == -ENOSPC) + pr_warn("Not enough space on storage\n"); + } + + return ret; +} + +static bool rec_has_valid_entries(struct fru_rec *rec) +{ + if (!(rec->fmp.validation_bits & FMP_VALID_LIST_ENTRIES)) + return false; + + if (!(rec->fmp.validation_bits & FMP_VALID_LIST)) + return false; + + return true; +} + +static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_desc *new) +{ + /* + * Ignore timestamp field. + * The same physical error may be reported multiple times due to stuck bits, etc. + * + * Also, order the checks from most->least likely to fail to shortcut the code. + */ + if (old->addr != new->addr) + return false; + + if (old->hw_id != new->hw_id) + return false; + + if (old->addr_type != new->addr_type) + return false; + + if (old->hw_id_type != new->hw_id_type) + return false; + + return true; +} + +static bool rec_has_fpd(struct fru_rec *rec, struct cper_fru_poison_desc *fpd) +{ + unsigned int i; + + for (i = 0; i < rec->fmp.nr_entries; i++) { + struct cper_fru_poison_desc *fpd_i = &rec->entries[i]; + + if (fpds_equal(fpd_i, fpd)) { + pr_debug("Found duplicate record\n"); + return true; + } + } + + return false; +} + +static void save_spa(struct fru_rec *rec, unsigned int entry, + u64 addr, u64 id, unsigned int cpu) +{ + unsigned int i, fru_idx, spa_entry; + struct atl_err a_err; + unsigned long spa; + + if (entry >= max_nr_entries) { + pr_warn_once("FRU descriptor entry %d out-of-bounds (max: %d)\n", + entry, max_nr_entries); + return; + } + + /* spa_nr_entries is always multiple of max_nr_entries */ + for (i = 0; i < spa_nr_entries; i += max_nr_entries) { + fru_idx = i / max_nr_entries; + if (fru_records[fru_idx] == rec) + break; + } + + if (i >= spa_nr_entries) { + pr_warn_once("FRU record %d not found\n", i); + return; + } + + spa_entry = i + entry; + if (spa_entry >= spa_nr_entries) { + pr_warn_once("spa_entries[] index out-of-bounds\n"); + return; + } + + memset(&a_err, 0, sizeof(struct atl_err)); + + a_err.addr = addr; + a_err.ipid = id; + a_err.cpu = cpu; + + spa = amd_convert_umc_mca_addr_to_sys_addr(&a_err); + if (IS_ERR_VALUE(spa)) { + pr_debug("Failed to get system address\n"); + return; + } + + spa_entries[spa_entry] = spa; + pr_debug("fru_idx: %u, entry: %u, spa_entry: %u, spa: 0x%016llx\n", + fru_idx, entry, spa_entry, spa_entries[spa_entry]); +} + +static void update_fru_record(struct fru_rec *rec, struct mce *m) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + struct cper_fru_poison_desc fpd, *fpd_dest; + u32 entry = 0; + + mutex_lock(&fmpm_update_mutex); + + memset(&fpd, 0, sizeof(struct cper_fru_poison_desc)); + + fpd.timestamp = m->time; + fpd.hw_id_type = FPD_HW_ID_TYPE_MCA_IPID; + fpd.hw_id = m->ipid; + fpd.addr_type = FPD_ADDR_TYPE_MCA_ADDR; + fpd.addr = m->addr; + + /* This is the first entry, so just save it. */ + if (!rec_has_valid_entries(rec)) + goto save_fpd; + + /* Ignore already recorded errors. */ + if (rec_has_fpd(rec, &fpd)) + goto out_unlock; + + if (rec->fmp.nr_entries >= max_nr_entries) { + pr_warn("Exceeded number of entries for FRU 0x%016llx\n", rec->fmp.fru_id); + goto out_unlock; + } + + entry = fmp->nr_entries; + +save_fpd: + save_spa(rec, entry, m->addr, m->ipid, m->extcpu); + fpd_dest = &rec->entries[entry]; + memcpy(fpd_dest, &fpd, sizeof(struct cper_fru_poison_desc)); + + fmp->nr_entries = entry + 1; + fmp->validation_bits |= FMP_VALID_LIST_ENTRIES; + fmp->validation_bits |= FMP_VALID_LIST; + + pr_debug("Updated FRU 0x%016llx entry #%u\n", fmp->fru_id, entry); + + update_record_on_storage(rec); + +out_unlock: + mutex_unlock(&fmpm_update_mutex); +} + +static void retire_dram_row(u64 addr, u64 id, u32 cpu) +{ + struct atl_err a_err; + + memset(&a_err, 0, sizeof(struct atl_err)); + + a_err.addr = addr; + a_err.ipid = id; + a_err.cpu = cpu; + + amd_retire_dram_row(&a_err); +} + +static int fru_handle_mem_poison(struct notifier_block *nb, unsigned long val, void *data) +{ + struct mce *m = (struct mce *)data; + struct fru_rec *rec; + + if (!mce_is_memory_error(m)) + return NOTIFY_DONE; + + retire_dram_row(m->addr, m->ipid, m->extcpu); + + /* + * An invalid FRU ID should not happen on real errors. But it + * could happen from software error injection, etc. + */ + rec = get_fru_record(m->ppin); + if (!rec) + return NOTIFY_DONE; + + update_fru_record(rec, m); + + return NOTIFY_OK; +} + +static struct notifier_block fru_mem_poison_nb = { + .notifier_call = fru_handle_mem_poison, + .priority = MCE_PRIO_LOWEST, +}; + +static void retire_mem_fmp(struct fru_rec *rec) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + unsigned int i, cpu; + + for (i = 0; i < fmp->nr_entries; i++) { + struct cper_fru_poison_desc *fpd = &rec->entries[i]; + unsigned int err_cpu = INVALID_CPU; + + if (fpd->hw_id_type != FPD_HW_ID_TYPE_MCA_IPID) + continue; + + if (fpd->addr_type != FPD_ADDR_TYPE_MCA_ADDR) + continue; + + cpus_read_lock(); + for_each_online_cpu(cpu) { + if (topology_ppin(cpu) == fmp->fru_id) { + err_cpu = cpu; + break; + } + } + cpus_read_unlock(); + + if (err_cpu == INVALID_CPU) + continue; + + retire_dram_row(fpd->addr, fpd->hw_id, err_cpu); + save_spa(rec, i, fpd->addr, fpd->hw_id, err_cpu); + } +} + +static void retire_mem_records(void) +{ + struct fru_rec *rec; + unsigned int i; + + for_each_fru(i, rec) { + if (!rec_has_valid_entries(rec)) + continue; + + retire_mem_fmp(rec); + } +} + +/* Set the CPER Record Header and CPER Section Descriptor fields. */ +static void set_rec_fields(struct fru_rec *rec) +{ + struct cper_section_descriptor *sec_desc = &rec->sec_desc; + struct cper_record_header *hdr = &rec->hdr; + + memcpy(hdr->signature, CPER_SIG_RECORD, CPER_SIG_SIZE); + hdr->revision = CPER_RECORD_REV; + hdr->signature_end = CPER_SIG_END; + + /* + * Currently, it is assumed that there is one FRU Memory Poison + * section per CPER. But this may change for other implementations. + */ + hdr->section_count = 1; + + /* The logged errors are recoverable. Otherwise, they'd never make it here. */ + hdr->error_severity = CPER_SEV_RECOVERABLE; + + hdr->validation_bits = 0; + hdr->record_length = max_rec_len; + hdr->creator_id = CPER_CREATOR_FMP; + hdr->notification_type = CPER_NOTIFY_MCE; + hdr->record_id = cper_next_record_id(); + hdr->flags = CPER_HW_ERROR_FLAGS_PREVERR; + + sec_desc->section_offset = sizeof(struct cper_record_header); + sec_desc->section_length = max_rec_len - sizeof(struct cper_record_header); + sec_desc->revision = CPER_SEC_REV; + sec_desc->validation_bits = 0; + sec_desc->flags = CPER_SEC_PRIMARY; + sec_desc->section_type = CPER_SECTION_TYPE_FMP; + sec_desc->section_severity = CPER_SEV_RECOVERABLE; +} + +static int save_new_records(void) +{ + DECLARE_BITMAP(new_records, FMPM_MAX_NR_FRU); + struct fru_rec *rec; + unsigned int i; + int ret = 0; + + for_each_fru(i, rec) { + if (rec->hdr.record_length) + continue; + + set_rec_fields(rec); + + ret = update_record_on_storage(rec); + if (ret) + goto out_clear; + + set_bit(i, new_records); + } + + return ret; + +out_clear: + for_each_fru(i, rec) { + if (!test_bit(i, new_records)) + continue; + + erst_clear(rec->hdr.record_id); + } + + return ret; +} + +/* Check that the record matches expected types for the current system.*/ +static bool fmp_is_usable(struct fru_rec *rec) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + u64 cpuid; + + pr_debug("Validation bits: 0x%016llx\n", fmp->validation_bits); + + if (!(fmp->validation_bits & FMP_VALID_ARCH_TYPE)) { + pr_debug("Arch type unknown\n"); + return false; + } + + if (fmp->fru_arch_type != FMP_ARCH_TYPE_X86_CPUID_1_EAX) { + pr_debug("Arch type not 'x86 Family/Model/Stepping'\n"); + return false; + } + + if (!(fmp->validation_bits & FMP_VALID_ARCH)) { + pr_debug("Arch value unknown\n"); + return false; + } + + cpuid = cpuid_eax(1); + if (fmp->fru_arch != cpuid) { + pr_debug("Arch value mismatch: record = 0x%016llx, system = 0x%016llx\n", + fmp->fru_arch, cpuid); + return false; + } + + if (!(fmp->validation_bits & FMP_VALID_ID_TYPE)) { + pr_debug("FRU ID type unknown\n"); + return false; + } + + if (fmp->fru_id_type != FMP_ID_TYPE_X86_PPIN) { + pr_debug("FRU ID type is not 'x86 PPIN'\n"); + return false; + } + + if (!(fmp->validation_bits & FMP_VALID_ID)) { + pr_debug("FRU ID value unknown\n"); + return false; + } + + return true; +} + +static bool fmp_is_valid(struct fru_rec *rec) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + u32 checksum, len; + + len = get_fmp_len(rec); + if (len < sizeof(struct cper_sec_fru_mem_poison)) { + pr_debug("fmp length is too small\n"); + return false; + } + + /* Checksum must sum to zero for the entire section. */ + checksum = do_fmp_checksum(fmp, len) + fmp->checksum; + if (checksum) { + pr_debug("fmp checksum failed: sum = 0x%x\n", checksum); + print_hex_dump_debug("fmp record: ", DUMP_PREFIX_NONE, 16, 1, fmp, len, false); + return false; + } + + if (!fmp_is_usable(rec)) + return false; + + return true; +} + +static struct fru_rec *get_valid_record(struct fru_rec *old) +{ + struct fru_rec *new; + + if (!fmp_is_valid(old)) { + pr_debug("Ignoring invalid record\n"); + return NULL; + } + + new = get_fru_record(old->fmp.fru_id); + if (!new) + pr_debug("Ignoring record for absent FRU\n"); + + return new; +} + +/* + * Fetch saved records from persistent storage. + * + * For each found record: + * - If it was not created by this module, then ignore it. + * - If it is valid, then copy its data to the local cache. + * - If it is not valid, then erase it. + */ +static int get_saved_records(void) +{ + struct fru_rec *old, *new; + u64 record_id; + int ret, pos; + ssize_t len; + + /* + * Assume saved records match current max size. + * + * However, this may not be true depending on module parameters. + */ + old = kmalloc(max_rec_len, GFP_KERNEL); + if (!old) { + ret = -ENOMEM; + goto out; + } + + ret = erst_get_record_id_begin(&pos); + if (ret < 0) + goto out_end; + + while (!erst_get_record_id_next(&pos, &record_id)) { + if (record_id == APEI_ERST_INVALID_RECORD_ID) + goto out_end; + /* + * Make sure to clear temporary buffer between reads to avoid + * leftover data from records of various sizes. + */ + memset(old, 0, max_rec_len); + + len = erst_read_record(record_id, &old->hdr, max_rec_len, + sizeof(struct fru_rec), &CPER_CREATOR_FMP); + if (len < 0) + continue; + + if (len > max_rec_len) { + pr_debug("Found record larger than max_rec_len\n"); + continue; + } + + new = get_valid_record(old); + if (!new) + erst_clear(record_id); + + /* Restore the record */ + memcpy(new, old, len); + } + +out_end: + erst_get_record_id_end(); + kfree(old); +out: + return ret; +} + +static void set_fmp_fields(struct fru_rec *rec, unsigned int cpu) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + + fmp->fru_arch_type = FMP_ARCH_TYPE_X86_CPUID_1_EAX; + fmp->validation_bits |= FMP_VALID_ARCH_TYPE; + + /* Assume all CPUs in the system have the same value for now. */ + fmp->fru_arch = cpuid_eax(1); + fmp->validation_bits |= FMP_VALID_ARCH; + + fmp->fru_id_type = FMP_ID_TYPE_X86_PPIN; + fmp->validation_bits |= FMP_VALID_ID_TYPE; + + fmp->fru_id = topology_ppin(cpu); + fmp->validation_bits |= FMP_VALID_ID; +} + +static int init_fmps(void) +{ + struct fru_rec *rec; + unsigned int i, cpu; + int ret = 0; + + for_each_fru(i, rec) { + unsigned int fru_cpu = INVALID_CPU; + + cpus_read_lock(); + for_each_online_cpu(cpu) { + if (topology_physical_package_id(cpu) == i) { + fru_cpu = cpu; + break; + } + } + cpus_read_unlock(); + + if (fru_cpu == INVALID_CPU) { + pr_debug("Failed to find matching CPU for FRU #%u\n", i); + ret = -ENODEV; + break; + } + + set_fmp_fields(rec, fru_cpu); + } + + return ret; +} + +static int get_system_info(void) +{ + /* Only load on MI300A systems for now. */ + if (!(boot_cpu_data.x86_model >= 0x90 && + boot_cpu_data.x86_model <= 0x9f)) + return -ENODEV; + + if (!cpu_feature_enabled(X86_FEATURE_AMD_PPIN)) { + pr_debug("PPIN feature not available\n"); + return -ENODEV; + } + + /* Use CPU socket as FRU for MI300 systems. */ + max_nr_fru = topology_max_packages(); + if (!max_nr_fru) + return -ENODEV; + + if (max_nr_fru > FMPM_MAX_NR_FRU) { + pr_warn("Too many FRUs to manage: found: %u, max: %u\n", + max_nr_fru, FMPM_MAX_NR_FRU); + return -ENODEV; + } + + if (!max_nr_entries) + max_nr_entries = FMPM_DEFAULT_MAX_NR_ENTRIES; + + spa_nr_entries = max_nr_fru * max_nr_entries; + + max_rec_len = sizeof(struct fru_rec); + max_rec_len += sizeof(struct cper_fru_poison_desc) * max_nr_entries; + + pr_info("max FRUs: %u, max entries: %u, max record length: %lu\n", + max_nr_fru, max_nr_entries, max_rec_len); + + return 0; +} + +static void free_records(void) +{ + struct fru_rec *rec; + int i; + + for_each_fru(i, rec) + kfree(rec); + + kfree(fru_records); + kfree(spa_entries); +} + +static int allocate_records(void) +{ + int i, ret = 0; + + fru_records = kcalloc(max_nr_fru, sizeof(struct fru_rec *), GFP_KERNEL); + if (!fru_records) { + ret = -ENOMEM; + goto out; + } + + for (i = 0; i < max_nr_fru; i++) { + fru_records[i] = kzalloc(max_rec_len, GFP_KERNEL); + if (!fru_records[i]) { + ret = -ENOMEM; + goto out_free; + } + } + + spa_entries = kcalloc(spa_nr_entries, sizeof(u64), GFP_KERNEL); + if (!spa_entries) { + ret = -ENOMEM; + goto out_free; + } + + for (i = 0; i < spa_nr_entries; i++) + spa_entries[i] = INVALID_SPA; + + return ret; + +out_free: + while (--i >= 0) + kfree(fru_records[i]); + + kfree(fru_records); +out: + return ret; +} + +static void *fmpm_start(struct seq_file *f, loff_t *pos) +{ + if (*pos >= (spa_nr_entries + 1)) + return NULL; + return pos; +} + +static void *fmpm_next(struct seq_file *f, void *data, loff_t *pos) +{ + if (++(*pos) >= (spa_nr_entries + 1)) + return NULL; + return pos; +} + +static void fmpm_stop(struct seq_file *f, void *data) +{ +} + +#define SHORT_WIDTH 8 +#define U64_WIDTH 18 +#define TIMESTAMP_WIDTH 19 +#define LONG_WIDTH 24 +#define U64_PAD (LONG_WIDTH - U64_WIDTH) +#define TS_PAD (LONG_WIDTH - TIMESTAMP_WIDTH) +static int fmpm_show(struct seq_file *f, void *data) +{ + unsigned int fru_idx, entry, spa_entry, line; + struct cper_fru_poison_desc *fpd; + struct fru_rec *rec; + + line = *(loff_t *)data; + if (line == 0) { + seq_printf(f, "%-*s", SHORT_WIDTH, "fru_idx"); + seq_printf(f, "%-*s", LONG_WIDTH, "fru_id"); + seq_printf(f, "%-*s", SHORT_WIDTH, "entry"); + seq_printf(f, "%-*s", LONG_WIDTH, "timestamp"); + seq_printf(f, "%-*s", LONG_WIDTH, "hw_id"); + seq_printf(f, "%-*s", LONG_WIDTH, "addr"); + seq_printf(f, "%-*s", LONG_WIDTH, "spa"); + goto out_newline; + } + + spa_entry = line - 1; + fru_idx = spa_entry / max_nr_entries; + entry = spa_entry % max_nr_entries; + + rec = fru_records[fru_idx]; + if (!rec) + goto out; + + seq_printf(f, "%-*u", SHORT_WIDTH, fru_idx); + seq_printf(f, "0x%016llx%-*s", rec->fmp.fru_id, U64_PAD, ""); + seq_printf(f, "%-*u", SHORT_WIDTH, entry); + + mutex_lock(&fmpm_update_mutex); + + if (entry >= rec->fmp.nr_entries) { + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + goto out_unlock; + } + + fpd = &rec->entries[entry]; + + seq_printf(f, "%ptT%-*s", &fpd->timestamp, TS_PAD, ""); + seq_printf(f, "0x%016llx%-*s", fpd->hw_id, U64_PAD, ""); + seq_printf(f, "0x%016llx%-*s", fpd->addr, U64_PAD, ""); + + if (spa_entries[spa_entry] == INVALID_SPA) + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + else + seq_printf(f, "0x%016llx%-*s", spa_entries[spa_entry], U64_PAD, ""); + +out_unlock: + mutex_unlock(&fmpm_update_mutex); +out_newline: + seq_putc(f, '\n'); +out: + return 0; +} + +static const struct seq_operations fmpm_seq_ops = { + .start = fmpm_start, + .next = fmpm_next, + .stop = fmpm_stop, + .show = fmpm_show, +}; + +static int fmpm_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &fmpm_seq_ops); +} + +static const struct file_operations fmpm_fops = { + .open = fmpm_open, + .release = seq_release, + .read = seq_read, + .llseek = seq_lseek, +}; + +static void setup_debugfs(void) +{ + struct dentry *dfs = ras_get_debugfs_root(); + + if (!dfs) + return; + + fmpm_dfs_dir = debugfs_create_dir("fmpm", dfs); + if (!fmpm_dfs_dir) + return; + + fmpm_dfs_entries = debugfs_create_file("entries", 0400, fmpm_dfs_dir, NULL, &fmpm_fops); + if (!fmpm_dfs_entries) + debugfs_remove(fmpm_dfs_dir); +} + +static const struct x86_cpu_id fmpm_cpuids[] = { + X86_MATCH_VENDOR_FAM(AMD, 0x19, NULL), + { } +}; +MODULE_DEVICE_TABLE(x86cpu, fmpm_cpuids); + +static int __init fru_mem_poison_init(void) +{ + int ret; + + if (!x86_match_cpu(fmpm_cpuids)) { + ret = -ENODEV; + goto out; + } + + if (erst_disable) { + pr_debug("ERST not available\n"); + ret = -ENODEV; + goto out; + } + + ret = get_system_info(); + if (ret) + goto out; + + ret = allocate_records(); + if (ret) + goto out; + + ret = init_fmps(); + if (ret) + goto out_free; + + ret = get_saved_records(); + if (ret) + goto out_free; + + ret = save_new_records(); + if (ret) + goto out_free; + + setup_debugfs(); + + retire_mem_records(); + + mce_register_decode_chain(&fru_mem_poison_nb); + + pr_info("FRU Memory Poison Manager initialized\n"); + return 0; + +out_free: + free_records(); +out: + return ret; +} + +static void __exit fru_mem_poison_exit(void) +{ + mce_unregister_decode_chain(&fru_mem_poison_nb); + debugfs_remove(fmpm_dfs_dir); + free_records(); +} + +module_init(fru_mem_poison_init); +module_exit(fru_mem_poison_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("FRU Memory Poison Manager"); diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c index 321af498ee11..e440b15fbabc 100644 --- a/drivers/ras/cec.c +++ b/drivers/ras/cec.c @@ -480,9 +480,15 @@ DEFINE_SHOW_ATTRIBUTE(array); static int __init create_debugfs_nodes(void) { - struct dentry *d, *pfn, *decay, *count, *array; + struct dentry *d, *pfn, *decay, *count, *array, *dfs; - d = debugfs_create_dir("cec", ras_debugfs_dir); + dfs = ras_get_debugfs_root(); + if (!dfs) { + pr_warn("Error getting RAS debugfs root!\n"); + return -1; + } + + d = debugfs_create_dir("cec", dfs); if (!d) { pr_warn("Error creating cec debugfs node!\n"); return -1; diff --git a/drivers/ras/debugfs.c b/drivers/ras/debugfs.c index ffb973c328e3..42afd3de68b2 100644 --- a/drivers/ras/debugfs.c +++ b/drivers/ras/debugfs.c @@ -3,10 +3,16 @@ #include <linux/ras.h> #include "debugfs.h" -struct dentry *ras_debugfs_dir; +static struct dentry *ras_debugfs_dir; static atomic_t trace_count = ATOMIC_INIT(0); +struct dentry *ras_get_debugfs_root(void) +{ + return ras_debugfs_dir; +} +EXPORT_SYMBOL_GPL(ras_get_debugfs_root); + int ras_userspace_consumers(void) { return atomic_read(&trace_count); diff --git a/drivers/ras/debugfs.h b/drivers/ras/debugfs.h index c07443b462ad..4749ccdeeba1 100644 --- a/drivers/ras/debugfs.h +++ b/drivers/ras/debugfs.h @@ -4,6 +4,6 @@ #include <linux/debugfs.h> -extern struct dentry *ras_debugfs_dir; +struct dentry *ras_get_debugfs_root(void); #endif /* __RAS_DEBUGFS_H__ */ diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c index 95540ea8dd9d..a6e4792a1b2e 100644 --- a/drivers/ras/ras.c +++ b/drivers/ras/ras.c @@ -10,6 +10,37 @@ #include <linux/ras.h> #include <linux/uuid.h> +#if IS_ENABLED(CONFIG_AMD_ATL) +/* + * Once set, this function pointer should never be unset. + * + * The library module will set this pointer if it successfully loads. The module + * should not be unloaded except for testing and debug purposes. + */ +static unsigned long (*amd_atl_umc_na_to_spa)(struct atl_err *err); + +void amd_atl_register_decoder(unsigned long (*f)(struct atl_err *)) +{ + amd_atl_umc_na_to_spa = f; +} +EXPORT_SYMBOL_GPL(amd_atl_register_decoder); + +void amd_atl_unregister_decoder(void) +{ + amd_atl_umc_na_to_spa = NULL; +} +EXPORT_SYMBOL_GPL(amd_atl_unregister_decoder); + +unsigned long amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err) +{ + if (!amd_atl_umc_na_to_spa) + return -EINVAL; + + return amd_atl_umc_na_to_spa(err); +} +EXPORT_SYMBOL_GPL(amd_convert_umc_mca_addr_to_sys_addr); +#endif /* CONFIG_AMD_ATL */ + #define CREATE_TRACE_POINTS #define TRACE_INCLUDE_PATH ../../include/ras #include <ras/ras_event.h> diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c index e374fa6e5f28..d89ae7f16d7a 100644 --- a/drivers/regulator/rk808-regulator.c +++ b/drivers/regulator/rk808-regulator.c @@ -1017,14 +1017,14 @@ static const struct regulator_desc rk805_reg[] = { }; static const struct linear_range rk806_buck_voltage_ranges[] = { - REGULATOR_LINEAR_RANGE(500000, 0, 160, 6250), /* 500mV ~ 1500mV */ - REGULATOR_LINEAR_RANGE(1500000, 161, 237, 25000), /* 1500mV ~ 3400mV */ - REGULATOR_LINEAR_RANGE(3400000, 238, 255, 0), + REGULATOR_LINEAR_RANGE(500000, 0, 159, 6250), /* 500mV ~ 1500mV */ + REGULATOR_LINEAR_RANGE(1500000, 160, 235, 25000), /* 1500mV ~ 3400mV */ + REGULATOR_LINEAR_RANGE(3400000, 236, 255, 0), }; static const struct linear_range rk806_ldo_voltage_ranges[] = { - REGULATOR_LINEAR_RANGE(500000, 0, 232, 12500), /* 500mV ~ 3400mV */ - REGULATOR_LINEAR_RANGE(3400000, 233, 255, 0), /* 500mV ~ 3400mV */ + REGULATOR_LINEAR_RANGE(500000, 0, 231, 12500), /* 500mV ~ 3400mV */ + REGULATOR_LINEAR_RANGE(3400000, 232, 255, 0), }; static const struct regulator_desc rk806_reg[] = { diff --git a/drivers/rtc/lib_test.c b/drivers/rtc/lib_test.c index d5caf36c56cd..225c859d6da5 100644 --- a/drivers/rtc/lib_test.c +++ b/drivers/rtc/lib_test.c @@ -54,7 +54,7 @@ static void rtc_time64_to_tm_test_date_range(struct kunit *test) days = div_s64(secs, 86400); - #define FAIL_MSG "%d/%02d/%02d (%2d) : %ld", \ + #define FAIL_MSG "%d/%02d/%02d (%2d) : %lld", \ year, month, mday, yday, days KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 7327e81352e9..cead018c3f06 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -8,9 +8,6 @@ * Copyright IBM Corp. 1999, 2009 */ -#define KMSG_COMPONENT "dasd" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt - #include <linux/kmod.h> #include <linux/init.h> #include <linux/interrupt.h> @@ -30,9 +27,6 @@ #include <asm/itcw.h> #include <asm/diag.h> -/* This is ugly... */ -#define PRINTK_HEADER "dasd:" - #include "dasd_int.h" /* * SECTION: Constant definitions to be used within this file @@ -313,39 +307,57 @@ static int dasd_state_basic_to_known(struct dasd_device *device) */ static int dasd_state_basic_to_ready(struct dasd_device *device) { - int rc; - struct dasd_block *block; - struct gendisk *disk; + struct dasd_block *block = device->block; + struct queue_limits lim; + int rc = 0; - rc = 0; - block = device->block; /* make disk known with correct capacity */ - if (block) { - if (block->base->discipline->do_analysis != NULL) - rc = block->base->discipline->do_analysis(block); - if (rc) { - if (rc != -EAGAIN) { - device->state = DASD_STATE_UNFMT; - disk = device->block->gdp; - kobject_uevent(&disk_to_dev(disk)->kobj, - KOBJ_CHANGE); - goto out; - } - return rc; - } - if (device->discipline->setup_blk_queue) - device->discipline->setup_blk_queue(block); - set_capacity(block->gdp, - block->blocks << block->s2b_shift); + if (!block) { device->state = DASD_STATE_READY; - rc = dasd_scan_partitions(block); - if (rc) { - device->state = DASD_STATE_BASIC; + goto out; + } + + if (block->base->discipline->do_analysis != NULL) + rc = block->base->discipline->do_analysis(block); + if (rc) { + if (rc == -EAGAIN) return rc; - } - } else { - device->state = DASD_STATE_READY; + device->state = DASD_STATE_UNFMT; + kobject_uevent(&disk_to_dev(device->block->gdp)->kobj, + KOBJ_CHANGE); + goto out; + } + + lim = queue_limits_start_update(block->gdp->queue); + lim.max_dev_sectors = device->discipline->max_sectors(block); + lim.max_hw_sectors = lim.max_dev_sectors; + lim.logical_block_size = block->bp_block; + + if (device->discipline->has_discard) { + unsigned int max_bytes; + + lim.discard_granularity = block->bp_block; + + /* Calculate max_discard_sectors and make it PAGE aligned */ + max_bytes = USHRT_MAX * block->bp_block; + max_bytes = ALIGN_DOWN(max_bytes, PAGE_SIZE); + + lim.max_hw_discard_sectors = max_bytes / block->bp_block; + lim.max_write_zeroes_sectors = lim.max_hw_discard_sectors; } + rc = queue_limits_commit_update(block->gdp->queue, &lim); + if (rc) + return rc; + + set_capacity(block->gdp, block->blocks << block->s2b_shift); + device->state = DASD_STATE_READY; + + rc = dasd_scan_partitions(block); + if (rc) { + device->state = DASD_STATE_BASIC; + return rc; + } + out: if (device->discipline->basic_to_ready) rc = device->discipline->basic_to_ready(device); @@ -412,7 +424,7 @@ dasd_state_ready_to_online(struct dasd_device * device) KOBJ_CHANGE); return 0; } - disk_uevent(device->block->bdev_handle->bdev->bd_disk, + disk_uevent(file_bdev(device->block->bdev_file)->bd_disk, KOBJ_CHANGE); } return 0; @@ -433,7 +445,7 @@ static int dasd_state_online_to_ready(struct dasd_device *device) device->state = DASD_STATE_READY; if (device->block && !(device->features & DASD_FEATURE_USERAW)) - disk_uevent(device->block->bdev_handle->bdev->bd_disk, + disk_uevent(file_bdev(device->block->bdev_file)->bd_disk, KOBJ_CHANGE); return 0; } @@ -1301,7 +1313,6 @@ int dasd_term_IO(struct dasd_ccw_req *cqr) { struct dasd_device *device; int retries, rc; - char errorstring[ERRORLENGTH]; /* Check the cqr */ rc = dasd_check_cqr(cqr); @@ -1340,10 +1351,8 @@ int dasd_term_IO(struct dasd_ccw_req *cqr) rc = 0; break; default: - /* internal error 10 - unknown rc*/ - snprintf(errorstring, ERRORLENGTH, "10 %d", rc); - dev_err(&device->cdev->dev, "An error occurred in the " - "DASD device driver, reason=%s\n", errorstring); + dev_err(&device->cdev->dev, + "Unexpected error during request termination %d\n", rc); BUG(); break; } @@ -1362,7 +1371,6 @@ int dasd_start_IO(struct dasd_ccw_req *cqr) { struct dasd_device *device; int rc; - char errorstring[ERRORLENGTH]; /* Check the cqr */ rc = dasd_check_cqr(cqr); @@ -1382,10 +1390,8 @@ int dasd_start_IO(struct dasd_ccw_req *cqr) return -EPERM; } if (cqr->retries < 0) { - /* internal error 14 - start_IO run out of retries */ - sprintf(errorstring, "14 %p", cqr); - dev_err(&device->cdev->dev, "An error occurred in the DASD " - "device driver, reason=%s\n", errorstring); + dev_err(&device->cdev->dev, + "Start I/O ran out of retries\n"); cqr->status = DASD_CQR_ERROR; return -EIO; } @@ -1463,11 +1469,8 @@ int dasd_start_IO(struct dasd_ccw_req *cqr) "not accessible"); break; default: - /* internal error 11 - unknown rc */ - snprintf(errorstring, ERRORLENGTH, "11 %d", rc); dev_err(&device->cdev->dev, - "An error occurred in the DASD device driver, " - "reason=%s\n", errorstring); + "Unexpected error during request start %d", rc); BUG(); break; } @@ -1904,8 +1907,6 @@ static void __dasd_device_process_ccw_queue(struct dasd_device *device, static void __dasd_process_cqr(struct dasd_device *device, struct dasd_ccw_req *cqr) { - char errorstring[ERRORLENGTH]; - switch (cqr->status) { case DASD_CQR_SUCCESS: cqr->status = DASD_CQR_DONE; @@ -1917,11 +1918,8 @@ static void __dasd_process_cqr(struct dasd_device *device, cqr->status = DASD_CQR_TERMINATED; break; default: - /* internal error 12 - wrong cqr status*/ - snprintf(errorstring, ERRORLENGTH, "12 %p %x02", cqr, cqr->status); dev_err(&device->cdev->dev, - "An error occurred in the DASD device driver, " - "reason=%s\n", errorstring); + "Unexpected CQR status %02x", cqr->status); BUG(); } if (cqr->callback) @@ -1986,16 +1984,14 @@ static void __dasd_device_check_expire(struct dasd_device *device) if (device->discipline->term_IO(cqr) != 0) { /* Hmpf, try again in 5 sec */ dev_err(&device->cdev->dev, - "cqr %p timed out (%lus) but cannot be " - "ended, retrying in 5 s\n", - cqr, (cqr->expires/HZ)); + "CQR timed out (%lus) but cannot be ended, retrying in 5s\n", + (cqr->expires / HZ)); cqr->expires += 5*HZ; dasd_device_set_timer(device, 5*HZ); } else { dev_err(&device->cdev->dev, - "cqr %p timed out (%lus), %i retries " - "remaining\n", cqr, (cqr->expires/HZ), - cqr->retries); + "CQR timed out (%lus), %i retries remaining\n", + (cqr->expires / HZ), cqr->retries); } __dasd_device_check_autoquiesce_timeout(device, cqr); } @@ -2116,8 +2112,7 @@ int dasd_flush_device_queue(struct dasd_device *device) if (rc) { /* unable to terminate requeust */ dev_err(&device->cdev->dev, - "Flushing the DASD request queue " - "failed for request %p\n", cqr); + "Flushing the DASD request queue failed\n"); /* stop flush processing */ goto finished; } @@ -2633,8 +2628,7 @@ static int __dasd_cancel_req(struct dasd_ccw_req *cqr) rc = device->discipline->term_IO(cqr); if (rc) { dev_err(&device->cdev->dev, - "Cancelling request %p failed with rc=%d\n", - cqr, rc); + "Cancelling request failed with rc=%d\n", rc); } else { cqr->stopclk = get_tod_clock(); } @@ -3402,8 +3396,7 @@ static void dasd_generic_auto_online(void *data, async_cookie_t cookie) ret = ccw_device_set_online(cdev); if (ret) - pr_warn("%s: Setting the DASD online failed with rc=%d\n", - dev_name(&cdev->dev), ret); + dev_warn(&cdev->dev, "Setting the DASD online failed with rc=%d\n", ret); } /* @@ -3490,8 +3483,11 @@ int dasd_generic_set_online(struct ccw_device *cdev, { struct dasd_discipline *discipline; struct dasd_device *device; + struct device *dev; int rc; + dev = &cdev->dev; + /* first online clears initial online feature flag */ dasd_set_feature(cdev, DASD_FEATURE_INITIAL_ONLINE, 0); device = dasd_create_device(cdev); @@ -3504,11 +3500,10 @@ int dasd_generic_set_online(struct ccw_device *cdev, /* Try to load the required module. */ rc = request_module(DASD_DIAG_MOD); if (rc) { - pr_warn("%s Setting the DASD online failed " - "because the required module %s " - "could not be loaded (rc=%d)\n", - dev_name(&cdev->dev), DASD_DIAG_MOD, - rc); + dev_warn(dev, "Setting the DASD online failed " + "because the required module %s " + "could not be loaded (rc=%d)\n", + DASD_DIAG_MOD, rc); dasd_delete_device(device); return -ENODEV; } @@ -3516,8 +3511,7 @@ int dasd_generic_set_online(struct ccw_device *cdev, /* Module init could have failed, so check again here after * request_module(). */ if (!dasd_diag_discipline_pointer) { - pr_warn("%s Setting the DASD online failed because of missing DIAG discipline\n", - dev_name(&cdev->dev)); + dev_warn(dev, "Setting the DASD online failed because of missing DIAG discipline\n"); dasd_delete_device(device); return -ENODEV; } @@ -3527,37 +3521,33 @@ int dasd_generic_set_online(struct ccw_device *cdev, dasd_delete_device(device); return -EINVAL; } + device->base_discipline = base_discipline; if (!try_module_get(discipline->owner)) { - module_put(base_discipline->owner); dasd_delete_device(device); return -EINVAL; } - device->base_discipline = base_discipline; device->discipline = discipline; /* check_device will allocate block device if necessary */ rc = discipline->check_device(device); if (rc) { - pr_warn("%s Setting the DASD online with discipline %s failed with rc=%i\n", - dev_name(&cdev->dev), discipline->name, rc); - module_put(discipline->owner); - module_put(base_discipline->owner); + dev_warn(dev, "Setting the DASD online with discipline %s failed with rc=%i\n", + discipline->name, rc); dasd_delete_device(device); return rc; } dasd_set_target_state(device, DASD_STATE_ONLINE); if (device->state <= DASD_STATE_KNOWN) { - pr_warn("%s Setting the DASD online failed because of a missing discipline\n", - dev_name(&cdev->dev)); + dev_warn(dev, "Setting the DASD online failed because of a missing discipline\n"); rc = -ENODEV; dasd_set_target_state(device, DASD_STATE_NEW); if (device->block) dasd_free_block(device->block); dasd_delete_device(device); - } else - pr_debug("dasd_generic device %s found\n", - dev_name(&cdev->dev)); + } else { + dev_dbg(dev, "dasd_generic device found\n"); + } wait_event(dasd_init_waitq, _wait_for_device(device)); @@ -3568,10 +3558,13 @@ EXPORT_SYMBOL_GPL(dasd_generic_set_online); int dasd_generic_set_offline(struct ccw_device *cdev) { + int max_count, open_count, rc; struct dasd_device *device; struct dasd_block *block; - int max_count, open_count, rc; unsigned long flags; + struct device *dev; + + dev = &cdev->dev; rc = 0; spin_lock_irqsave(get_ccwdev_lock(cdev), flags); @@ -3588,15 +3581,14 @@ int dasd_generic_set_offline(struct ccw_device *cdev) * in the other openers. */ if (device->block) { - max_count = device->block->bdev_handle ? 0 : -1; + max_count = device->block->bdev_file ? 0 : -1; open_count = atomic_read(&device->block->open_count); if (open_count > max_count) { if (open_count > 0) - pr_warn("%s: The DASD cannot be set offline with open count %i\n", - dev_name(&cdev->dev), open_count); + dev_warn(dev, "The DASD cannot be set offline with open count %i\n", + open_count); else - pr_warn("%s: The DASD cannot be set offline while it is in use\n", - dev_name(&cdev->dev)); + dev_warn(dev, "The DASD cannot be set offline while it is in use\n"); rc = -EBUSY; goto out_err; } @@ -3634,8 +3626,8 @@ int dasd_generic_set_offline(struct ccw_device *cdev) * so sync bdev first and then wait for our queues to become * empty */ - if (device->block && device->block->bdev_handle) - bdev_mark_dead(device->block->bdev_handle->bdev, false); + if (device->block && device->block->bdev_file) + bdev_mark_dead(file_bdev(device->block->bdev_file), false); dasd_schedule_device_bh(device); rc = wait_event_interruptible(shutdown_waitq, _wait_for_empty_queues(device)); @@ -3956,8 +3948,8 @@ static int dasd_handle_autoquiesce(struct dasd_device *device, if (dasd_eer_enabled(device)) dasd_eer_write(device, NULL, DASD_EER_AUTOQUIESCE); - pr_info("%s: The DASD has been put in the quiesce state\n", - dev_name(&device->cdev->dev)); + dev_info(&device->cdev->dev, + "The DASD has been put in the quiesce state\n"); dasd_device_set_stop_bits(device, DASD_STOPPED_QUIESCE); if (device->features & DASD_FEATURE_REQUEUEQUIESCE) @@ -3977,10 +3969,8 @@ static struct dasd_ccw_req *dasd_generic_build_rdc(struct dasd_device *device, NULL); if (IS_ERR(cqr)) { - /* internal error 13 - Allocating the RDC request failed*/ - dev_err(&device->cdev->dev, - "An error occurred in the DASD device driver, " - "reason=%s\n", "13"); + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", + "Could not allocate RDC request"); return cqr; } diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c index 89957bb7244d..459b7f8ac883 100644 --- a/drivers/s390/block/dasd_3990_erp.c +++ b/drivers/s390/block/dasd_3990_erp.c @@ -7,13 +7,9 @@ * */ -#define KMSG_COMPONENT "dasd-eckd" - #include <linux/timer.h> #include <asm/idals.h> -#define PRINTK_HEADER "dasd_erp(3990): " - #include "dasd_int.h" #include "dasd_eckd.h" @@ -398,7 +394,6 @@ dasd_3990_handle_env_data(struct dasd_ccw_req * erp, char *sense) struct dasd_device *device = erp->startdev; char msg_format = (sense[7] & 0xF0); char msg_no = (sense[7] & 0x0F); - char errorstring[ERRORLENGTH]; switch (msg_format) { case 0x00: /* Format 0 - Program or System Checks */ @@ -1004,12 +999,9 @@ dasd_3990_handle_env_data(struct dasd_ccw_req * erp, char *sense) } break; - default: /* unknown message format - should not happen - internal error 03 - unknown message format */ - snprintf(errorstring, ERRORLENGTH, "03 %x02", msg_format); + default: dev_err(&device->cdev->dev, - "An error occurred in the DASD device driver, " - "reason=%s\n", errorstring); + "Unknown message format %02x", msg_format); break; } /* end switch message format */ @@ -1056,11 +1048,9 @@ dasd_3990_erp_com_rej(struct dasd_ccw_req * erp, char *sense) set_bit(DASD_CQR_SUPPRESS_CR, &erp->refers->flags); erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED); } else { - /* fatal error - set status to FAILED - internal error 09 - Command Reject */ if (!test_bit(DASD_CQR_SUPPRESS_CR, &erp->flags)) dev_err(&device->cdev->dev, - "An error occurred in the DASD device driver, reason=09\n"); + "An I/O command request was rejected\n"); erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED); } @@ -1128,13 +1118,7 @@ dasd_3990_erp_equip_check(struct dasd_ccw_req * erp, char *sense) erp->function = dasd_3990_erp_equip_check; if (sense[1] & SNS1_WRITE_INHIBITED) { - dev_info(&device->cdev->dev, - "Write inhibited path encountered\n"); - - /* vary path offline - internal error 04 - Path should be varied off-line.*/ - dev_err(&device->cdev->dev, "An error occurred in the DASD " - "device driver, reason=%s\n", "04"); + dev_err(&device->cdev->dev, "Write inhibited path encountered\n"); erp = dasd_3990_erp_action_1(erp); @@ -1285,11 +1269,7 @@ dasd_3990_erp_inv_format(struct dasd_ccw_req * erp, char *sense) erp = dasd_3990_erp_action_4(erp, sense); } else { - /* internal error 06 - The track format is not valid*/ - dev_err(&device->cdev->dev, - "An error occurred in the DASD device driver, " - "reason=%s\n", "06"); - + dev_err(&device->cdev->dev, "Track format is not valid\n"); erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED); } @@ -1663,9 +1643,8 @@ dasd_3990_erp_action_1B_32(struct dasd_ccw_req * default_erp, char *sense) sizeof(struct LO_eckd_data), device); if (IS_ERR(erp)) { - /* internal error 01 - Unable to allocate ERP */ - dev_err(&device->cdev->dev, "An error occurred in the DASD " - "device driver, reason=%s\n", "01"); + DBF_DEV_EVENT(DBF_ERR, device, "%s", + "Unable to allocate ERP request (1B 32)"); return dasd_3990_erp_cleanup(default_erp, DASD_CQR_FAILED); } @@ -1807,10 +1786,8 @@ dasd_3990_update_1B(struct dasd_ccw_req * previous_erp, char *sense) cpa = previous_erp->irb.scsw.cmd.cpa; if (cpa == 0) { - /* internal error 02 - - Unable to determine address of the CCW to be restarted */ - dev_err(&device->cdev->dev, "An error occurred in the DASD " - "device driver, reason=%s\n", "02"); + dev_err(&device->cdev->dev, + "Unable to determine address of to be restarted CCW\n"); previous_erp->status = DASD_CQR_FAILED; @@ -2009,15 +1986,9 @@ dasd_3990_erp_compound_config(struct dasd_ccw_req * erp, char *sense) { if ((sense[25] & DASD_SENSE_BIT_1) && (sense[26] & DASD_SENSE_BIT_2)) { - - /* set to suspended duplex state then restart - internal error 05 - Set device to suspended duplex state - should be done */ struct dasd_device *device = erp->startdev; dev_err(&device->cdev->dev, - "An error occurred in the DASD device driver, " - "reason=%s\n", "05"); - + "Compound configuration error occurred\n"); } erp->function = dasd_3990_erp_compound_config; @@ -2153,10 +2124,9 @@ dasd_3990_erp_inspect_32(struct dasd_ccw_req * erp, char *sense) erp = dasd_3990_erp_int_req(erp); break; - case 0x0F: /* length mismatch during update write command - internal error 08 - update write command error*/ - dev_err(&device->cdev->dev, "An error occurred in the " - "DASD device driver, reason=%s\n", "08"); + case 0x0F: + dev_err(&device->cdev->dev, + "Update write command error occurred\n"); erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED); break; @@ -2165,12 +2135,9 @@ dasd_3990_erp_inspect_32(struct dasd_ccw_req * erp, char *sense) erp = dasd_3990_erp_action_10_32(erp, sense); break; - case 0x15: /* next track outside defined extend - internal error 07 - The next track is not - within the defined storage extent */ + case 0x15: dev_err(&device->cdev->dev, - "An error occurred in the DASD device driver, " - "reason=%s\n", "07"); + "Track outside defined extent error occurred\n"); erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED); break; @@ -2663,7 +2630,7 @@ dasd_3990_erp_further_erp(struct dasd_ccw_req *erp) * necessary */ dev_err(&device->cdev->dev, - "ERP %p has run out of retries and failed\n", erp); + "ERP %px has run out of retries and failed\n", erp); erp->status = DASD_CQR_FAILED; } @@ -2704,8 +2671,7 @@ dasd_3990_erp_handle_match_erp(struct dasd_ccw_req *erp_head, while (erp_done != erp) { if (erp_done == NULL) /* end of chain reached */ - panic(PRINTK_HEADER "Programming error in ERP! The " - "original request was lost\n"); + panic("Programming error in ERP! The original request was lost\n"); /* remove the request from the device queue */ list_del(&erp_done->blocklist); @@ -2786,11 +2752,9 @@ dasd_3990_erp_action(struct dasd_ccw_req * cqr) "ERP chain at BEGINNING of ERP-ACTION\n"); for (temp_erp = cqr; temp_erp != NULL; temp_erp = temp_erp->refers) { - dev_err(&device->cdev->dev, - "ERP %p (%02x) refers to %p\n", - temp_erp, temp_erp->status, - temp_erp->refers); + "ERP %px (%02x) refers to %px\n", + temp_erp, temp_erp->status, temp_erp->refers); } } @@ -2837,11 +2801,9 @@ dasd_3990_erp_action(struct dasd_ccw_req * cqr) "ERP chain at END of ERP-ACTION\n"); for (temp_erp = erp; temp_erp != NULL; temp_erp = temp_erp->refers) { - dev_err(&device->cdev->dev, - "ERP %p (%02x) refers to %p\n", - temp_erp, temp_erp->status, - temp_erp->refers); + "ERP %px (%02x) refers to %px\n", + temp_erp, temp_erp->status, temp_erp->refers); } } diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index c9740ae88d1a..e84cd5436556 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -6,20 +6,12 @@ * Author(s): Stefan Weinhuber <wein@de.ibm.com> */ -#define KMSG_COMPONENT "dasd-eckd" - #include <linux/list.h> #include <linux/slab.h> #include <asm/ebcdic.h> #include "dasd_int.h" #include "dasd_eckd.h" -#ifdef PRINTK_HEADER -#undef PRINTK_HEADER -#endif /* PRINTK_HEADER */ -#define PRINTK_HEADER "dasd(eckd):" - - /* * General concept of alias management: * - PAV and DASD alias management is specific to the eckd discipline. diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index c4e36650c426..0316c20823ee 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -13,8 +13,6 @@ * */ -#define KMSG_COMPONENT "dasd" - #include <linux/ctype.h> #include <linux/init.h> #include <linux/module.h> @@ -24,8 +22,6 @@ #include <linux/uaccess.h> #include <asm/ipl.h> -/* This is ugly... */ -#define PRINTK_HEADER "dasd_devmap:" #define DASD_MAX_PARAMS 256 #include "dasd_int.h" @@ -1114,7 +1110,7 @@ dasd_use_diag_show(struct device *dev, struct device_attribute *attr, char *buf) use_diag = (devmap->features & DASD_FEATURE_USEDIAG) != 0; else use_diag = (DASD_FEATURE_DEFAULT & DASD_FEATURE_USEDIAG) != 0; - return sprintf(buf, use_diag ? "1\n" : "0\n"); + return sysfs_emit(buf, use_diag ? "1\n" : "0\n"); } static ssize_t @@ -1163,7 +1159,7 @@ dasd_use_raw_show(struct device *dev, struct device_attribute *attr, char *buf) use_raw = (devmap->features & DASD_FEATURE_USERAW) != 0; else use_raw = (DASD_FEATURE_DEFAULT & DASD_FEATURE_USERAW) != 0; - return sprintf(buf, use_raw ? "1\n" : "0\n"); + return sysfs_emit(buf, use_raw ? "1\n" : "0\n"); } static ssize_t @@ -1259,7 +1255,7 @@ dasd_access_show(struct device *dev, struct device_attribute *attr, if (count < 0) return count; - return sprintf(buf, "%d\n", count); + return sysfs_emit(buf, "%d\n", count); } static DEVICE_ATTR(host_access_count, 0444, dasd_access_show, NULL); @@ -1338,19 +1334,19 @@ static ssize_t dasd_alias_show(struct device *dev, device = dasd_device_from_cdev(to_ccwdev(dev)); if (IS_ERR(device)) - return sprintf(buf, "0\n"); + return sysfs_emit(buf, "0\n"); if (device->discipline && device->discipline->get_uid && !device->discipline->get_uid(device, &uid)) { if (uid.type == UA_BASE_PAV_ALIAS || uid.type == UA_HYPER_PAV_ALIAS) { dasd_put_device(device); - return sprintf(buf, "1\n"); + return sysfs_emit(buf, "1\n"); } } dasd_put_device(device); - return sprintf(buf, "0\n"); + return sysfs_emit(buf, "0\n"); } static DEVICE_ATTR(alias, 0444, dasd_alias_show, NULL); @@ -1412,15 +1408,9 @@ dasd_uid_show(struct device *dev, struct device_attribute *attr, char *buf) break; } - if (strlen(uid.vduit) > 0) - snprintf(uid_string, sizeof(uid_string), - "%s.%s.%04x.%s.%s", - uid.vendor, uid.serial, uid.ssid, ua_string, - uid.vduit); - else - snprintf(uid_string, sizeof(uid_string), - "%s.%s.%04x.%s", - uid.vendor, uid.serial, uid.ssid, ua_string); + snprintf(uid_string, sizeof(uid_string), "%s.%s.%04x.%s%s%s", + uid.vendor, uid.serial, uid.ssid, ua_string, + uid.vduit[0] ? "." : "", uid.vduit); } dasd_put_device(device); @@ -1862,7 +1852,7 @@ static ssize_t dasd_pm_show(struct device *dev, device = dasd_device_from_cdev(to_ccwdev(dev)); if (IS_ERR(device)) - return sprintf(buf, "0\n"); + return sysfs_emit(buf, "0\n"); opm = dasd_path_get_opm(device); nppm = dasd_path_get_nppm(device); @@ -1872,8 +1862,8 @@ static ssize_t dasd_pm_show(struct device *dev, ifccpm = dasd_path_get_ifccpm(device); dasd_put_device(device); - return sprintf(buf, "%02x %02x %02x %02x %02x %02x\n", opm, nppm, - cablepm, cuirpm, hpfpm, ifccpm); + return sysfs_emit(buf, "%02x %02x %02x %02x %02x %02x\n", opm, nppm, + cablepm, cuirpm, hpfpm, ifccpm); } static DEVICE_ATTR(path_masks, 0444, dasd_pm_show, NULL); diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index 2e4e555b37c3..ea4b1d01bb76 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -8,8 +8,6 @@ * */ -#define KMSG_COMPONENT "dasd" - #include <linux/kernel_stat.h> #include <linux/stddef.h> #include <linux/kernel.h> @@ -31,8 +29,6 @@ #include "dasd_int.h" #include "dasd_diag.h" -#define PRINTK_HEADER "dasd(diag):" - MODULE_LICENSE("GPL"); /* The maximum number of blocks per request (max_blocks) is dependent on the @@ -621,25 +617,9 @@ 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) +static unsigned int dasd_diag_max_sectors(struct dasd_block *block) { - unsigned int logical_block_size = block->bp_block; - struct request_queue *q = block->gdp->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); - blk_queue_dma_alignment(q, PAGE_SIZE - 1); + return DIAG_MAX_BLOCKS << block->s2b_shift; } static int dasd_diag_pe_handler(struct dasd_device *device, @@ -652,10 +632,10 @@ static struct dasd_discipline dasd_diag_discipline = { .owner = THIS_MODULE, .name = "DIAG", .ebcname = "DIAG", + .max_sectors = dasd_diag_max_sectors, .check_device = dasd_diag_check_device, .pe_handler = dasd_diag_pe_handler, .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 bd89b032968a..373c1a86c33e 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -10,8 +10,6 @@ * Author.........: Nigel Hislop <hislop_nigel@emc.com> */ -#define KMSG_COMPONENT "dasd-eckd" - #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/slab.h> @@ -37,11 +35,6 @@ #include "dasd_int.h" #include "dasd_eckd.h" -#ifdef PRINTK_HEADER -#undef PRINTK_HEADER -#endif /* PRINTK_HEADER */ -#define PRINTK_HEADER "dasd(eckd):" - /* * raw track access always map to 64k in memory * so it maps to 16 blocks of 4k per track @@ -1072,22 +1065,14 @@ static void dasd_eckd_read_fc_security(struct dasd_device *device) } } -static void dasd_eckd_get_uid_string(struct dasd_conf *conf, - char *print_uid) +static void dasd_eckd_get_uid_string(struct dasd_conf *conf, char *print_uid) { struct dasd_uid uid; create_uid(conf, &uid); - if (strlen(uid.vduit) > 0) - snprintf(print_uid, DASD_UID_STRLEN, - "%s.%s.%04x.%02x.%s", - uid.vendor, uid.serial, uid.ssid, - uid.real_unit_addr, uid.vduit); - else - snprintf(print_uid, DASD_UID_STRLEN, - "%s.%s.%04x.%02x", - uid.vendor, uid.serial, uid.ssid, - uid.real_unit_addr); + snprintf(print_uid, DASD_UID_STRLEN, "%s.%s.%04x.%02x%s%s", + uid.vendor, uid.serial, uid.ssid, uid.real_unit_addr, + uid.vduit[0] ? "." : "", uid.vduit); } static int dasd_eckd_check_cabling(struct dasd_device *device, @@ -5529,15 +5514,15 @@ dasd_eckd_ioctl(struct dasd_block *block, unsigned int cmd, void __user *argp) * and return number of printed chars. */ static void -dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page) +dasd_eckd_dump_ccw_range(struct dasd_device *device, struct ccw1 *from, + struct ccw1 *to, char *page) { int len, count; char *datap; len = 0; while (from <= to) { - len += sprintf(page + len, PRINTK_HEADER - " CCW %p: %08X %08X DAT:", + len += sprintf(page + len, "CCW %px: %08X %08X DAT:", from, ((int *) from)[0], ((int *) from)[1]); /* get pointer to data (consider IDALs) */ @@ -5560,7 +5545,7 @@ dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page) from++; } if (len > 0) - printk(KERN_ERR "%s", page); + dev_err(&device->cdev->dev, "%s", page); } static void @@ -5591,9 +5576,12 @@ dasd_eckd_dump_sense_dbf(struct dasd_device *device, struct irb *irb, static void dasd_eckd_dump_sense_ccw(struct dasd_device *device, struct dasd_ccw_req *req, struct irb *irb) { - char *page; struct ccw1 *first, *last, *fail, *from, *to; + struct device *dev; int len, sl, sct; + char *page; + + dev = &device->cdev->dev; page = (char *) get_zeroed_page(GFP_ATOMIC); if (page == NULL) { @@ -5602,24 +5590,18 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device, return; } /* dump the sense data */ - len = sprintf(page, PRINTK_HEADER - " I/O status report for device %s:\n", - dev_name(&device->cdev->dev)); - len += sprintf(page + len, PRINTK_HEADER - " in req: %p CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X " - "CS:%02X RC:%d\n", + len = sprintf(page, "I/O status report:\n"); + len += sprintf(page + len, + "in req: %px CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X CS:%02X RC:%d\n", req, scsw_cc(&irb->scsw), scsw_fctl(&irb->scsw), scsw_actl(&irb->scsw), scsw_stctl(&irb->scsw), scsw_dstat(&irb->scsw), scsw_cstat(&irb->scsw), req ? req->intrc : 0); - len += sprintf(page + len, PRINTK_HEADER - " device %s: Failing CCW: %p\n", - dev_name(&device->cdev->dev), + len += sprintf(page + len, "Failing CCW: %px\n", phys_to_virt(irb->scsw.cmd.cpa)); if (irb->esw.esw0.erw.cons) { for (sl = 0; sl < 4; sl++) { - len += sprintf(page + len, PRINTK_HEADER - " Sense(hex) %2d-%2d:", + len += sprintf(page + len, "Sense(hex) %2d-%2d:", (8 * sl), ((8 * sl) + 7)); for (sct = 0; sct < 8; sct++) { @@ -5631,23 +5613,20 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device, if (irb->ecw[27] & DASD_SENSE_BIT_0) { /* 24 Byte Sense Data */ - sprintf(page + len, PRINTK_HEADER - " 24 Byte: %x MSG %x, " - "%s MSGb to SYSOP\n", + sprintf(page + len, + "24 Byte: %x MSG %x, %s MSGb to SYSOP\n", irb->ecw[7] >> 4, irb->ecw[7] & 0x0f, irb->ecw[1] & 0x10 ? "" : "no"); } else { /* 32 Byte Sense Data */ - sprintf(page + len, PRINTK_HEADER - " 32 Byte: Format: %x " - "Exception class %x\n", + sprintf(page + len, + "32 Byte: Format: %x Exception class %x\n", irb->ecw[6] & 0x0f, irb->ecw[22] >> 4); } } else { - sprintf(page + len, PRINTK_HEADER - " SORRY - NO VALID SENSE AVAILABLE\n"); + sprintf(page + len, "SORRY - NO VALID SENSE AVAILABLE\n"); } - printk(KERN_ERR "%s", page); + dev_err(dev, "%s", page); if (req) { /* req == NULL for unsolicited interrupts */ @@ -5656,8 +5635,8 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device, first = req->cpaddr; for (last = first; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++); to = min(first + 6, last); - printk(KERN_ERR PRINTK_HEADER " Related CP in req: %p\n", req); - dasd_eckd_dump_ccw_range(first, to, page); + dev_err(dev, "Related CP in req: %px\n", req); + dasd_eckd_dump_ccw_range(device, first, to, page); /* print failing CCW area (maximum 4) */ /* scsw->cda is either valid or zero */ @@ -5665,19 +5644,19 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device, fail = phys_to_virt(irb->scsw.cmd.cpa); /* failing CCW */ if (from < fail - 2) { from = fail - 2; /* there is a gap - print header */ - printk(KERN_ERR PRINTK_HEADER "......\n"); + dev_err(dev, "......\n"); } to = min(fail + 1, last); - dasd_eckd_dump_ccw_range(from, to, page + len); + dasd_eckd_dump_ccw_range(device, from, to, page + len); /* print last CCWs (maximum 2) */ len = 0; from = max(from, ++to); if (from < last - 1) { from = last - 1; /* there is a gap - print header */ - printk(KERN_ERR PRINTK_HEADER "......\n"); + dev_err(dev, "......\n"); } - dasd_eckd_dump_ccw_range(from, last, page + len); + dasd_eckd_dump_ccw_range(device, from, last, page + len); } free_page((unsigned long) page); } @@ -5701,11 +5680,9 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device, return; } /* dump the sense data */ - len = sprintf(page, PRINTK_HEADER - " I/O status report for device %s:\n", - dev_name(&device->cdev->dev)); - len += sprintf(page + len, PRINTK_HEADER - " in req: %p CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X " + len = sprintf(page, "I/O status report:\n"); + len += sprintf(page + len, + "in req: %px CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X " "CS:%02X fcxs:%02X schxs:%02X RC:%d\n", req, scsw_cc(&irb->scsw), scsw_fctl(&irb->scsw), scsw_actl(&irb->scsw), scsw_stctl(&irb->scsw), @@ -5713,9 +5690,7 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device, irb->scsw.tm.fcxs, (irb->scsw.tm.ifob << 7) | irb->scsw.tm.sesq, req ? req->intrc : 0); - len += sprintf(page + len, PRINTK_HEADER - " device %s: Failing TCW: %p\n", - dev_name(&device->cdev->dev), + len += sprintf(page + len, "Failing TCW: %px\n", phys_to_virt(irb->scsw.tm.tcw)); tsb = NULL; @@ -5724,47 +5699,37 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device, tsb = tcw_get_tsb(phys_to_virt(irb->scsw.tm.tcw)); if (tsb) { - len += sprintf(page + len, PRINTK_HEADER - " tsb->length %d\n", tsb->length); - len += sprintf(page + len, PRINTK_HEADER - " tsb->flags %x\n", tsb->flags); - len += sprintf(page + len, PRINTK_HEADER - " tsb->dcw_offset %d\n", tsb->dcw_offset); - len += sprintf(page + len, PRINTK_HEADER - " tsb->count %d\n", tsb->count); + len += sprintf(page + len, "tsb->length %d\n", tsb->length); + len += sprintf(page + len, "tsb->flags %x\n", tsb->flags); + len += sprintf(page + len, "tsb->dcw_offset %d\n", tsb->dcw_offset); + len += sprintf(page + len, "tsb->count %d\n", tsb->count); residual = tsb->count - 28; - len += sprintf(page + len, PRINTK_HEADER - " residual %d\n", residual); + len += sprintf(page + len, "residual %d\n", residual); switch (tsb->flags & 0x07) { case 1: /* tsa_iostat */ - len += sprintf(page + len, PRINTK_HEADER - " tsb->tsa.iostat.dev_time %d\n", + len += sprintf(page + len, "tsb->tsa.iostat.dev_time %d\n", tsb->tsa.iostat.dev_time); - len += sprintf(page + len, PRINTK_HEADER - " tsb->tsa.iostat.def_time %d\n", + len += sprintf(page + len, "tsb->tsa.iostat.def_time %d\n", tsb->tsa.iostat.def_time); - len += sprintf(page + len, PRINTK_HEADER - " tsb->tsa.iostat.queue_time %d\n", + len += sprintf(page + len, "tsb->tsa.iostat.queue_time %d\n", tsb->tsa.iostat.queue_time); - len += sprintf(page + len, PRINTK_HEADER - " tsb->tsa.iostat.dev_busy_time %d\n", + len += sprintf(page + len, "tsb->tsa.iostat.dev_busy_time %d\n", tsb->tsa.iostat.dev_busy_time); - len += sprintf(page + len, PRINTK_HEADER - " tsb->tsa.iostat.dev_act_time %d\n", + len += sprintf(page + len, "tsb->tsa.iostat.dev_act_time %d\n", tsb->tsa.iostat.dev_act_time); sense = tsb->tsa.iostat.sense; break; case 2: /* ts_ddpc */ - len += sprintf(page + len, PRINTK_HEADER - " tsb->tsa.ddpc.rc %d\n", tsb->tsa.ddpc.rc); + len += sprintf(page + len, "tsb->tsa.ddpc.rc %d\n", + tsb->tsa.ddpc.rc); for (sl = 0; sl < 2; sl++) { - len += sprintf(page + len, PRINTK_HEADER - " tsb->tsa.ddpc.rcq %2d-%2d: ", + len += sprintf(page + len, + "tsb->tsa.ddpc.rcq %2d-%2d: ", (8 * sl), ((8 * sl) + 7)); rcq = tsb->tsa.ddpc.rcq; for (sct = 0; sct < 8; sct++) { - len += sprintf(page + len, " %02x", + len += sprintf(page + len, "%02x", rcq[8 * sl + sct]); } len += sprintf(page + len, "\n"); @@ -5772,15 +5737,15 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device, sense = tsb->tsa.ddpc.sense; break; case 3: /* tsa_intrg */ - len += sprintf(page + len, PRINTK_HEADER - " tsb->tsa.intrg.: not supported yet\n"); + len += sprintf(page + len, + "tsb->tsa.intrg.: not supported yet\n"); break; } if (sense) { for (sl = 0; sl < 4; sl++) { - len += sprintf(page + len, PRINTK_HEADER - " Sense(hex) %2d-%2d:", + len += sprintf(page + len, + "Sense(hex) %2d-%2d:", (8 * sl), ((8 * sl) + 7)); for (sct = 0; sct < 8; sct++) { len += sprintf(page + len, " %02x", @@ -5791,27 +5756,23 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device, if (sense[27] & DASD_SENSE_BIT_0) { /* 24 Byte Sense Data */ - sprintf(page + len, PRINTK_HEADER - " 24 Byte: %x MSG %x, " - "%s MSGb to SYSOP\n", + sprintf(page + len, + "24 Byte: %x MSG %x, %s MSGb to SYSOP\n", sense[7] >> 4, sense[7] & 0x0f, sense[1] & 0x10 ? "" : "no"); } else { /* 32 Byte Sense Data */ - sprintf(page + len, PRINTK_HEADER - " 32 Byte: Format: %x " - "Exception class %x\n", + sprintf(page + len, + "32 Byte: Format: %x Exception class %x\n", sense[6] & 0x0f, sense[22] >> 4); } } else { - sprintf(page + len, PRINTK_HEADER - " SORRY - NO VALID SENSE AVAILABLE\n"); + sprintf(page + len, "SORRY - NO VALID SENSE AVAILABLE\n"); } } else { - sprintf(page + len, PRINTK_HEADER - " SORRY - NO TSB DATA AVAILABLE\n"); + sprintf(page + len, "SORRY - NO TSB DATA AVAILABLE\n"); } - printk(KERN_ERR "%s", page); + dev_err(&device->cdev->dev, "%s", page); free_page((unsigned long) page); } @@ -6865,17 +6826,9 @@ 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) +static unsigned int dasd_eckd_max_sectors(struct dasd_block *block) { - unsigned int logical_block_size = block->bp_block; - struct request_queue *q = block->gdp->queue; - struct dasd_device *device = block->base; - int max; - - if (device->features & DASD_FEATURE_USERAW) { + 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 @@ -6883,19 +6836,10 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block) * 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; + return DASD_ECKD_MAX_BLOCKS_RAW << 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); - blk_queue_dma_alignment(q, PAGE_SIZE - 1); + + return DASD_ECKD_MAX_BLOCKS << block->s2b_shift; } static struct ccw_driver dasd_eckd_driver = { @@ -6927,7 +6871,7 @@ 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, + .max_sectors = dasd_eckd_max_sectors, .fill_geometry = dasd_eckd_fill_geometry, .start_IO = dasd_start_IO, .term_IO = dasd_term_IO, diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c index c956de711cf7..5064a616e041 100644 --- a/drivers/s390/block/dasd_eer.c +++ b/drivers/s390/block/dasd_eer.c @@ -7,8 +7,6 @@ * Author(s): Stefan Weinhuber <wein@de.ibm.com> */ -#define KMSG_COMPONENT "dasd-eckd" - #include <linux/init.h> #include <linux/fs.h> #include <linux/kernel.h> @@ -28,11 +26,6 @@ #include "dasd_int.h" #include "dasd_eckd.h" -#ifdef PRINTK_HEADER -#undef PRINTK_HEADER -#endif /* PRINTK_HEADER */ -#define PRINTK_HEADER "dasd(eer):" - /* * SECTION: the internal buffer */ diff --git a/drivers/s390/block/dasd_erp.c b/drivers/s390/block/dasd_erp.c index c07e6e713518..4c0d3a704513 100644 --- a/drivers/s390/block/dasd_erp.c +++ b/drivers/s390/block/dasd_erp.c @@ -9,8 +9,6 @@ * */ -#define KMSG_COMPONENT "dasd" - #include <linux/ctype.h> #include <linux/init.h> @@ -18,9 +16,6 @@ #include <asm/ebcdic.h> #include <linux/uaccess.h> -/* This is ugly... */ -#define PRINTK_HEADER "dasd_erp:" - #include "dasd_int.h" struct dasd_ccw_req * @@ -170,12 +165,12 @@ dasd_log_sense(struct dasd_ccw_req *cqr, struct irb *irb) device = cqr->startdev; if (cqr->intrc == -ETIMEDOUT) { dev_err(&device->cdev->dev, - "A timeout error occurred for cqr %p\n", cqr); + "A timeout error occurred for cqr %px\n", cqr); return; } if (cqr->intrc == -ENOLINK) { dev_err(&device->cdev->dev, - "A transport error occurred for cqr %p\n", cqr); + "A transport error occurred for cqr %px\n", cqr); return; } /* dump sense data */ diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index c06fa2b27120..bcbb2f8e91fe 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -25,11 +25,6 @@ #include "dasd_int.h" #include "dasd_fba.h" -#ifdef PRINTK_HEADER -#undef PRINTK_HEADER -#endif /* PRINTK_HEADER */ -#define PRINTK_HEADER "dasd(fba):" - #define FBA_DEFAULT_RETRIES 32 #define DASD_FBA_CCW_WRITE 0x41 @@ -660,30 +655,27 @@ static void dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req, struct irb *irb) { - char *page; struct ccw1 *act, *end, *last; int len, sl, sct, count; + struct device *dev; + char *page; + + dev = &device->cdev->dev; page = (char *) get_zeroed_page(GFP_ATOMIC); if (page == NULL) { DBF_DEV_EVENT(DBF_WARNING, device, "%s", - "No memory to dump sense data"); + "No memory to dump sense data"); return; } - len = sprintf(page, PRINTK_HEADER - " I/O status report for device %s:\n", - dev_name(&device->cdev->dev)); - len += sprintf(page + len, PRINTK_HEADER - " in req: %p CS: 0x%02X DS: 0x%02X\n", req, - irb->scsw.cmd.cstat, irb->scsw.cmd.dstat); - len += sprintf(page + len, PRINTK_HEADER - " device %s: Failing CCW: %p\n", - dev_name(&device->cdev->dev), + len = sprintf(page, "I/O status report:\n"); + len += sprintf(page + len, "in req: %px CS: 0x%02X DS: 0x%02X\n", + req, irb->scsw.cmd.cstat, irb->scsw.cmd.dstat); + len += sprintf(page + len, "Failing CCW: %px\n", (void *) (addr_t) irb->scsw.cmd.cpa); if (irb->esw.esw0.erw.cons) { for (sl = 0; sl < 4; sl++) { - len += sprintf(page + len, PRINTK_HEADER - " Sense(hex) %2d-%2d:", + len += sprintf(page + len, "Sense(hex) %2d-%2d:", (8 * sl), ((8 * sl) + 7)); for (sct = 0; sct < 8; sct++) { @@ -693,20 +685,18 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req, len += sprintf(page + len, "\n"); } } else { - len += sprintf(page + len, PRINTK_HEADER - " SORRY - NO VALID SENSE AVAILABLE\n"); + len += sprintf(page + len, "SORRY - NO VALID SENSE AVAILABLE\n"); } - printk(KERN_ERR "%s", page); + dev_err(dev, "%s", page); /* dump the Channel Program */ /* print first CCWs (maximum 8) */ act = req->cpaddr; - for (last = act; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++); + for (last = act; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++); end = min(act + 8, last); - len = sprintf(page, PRINTK_HEADER " Related CP in req: %p\n", req); + len = sprintf(page, "Related CP in req: %px\n", req); while (act <= end) { - len += sprintf(page + len, PRINTK_HEADER - " CCW %p: %08X %08X DAT:", + len += sprintf(page + len, "CCW %px: %08X %08X DAT:", act, ((int *) act)[0], ((int *) act)[1]); for (count = 0; count < 32 && count < act->count; count += sizeof(int)) @@ -716,19 +706,17 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req, len += sprintf(page + len, "\n"); act++; } - printk(KERN_ERR "%s", page); - + dev_err(dev, "%s", page); /* print failing CCW area */ len = 0; if (act < ((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa) - 2) { act = ((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa) - 2; - len += sprintf(page + len, PRINTK_HEADER "......\n"); + len += sprintf(page + len, "......\n"); } end = min((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa + 2, last); while (act <= end) { - len += sprintf(page + len, PRINTK_HEADER - " CCW %p: %08X %08X DAT:", + len += sprintf(page + len, "CCW %px: %08X %08X DAT:", act, ((int *) act)[0], ((int *) act)[1]); for (count = 0; count < 32 && count < act->count; count += sizeof(int)) @@ -742,11 +730,10 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req, /* print last CCWs */ if (act < last - 2) { act = last - 2; - len += sprintf(page + len, PRINTK_HEADER "......\n"); + len += sprintf(page + len, "......\n"); } while (act <= last) { - len += sprintf(page + len, PRINTK_HEADER - " CCW %p: %08X %08X DAT:", + len += sprintf(page + len, "CCW %px: %08X %08X DAT:", act, ((int *) act)[0], ((int *) act)[1]); for (count = 0; count < 32 && count < act->count; count += sizeof(int)) @@ -757,39 +744,13 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req, act++; } if (len > 0) - printk(KERN_ERR "%s", page); + dev_err(dev, "%s", page); free_page((unsigned long) page); } -/* - * Initialize block layer request queue. - */ -static void dasd_fba_setup_blk_queue(struct dasd_block *block) +static unsigned int dasd_fba_max_sectors(struct dasd_block *block) { - unsigned int logical_block_size = block->bp_block; - struct request_queue *q = block->gdp->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; - - /* 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); + return DASD_FBA_MAX_BLOCKS << block->s2b_shift; } static int dasd_fba_pe_handler(struct dasd_device *device, @@ -802,10 +763,11 @@ static struct dasd_discipline dasd_fba_discipline = { .owner = THIS_MODULE, .name = "FBA ", .ebcname = "FBA ", + .has_discard = true, .check_device = dasd_fba_check_characteristics, .do_analysis = dasd_fba_do_analysis, .pe_handler = dasd_fba_pe_handler, - .setup_blk_queue = dasd_fba_setup_blk_queue, + .max_sectors = dasd_fba_max_sectors, .fill_geometry = dasd_fba_fill_geometry, .start_IO = dasd_start_IO, .term_IO = dasd_term_IO, diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 55e3abe94cde..4533dd055ca8 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -11,8 +11,6 @@ * */ -#define KMSG_COMPONENT "dasd" - #include <linux/interrupt.h> #include <linux/major.h> #include <linux/fs.h> @@ -20,9 +18,6 @@ #include <linux/uaccess.h> -/* This is ugly... */ -#define PRINTK_HEADER "dasd_gendisk:" - #include "dasd_int.h" static unsigned int queue_depth = 32; @@ -39,6 +34,16 @@ MODULE_PARM_DESC(nr_hw_queues, "Default number of hardware queues for new DASD d */ int dasd_gendisk_alloc(struct dasd_block *block) { + struct queue_limits lim = { + /* + * With page sized segments, each segment can be translated into + * one idaw/tidaw. + */ + .max_segment_size = PAGE_SIZE, + .seg_boundary_mask = PAGE_SIZE - 1, + .dma_alignment = PAGE_SIZE - 1, + .max_segments = USHRT_MAX, + }; struct gendisk *gdp; struct dasd_device *base; int len, rc; @@ -58,11 +63,12 @@ int dasd_gendisk_alloc(struct dasd_block *block) if (rc) return rc; - gdp = blk_mq_alloc_disk(&block->tag_set, block); + gdp = blk_mq_alloc_disk(&block->tag_set, &lim, block); if (IS_ERR(gdp)) { blk_mq_free_tag_set(&block->tag_set); return PTR_ERR(gdp); } + blk_queue_flag_set(QUEUE_FLAG_NONROT, gdp->queue); /* Initialize gendisk structure. */ gdp->major = DASD_MAJOR; @@ -127,15 +133,15 @@ void dasd_gendisk_free(struct dasd_block *block) */ int dasd_scan_partitions(struct dasd_block *block) { - struct bdev_handle *bdev_handle; + struct file *bdev_file; int rc; - bdev_handle = bdev_open_by_dev(disk_devt(block->gdp), BLK_OPEN_READ, + bdev_file = bdev_file_open_by_dev(disk_devt(block->gdp), BLK_OPEN_READ, NULL, NULL); - if (IS_ERR(bdev_handle)) { + if (IS_ERR(bdev_file)) { DBF_DEV_EVENT(DBF_ERR, block->base, "scan partitions error, blkdev_get returned %ld", - PTR_ERR(bdev_handle)); + PTR_ERR(bdev_file)); return -ENODEV; } @@ -147,15 +153,15 @@ int dasd_scan_partitions(struct dasd_block *block) "scan partitions error, rc %d", rc); /* - * Since the matching bdev_release() call to the - * bdev_open_by_path() in this function is not called before + * Since the matching fput() call to the + * bdev_file_open_by_path() in this function is not called before * dasd_destroy_partitions the offline open_count limit needs to be - * increased from 0 to 1. This is done by setting device->bdev_handle + * increased from 0 to 1. This is done by setting device->bdev_file * (see dasd_generic_set_offline). As long as the partition detection * is running no offline should be allowed. That is why the assignment - * to block->bdev_handle is done AFTER the BLKRRPART ioctl. + * to block->bdev_file is done AFTER the BLKRRPART ioctl. */ - block->bdev_handle = bdev_handle; + block->bdev_file = bdev_file; return 0; } @@ -165,21 +171,21 @@ int dasd_scan_partitions(struct dasd_block *block) */ void dasd_destroy_partitions(struct dasd_block *block) { - struct bdev_handle *bdev_handle; + struct file *bdev_file; /* - * Get the bdev_handle pointer from the device structure and clear - * device->bdev_handle to lower the offline open_count limit again. + * Get the bdev_file pointer from the device structure and clear + * device->bdev_file to lower the offline open_count limit again. */ - bdev_handle = block->bdev_handle; - block->bdev_handle = NULL; + bdev_file = block->bdev_file; + block->bdev_file = NULL; - mutex_lock(&bdev_handle->bdev->bd_disk->open_mutex); - bdev_disk_changed(bdev_handle->bdev->bd_disk, true); - mutex_unlock(&bdev_handle->bdev->bd_disk->open_mutex); + mutex_lock(&file_bdev(bdev_file)->bd_disk->open_mutex); + bdev_disk_changed(file_bdev(bdev_file)->bd_disk, true); + mutex_unlock(&file_bdev(bdev_file)->bd_disk->open_mutex); /* Matching blkdev_put to the blkdev_get in dasd_scan_partitions. */ - bdev_release(bdev_handle); + fput(bdev_file); } int dasd_gendisk_init(void) diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 1b1b8a41c4d4..e5f40536b425 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -113,9 +113,6 @@ do { \ __dev_id.ssid, __dev_id.devno, d_data); \ } while (0) -/* limit size for an errorstring */ -#define ERRORLENGTH 30 - /* definition of dbf debug levels */ #define DBF_EMERG 0 /* system is unusable */ #define DBF_ALERT 1 /* action must be taken immediately */ @@ -126,32 +123,6 @@ do { \ #define DBF_INFO 6 /* informational */ #define DBF_DEBUG 6 /* debug-level messages */ -/* messages to be written via klogd and dbf */ -#define DEV_MESSAGE(d_loglevel,d_device,d_string,d_args...)\ -do { \ - printk(d_loglevel PRINTK_HEADER " %s: " d_string "\n", \ - dev_name(&d_device->cdev->dev), d_args); \ - DBF_DEV_EVENT(DBF_ALERT, d_device, d_string, d_args); \ -} while(0) - -#define MESSAGE(d_loglevel,d_string,d_args...)\ -do { \ - printk(d_loglevel PRINTK_HEADER " " d_string "\n", d_args); \ - DBF_EVENT(DBF_ALERT, d_string, d_args); \ -} while(0) - -/* messages to be written via klogd only */ -#define DEV_MESSAGE_LOG(d_loglevel,d_device,d_string,d_args...)\ -do { \ - printk(d_loglevel PRINTK_HEADER " %s: " d_string "\n", \ - dev_name(&d_device->cdev->dev), d_args); \ -} while(0) - -#define MESSAGE_LOG(d_loglevel,d_string,d_args...)\ -do { \ - printk(d_loglevel PRINTK_HEADER " " d_string "\n", d_args); \ -} while(0) - /* Macro to calculate number of blocks per page */ #define BLOCKS_PER_PAGE(blksize) (PAGE_SIZE / blksize) @@ -322,6 +293,7 @@ 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 */ + bool has_discard; struct list_head list; /* used for list of disciplines */ @@ -360,10 +332,7 @@ 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 *); + unsigned int (*max_sectors)(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 @@ -650,7 +619,7 @@ struct dasd_block { struct gendisk *gdp; spinlock_t request_queue_lock; struct blk_mq_tag_set tag_set; - struct bdev_handle *bdev_handle; + struct file *bdev_file; atomic_t open_count; unsigned long blocks; /* size of volume in blocks */ diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 61b9675e2a67..7e0ed7032f76 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -10,8 +10,6 @@ * i/o controls for the dasd driver. */ -#define KMSG_COMPONENT "dasd" - #include <linux/interrupt.h> #include <linux/compat.h> #include <linux/major.h> @@ -24,12 +22,8 @@ #include <linux/uaccess.h> #include <linux/dasd_mod.h> -/* This is ugly... */ -#define PRINTK_HEADER "dasd_ioctl:" - #include "dasd_int.h" - static int dasd_ioctl_api_version(void __user *argp) { @@ -537,7 +531,7 @@ static int __dasd_ioctl_information(struct dasd_block *block, * This must be hidden from user-space. */ dasd_info->open_count = atomic_read(&block->open_count); - if (!block->bdev_handle) + if (!block->bdev_file) dasd_info->open_count++; /* diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c index 62a859ea67f8..0faaa437d9be 100644 --- a/drivers/s390/block/dasd_proc.c +++ b/drivers/s390/block/dasd_proc.c @@ -11,8 +11,6 @@ * */ -#define KMSG_COMPONENT "dasd" - #include <linux/ctype.h> #include <linux/slab.h> #include <linux/string.h> @@ -23,9 +21,6 @@ #include <asm/debug.h> #include <linux/uaccess.h> -/* This is ugly... */ -#define PRINTK_HEADER "dasd_proc:" - #include "dasd_int.h" static struct proc_dir_entry *dasd_proc_root_entry = NULL; diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 4b7ecd4fd431..9c8f529b827c 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -546,6 +546,9 @@ static const struct attribute_group *dcssblk_dev_attr_groups[] = { static ssize_t dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { + struct queue_limits lim = { + .logical_block_size = 4096, + }; int rc, i, j, num_of_segments; struct dcssblk_dev_info *dev_info; struct segment_info *seg_info, *temp; @@ -629,9 +632,9 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char dev_info->dev.release = dcssblk_release_segment; dev_info->dev.groups = dcssblk_dev_attr_groups; INIT_LIST_HEAD(&dev_info->lh); - dev_info->gd = blk_alloc_disk(NUMA_NO_NODE); - if (dev_info->gd == NULL) { - rc = -ENOMEM; + dev_info->gd = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(dev_info->gd)) { + rc = PTR_ERR(dev_info->gd); goto seg_list_del; } dev_info->gd->major = dcssblk_major; @@ -639,7 +642,6 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char dev_info->gd->fops = &dcssblk_devops; dev_info->gd->private_data = dev_info; dev_info->gd->flags |= GENHD_FL_NO_PART; - blk_queue_logical_block_size(dev_info->gd->queue, 4096); blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->gd->queue); seg_byte_size = (dev_info->end - dev_info->start + 1); diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index ade95e91b3c8..9f6fdd0daa74 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -435,10 +435,17 @@ static const struct blk_mq_ops scm_mq_ops = { int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) { - unsigned int devindex, nr_max_blk; + struct queue_limits lim = { + .logical_block_size = 1 << 12, + }; + unsigned int devindex; struct request_queue *rq; int len, ret; + lim.max_segments = min(scmdev->nr_max_block, + (unsigned int) (PAGE_SIZE / sizeof(struct aidaw))); + lim.max_hw_sectors = lim.max_segments << 3; /* 8 * 512 = blk_size */ + devindex = atomic_inc_return(&nr_devices) - 1; /* scma..scmz + scmaa..scmzz */ if (devindex > 701) { @@ -462,18 +469,12 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) if (ret) goto out; - bdev->gendisk = blk_mq_alloc_disk(&bdev->tag_set, scmdev); + bdev->gendisk = blk_mq_alloc_disk(&bdev->tag_set, &lim, scmdev); if (IS_ERR(bdev->gendisk)) { ret = PTR_ERR(bdev->gendisk); goto out_tag; } rq = bdev->rq = bdev->gendisk->queue; - nr_max_blk = min(scmdev->nr_max_block, - (unsigned int) (PAGE_SIZE / sizeof(struct aidaw))); - - blk_queue_logical_block_size(rq, 1 << 12); - blk_queue_max_hw_sectors(rq, nr_max_blk << 3); /* 8 * 512 = blk_size */ - blk_queue_max_segments(rq, nr_max_blk); blk_queue_flag_set(QUEUE_FLAG_NONROT, rq); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, rq); diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 44680f65ea14..9969f4e2f1c3 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -332,7 +332,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, sdev->sg_reserved_size = INT_MAX; - q = blk_mq_init_queue(&sdev->host->tag_set); + q = blk_mq_alloc_queue(&sdev->host->tag_set, NULL, NULL); if (IS_ERR(q)) { /* release fn is set up in scsi_sysfs_device_initialise, so * have to free and put manually here */ diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c index b24190526ce9..adf19e8c4c8a 100644 --- a/drivers/spi/spi-cs42l43.c +++ b/drivers/spi/spi-cs42l43.c @@ -148,8 +148,7 @@ static void cs42l43_set_cs(struct spi_device *spi, bool is_high) { struct cs42l43_spi *priv = spi_controller_get_devdata(spi->controller); - if (spi_get_chipselect(spi, 0) == 0) - regmap_write(priv->regmap, CS42L43_SPI_CONFIG2, !is_high); + regmap_write(priv->regmap, CS42L43_SPI_CONFIG2, !is_high); } static int cs42l43_prepare_message(struct spi_controller *ctlr, struct spi_message *msg) diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 8eb9eb7ce5df..7f6ca8177845 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -91,7 +91,7 @@ static int iblock_configure_device(struct se_device *dev) { struct iblock_dev *ib_dev = IBLOCK_DEV(dev); struct request_queue *q; - struct bdev_handle *bdev_handle; + struct file *bdev_file; struct block_device *bd; struct blk_integrity *bi; blk_mode_t mode = BLK_OPEN_READ; @@ -117,14 +117,14 @@ static int iblock_configure_device(struct se_device *dev) else dev->dev_flags |= DF_READ_ONLY; - bdev_handle = bdev_open_by_path(ib_dev->ibd_udev_path, mode, ib_dev, + bdev_file = bdev_file_open_by_path(ib_dev->ibd_udev_path, mode, ib_dev, NULL); - if (IS_ERR(bdev_handle)) { - ret = PTR_ERR(bdev_handle); + if (IS_ERR(bdev_file)) { + ret = PTR_ERR(bdev_file); goto out_free_bioset; } - ib_dev->ibd_bdev_handle = bdev_handle; - ib_dev->ibd_bd = bd = bdev_handle->bdev; + ib_dev->ibd_bdev_file = bdev_file; + ib_dev->ibd_bd = bd = file_bdev(bdev_file); q = bdev_get_queue(bd); @@ -180,7 +180,7 @@ static int iblock_configure_device(struct se_device *dev) return 0; out_blkdev_put: - bdev_release(ib_dev->ibd_bdev_handle); + fput(ib_dev->ibd_bdev_file); out_free_bioset: bioset_exit(&ib_dev->ibd_bio_set); out: @@ -205,8 +205,8 @@ static void iblock_destroy_device(struct se_device *dev) { struct iblock_dev *ib_dev = IBLOCK_DEV(dev); - if (ib_dev->ibd_bdev_handle) - bdev_release(ib_dev->ibd_bdev_handle); + if (ib_dev->ibd_bdev_file) + fput(ib_dev->ibd_bdev_file); bioset_exit(&ib_dev->ibd_bio_set); } diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h index 683f9a55945b..91f6f4280666 100644 --- a/drivers/target/target_core_iblock.h +++ b/drivers/target/target_core_iblock.h @@ -32,7 +32,7 @@ struct iblock_dev { u32 ibd_flags; struct bio_set ibd_bio_set; struct block_device *ibd_bd; - struct bdev_handle *ibd_bdev_handle; + struct file *ibd_bdev_file; bool ibd_readonly; struct iblock_dev_plug *ibd_plug; } ____cacheline_aligned; diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index ed4fd22eac6e..f98ebb18666b 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -352,7 +352,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd) struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr; struct pscsi_dev_virt *pdv = PSCSI_DEV(dev); struct Scsi_Host *sh = sd->host; - struct bdev_handle *bdev_handle; + struct file *bdev_file; int ret; if (scsi_device_get(sd)) { @@ -366,18 +366,18 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd) * Claim exclusive struct block_device access to struct scsi_device * for TYPE_DISK and TYPE_ZBC using supplied udev_path */ - bdev_handle = bdev_open_by_path(dev->udev_path, + bdev_file = bdev_file_open_by_path(dev->udev_path, BLK_OPEN_WRITE | BLK_OPEN_READ, pdv, NULL); - if (IS_ERR(bdev_handle)) { + if (IS_ERR(bdev_file)) { pr_err("pSCSI: bdev_open_by_path() failed\n"); scsi_device_put(sd); - return PTR_ERR(bdev_handle); + return PTR_ERR(bdev_file); } - pdv->pdv_bdev_handle = bdev_handle; + pdv->pdv_bdev_file = bdev_file; ret = pscsi_add_device_to_list(dev, sd); if (ret) { - bdev_release(bdev_handle); + fput(bdev_file); scsi_device_put(sd); return ret; } @@ -564,9 +564,9 @@ static void pscsi_destroy_device(struct se_device *dev) * from pscsi_create_type_disk() */ if ((sd->type == TYPE_DISK || sd->type == TYPE_ZBC) && - pdv->pdv_bdev_handle) { - bdev_release(pdv->pdv_bdev_handle); - pdv->pdv_bdev_handle = NULL; + pdv->pdv_bdev_file) { + fput(pdv->pdv_bdev_file); + pdv->pdv_bdev_file = NULL; } /* * For HBA mode PHV_LLD_SCSI_HOST_NO, release the reference @@ -997,8 +997,8 @@ static sector_t pscsi_get_blocks(struct se_device *dev) { struct pscsi_dev_virt *pdv = PSCSI_DEV(dev); - if (pdv->pdv_bdev_handle) - return bdev_nr_sectors(pdv->pdv_bdev_handle->bdev); + if (pdv->pdv_bdev_file) + return bdev_nr_sectors(file_bdev(pdv->pdv_bdev_file)); return 0; } diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h index b0a3ef136592..9acaa21e4c78 100644 --- a/drivers/target/target_core_pscsi.h +++ b/drivers/target/target_core_pscsi.h @@ -37,7 +37,7 @@ struct pscsi_dev_virt { int pdv_channel_id; int pdv_target_id; int pdv_lun_id; - struct bdev_handle *pdv_bdev_handle; + struct file *pdv_bdev_file; struct scsi_device *pdv_sd; struct Scsi_Host *pdv_lld_host; } ____cacheline_aligned; diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c index 4b1092127694..1892e49a8e6a 100644 --- a/drivers/tee/optee/device.c +++ b/drivers/tee/optee/device.c @@ -90,13 +90,14 @@ static int optee_register_device(const uuid_t *device_uuid, u32 func) if (rc) { pr_err("device registration failed, err: %d\n", rc); put_device(&optee_device->dev); + return rc; } if (func == PTA_CMD_GET_DEVICES_SUPP) device_create_file(&optee_device->dev, &dev_attr_need_supplicant); - return rc; + return 0; } static int __optee_enumerate_devices(u32 func) diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c index 3b04c6ec4fca..40d664a66cdc 100644 --- a/drivers/thermal/intel/intel_hfi.c +++ b/drivers/thermal/intel/intel_hfi.c @@ -607,7 +607,7 @@ void __init intel_hfi_init(void) /* There is one HFI instance per die/package. */ max_hfi_instances = topology_max_packages() * - topology_max_die_per_package(); + topology_max_dies_per_package(); /* * This allocation may fail. CPU hotplug callbacks must check diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c index bc6eb0dd66a4..4ba649370aa1 100644 --- a/drivers/thermal/intel/intel_powerclamp.c +++ b/drivers/thermal/intel/intel_powerclamp.c @@ -587,7 +587,7 @@ static int powerclamp_idle_injection_register(void) poll_pkg_cstate_enable = false; if (cpumask_equal(cpu_present_mask, idle_injection_cpu_mask)) { ii_dev = idle_inject_register_full(idle_injection_cpu_mask, idle_inject_update); - if (topology_max_packages() == 1 && topology_max_die_per_package() == 1) + if (topology_max_packages() == 1 && topology_max_dies_per_package() == 1) poll_pkg_cstate_enable = true; } else { ii_dev = idle_inject_register(idle_injection_cpu_mask); diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c index 11a7f8108bbb..f6c2e5964b8f 100644 --- a/drivers/thermal/intel/x86_pkg_temp_thermal.c +++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c @@ -494,7 +494,7 @@ static int __init pkg_temp_thermal_init(void) if (!x86_match_cpu(pkg_temp_thermal_ids)) return -ENODEV; - max_id = topology_max_packages() * topology_max_die_per_package(); + max_id = topology_max_packages() * topology_max_dies_per_package(); zones = kcalloc(max_id, sizeof(struct zone_device *), GFP_KERNEL); if (!zones) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 900114ba4371..fad40c4bc710 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1249,6 +1249,9 @@ int tb_port_update_credits(struct tb_port *port) ret = tb_port_do_update_credits(port); if (ret) return ret; + + if (!port->dual_link_port) + return 0; return tb_port_do_update_credits(port->dual_link_port); } diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index 2d1f350a4bea..c1d43f040c43 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -357,9 +357,9 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios, long rate; int ret; - clk_disable_unprepare(d->clk); rate = clk_round_rate(d->clk, newrate); - if (rate > 0) { + if (rate > 0 && p->uartclk != rate) { + clk_disable_unprepare(d->clk); /* * Note that any clock-notifer worker will block in * serial8250_update_uartclk() until we are done. @@ -367,8 +367,8 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios, ret = clk_set_rate(d->clk, newrate); if (!ret) p->uartclk = rate; + clk_prepare_enable(d->clk); } - clk_prepare_enable(d->clk); dw8250_do_set_termios(p, termios, old); } diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 5ddf110aedbe..bbcbc91482af 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2345,9 +2345,12 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios, lpuart32_write(&sport->port, bd, UARTBAUD); lpuart32_serial_setbrg(sport, baud); - lpuart32_write(&sport->port, modem, UARTMODIR); - lpuart32_write(&sport->port, ctrl, UARTCTRL); + /* disable CTS before enabling UARTCTRL_TE to avoid pending idle preamble */ + lpuart32_write(&sport->port, modem & ~UARTMODIR_TXCTSE, UARTMODIR); /* restore control register */ + lpuart32_write(&sport->port, ctrl, UARTCTRL); + /* re-enable the CTS if needed */ + lpuart32_write(&sport->port, modem, UARTMODIR); if ((ctrl & (UARTCTRL_PE | UARTCTRL_M)) == UARTCTRL_PE) sport->is_cs7 = true; diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 4aa72d5aeafb..e14813250616 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -462,8 +462,7 @@ static void imx_uart_stop_tx(struct uart_port *port) } } -/* called with port.lock taken and irqs off */ -static void imx_uart_stop_rx(struct uart_port *port) +static void imx_uart_stop_rx_with_loopback_ctrl(struct uart_port *port, bool loopback) { struct imx_port *sport = (struct imx_port *)port; u32 ucr1, ucr2, ucr4, uts; @@ -485,7 +484,7 @@ static void imx_uart_stop_rx(struct uart_port *port) /* See SER_RS485_ENABLED/UTS_LOOP comment in imx_uart_probe() */ if (port->rs485.flags & SER_RS485_ENABLED && port->rs485.flags & SER_RS485_RTS_ON_SEND && - sport->have_rtscts && !sport->have_rtsgpio) { + sport->have_rtscts && !sport->have_rtsgpio && loopback) { uts = imx_uart_readl(sport, imx_uart_uts_reg(sport)); uts |= UTS_LOOP; imx_uart_writel(sport, uts, imx_uart_uts_reg(sport)); @@ -498,6 +497,16 @@ static void imx_uart_stop_rx(struct uart_port *port) } /* called with port.lock taken and irqs off */ +static void imx_uart_stop_rx(struct uart_port *port) +{ + /* + * Stop RX and enable loopback in order to make sure RS485 bus + * is not blocked. Se comment in imx_uart_probe(). + */ + imx_uart_stop_rx_with_loopback_ctrl(port, true); +} + +/* called with port.lock taken and irqs off */ static void imx_uart_enable_ms(struct uart_port *port) { struct imx_port *sport = (struct imx_port *)port; @@ -682,9 +691,14 @@ static void imx_uart_start_tx(struct uart_port *port) imx_uart_rts_inactive(sport, &ucr2); imx_uart_writel(sport, ucr2, UCR2); + /* + * Since we are about to transmit we can not stop RX + * with loopback enabled because that will make our + * transmitted data being just looped to RX. + */ if (!(port->rs485.flags & SER_RS485_RX_DURING_TX) && !port->rs485_rx_during_tx_gpio) - imx_uart_stop_rx(port); + imx_uart_stop_rx_with_loopback_ctrl(port, false); sport->tx_state = WAIT_AFTER_RTS; diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index e63a8fbe63bd..99e08737f293 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -851,19 +851,21 @@ static void qcom_geni_serial_stop_tx(struct uart_port *uport) } static void qcom_geni_serial_send_chunk_fifo(struct uart_port *uport, - unsigned int remaining) + unsigned int chunk) { struct qcom_geni_serial_port *port = to_dev_port(uport); struct circ_buf *xmit = &uport->state->xmit; - unsigned int tx_bytes; + unsigned int tx_bytes, c, remaining = chunk; u8 buf[BYTES_PER_FIFO_WORD]; while (remaining) { memset(buf, 0, sizeof(buf)); tx_bytes = min(remaining, BYTES_PER_FIFO_WORD); - memcpy(buf, &xmit->buf[xmit->tail], tx_bytes); - uart_xmit_advance(uport, tx_bytes); + for (c = 0; c < tx_bytes ; c++) { + buf[c] = xmit->buf[xmit->tail]; + uart_xmit_advance(uport, 1); + } iowrite32_rep(uport->membase + SE_GENI_TX_FIFOn, buf, 1); diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c index 88975a4df306..72b6f4f326e2 100644 --- a/drivers/tty/serial/serial_port.c +++ b/drivers/tty/serial/serial_port.c @@ -46,8 +46,31 @@ out: return 0; } +static int serial_port_runtime_suspend(struct device *dev) +{ + struct serial_port_device *port_dev = to_serial_base_port_device(dev); + struct uart_port *port = port_dev->port; + unsigned long flags; + bool busy; + + if (port->flags & UPF_DEAD) + return 0; + + uart_port_lock_irqsave(port, &flags); + busy = __serial_port_busy(port); + if (busy) + port->ops->start_tx(port); + uart_port_unlock_irqrestore(port, flags); + + if (busy) + pm_runtime_mark_last_busy(dev); + + return busy ? -EBUSY : 0; +} + static DEFINE_RUNTIME_DEV_PM_OPS(serial_port_pm, - NULL, serial_port_runtime_resume, NULL); + serial_port_runtime_suspend, + serial_port_runtime_resume, NULL); static int serial_port_probe(struct device *dev) { diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 156efda7c80d..38a765eadbe2 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -381,7 +381,7 @@ static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr) u32 *ln = vc->vc_uni_lines[vc->state.y]; unsigned int x = vc->state.x, cols = vc->vc_cols; - memcpy(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln)); + memmove(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln)); memset32(&ln[cols - nr], ' ', nr); } } diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 3b89c9d4aa40..eac7fff6992d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -10593,7 +10593,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) err = blk_mq_alloc_tag_set(&hba->tmf_tag_set); if (err < 0) goto out_remove_scsi_host; - hba->tmf_queue = blk_mq_init_queue(&hba->tmf_tag_set); + hba->tmf_queue = blk_mq_alloc_queue(&hba->tmf_tag_set, NULL, NULL); if (IS_ERR(hba->tmf_queue)) { err = PTR_ERR(hba->tmf_queue); goto free_tmf_tag_set; diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 39eef470f8fa..8fde5204e88b 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -1712,8 +1712,8 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba) * 2. Poll queues do not need ESI. */ nr_irqs = hba->nr_hw_queues - hba->nr_queues[HCTX_TYPE_POLL]; - ret = platform_msi_domain_alloc_irqs(hba->dev, nr_irqs, - ufs_qcom_write_msi_msg); + ret = platform_device_msi_init_and_alloc_irqs(hba->dev, nr_irqs, + ufs_qcom_write_msi_msg); if (ret) { dev_err(hba->dev, "Failed to request Platform MSI %d\n", ret); return ret; @@ -1742,7 +1742,7 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba) devm_free_irq(hba->dev, desc->irq, hba); } msi_unlock_descs(hba->dev); - platform_msi_domain_free_irqs(hba->dev); + platform_device_msi_free_irqs_all(hba->dev); } else { if (host->hw_ver.major == 6 && host->hw_ver.minor == 0 && host->hw_ver.step == 0) @@ -1818,7 +1818,7 @@ static void ufs_qcom_remove(struct platform_device *pdev) pm_runtime_get_sync(&(pdev)->dev); ufshcd_remove(hba); - platform_msi_domain_free_irqs(hba->dev); + platform_device_msi_free_irqs_all(hba->dev); } static const struct of_device_id ufs_qcom_of_match[] __maybe_unused = { diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 12b6dfeaf658..edf74458474a 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1664,9 +1664,10 @@ static void __usb_hcd_giveback_urb(struct urb *urb) usb_put_urb(urb); } -static void usb_giveback_urb_bh(struct tasklet_struct *t) +static void usb_giveback_urb_bh(struct work_struct *work) { - struct giveback_urb_bh *bh = from_tasklet(bh, t, bh); + struct giveback_urb_bh *bh = + container_of(work, struct giveback_urb_bh, bh); struct list_head local_list; spin_lock_irq(&bh->lock); @@ -1691,9 +1692,9 @@ static void usb_giveback_urb_bh(struct tasklet_struct *t) spin_lock_irq(&bh->lock); if (!list_empty(&bh->head)) { if (bh->high_prio) - tasklet_hi_schedule(&bh->bh); + queue_work(system_bh_highpri_wq, &bh->bh); else - tasklet_schedule(&bh->bh); + queue_work(system_bh_wq, &bh->bh); } bh->running = false; spin_unlock_irq(&bh->lock); @@ -1706,7 +1707,7 @@ static void usb_giveback_urb_bh(struct tasklet_struct *t) * @status: completion status code for the URB. * * Context: atomic. The completion callback is invoked in caller's context. - * For HCDs with HCD_BH flag set, the completion callback is invoked in tasklet + * For HCDs with HCD_BH flag set, the completion callback is invoked in BH * context (except for URBs submitted to the root hub which always complete in * caller's context). * @@ -1725,7 +1726,7 @@ void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status) struct giveback_urb_bh *bh; bool running; - /* pass status to tasklet via unlinked */ + /* pass status to BH via unlinked */ if (likely(!urb->unlinked)) urb->unlinked = status; @@ -1747,9 +1748,9 @@ void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status) if (running) ; else if (bh->high_prio) - tasklet_hi_schedule(&bh->bh); + queue_work(system_bh_highpri_wq, &bh->bh); else - tasklet_schedule(&bh->bh); + queue_work(system_bh_wq, &bh->bh); } EXPORT_SYMBOL_GPL(usb_hcd_giveback_urb); @@ -2540,7 +2541,7 @@ static void init_giveback_urb_bh(struct giveback_urb_bh *bh) spin_lock_init(&bh->lock); INIT_LIST_HEAD(&bh->head); - tasklet_setup(&bh->bh, usb_giveback_urb_bh); + INIT_WORK(&bh->bh, usb_giveback_urb_bh); } struct usb_hcd *__usb_create_hcd(const struct hc_driver *driver, @@ -2926,7 +2927,7 @@ int usb_add_hcd(struct usb_hcd *hcd, && device_can_wakeup(&hcd->self.root_hub->dev)) dev_dbg(hcd->self.controller, "supports USB remote wakeup\n"); - /* initialize tasklets */ + /* initialize BHs */ init_giveback_urb_bh(&hcd->high_prio_bh); hcd->high_prio_bh.high_prio = true; init_giveback_urb_bh(&hcd->low_prio_bh); @@ -3036,7 +3037,7 @@ void usb_remove_hcd(struct usb_hcd *hcd) mutex_unlock(&usb_bus_idr_lock); /* - * tasklet_kill() isn't needed here because: + * flush_work() isn't needed here because: * - driver's disconnect() called from usb_disconnect() should * make sure its URBs are completed during the disconnect() * callback diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index c628c1abc907..4d63496f98b6 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -573,7 +573,7 @@ static int match_location(struct usb_device *peer_hdev, void *p) struct usb_hub *peer_hub = usb_hub_to_struct_hub(peer_hdev); struct usb_device *hdev = to_usb_device(port_dev->dev.parent->parent); - if (!peer_hub) + if (!peer_hub || port_dev->connect_type == USB_PORT_NOT_USED) return 0; hcd = bus_to_hcd(hdev->bus); @@ -584,7 +584,8 @@ static int match_location(struct usb_device *peer_hdev, void *p) for (port1 = 1; port1 <= peer_hdev->maxchild; port1++) { peer = peer_hub->ports[port1 - 1]; - if (peer && peer->location == port_dev->location) { + if (peer && peer->connect_type != USB_PORT_NOT_USED && + peer->location == port_dev->location) { link_peers_report(port_dev, peer); return 1; /* done */ } diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index e2a059cfda2c..28f4e6552e84 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1346,7 +1346,7 @@ parse_ntb: if (to_process == 1 && (*(unsigned char *)(ntb_ptr + block_len) == 0x00)) { to_process--; - } else if (to_process > 0) { + } else if ((to_process > 0) && (block_len != 0)) { ntb_ptr = (unsigned char *)(ntb_ptr + block_len); goto parse_ntb; } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index f0d8a607ff21..4f64b814d4aa 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -326,7 +326,13 @@ static unsigned int xhci_ring_expansion_needed(struct xhci_hcd *xhci, struct xhc /* how many trbs will be queued past the enqueue segment? */ trbs_past_seg = enq_used + num_trbs - (TRBS_PER_SEGMENT - 1); - if (trbs_past_seg <= 0) + /* + * Consider expanding the ring already if num_trbs fills the current + * segment (i.e. trbs_past_seg == 0), not only when num_trbs goes into + * the next segment. Avoids confusing full ring with special empty ring + * case below + */ + if (trbs_past_seg < 0) return 0; /* Empty ring special case, enqueue stuck on link trb while dequeue advanced */ diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c index 4e0eef1440b7..300aeef160e7 100644 --- a/drivers/usb/storage/isd200.c +++ b/drivers/usb/storage/isd200.c @@ -1105,7 +1105,7 @@ static void isd200_dump_driveid(struct us_data *us, u16 *id) static int isd200_get_inquiry_data( struct us_data *us ) { struct isd200_info *info = (struct isd200_info *)us->extra; - int retStatus = ISD200_GOOD; + int retStatus; u16 *id = info->id; usb_stor_dbg(us, "Entering isd200_get_inquiry_data\n"); @@ -1137,6 +1137,13 @@ static int isd200_get_inquiry_data( struct us_data *us ) isd200_fix_driveid(id); isd200_dump_driveid(us, id); + /* Prevent division by 0 in isd200_scsi_to_ata() */ + if (id[ATA_ID_HEADS] == 0 || id[ATA_ID_SECTORS] == 0) { + usb_stor_dbg(us, " Invalid ATA Identify data\n"); + retStatus = ISD200_ERROR; + goto Done; + } + memset(&info->InquiryData, 0, sizeof(info->InquiryData)); /* Standard IDE interface only supports disks */ @@ -1202,6 +1209,7 @@ static int isd200_get_inquiry_data( struct us_data *us ) } } + Done: usb_stor_dbg(us, "Leaving isd200_get_inquiry_data %08X\n", retStatus); return(retStatus); @@ -1481,22 +1489,27 @@ static int isd200_init_info(struct us_data *us) static int isd200_Initialization(struct us_data *us) { + int rc = 0; + usb_stor_dbg(us, "ISD200 Initialization...\n"); /* Initialize ISD200 info struct */ - if (isd200_init_info(us) == ISD200_ERROR) { + if (isd200_init_info(us) < 0) { usb_stor_dbg(us, "ERROR Initializing ISD200 Info struct\n"); + rc = -ENOMEM; } else { /* Get device specific data */ - if (isd200_get_inquiry_data(us) != ISD200_GOOD) + if (isd200_get_inquiry_data(us) != ISD200_GOOD) { usb_stor_dbg(us, "ISD200 Initialization Failure\n"); - else + rc = -EINVAL; + } else { usb_stor_dbg(us, "ISD200 Initialization complete\n"); + } } - return 0; + return rc; } diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index f81bec0c7b86..f8ea3054be54 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -559,16 +559,21 @@ static ssize_t hpd_show(struct device *dev, struct device_attribute *attr, char } static DEVICE_ATTR_RO(hpd); -static struct attribute *dp_altmode_attrs[] = { +static struct attribute *displayport_attrs[] = { &dev_attr_configuration.attr, &dev_attr_pin_assignment.attr, &dev_attr_hpd.attr, NULL }; -static const struct attribute_group dp_altmode_group = { +static const struct attribute_group displayport_group = { .name = "displayport", - .attrs = dp_altmode_attrs, + .attrs = displayport_attrs, +}; + +static const struct attribute_group *displayport_groups[] = { + &displayport_group, + NULL, }; int dp_altmode_probe(struct typec_altmode *alt) @@ -576,7 +581,6 @@ int dp_altmode_probe(struct typec_altmode *alt) const struct typec_altmode *port = typec_altmode_get_partner(alt); struct fwnode_handle *fwnode; struct dp_altmode *dp; - int ret; /* FIXME: Port can only be DFP_U. */ @@ -587,10 +591,6 @@ int dp_altmode_probe(struct typec_altmode *alt) DP_CAP_PIN_ASSIGN_DFP_D(alt->vdo))) return -ENODEV; - ret = sysfs_create_group(&alt->dev.kobj, &dp_altmode_group); - if (ret) - return ret; - dp = devm_kzalloc(&alt->dev, sizeof(*dp), GFP_KERNEL); if (!dp) return -ENOMEM; @@ -624,7 +624,6 @@ void dp_altmode_remove(struct typec_altmode *alt) { struct dp_altmode *dp = typec_altmode_get_drvdata(alt); - sysfs_remove_group(&alt->dev.kobj, &dp_altmode_group); cancel_work_sync(&dp->work); if (dp->connector_fwnode) { @@ -649,6 +648,7 @@ static struct typec_altmode_driver dp_altmode_driver = { .driver = { .name = "typec_displayport", .owner = THIS_MODULE, + .dev_groups = displayport_groups, }, }; module_typec_altmode_driver(dp_altmode_driver); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 66e532edcece..096597231027 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4873,8 +4873,11 @@ static void run_state_machine(struct tcpm_port *port) break; case PORT_RESET: tcpm_reset_port(port); - tcpm_set_cc(port, tcpm_default_state(port) == SNK_UNATTACHED ? - TYPEC_CC_RD : tcpm_rp_cc(port)); + if (port->self_powered) + tcpm_set_cc(port, TYPEC_CC_OPEN); + else + tcpm_set_cc(port, tcpm_default_state(port) == SNK_UNATTACHED ? + TYPEC_CC_RD : tcpm_rp_cc(port)); tcpm_set_state(port, PORT_RESET_WAIT_OFF, PD_T_ERROR_RECOVERY); break; diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index 53a7ede8556d..faccc942b381 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -301,6 +301,7 @@ static const struct of_device_id pmic_glink_ucsi_of_quirks[] = { { .compatible = "qcom,sc8180x-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, }, { .compatible = "qcom,sc8280xp-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, }, { .compatible = "qcom,sm8350-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, }, + { .compatible = "qcom,sm8550-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, }, {} }; diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index c26ee6fd73c9..8fdccf033b2d 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -1010,8 +1010,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) goto getmem_done; } pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n"); - } else { - goto err1; } /* diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 3b9f080109d7..2faa4bf78c7a 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -2220,7 +2220,7 @@ static __init void xen_alloc_callback_vector(void) return; pr_info("Xen HVM callback vector for event delivery is enabled\n"); - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_xen_hvm_callback); + sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_xen_hvm_callback); } #else void xen_setup_callback_vector(void) {} |