diff options
Diffstat (limited to 'drivers')
259 files changed, 9915 insertions, 2706 deletions
diff --git a/drivers/Kconfig b/drivers/Kconfig index 74920bda3fda..dcecc9f6e33f 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -138,6 +138,10 @@ source "drivers/virt/Kconfig" source "drivers/virtio/Kconfig" +source "drivers/vdpa/Kconfig" + +source "drivers/vhost/Kconfig" + source "drivers/hv/Kconfig" source "drivers/xen/Kconfig" diff --git a/drivers/Makefile b/drivers/Makefile index 7646549a1e93..c0cd1b9075e3 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -42,6 +42,7 @@ obj-$(CONFIG_DMADEVICES) += dma/ obj-y += soc/ obj-$(CONFIG_VIRTIO) += virtio/ +obj-$(CONFIG_VDPA) += vdpa/ obj-$(CONFIG_XEN) += xen/ # regulators early, since some subsystems rely on them to initialize diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index ed3d2d1a7ae9..7d04424189df 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1015,6 +1015,7 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev) return ops; if (dev_is_pci(dev)) { + struct iommu_fwspec *fwspec; struct pci_bus *bus = to_pci_dev(dev)->bus; struct iort_pci_alias_info info = { .dev = dev }; @@ -1027,8 +1028,9 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev) err = pci_for_each_dma_alias(to_pci_dev(dev), iort_pci_iommu_init, &info); - if (!err && iort_pci_rc_supports_ats(node)) - dev->iommu_fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS; + fwspec = dev_iommu_fwspec_get(dev); + if (fwspec && iort_pci_rc_supports_ats(node)) + fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS; } else { int i = 0; diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 4816df520f72..b4c0152e92aa 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1589,8 +1589,8 @@ static int acpi_ec_add(struct acpi_device *device) strcpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME); strcpy(acpi_device_class(device), ACPI_EC_CLASS); - if ((boot_ec && boot_ec->handle == device->handle) || - !strcmp(acpi_device_hid(device), ACPI_ECDT_HID)) { + if (boot_ec && (boot_ec->handle == device->handle || + !strcmp(acpi_device_hid(device), ACPI_ECDT_HID))) { /* Fast path: this device corresponds to the boot EC. */ ec = boot_ec; } else { diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index a3320f93616d..fa4500f9cfd1 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -360,7 +360,7 @@ static union acpi_object *acpi_label_info(acpi_handle handle) static u8 nfit_dsm_revid(unsigned family, unsigned func) { - static const u8 revid_table[NVDIMM_FAMILY_MAX+1][32] = { + static const u8 revid_table[NVDIMM_FAMILY_MAX+1][NVDIMM_CMD_MAX+1] = { [NVDIMM_FAMILY_INTEL] = { [NVDIMM_INTEL_GET_MODES] = 2, [NVDIMM_INTEL_GET_FWINFO] = 2, @@ -386,7 +386,7 @@ static u8 nfit_dsm_revid(unsigned family, unsigned func) if (family > NVDIMM_FAMILY_MAX) return 0; - if (func > 31) + if (func > NVDIMM_CMD_MAX) return 0; id = revid_table[family][func]; if (id == 0) @@ -492,7 +492,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, * Check for a valid command. For ND_CMD_CALL, we also have to * make sure that the DSM function is supported. */ - if (cmd == ND_CMD_CALL && !test_bit(func, &dsm_mask)) + if (cmd == ND_CMD_CALL && + (func > NVDIMM_CMD_MAX || !test_bit(func, &dsm_mask))) return -ENOTTY; else if (!test_bit(cmd, &cmd_mask)) return -ENOTTY; @@ -2026,8 +2027,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) continue; } - if (nfit_mem->bdw && nfit_mem->memdev_pmem) + if (nfit_mem->bdw && nfit_mem->memdev_pmem) { set_bit(NDD_ALIASING, &flags); + set_bit(NDD_LABELING, &flags); + } /* collate flags across all memdevs for this dimm */ list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { @@ -3492,7 +3495,8 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, if (nvdimm && cmd == ND_CMD_CALL && call_pkg->nd_family == NVDIMM_FAMILY_INTEL) { func = call_pkg->nd_command; - if ((1 << func) & NVDIMM_INTEL_SECURITY_CMDMASK) + if (func > NVDIMM_CMD_MAX || + (1 << func) & NVDIMM_INTEL_SECURITY_CMDMASK) return -EOPNOTSUPP; } diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 24241941181c..f5525f8bb770 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -34,6 +34,7 @@ | ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED) #define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_HYPERV +#define NVDIMM_CMD_MAX 31 #define NVDIMM_STANDARD_CMDMASK \ (1 << ND_CMD_SMART | 1 << ND_CMD_SMART_THRESHOLD | 1 << ND_CMD_DIMM_FLAGS \ @@ -144,32 +145,32 @@ struct nfit_spa { unsigned long ars_state; u32 clear_err_unit; u32 max_ars; - struct acpi_nfit_system_address spa[0]; + struct acpi_nfit_system_address spa[]; }; struct nfit_dcr { struct list_head list; - struct acpi_nfit_control_region dcr[0]; + struct acpi_nfit_control_region dcr[]; }; struct nfit_bdw { struct list_head list; - struct acpi_nfit_data_region bdw[0]; + struct acpi_nfit_data_region bdw[]; }; struct nfit_idt { struct list_head list; - struct acpi_nfit_interleave idt[0]; + struct acpi_nfit_interleave idt[]; }; struct nfit_flush { struct list_head list; - struct acpi_nfit_flush_address flush[0]; + struct acpi_nfit_flush_address flush[]; }; struct nfit_memdev { struct list_head list; - struct acpi_nfit_memory_map memdev[0]; + struct acpi_nfit_memory_map memdev[]; }; enum nfit_mem_flags { diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index eadbf90e65d1..47b4969d9b93 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -72,47 +72,6 @@ int acpi_map_pxm_to_node(int pxm) } EXPORT_SYMBOL(acpi_map_pxm_to_node); -/** - * acpi_map_pxm_to_online_node - Map proximity ID to online node - * @pxm: ACPI proximity ID - * - * This is similar to acpi_map_pxm_to_node(), but always returns an online - * node. When the mapped node from a given proximity ID is offline, it - * looks up the node distance table and returns the nearest online node. - * - * ACPI device drivers, which are called after the NUMA initialization has - * completed in the kernel, can call this interface to obtain their device - * NUMA topology from ACPI tables. Such drivers do not have to deal with - * offline nodes. A node may be offline when a device proximity ID is - * unique, SRAT memory entry does not exist, or NUMA is disabled, ex. - * "numa=off" on x86. - */ -int acpi_map_pxm_to_online_node(int pxm) -{ - int node, min_node; - - node = acpi_map_pxm_to_node(pxm); - - if (node == NUMA_NO_NODE) - node = 0; - - min_node = node; - if (!node_online(node)) { - int min_dist = INT_MAX, dist, n; - - for_each_online_node(n) { - dist = node_distance(node, n); - if (dist < min_dist) { - min_dist = dist; - min_node = n; - } - } - } - - return min_node; -} -EXPORT_SYMBOL(acpi_map_pxm_to_online_node); - static void __init acpi_table_print_srat_entry(struct acpi_subtable_header *header) { diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index ad0185c8dcee..0101b65250cb 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -410,6 +410,7 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */ { PCI_VDEVICE(INTEL, 0x5ae3), board_ahci_mobile }, /* ApolloLake AHCI */ { PCI_VDEVICE(INTEL, 0x34d3), board_ahci_mobile }, /* Ice Lake LP AHCI */ + { PCI_VDEVICE(INTEL, 0x02d7), board_ahci_mobile }, /* Comet Lake PCH RAID */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, @@ -1495,7 +1496,7 @@ static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance) static void ahci_remap_check(struct pci_dev *pdev, int bar, struct ahci_host_priv *hpriv) { - int i, count = 0; + int i; u32 cap; /* @@ -1516,13 +1517,14 @@ static void ahci_remap_check(struct pci_dev *pdev, int bar, continue; /* We've found a remapped device */ - count++; + hpriv->remapped_nvme++; } - if (!count) + if (!hpriv->remapped_nvme) return; - dev_warn(&pdev->dev, "Found %d remapped NVMe devices.\n", count); + dev_warn(&pdev->dev, "Found %u remapped NVMe devices.\n", + hpriv->remapped_nvme); dev_warn(&pdev->dev, "Switch your BIOS from RAID to AHCI mode to use them.\n"); @@ -1642,6 +1644,18 @@ static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hp } } +static ssize_t remapped_nvme_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ata_host *host = dev_get_drvdata(dev); + struct ahci_host_priv *hpriv = host->private_data; + + return sprintf(buf, "%u\n", hpriv->remapped_nvme); +} + +static DEVICE_ATTR_RO(remapped_nvme); + static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { unsigned int board_id = ent->driver_data; @@ -1745,6 +1759,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* detect remapped nvme devices */ ahci_remap_check(pdev, ahci_pci_bar, hpriv); + sysfs_add_file_to_group(&pdev->dev.kobj, + &dev_attr_remapped_nvme.attr, + NULL); + /* must set flag prior to save config in order to take effect */ if (ahci_broken_devslp(pdev)) hpriv->flags |= AHCI_HFLAG_NO_DEVSLP; @@ -1896,6 +1914,9 @@ static void ahci_shutdown_one(struct pci_dev *pdev) static void ahci_remove_one(struct pci_dev *pdev) { + sysfs_remove_file_from_group(&pdev->dev.kobj, + &dev_attr_remapped_nvme.attr, + NULL); pm_runtime_get_noresume(&pdev->dev); ata_pci_remove_one(pdev); } diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 3dbf398c92ea..d991dd46e89c 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -336,6 +336,7 @@ struct ahci_host_priv { u32 em_loc; /* enclosure management location */ u32 em_buf_sz; /* EM buffer size in byte */ u32 em_msg_type; /* EM message type */ + u32 remapped_nvme; /* NVMe remapped device count */ bool got_runtime_pm; /* Did we do pm_runtime_get? */ struct clk *clks[AHCI_MAX_CLKS]; /* Optional */ struct reset_control *rsts; /* Optional */ diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index 948d2c6557f3..388baf528fa8 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -782,7 +782,7 @@ static int ahci_imx_softreset(struct ata_link *link, unsigned int *class, struct ata_host *host = dev_get_drvdata(ap->dev); struct ahci_host_priv *hpriv = host->private_data; struct imx_ahci_priv *imxpriv = hpriv->plat_data; - int ret = -EIO; + int ret; if (imxpriv->type == AHCI_IMX53) ret = ahci_pmp_retry_srst_ops.softreset(link, class, deadline); diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index 3ff14071617c..79f2aeeb482a 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -763,6 +763,7 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap, if (dev->flags & ATA_DFLAG_DETACH) { detach = 1; + rc = -ENODEV; goto fail; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a42c49e04954..da693e6a834e 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -429,11 +429,12 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, * information. */ struct file *file = lo->lo_backing_file; + struct request_queue *q = lo->lo_queue; int ret; mode |= FALLOC_FL_KEEP_SIZE; - if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) { + if (!blk_queue_discard(q)) { ret = -EOPNOTSUPP; goto out; } @@ -463,7 +464,7 @@ static void lo_complete_rq(struct request *rq) if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || req_op(rq) != REQ_OP_READ) { if (cmd->ret < 0) - ret = BLK_STS_IOERR; + ret = errno_to_blk_status(cmd->ret); goto end_io; } @@ -868,27 +869,46 @@ static void loop_config_discard(struct loop_device *lo) struct request_queue *q = lo->lo_queue; /* + * If the backing device is a block device, mirror its zeroing + * capability. Set the discard sectors to the block device's zeroing + * capabilities because loop discards result in blkdev_issue_zeroout(), + * not blkdev_issue_discard(). This maintains consistent behavior with + * file-backed loop devices: discarded regions read back as zero. + */ + if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) { + struct request_queue *backingq; + + backingq = bdev_get_queue(inode->i_bdev); + blk_queue_max_discard_sectors(q, + backingq->limits.max_write_zeroes_sectors); + + blk_queue_max_write_zeroes_sectors(q, + backingq->limits.max_write_zeroes_sectors); + + /* * We use punch hole to reclaim the free space used by the * image a.k.a. discard. However we do not support discard if * encryption is enabled, because it may give an attacker * useful information. */ - if ((!file->f_op->fallocate) || - lo->lo_encrypt_key_size) { + } else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) { q->limits.discard_granularity = 0; q->limits.discard_alignment = 0; blk_queue_max_discard_sectors(q, 0); blk_queue_max_write_zeroes_sectors(q, 0); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); - return; - } - q->limits.discard_granularity = inode->i_sb->s_blocksize; - q->limits.discard_alignment = 0; + } else { + q->limits.discard_granularity = inode->i_sb->s_blocksize; + q->limits.discard_alignment = 0; + + blk_queue_max_discard_sectors(q, UINT_MAX >> 9); + blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9); + } - blk_queue_max_discard_sectors(q, UINT_MAX >> 9); - blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); + if (q->limits.max_write_zeroes_sectors) + blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); + else + blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); } static void loop_unprepare_queue(struct loop_device *lo) @@ -1955,7 +1975,10 @@ static void loop_handle_cmd(struct loop_cmd *cmd) failed: /* complete non-aio request */ if (!cmd->use_aio || ret) { - cmd->ret = ret ? -EIO : 0; + if (ret == -EOPNOTSUPP) + cmd->ret = ret; + else + cmd->ret = ret ? -EIO : 0; blk_mq_complete_request(rq); } } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 6343402c09e6..1e0a6b19ae0d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -337,10 +337,7 @@ struct rbd_img_request { u64 snap_id; /* for reads */ struct ceph_snap_context *snapc; /* for writes */ }; - union { - struct request *rq; /* block request */ - struct rbd_obj_request *obj_request; /* obj req initiator */ - }; + struct rbd_obj_request *obj_request; /* obj req initiator */ struct list_head lock_item; struct list_head object_extents; /* obj_req.ex structs */ @@ -349,7 +346,6 @@ struct rbd_img_request { struct pending_result pending; struct work_struct work; int work_result; - struct kref kref; }; #define for_each_obj_request(ireq, oreq) \ @@ -1320,15 +1316,6 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request) kref_put(&obj_request->kref, rbd_obj_request_destroy); } -static void rbd_img_request_destroy(struct kref *kref); -static void rbd_img_request_put(struct rbd_img_request *img_request) -{ - rbd_assert(img_request != NULL); - dout("%s: img %p (was %d)\n", __func__, img_request, - kref_read(&img_request->kref)); - kref_put(&img_request->kref, rbd_img_request_destroy); -} - static inline void rbd_img_obj_request_add(struct rbd_img_request *img_request, struct rbd_obj_request *obj_request) { @@ -1366,18 +1353,10 @@ static void rbd_osd_submit(struct ceph_osd_request *osd_req) static void img_request_layered_set(struct rbd_img_request *img_request) { set_bit(IMG_REQ_LAYERED, &img_request->flags); - smp_mb(); -} - -static void img_request_layered_clear(struct rbd_img_request *img_request) -{ - clear_bit(IMG_REQ_LAYERED, &img_request->flags); - smp_mb(); } static bool img_request_layered_test(struct rbd_img_request *img_request) { - smp_mb(); return test_bit(IMG_REQ_LAYERED, &img_request->flags) != 0; } @@ -1619,10 +1598,8 @@ static bool rbd_dev_parent_get(struct rbd_device *rbd_dev) if (!rbd_dev->parent_spec) return false; - down_read(&rbd_dev->header_rwsem); if (rbd_dev->parent_overlap) counter = atomic_inc_return_safe(&rbd_dev->parent_ref); - up_read(&rbd_dev->header_rwsem); if (counter < 0) rbd_warn(rbd_dev, "parent reference overflow"); @@ -1630,63 +1607,54 @@ static bool rbd_dev_parent_get(struct rbd_device *rbd_dev) return counter > 0; } -/* - * Caller is responsible for filling in the list of object requests - * that comprises the image request, and the Linux request pointer - * (if there is one). - */ -static struct rbd_img_request *rbd_img_request_create( - struct rbd_device *rbd_dev, - enum obj_operation_type op_type, - struct ceph_snap_context *snapc) +static void rbd_img_request_init(struct rbd_img_request *img_request, + struct rbd_device *rbd_dev, + enum obj_operation_type op_type) { - struct rbd_img_request *img_request; - - img_request = kmem_cache_zalloc(rbd_img_request_cache, GFP_NOIO); - if (!img_request) - return NULL; + memset(img_request, 0, sizeof(*img_request)); img_request->rbd_dev = rbd_dev; img_request->op_type = op_type; - if (!rbd_img_is_write(img_request)) - img_request->snap_id = rbd_dev->spec->snap_id; - else - img_request->snapc = snapc; - - if (rbd_dev_parent_get(rbd_dev)) - img_request_layered_set(img_request); INIT_LIST_HEAD(&img_request->lock_item); INIT_LIST_HEAD(&img_request->object_extents); mutex_init(&img_request->state_mutex); - kref_init(&img_request->kref); +} + +static void rbd_img_capture_header(struct rbd_img_request *img_req) +{ + struct rbd_device *rbd_dev = img_req->rbd_dev; + + lockdep_assert_held(&rbd_dev->header_rwsem); - return img_request; + if (rbd_img_is_write(img_req)) + img_req->snapc = ceph_get_snap_context(rbd_dev->header.snapc); + else + img_req->snap_id = rbd_dev->spec->snap_id; + + if (rbd_dev_parent_get(rbd_dev)) + img_request_layered_set(img_req); } -static void rbd_img_request_destroy(struct kref *kref) +static void rbd_img_request_destroy(struct rbd_img_request *img_request) { - struct rbd_img_request *img_request; struct rbd_obj_request *obj_request; struct rbd_obj_request *next_obj_request; - img_request = container_of(kref, struct rbd_img_request, kref); - dout("%s: img %p\n", __func__, img_request); WARN_ON(!list_empty(&img_request->lock_item)); for_each_obj_request_safe(img_request, obj_request, next_obj_request) rbd_img_obj_request_del(img_request, obj_request); - if (img_request_layered_test(img_request)) { - img_request_layered_clear(img_request); + if (img_request_layered_test(img_request)) rbd_dev_parent_put(img_request->rbd_dev); - } if (rbd_img_is_write(img_request)) ceph_put_snap_context(img_request->snapc); - kmem_cache_free(rbd_img_request_cache, img_request); + if (test_bit(IMG_REQ_CHILD, &img_request->flags)) + kmem_cache_free(rbd_img_request_cache, img_request); } #define BITS_PER_OBJ 2 @@ -2849,17 +2817,22 @@ static int rbd_obj_read_object(struct rbd_obj_request *obj_req) static int rbd_obj_read_from_parent(struct rbd_obj_request *obj_req) { struct rbd_img_request *img_req = obj_req->img_request; + struct rbd_device *parent = img_req->rbd_dev->parent; struct rbd_img_request *child_img_req; int ret; - child_img_req = rbd_img_request_create(img_req->rbd_dev->parent, - OBJ_OP_READ, NULL); + child_img_req = kmem_cache_alloc(rbd_img_request_cache, GFP_NOIO); if (!child_img_req) return -ENOMEM; + rbd_img_request_init(child_img_req, parent, OBJ_OP_READ); __set_bit(IMG_REQ_CHILD, &child_img_req->flags); child_img_req->obj_request = obj_req; + down_read(&parent->header_rwsem); + rbd_img_capture_header(child_img_req); + up_read(&parent->header_rwsem); + dout("%s child_img_req %p for obj_req %p\n", __func__, child_img_req, obj_req); @@ -2888,7 +2861,7 @@ static int rbd_obj_read_from_parent(struct rbd_obj_request *obj_req) obj_req->copyup_bvecs); } if (ret) { - rbd_img_request_put(child_img_req); + rbd_img_request_destroy(child_img_req); return ret; } @@ -3647,15 +3620,15 @@ again: if (test_bit(IMG_REQ_CHILD, &img_req->flags)) { struct rbd_obj_request *obj_req = img_req->obj_request; - rbd_img_request_put(img_req); + rbd_img_request_destroy(img_req); if (__rbd_obj_handle_request(obj_req, &result)) { img_req = obj_req->img_request; goto again; } } else { - struct request *rq = img_req->rq; + struct request *rq = blk_mq_rq_from_pdu(img_req); - rbd_img_request_put(img_req); + rbd_img_request_destroy(img_req); blk_mq_end_request(rq, errno_to_blk_status(result)); } } @@ -4707,84 +4680,36 @@ static int rbd_obj_method_sync(struct rbd_device *rbd_dev, static void rbd_queue_workfn(struct work_struct *work) { - struct request *rq = blk_mq_rq_from_pdu(work); - struct rbd_device *rbd_dev = rq->q->queuedata; - struct rbd_img_request *img_request; - struct ceph_snap_context *snapc = NULL; + struct rbd_img_request *img_request = + container_of(work, struct rbd_img_request, work); + struct rbd_device *rbd_dev = img_request->rbd_dev; + enum obj_operation_type op_type = img_request->op_type; + struct request *rq = blk_mq_rq_from_pdu(img_request); u64 offset = (u64)blk_rq_pos(rq) << SECTOR_SHIFT; u64 length = blk_rq_bytes(rq); - enum obj_operation_type op_type; u64 mapping_size; int result; - switch (req_op(rq)) { - case REQ_OP_DISCARD: - op_type = OBJ_OP_DISCARD; - break; - case REQ_OP_WRITE_ZEROES: - op_type = OBJ_OP_ZEROOUT; - break; - case REQ_OP_WRITE: - op_type = OBJ_OP_WRITE; - break; - case REQ_OP_READ: - op_type = OBJ_OP_READ; - break; - default: - dout("%s: non-fs request type %d\n", __func__, req_op(rq)); - result = -EIO; - goto err; - } - /* Ignore/skip any zero-length requests */ - if (!length) { dout("%s: zero-length request\n", __func__); result = 0; - goto err_rq; - } - - if (op_type != OBJ_OP_READ) { - if (rbd_is_ro(rbd_dev)) { - rbd_warn(rbd_dev, "%s on read-only mapping", - obj_op_name(op_type)); - result = -EIO; - goto err; - } - rbd_assert(!rbd_is_snap(rbd_dev)); - } - - if (offset && length > U64_MAX - offset + 1) { - rbd_warn(rbd_dev, "bad request range (%llu~%llu)", offset, - length); - result = -EINVAL; - goto err_rq; /* Shouldn't happen */ + goto err_img_request; } blk_mq_start_request(rq); down_read(&rbd_dev->header_rwsem); mapping_size = rbd_dev->mapping.size; - if (op_type != OBJ_OP_READ) { - snapc = rbd_dev->header.snapc; - ceph_get_snap_context(snapc); - } + rbd_img_capture_header(img_request); up_read(&rbd_dev->header_rwsem); if (offset + length > mapping_size) { rbd_warn(rbd_dev, "beyond EOD (%llu~%llu > %llu)", offset, length, mapping_size); result = -EIO; - goto err_rq; - } - - img_request = rbd_img_request_create(rbd_dev, op_type, snapc); - if (!img_request) { - result = -ENOMEM; - goto err_rq; + goto err_img_request; } - img_request->rq = rq; - snapc = NULL; /* img_request consumes a ref */ dout("%s rbd_dev %p img_req %p %s %llu~%llu\n", __func__, rbd_dev, img_request, obj_op_name(op_type), offset, length); @@ -4801,23 +4726,51 @@ static void rbd_queue_workfn(struct work_struct *work) return; err_img_request: - rbd_img_request_put(img_request); -err_rq: + rbd_img_request_destroy(img_request); if (result) rbd_warn(rbd_dev, "%s %llx at %llx result %d", obj_op_name(op_type), length, offset, result); - ceph_put_snap_context(snapc); -err: blk_mq_end_request(rq, errno_to_blk_status(result)); } static blk_status_t rbd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { - struct request *rq = bd->rq; - struct work_struct *work = blk_mq_rq_to_pdu(rq); + struct rbd_device *rbd_dev = hctx->queue->queuedata; + struct rbd_img_request *img_req = blk_mq_rq_to_pdu(bd->rq); + enum obj_operation_type op_type; - queue_work(rbd_wq, work); + switch (req_op(bd->rq)) { + case REQ_OP_DISCARD: + op_type = OBJ_OP_DISCARD; + break; + case REQ_OP_WRITE_ZEROES: + op_type = OBJ_OP_ZEROOUT; + break; + case REQ_OP_WRITE: + op_type = OBJ_OP_WRITE; + break; + case REQ_OP_READ: + op_type = OBJ_OP_READ; + break; + default: + rbd_warn(rbd_dev, "unknown req_op %d", req_op(bd->rq)); + return BLK_STS_IOERR; + } + + rbd_img_request_init(img_req, rbd_dev, op_type); + + if (rbd_img_is_write(img_req)) { + if (rbd_is_ro(rbd_dev)) { + rbd_warn(rbd_dev, "%s on read-only mapping", + obj_op_name(img_req->op_type)); + return BLK_STS_IOERR; + } + rbd_assert(!rbd_is_snap(rbd_dev)); + } + + INIT_WORK(&img_req->work, rbd_queue_workfn); + queue_work(rbd_wq, &img_req->work); return BLK_STS_OK; } @@ -4984,18 +4937,8 @@ out: return ret; } -static int rbd_init_request(struct blk_mq_tag_set *set, struct request *rq, - unsigned int hctx_idx, unsigned int numa_node) -{ - struct work_struct *work = blk_mq_rq_to_pdu(rq); - - INIT_WORK(work, rbd_queue_workfn); - return 0; -} - static const struct blk_mq_ops rbd_mq_ops = { .queue_rq = rbd_queue_rq, - .init_request = rbd_init_request, }; static int rbd_init_disk(struct rbd_device *rbd_dev) @@ -5027,8 +4970,8 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) rbd_dev->tag_set.queue_depth = rbd_dev->opts->queue_depth; rbd_dev->tag_set.numa_node = NUMA_NO_NODE; rbd_dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - rbd_dev->tag_set.nr_hw_queues = 1; - rbd_dev->tag_set.cmd_size = sizeof(struct work_struct); + rbd_dev->tag_set.nr_hw_queues = num_present_cpus(); + rbd_dev->tag_set.cmd_size = sizeof(struct rbd_img_request); err = blk_mq_alloc_tag_set(&rbd_dev->tag_set); if (err) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 915cf5b6388c..3b889ea950c2 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -47,6 +47,7 @@ #include <linux/bitmap.h> #include <linux/list.h> #include <linux/workqueue.h> +#include <linux/sched/mm.h> #include <xen/xen.h> #include <xen/xenbus.h> @@ -2189,10 +2190,12 @@ static void blkfront_setup_discard(struct blkfront_info *info) static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) { - unsigned int psegs, grants; + unsigned int psegs, grants, memflags; int err, i; struct blkfront_info *info = rinfo->dev_info; + memflags = memalloc_noio_save(); + if (info->max_indirect_segments == 0) { if (!HAS_EXTRA_REQ) grants = BLKIF_MAX_SEGMENTS_PER_REQUEST; @@ -2224,7 +2227,7 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) BUG_ON(!list_empty(&rinfo->indirect_pages)); for (i = 0; i < num; i++) { - struct page *indirect_page = alloc_page(GFP_NOIO); + struct page *indirect_page = alloc_page(GFP_KERNEL); if (!indirect_page) goto out_of_memory; list_add(&indirect_page->lru, &rinfo->indirect_pages); @@ -2235,15 +2238,15 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) rinfo->shadow[i].grants_used = kvcalloc(grants, sizeof(rinfo->shadow[i].grants_used[0]), - GFP_NOIO); + GFP_KERNEL); rinfo->shadow[i].sg = kvcalloc(psegs, sizeof(rinfo->shadow[i].sg[0]), - GFP_NOIO); + GFP_KERNEL); if (info->max_indirect_segments) rinfo->shadow[i].indirect_grants = kvcalloc(INDIRECT_GREFS(grants), sizeof(rinfo->shadow[i].indirect_grants[0]), - GFP_NOIO); + GFP_KERNEL); if ((rinfo->shadow[i].grants_used == NULL) || (rinfo->shadow[i].sg == NULL) || (info->max_indirect_segments && @@ -2252,6 +2255,7 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) sg_init_table(rinfo->shadow[i].sg, psegs); } + memalloc_noio_restore(memflags); return 0; @@ -2271,6 +2275,9 @@ out_of_memory: __free_page(indirect_page); } } + + memalloc_noio_restore(memflags); + return -ENOMEM; } diff --git a/drivers/char/hw_random/omap3-rom-rng.c b/drivers/char/hw_random/omap3-rom-rng.c index a431c5cbe2be..e0d77fa048fb 100644 --- a/drivers/char/hw_random/omap3-rom-rng.c +++ b/drivers/char/hw_random/omap3-rom-rng.c @@ -4,7 +4,7 @@ * Copyright (C) 2009 Nokia Corporation * Author: Juha Yrjola <juha.yrjola@solidboot.com> * - * Copyright (C) 2013 Pali Rohár <pali.rohar@gmail.com> + * Copyright (C) 2013 Pali Rohár <pali@kernel.org> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any @@ -178,5 +178,5 @@ module_platform_driver(omap3_rom_rng_driver); MODULE_ALIAS("platform:omap3-rom-rng"); MODULE_AUTHOR("Juha Yrjola"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); MODULE_LICENSE("GPL"); diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index cad9563f8f48..c48d8f086382 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -618,6 +618,8 @@ static DEFINE_MUTEX(ipmidriver_mutex); static LIST_HEAD(ipmi_interfaces); static DEFINE_MUTEX(ipmi_interfaces_mutex); +#define ipmi_interfaces_mutex_held() \ + lockdep_is_held(&ipmi_interfaces_mutex) static struct srcu_struct ipmi_interfaces_srcu; /* @@ -1321,7 +1323,8 @@ static void _ipmi_destroy_user(struct ipmi_user *user) * synchronize_srcu()) then free everything in that list. */ mutex_lock(&intf->cmd_rcvrs_mutex); - list_for_each_entry_rcu(rcvr, &intf->cmd_rcvrs, link) { + list_for_each_entry_rcu(rcvr, &intf->cmd_rcvrs, link, + lockdep_is_held(&intf->cmd_rcvrs_mutex)) { if (rcvr->user == user) { list_del_rcu(&rcvr->link); rcvr->next = rcvrs; @@ -1599,7 +1602,8 @@ static struct cmd_rcvr *find_cmd_rcvr(struct ipmi_smi *intf, { struct cmd_rcvr *rcvr; - list_for_each_entry_rcu(rcvr, &intf->cmd_rcvrs, link) { + list_for_each_entry_rcu(rcvr, &intf->cmd_rcvrs, link, + lockdep_is_held(&intf->cmd_rcvrs_mutex)) { if ((rcvr->netfn == netfn) && (rcvr->cmd == cmd) && (rcvr->chans & (1 << chan))) return rcvr; @@ -1614,7 +1618,8 @@ static int is_cmd_rcvr_exclusive(struct ipmi_smi *intf, { struct cmd_rcvr *rcvr; - list_for_each_entry_rcu(rcvr, &intf->cmd_rcvrs, link) { + list_for_each_entry_rcu(rcvr, &intf->cmd_rcvrs, link, + lockdep_is_held(&intf->cmd_rcvrs_mutex)) { if ((rcvr->netfn == netfn) && (rcvr->cmd == cmd) && (rcvr->chans & chans)) return 0; @@ -3188,8 +3193,8 @@ static void __get_guid(struct ipmi_smi *intf) if (rv) /* Send failed, no GUID available. */ bmc->dyn_guid_set = 0; - - wait_event(intf->waitq, bmc->dyn_guid_set != 2); + else + wait_event(intf->waitq, bmc->dyn_guid_set != 2); /* dyn_guid_set makes the guid data available. */ smp_rmb(); @@ -3450,7 +3455,8 @@ int ipmi_add_smi(struct module *owner, /* Look for a hole in the numbers. */ i = 0; link = &ipmi_interfaces; - list_for_each_entry_rcu(tintf, &ipmi_interfaces, link) { + list_for_each_entry_rcu(tintf, &ipmi_interfaces, link, + ipmi_interfaces_mutex_held()) { if (tintf->intf_num != i) { link = &tintf->link; break; diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 8ac390c2b514..b7145f370d3b 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -313,6 +313,7 @@ static int start_send(struct ssif_info *ssif_info, static unsigned long *ipmi_ssif_lock_cond(struct ssif_info *ssif_info, unsigned long *flags) + __acquires(&ssif_info->lock) { spin_lock_irqsave(&ssif_info->lock, *flags); return flags; @@ -320,6 +321,7 @@ static unsigned long *ipmi_ssif_lock_cond(struct ssif_info *ssif_info, static void ipmi_ssif_unlock_cond(struct ssif_info *ssif_info, unsigned long *flags) + __releases(&ssif_info->lock) { spin_unlock_irqrestore(&ssif_info->lock, *flags); } diff --git a/drivers/char/ipmi/kcs_bmc_aspeed.c b/drivers/char/ipmi/kcs_bmc_aspeed.c index 3c955946e647..a140203c079b 100644 --- a/drivers/char/ipmi/kcs_bmc_aspeed.c +++ b/drivers/char/ipmi/kcs_bmc_aspeed.c @@ -12,6 +12,7 @@ #include <linux/mfd/syscon.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/platform_device.h> #include <linux/poll.h> #include <linux/regmap.h> @@ -233,58 +234,154 @@ static const struct kcs_ioreg ast_kcs_bmc_ioregs[KCS_CHANNEL_MAX] = { { .idr = LPC_IDR4, .odr = LPC_ODR4, .str = LPC_STR4 }, }; -static int aspeed_kcs_probe(struct platform_device *pdev) +static struct kcs_bmc *aspeed_kcs_probe_of_v1(struct platform_device *pdev) { - struct device *dev = &pdev->dev; struct aspeed_kcs_bmc *priv; - struct kcs_bmc *kcs_bmc; - u32 chan, addr; + struct device_node *np; + struct kcs_bmc *kcs; + u32 channel; + u32 slave; int rc; - rc = of_property_read_u32(dev->of_node, "kcs_chan", &chan); - if ((rc != 0) || (chan == 0 || chan > KCS_CHANNEL_MAX)) { - dev_err(dev, "no valid 'kcs_chan' configured\n"); - return -ENODEV; + np = pdev->dev.of_node; + + rc = of_property_read_u32(np, "kcs_chan", &channel); + if ((rc != 0) || (channel == 0 || channel > KCS_CHANNEL_MAX)) { + dev_err(&pdev->dev, "no valid 'kcs_chan' configured\n"); + return ERR_PTR(-EINVAL); + } + + kcs = kcs_bmc_alloc(&pdev->dev, sizeof(struct aspeed_kcs_bmc), channel); + if (!kcs) + return ERR_PTR(-ENOMEM); + + priv = kcs_bmc_priv(kcs); + priv->map = syscon_node_to_regmap(pdev->dev.parent->of_node); + if (IS_ERR(priv->map)) { + dev_err(&pdev->dev, "Couldn't get regmap\n"); + return ERR_PTR(-ENODEV); } - rc = of_property_read_u32(dev->of_node, "kcs_addr", &addr); + rc = of_property_read_u32(np, "kcs_addr", &slave); if (rc) { - dev_err(dev, "no valid 'kcs_addr' configured\n"); - return -ENODEV; + dev_err(&pdev->dev, "no valid 'kcs_addr' configured\n"); + return ERR_PTR(-EINVAL); + } + + kcs->ioreg = ast_kcs_bmc_ioregs[channel - 1]; + aspeed_kcs_set_address(kcs, slave); + + return kcs; +} + +static int aspeed_kcs_calculate_channel(const struct kcs_ioreg *regs) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(ast_kcs_bmc_ioregs); i++) { + if (!memcmp(&ast_kcs_bmc_ioregs[i], regs, sizeof(*regs))) + return i + 1; } - kcs_bmc = kcs_bmc_alloc(dev, sizeof(*priv), chan); - if (!kcs_bmc) - return -ENOMEM; + return -EINVAL; +} + +static struct kcs_bmc *aspeed_kcs_probe_of_v2(struct platform_device *pdev) +{ + struct aspeed_kcs_bmc *priv; + struct device_node *np; + struct kcs_ioreg ioreg; + struct kcs_bmc *kcs; + const __be32 *reg; + int channel; + u32 slave; + int rc; + + np = pdev->dev.of_node; + + /* Don't translate addresses, we want offsets for the regmaps */ + reg = of_get_address(np, 0, NULL, NULL); + if (!reg) + return ERR_PTR(-EINVAL); + ioreg.idr = be32_to_cpup(reg); + + reg = of_get_address(np, 1, NULL, NULL); + if (!reg) + return ERR_PTR(-EINVAL); + ioreg.odr = be32_to_cpup(reg); + + reg = of_get_address(np, 2, NULL, NULL); + if (!reg) + return ERR_PTR(-EINVAL); + ioreg.str = be32_to_cpup(reg); - priv = kcs_bmc_priv(kcs_bmc); - priv->map = syscon_node_to_regmap(dev->parent->of_node); + channel = aspeed_kcs_calculate_channel(&ioreg); + if (channel < 0) + return ERR_PTR(channel); + + kcs = kcs_bmc_alloc(&pdev->dev, sizeof(struct aspeed_kcs_bmc), channel); + if (!kcs) + return ERR_PTR(-ENOMEM); + + kcs->ioreg = ioreg; + + priv = kcs_bmc_priv(kcs); + priv->map = syscon_node_to_regmap(pdev->dev.parent->of_node); if (IS_ERR(priv->map)) { - dev_err(dev, "Couldn't get regmap\n"); - return -ENODEV; + dev_err(&pdev->dev, "Couldn't get regmap\n"); + return ERR_PTR(-ENODEV); } - kcs_bmc->ioreg = ast_kcs_bmc_ioregs[chan - 1]; + rc = of_property_read_u32(np, "aspeed,lpc-io-reg", &slave); + if (rc) + return ERR_PTR(rc); + + aspeed_kcs_set_address(kcs, slave); + + return kcs; +} + +static int aspeed_kcs_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct kcs_bmc *kcs_bmc; + struct device_node *np; + int rc; + + np = pdev->dev.of_node; + if (of_device_is_compatible(np, "aspeed,ast2400-kcs-bmc") || + of_device_is_compatible(np, "aspeed,ast2500-kcs-bmc")) + kcs_bmc = aspeed_kcs_probe_of_v1(pdev); + else if (of_device_is_compatible(np, "aspeed,ast2400-kcs-bmc-v2") || + of_device_is_compatible(np, "aspeed,ast2500-kcs-bmc-v2")) + kcs_bmc = aspeed_kcs_probe_of_v2(pdev); + else + return -EINVAL; + + if (IS_ERR(kcs_bmc)) + return PTR_ERR(kcs_bmc); + kcs_bmc->io_inputb = aspeed_kcs_inb; kcs_bmc->io_outputb = aspeed_kcs_outb; - dev_set_drvdata(dev, kcs_bmc); - - aspeed_kcs_set_address(kcs_bmc, addr); - aspeed_kcs_enable_channel(kcs_bmc, true); rc = aspeed_kcs_config_irq(kcs_bmc, pdev); if (rc) return rc; + dev_set_drvdata(dev, kcs_bmc); + + aspeed_kcs_enable_channel(kcs_bmc, true); + rc = misc_register(&kcs_bmc->miscdev); if (rc) { dev_err(dev, "Unable to register device\n"); return rc; } - pr_info("channel=%u addr=0x%x idr=0x%x odr=0x%x str=0x%x\n", - chan, addr, - kcs_bmc->ioreg.idr, kcs_bmc->ioreg.odr, kcs_bmc->ioreg.str); + dev_dbg(&pdev->dev, + "Probed KCS device %d (IDR=0x%x, ODR=0x%x, STR=0x%x)\n", + kcs_bmc->channel, kcs_bmc->ioreg.idr, kcs_bmc->ioreg.odr, + kcs_bmc->ioreg.str); return 0; } @@ -301,6 +398,8 @@ static int aspeed_kcs_remove(struct platform_device *pdev) static const struct of_device_id ast_kcs_bmc_match[] = { { .compatible = "aspeed,ast2400-kcs-bmc" }, { .compatible = "aspeed,ast2500-kcs-bmc" }, + { .compatible = "aspeed,ast2400-kcs-bmc-v2" }, + { .compatible = "aspeed,ast2500-kcs-bmc-v2" }, { } }; MODULE_DEVICE_TABLE(of, ast_kcs_bmc_match); diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c index db124bc1ca2c..fcc53215bac8 100644 --- a/drivers/cpuidle/cpuidle-haltpoll.c +++ b/drivers/cpuidle/cpuidle-haltpoll.c @@ -94,7 +94,7 @@ static void haltpoll_uninit(void) haltpoll_cpuidle_devices = NULL; } -static bool haltpool_want(void) +static bool haltpoll_want(void) { return kvm_para_has_hint(KVM_HINTS_REALTIME) || force; } @@ -110,7 +110,7 @@ static int __init haltpoll_init(void) cpuidle_poll_state_init(drv); - if (!kvm_para_available() || !haltpool_want()) + if (!kvm_para_available() || !haltpoll_want()) return -ENODEV; ret = cpuidle_register_driver(drv); diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig index 095850d01dcc..f09c6cf7823e 100644 --- a/drivers/crypto/hisilicon/Kconfig +++ b/drivers/crypto/hisilicon/Kconfig @@ -27,6 +27,7 @@ config CRYPTO_DEV_HISI_SEC2 select CRYPTO_SHA256 select CRYPTO_SHA512 depends on PCI && PCI_MSI + depends on UACCE || UACCE=n depends on ARM64 || (COMPILE_TEST && 64BIT) help Support for HiSilicon SEC Engine of version 2 in crypto subsystem. @@ -58,6 +59,7 @@ config CRYPTO_DEV_HISI_ZIP config CRYPTO_DEV_HISI_HPRE tristate "Support for HISI HPRE accelerator" depends on PCI && PCI_MSI + depends on UACCE || UACCE=n depends on ARM64 || (COMPILE_TEST && 64BIT) select CRYPTO_DEV_HISI_QM select CRYPTO_DH diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c index 946fb62949b2..06202bcffb33 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c +++ b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c @@ -1161,13 +1161,13 @@ static inline u32 create_aead_null_output_list(struct aead_request *req, inputlen); if (status != inputlen) { status = -EINVAL; - goto error; + goto error_free; } status = sg_copy_from_buffer(req->dst, sg_nents(req->dst), ptr, inputlen); if (status != inputlen) { status = -EINVAL; - goto error; + goto error_free; } kfree(ptr); } @@ -1209,8 +1209,10 @@ static inline u32 create_aead_null_output_list(struct aead_request *req, req_info->outcnt = argcnt; return 0; -error: + +error_free: kfree(ptr); +error: return status; } diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 46e46047a1f7..df238c8b6ef2 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -421,8 +421,10 @@ struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id, * device outside of mmap of the resulting character device. */ dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC); - if (!dax_dev) + if (IS_ERR(dax_dev)) { + rc = PTR_ERR(dax_dev); goto err; + } /* a device_dax instance is dead while the driver is not attached */ kill_dax(dax_dev); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 0aa4b6bc5101..8e32345be0f7 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -344,6 +344,23 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, } EXPORT_SYMBOL_GPL(dax_copy_to_iter); +int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, + size_t nr_pages) +{ + if (!dax_alive(dax_dev)) + return -ENXIO; + /* + * There are no callers that want to zero more than one page as of now. + * Once users are there, this check can be removed after the + * device mapper code has been updated to split ranges across targets. + */ + if (nr_pages != 1) + return -EIO; + + return dax_dev->ops->zero_page_range(dax_dev, pgoff, nr_pages); +} +EXPORT_SYMBOL_GPL(dax_zero_page_range); + #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size) @@ -551,9 +568,16 @@ struct dax_device *alloc_dax(void *private, const char *__host, dev_t devt; int minor; + if (ops && !ops->zero_page_range) { + pr_debug("%s: error: device does not provide dax" + " operation zero_page_range()\n", + __host ? __host : "Unknown"); + return ERR_PTR(-EINVAL); + } + host = kstrdup(__host, GFP_KERNEL); if (__host && !host) - return NULL; + return ERR_PTR(-ENOMEM); minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL); if (minor < 0) @@ -576,7 +600,7 @@ struct dax_device *alloc_dax(void *private, const char *__host, ida_simple_remove(&dax_minor_ida, minor); err_minor: kfree(host); - return NULL; + return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(alloc_dax); diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index 265303a396ca..f6a2f42ffc51 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -1493,7 +1493,6 @@ static int tegra_dma_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, i); if (irq < 0) { ret = irq; - dev_err(&pdev->dev, "No irq resource for chan %d\n", i); goto err_pm_disable; } diff --git a/drivers/firmware/edd.c b/drivers/firmware/edd.c index 29906e39ab4b..14d0970a7198 100644 --- a/drivers/firmware/edd.c +++ b/drivers/firmware/edd.c @@ -341,7 +341,7 @@ edd_show_legacy_max_cylinder(struct edd_device *edev, char *buf) if (!info || !buf) return -EINVAL; - p += snprintf(p, left, "%u\n", info->legacy_max_cylinder); + p += scnprintf(p, left, "%u\n", info->legacy_max_cylinder); return (p - buf); } @@ -356,7 +356,7 @@ edd_show_legacy_max_head(struct edd_device *edev, char *buf) if (!info || !buf) return -EINVAL; - p += snprintf(p, left, "%u\n", info->legacy_max_head); + p += scnprintf(p, left, "%u\n", info->legacy_max_head); return (p - buf); } @@ -371,7 +371,7 @@ edd_show_legacy_sectors_per_track(struct edd_device *edev, char *buf) if (!info || !buf) return -EINVAL; - p += snprintf(p, left, "%u\n", info->legacy_sectors_per_track); + p += scnprintf(p, left, "%u\n", info->legacy_sectors_per_track); return (p - buf); } diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index db0c1a9c1699..fc9f8ab533a7 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -75,14 +75,12 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && phys_seed != 0) { /* - * If CONFIG_DEBUG_ALIGN_RODATA is not set, produce a - * displacement in the interval [0, MIN_KIMG_ALIGN) that - * doesn't violate this kernel's de-facto alignment + * Produce a displacement in the interval [0, MIN_KIMG_ALIGN) + * that doesn't violate this kernel's de-facto alignment * constraints. */ u32 mask = (MIN_KIMG_ALIGN - 1) & ~(EFI_KIMG_ALIGN - 1); - u32 offset = !IS_ENABLED(CONFIG_DEBUG_ALIGN_RODATA) ? - (phys_seed >> 32) & mask : TEXT_OFFSET; + u32 offset = (phys_seed >> 32) & mask; /* * With CONFIG_RANDOMIZE_TEXT_OFFSET=y, TEXT_OFFSET may not diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index faa3e7102156..559dc24ef436 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2340,8 +2340,6 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev) { int i, r; - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.valid) @@ -3356,6 +3354,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) } } + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); + amdgpu_amdkfd_suspend(adev, !fbcon); amdgpu_ras_suspend(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index f197f1be0969..abe94a55ecad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -89,7 +89,8 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev) adev->pm.ac_power = true; else adev->pm.ac_power = false; - if (adev->powerplay.pp_funcs->enable_bapm) + if (adev->powerplay.pp_funcs && + adev->powerplay.pp_funcs->enable_bapm) amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power); mutex_unlock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index be50867ea644..deaa26808841 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -818,7 +818,7 @@ static int psp_ras_initialize(struct psp_context *psp) if (!psp->adev->psp.ta_ras_ucode_size || !psp->adev->psp.ta_ras_start_addr) { - dev_warn(psp->adev->dev, "RAS: ras ta ucode is not available\n"); + dev_info(psp->adev->dev, "RAS: optional ras ta ucode is not available\n"); return 0; } @@ -902,7 +902,7 @@ static int psp_hdcp_initialize(struct psp_context *psp) if (!psp->adev->psp.ta_hdcp_ucode_size || !psp->adev->psp.ta_hdcp_start_addr) { - dev_warn(psp->adev->dev, "HDCP: hdcp ta ucode is not available\n"); + dev_info(psp->adev->dev, "HDCP: optional hdcp ta ucode is not available\n"); return 0; } @@ -1048,7 +1048,7 @@ static int psp_dtm_initialize(struct psp_context *psp) if (!psp->adev->psp.ta_dtm_ucode_size || !psp->adev->psp.ta_dtm_start_addr) { - dev_warn(psp->adev->dev, "DTM: dtm ta ucode is not available\n"); + dev_info(psp->adev->dev, "DTM: optional dtm ta ucode is not available\n"); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 3c32a94d2424..ab379b44679c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1424,12 +1424,22 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) { struct amdgpu_ras *ras = container_of(work, struct amdgpu_ras, recovery_work); + struct amdgpu_device *remote_adev = NULL; + struct amdgpu_device *adev = ras->adev; + struct list_head device_list, *device_list_handle = NULL; + struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, false); + + /* Build list of devices to query RAS related errors */ + if (hive && adev->gmc.xgmi.num_physical_nodes > 1) { + device_list_handle = &hive->device_list; + } else { + list_add_tail(&adev->gmc.xgmi.head, &device_list); + device_list_handle = &device_list; + } - /* - * Query and print non zero error counter per IP block for - * awareness before recovering GPU. - */ - amdgpu_ras_log_on_err_counter(ras->adev); + list_for_each_entry(remote_adev, device_list_handle, gmc.xgmi.head) { + amdgpu_ras_log_on_err_counter(remote_adev); + } if (amdgpu_device_should_recover_gpu(ras->adev)) amdgpu_device_gpu_recover(ras->adev, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f6e3f59efa2f..d78059fd2c72 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -279,7 +279,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2_nv12[] = #define DEFAULT_SH_MEM_CONFIG \ ((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \ - (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \ + (SH_MEM_ALIGNMENT_MODE_DWORD << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \ (SH_MEM_RETRY_MODE_ALL << SH_MEM_CONFIG__RETRY_MODE__SHIFT) | \ (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT)) @@ -4104,6 +4104,12 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade /* It is disabled by HW by default */ if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) { + /* 0 - Disable some blocks' MGCG */ + WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xe0000000); + WREG32_SOC15(GC, 0, mmCGTT_WD_CLK_CTRL, 0xff000000); + WREG32_SOC15(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xff000000); + WREG32_SOC15(GC, 0, mmCGTT_IA_CLK_CTRL, 0xff000000); + /* 1 - RLC_CGTT_MGCG_OVERRIDE */ def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK | @@ -4143,19 +4149,20 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); - /* 2 - disable MGLS in RLC */ + /* 2 - disable MGLS in CP */ + data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL); + if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) { + data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK; + WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data); + } + + /* 3 - disable MGLS in RLC */ data = RREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL); if (data & RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK) { data &= ~RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK; WREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL, data); } - /* 3 - disable MGLS in CP */ - data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL); - if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) { - data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK; - WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data); - } } } @@ -4266,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, /* === CGCG /CGLS for GFX 3D Only === */ gfx_v10_0_update_3d_clock_gating(adev, enable); /* === MGCG + MGLS === */ - gfx_v10_0_update_medium_grain_clock_gating(adev, enable); + /* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */ } if (adev->cg_flags & diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 608ffe3b684e..e6b113ed2f40 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1217,6 +1217,8 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev) adev->gfx.mec_fw_write_wait = true; break; default: + adev->gfx.me_fw_write_wait = true; + adev->gfx.mec_fw_write_wait = true; break; } } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c index cceb46faf212..dce945ef21a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c @@ -710,14 +710,16 @@ static int gfx_v9_4_query_utc_edc_status(struct amdgpu_device *adev, sec_count = REG_GET_FIELD(data, VML2_MEM_ECC_CNTL, SEC_COUNT); if (sec_count) { - DRM_INFO("Instance[%d]: SubBlock %s, SEC %d\n", i, + dev_info(adev->dev, + "Instance[%d]: SubBlock %s, SEC %d\n", i, vml2_mems[i], sec_count); err_data->ce_count += sec_count; } ded_count = REG_GET_FIELD(data, VML2_MEM_ECC_CNTL, DED_COUNT); if (ded_count) { - DRM_INFO("Instance[%d]: SubBlock %s, DED %d\n", i, + dev_info(adev->dev, + "Instance[%d]: SubBlock %s, DED %d\n", i, vml2_mems[i], ded_count); err_data->ue_count += ded_count; } diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 0d413fabd015..c0e3efcb09bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -1539,8 +1539,11 @@ static const struct soc15_reg_entry mmhub_v9_4_edc_cnt_regs[] = { { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA7_EDC_CNT3), 0, 0, 0 }, }; -static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg, - uint32_t value, uint32_t *sec_count, uint32_t *ded_count) +static int mmhub_v9_4_get_ras_error_count(struct amdgpu_device *adev, + const struct soc15_reg_entry *reg, + uint32_t value, + uint32_t *sec_count, + uint32_t *ded_count) { uint32_t i; uint32_t sec_cnt, ded_cnt; @@ -1553,7 +1556,7 @@ static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg, mmhub_v9_4_ras_fields[i].sec_count_mask) >> mmhub_v9_4_ras_fields[i].sec_count_shift; if (sec_cnt) { - DRM_INFO("MMHUB SubBlock %s, SEC %d\n", + dev_info(adev->dev, "MMHUB SubBlock %s, SEC %d\n", mmhub_v9_4_ras_fields[i].name, sec_cnt); *sec_count += sec_cnt; @@ -1563,7 +1566,7 @@ static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg, mmhub_v9_4_ras_fields[i].ded_count_mask) >> mmhub_v9_4_ras_fields[i].ded_count_shift; if (ded_cnt) { - DRM_INFO("MMHUB SubBlock %s, DED %d\n", + dev_info(adev->dev, "MMHUB SubBlock %s, DED %d\n", mmhub_v9_4_ras_fields[i].name, ded_cnt); *ded_count += ded_cnt; @@ -1588,7 +1591,7 @@ static void mmhub_v9_4_query_ras_error_count(struct amdgpu_device *adev, reg_value = RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_edc_cnt_regs[i])); if (reg_value) - mmhub_v9_4_get_ras_error_count(&mmhub_v9_4_edc_cnt_regs[i], + mmhub_v9_4_get_ras_error_count(adev, &mmhub_v9_4_edc_cnt_regs[i], reg_value, &sec_count, &ded_count); } 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 bab587ab6e8d..f7c5cdc10a70 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4723,10 +4723,10 @@ amdgpu_dm_connector_atomic_duplicate_state(struct drm_connector *connector) static int amdgpu_dm_connector_late_register(struct drm_connector *connector) { +#if defined(CONFIG_DEBUG_FS) struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); -#if defined(CONFIG_DEBUG_FS) connector_debugfs_init(amdgpu_dm_connector); #endif @@ -5929,7 +5929,8 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, adev->mode_info.underscan_vborder_property, 0); - drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16); + if (!aconnector->mst_port) + drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16); /* This defaults to the max in the range, but we want 8bpc for non-edp. */ aconnector->base.state->max_bpc = (connector_type == DRM_MODE_CONNECTOR_eDP) ? 16 : 8; @@ -5948,8 +5949,9 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, &aconnector->base.base, dm->ddev->mode_config.hdr_output_metadata_property, 0); - drm_connector_attach_vrr_capable_property( - &aconnector->base); + if (!aconnector->mst_port) + drm_connector_attach_vrr_capable_property(&aconnector->base); + #ifdef CONFIG_DRM_AMD_DC_HDCP if (adev->dm.hdcp_workqueue) drm_connector_attach_content_protection_property(&aconnector->base, true); @@ -6272,12 +6274,6 @@ static int get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc, y <= -amdgpu_crtc->max_cursor_height) return 0; - if (crtc->primary->state) { - /* avivo cursor are offset into the total surface */ - x += crtc->primary->state->src_x >> 16; - y += crtc->primary->state->src_y >> 16; - } - if (x < 0) { xorigin = min(-x, amdgpu_crtc->max_cursor_width - 1); x = 0; @@ -6287,6 +6283,7 @@ static int get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc, y = 0; } position->enable = true; + position->translate_by_source = true; position->x = x; position->y = y; position->x_hotspot = xorigin; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index e8208df420d9..fabbe78d5aef 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -410,6 +410,14 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, drm_connector_attach_encoder(&aconnector->base, &aconnector->mst_encoder->base); + connector->max_bpc_property = master->base.max_bpc_property; + if (connector->max_bpc_property) + drm_connector_attach_max_bpc_property(connector, 8, 16); + + connector->vrr_capable_property = master->base.vrr_capable_property; + if (connector->vrr_capable_property) + drm_connector_attach_vrr_capable_property(connector); + drm_object_attach_property( &connector->base, dev->mode_config.path_property, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index ab267ddd4abe..24c5765890fa 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -643,7 +643,7 @@ static void rn_clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params /* Find lowest DPM, FCLK is filled in reverse order*/ for (i = PP_SMU_NUM_FCLK_DPM_LEVELS - 1; i >= 0; i--) { - if (clock_table->FClocks[i].Freq != 0) { + if (clock_table->FClocks[i].Freq != 0 && clock_table->FClocks[i].Vol != 0) { j = i; break; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f21bbb295ad3..8489f1e56892 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -283,6 +283,8 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, int i = 0; bool ret = false; + stream->adjust = *adjust; + for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; @@ -1859,8 +1861,9 @@ enum surface_update_type dc_check_update_surfaces_for_stream( // Else we fallback to mem compare. } else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) { dc->optimized_required = true; - } else if (dc->wm_optimized_required) - dc->optimized_required = true; + } + + dc->optimized_required |= dc->wm_optimized_required; } return type; @@ -2462,7 +2465,7 @@ void dc_commit_updates_for_stream(struct dc *dc, enum surface_update_type update_type; struct dc_state *context; struct dc_context *dc_ctx = dc->ctx; - int i; + int i, j; stream_status = dc_stream_get_status(stream); context = dc->current_state; @@ -2500,6 +2503,17 @@ void dc_commit_updates_for_stream(struct dc *dc, copy_surface_update_to_plane(surface, &srf_updates[i]); + if (update_type >= UPDATE_TYPE_MED) { + for (j = 0; j < dc->res_pool->pipe_count; j++) { + struct pipe_ctx *pipe_ctx = + &context->res_ctx.pipe_ctx[j]; + + if (pipe_ctx->plane_state != surface) + continue; + + resource_build_scaling_params(pipe_ctx); + } + } } copy_stream_update_to_stream(dc, context, stream, stream_update); diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index 25c50bcab9e9..a8dc3082e3e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -385,6 +385,8 @@ struct dc_cursor_position { */ bool enable; + /* Translate cursor x/y by the source rectangle for each plane. */ + bool translate_by_source; }; struct dc_cursor_mi_param { diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 0976e378659f..c279982947e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -2685,6 +2685,23 @@ void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx) .mirror = pipe_ctx->plane_state->horizontal_mirror }; + /** + * If the cursor's source viewport is clipped then we need to + * translate the cursor to appear in the correct position on + * the screen. + * + * This translation isn't affected by scaling so it needs to be + * done *after* we adjust the position for the scale factor. + * + * This is only done by opt-in for now since there are still + * some usecases like tiled display that might enable the + * cursor on both streams while expecting dc to clip it. + */ + if (pos_cpy.translate_by_source) { + pos_cpy.x += pipe_ctx->plane_state->src_rect.x; + pos_cpy.y += pipe_ctx->plane_state->src_rect.y; + } + if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) pos_cpy.enable = false; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 0be010085575..b0357546471b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3021,12 +3021,50 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) int x_pos = pos_cpy.x; int y_pos = pos_cpy.y; - // translate cursor from stream space to plane space + /** + * DC cursor is stream space, HW cursor is plane space and drawn + * as part of the framebuffer. + * + * Cursor position can't be negative, but hotspot can be used to + * shift cursor out of the plane bounds. Hotspot must be smaller + * than the cursor size. + */ + + /** + * Translate cursor from stream space to plane space. + * + * If the cursor is scaled then we need to scale the position + * to be in the approximately correct place. We can't do anything + * about the actual size being incorrect, that's a limitation of + * the hardware. + */ x_pos = (x_pos - x_plane) * pipe_ctx->plane_state->src_rect.width / pipe_ctx->plane_state->dst_rect.width; y_pos = (y_pos - y_plane) * pipe_ctx->plane_state->src_rect.height / pipe_ctx->plane_state->dst_rect.height; + /** + * If the cursor's source viewport is clipped then we need to + * translate the cursor to appear in the correct position on + * the screen. + * + * This translation isn't affected by scaling so it needs to be + * done *after* we adjust the position for the scale factor. + * + * This is only done by opt-in for now since there are still + * some usecases like tiled display that might enable the + * cursor on both streams while expecting dc to clip it. + */ + if (pos_cpy.translate_by_source) { + x_pos += pipe_ctx->plane_state->src_rect.x; + y_pos += pipe_ctx->plane_state->src_rect.y; + } + + /** + * If the position is negative then we need to add to the hotspot + * to shift the cursor outside the plane. + */ + if (x_pos < 0) { pos_cpy.x_hotspot -= x_pos; x_pos = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 8b7122249ddc..07265ca7d28c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -585,7 +585,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_pplib_clock_request = false, .disable_pplib_wm_range = false, .pplib_wm_report_mode = WM_REPORT_DEFAULT, - .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = true, .disable_dcc = DCC_ENABLE, .voltage_align_fclk = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 233318260da4..22f421e82733 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1373,6 +1373,7 @@ static void dcn20_update_dchubp_dpp( } if (pipe_ctx->update_flags.bits.viewport || + (context == dc->current_state && plane_state->update_flags.bits.position_change) || (context == dc->current_state && plane_state->update_flags.bits.scaling_change) || (context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling)) { diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 8a87d0ed90ae..2359e88d6029 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -136,6 +136,7 @@ #define RAVEN2_A0 0x81 #define RAVEN1_F0 0xF0 #define RAVEN_UNKNOWN 0xFF +#define RENOIR_A0 0x91 #ifndef ASICREV_IS_RAVEN #define ASICREV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN) #endif @@ -171,8 +172,6 @@ enum { #define ASICREV_IS_NAVI10_P(eChipRev) (eChipRev < NV_NAVI12_P_A0) #define ASICREV_IS_NAVI12_P(eChipRev) ((eChipRev >= NV_NAVI12_P_A0) && (eChipRev < NV_NAVI14_M_A0)) #define ASICREV_IS_NAVI14_M(eChipRev) ((eChipRev >= NV_NAVI14_M_A0) && (eChipRev < NV_UNKNOWN)) -#define RENOIR_A0 0x91 -#define DEVICE_ID_RENOIR_1636 0x1636 // Renoir #define ASICREV_IS_RENOIR(eChipRev) ((eChipRev >= RENOIR_A0) && (eChipRev < RAVEN1_F0)) /* @@ -183,6 +182,9 @@ enum { #define DEVICE_ID_TEMASH_9839 0x9839 #define DEVICE_ID_TEMASH_983D 0x983D +/* RENOIR */ +#define DEVICE_ID_RENOIR_1636 0x1636 + /* Asic Family IDs for different asic family. */ #define FAMILY_CI 120 /* Sea Islands: Hawaii (P), Bonaire (M) */ #define FAMILY_KV 125 /* Fusion => Kaveri: Spectre, Spooky; Kabini: Kalindi */ diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index c195575366a3..2a12614a12c2 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -1452,7 +1452,8 @@ static int pp_get_asic_baco_state(void *handle, int *state) if (!hwmgr) return -EINVAL; - if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_asic_baco_state) + if (!(hwmgr->not_vf && amdgpu_dpm) || + !hwmgr->hwmgr_func->get_asic_baco_state) return 0; mutex_lock(&hwmgr->smu_lock); diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index 5db8c56066ee..1ef0923f7190 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -794,8 +794,21 @@ static int arcturus_force_clk_levels(struct smu_context *smu, struct arcturus_dpm_table *dpm_table; struct arcturus_single_dpm_table *single_dpm_table; uint32_t soft_min_level, soft_max_level; + uint32_t smu_version; int ret = 0; + ret = smu_get_smc_version(smu, NULL, &smu_version); + if (ret) { + pr_err("Failed to get smu version!\n"); + return ret; + } + + if (smu_version >= 0x361200) { + pr_err("Forcing clock level is not supported with " + "54.18 and onwards SMU firmwares\n"); + return -EOPNOTSUPP; + } + soft_min_level = mask ? (ffs(mask) - 1) : 0; soft_max_level = mask ? (fls(mask) - 1) : 0; @@ -1512,6 +1525,38 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu, return 0; } +static int arcturus_set_performance_level(struct smu_context *smu, + enum amd_dpm_forced_level level) +{ + uint32_t smu_version; + int ret; + + ret = smu_get_smc_version(smu, NULL, &smu_version); + if (ret) { + pr_err("Failed to get smu version!\n"); + return ret; + } + + switch (level) { + case AMD_DPM_FORCED_LEVEL_HIGH: + case AMD_DPM_FORCED_LEVEL_LOW: + case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: + if (smu_version >= 0x361200) { + pr_err("Forcing clock level is not supported with " + "54.18 and onwards SMU firmwares\n"); + return -EOPNOTSUPP; + } + break; + default: + break; + } + + return smu_v11_0_set_performance_level(smu, level); +} + static void arcturus_dump_pptable(struct smu_context *smu) { struct smu_table_context *table_context = &smu->smu_table; @@ -2285,7 +2330,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = { .get_profiling_clk_mask = arcturus_get_profiling_clk_mask, .get_power_profile_mode = arcturus_get_power_profile_mode, .set_power_profile_mode = arcturus_set_power_profile_mode, - .set_performance_level = smu_v11_0_set_performance_level, + .set_performance_level = arcturus_set_performance_level, /* debug (internal used) */ .dump_pptable = arcturus_dump_pptable, .get_power_limit = arcturus_get_power_limit, diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index 7bf52ecba01d..ff73a735b888 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -239,6 +239,7 @@ static int renoir_print_clk_levels(struct smu_context *smu, uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0; DpmClocks_t *clk_table = smu->smu_table.clocks_table; SmuMetrics_t metrics; + bool cur_value_match_level = false; if (!clk_table || clk_type >= SMU_CLK_COUNT) return -EINVAL; @@ -297,8 +298,13 @@ static int renoir_print_clk_levels(struct smu_context *smu, GET_DPM_CUR_FREQ(clk_table, clk_type, i, value); size += sprintf(buf + size, "%d: %uMhz %s\n", i, value, cur_value == value ? "*" : ""); + if (cur_value == value) + cur_value_match_level = true; } + if (!cur_value_match_level) + size += sprintf(buf + size, " %uMhz *\n", cur_value); + return size; } @@ -887,6 +893,17 @@ static int renoir_read_sensor(struct smu_context *smu, return ret; } +static bool renoir_is_dpm_running(struct smu_context *smu) +{ + /* + * Util now, the pmfw hasn't exported the interface of SMU + * feature mask to APU SKU so just force on all the feature + * at early initial stage. + */ + return true; + +} + static const struct pptable_funcs renoir_ppt_funcs = { .get_smu_msg_index = renoir_get_smu_msg_index, .get_smu_clk_index = renoir_get_smu_clk_index, @@ -927,6 +944,7 @@ static const struct pptable_funcs renoir_ppt_funcs = { .mode2_reset = smu_v12_0_mode2_reset, .set_soft_freq_limited_range = smu_v12_0_set_soft_freq_limited_range, .set_driver_table_location = smu_v12_0_set_driver_table_location, + .is_dpm_running = renoir_is_dpm_running, }; void renoir_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h index 2a390ddd37dd..89cd6da118a3 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h @@ -37,7 +37,7 @@ extern void renoir_set_ppt_funcs(struct smu_context *smu); freq = table->SocClocks[dpm_level].Freq; \ break; \ case SMU_MCLK: \ - freq = table->MemClocks[dpm_level].Freq; \ + freq = table->FClocks[dpm_level].Freq; \ break; \ case SMU_DCEFCLK: \ freq = table->DcfClocks[dpm_level].Freq; \ diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index 9ded2cef57dd..76736fb8ed94 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1652,8 +1652,7 @@ static ssize_t analogix_dpaux_transfer(struct drm_dp_aux *aux, } struct analogix_dp_device * -analogix_dp_bind(struct device *dev, struct drm_device *drm_dev, - struct analogix_dp_plat_data *plat_data) +analogix_dp_probe(struct device *dev, struct analogix_dp_plat_data *plat_data) { struct platform_device *pdev = to_platform_device(dev); struct analogix_dp_device *dp; @@ -1756,22 +1755,30 @@ analogix_dp_bind(struct device *dev, struct drm_device *drm_dev, irq_flags, "analogix-dp", dp); if (ret) { dev_err(&pdev->dev, "failed to request irq\n"); - goto err_disable_pm_runtime; + return ERR_PTR(ret); } disable_irq(dp->irq); + return dp; +} +EXPORT_SYMBOL_GPL(analogix_dp_probe); + +int analogix_dp_bind(struct analogix_dp_device *dp, struct drm_device *drm_dev) +{ + int ret; + dp->drm_dev = drm_dev; dp->encoder = dp->plat_data->encoder; dp->aux.name = "DP-AUX"; dp->aux.transfer = analogix_dpaux_transfer; - dp->aux.dev = &pdev->dev; + dp->aux.dev = dp->dev; ret = drm_dp_aux_register(&dp->aux); if (ret) - return ERR_PTR(ret); + return ret; - pm_runtime_enable(dev); + pm_runtime_enable(dp->dev); ret = analogix_dp_create_bridge(drm_dev, dp); if (ret) { @@ -1779,13 +1786,12 @@ analogix_dp_bind(struct device *dev, struct drm_device *drm_dev, goto err_disable_pm_runtime; } - return dp; + return 0; err_disable_pm_runtime: + pm_runtime_disable(dp->dev); - pm_runtime_disable(dev); - - return ERR_PTR(ret); + return ret; } EXPORT_SYMBOL_GPL(analogix_dp_bind); @@ -1802,10 +1808,15 @@ void analogix_dp_unbind(struct analogix_dp_device *dp) drm_dp_aux_unregister(&dp->aux); pm_runtime_disable(dp->dev); - clk_disable_unprepare(dp->clock); } EXPORT_SYMBOL_GPL(analogix_dp_unbind); +void analogix_dp_remove(struct analogix_dp_device *dp) +{ + clk_disable_unprepare(dp->clock); +} +EXPORT_SYMBOL_GPL(analogix_dp_remove); + #ifdef CONFIG_PM int analogix_dp_suspend(struct analogix_dp_device *dp) { diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 1de2cde2277c..282774e469ac 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -962,27 +962,40 @@ int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages, unsigned count; struct scatterlist *sg; struct page *page; - u32 len, index; + u32 page_len, page_index; dma_addr_t addr; + u32 dma_len, dma_index; - index = 0; + /* + * Scatterlist elements contains both pages and DMA addresses, but + * one shoud not assume 1:1 relation between them. The sg->length is + * the size of the physical memory chunk described by the sg->page, + * while sg_dma_len(sg) is the size of the DMA (IO virtual) chunk + * described by the sg_dma_address(sg). + */ + page_index = 0; + dma_index = 0; for_each_sg(sgt->sgl, sg, sgt->nents, count) { - len = sg_dma_len(sg); + page_len = sg->length; page = sg_page(sg); + dma_len = sg_dma_len(sg); addr = sg_dma_address(sg); - while (len > 0) { - if (WARN_ON(index >= max_entries)) + while (pages && page_len > 0) { + if (WARN_ON(page_index >= max_entries)) return -1; - if (pages) - pages[index] = page; - if (addrs) - addrs[index] = addr; - + pages[page_index] = page; page++; + page_len -= PAGE_SIZE; + page_index++; + } + while (addrs && dma_len > 0) { + if (WARN_ON(dma_index >= max_entries)) + return -1; + addrs[dma_index] = addr; addr += PAGE_SIZE; - len -= PAGE_SIZE; - index++; + dma_len -= PAGE_SIZE; + dma_index++; } } return 0; diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c index d23d3502ca91..5ee090691390 100644 --- a/drivers/gpu/drm/exynos/exynos_dp.c +++ b/drivers/gpu/drm/exynos/exynos_dp.c @@ -159,15 +159,8 @@ static int exynos_dp_bind(struct device *dev, struct device *master, void *data) struct drm_device *drm_dev = data; int ret; - dp->dev = dev; dp->drm_dev = drm_dev; - dp->plat_data.dev_type = EXYNOS_DP; - dp->plat_data.power_on_start = exynos_dp_poweron; - dp->plat_data.power_off = exynos_dp_poweroff; - dp->plat_data.attach = exynos_dp_bridge_attach; - dp->plat_data.get_modes = exynos_dp_get_modes; - if (!dp->plat_data.panel && !dp->ptn_bridge) { ret = exynos_dp_dt_parse_panel(dp); if (ret) @@ -185,13 +178,11 @@ static int exynos_dp_bind(struct device *dev, struct device *master, void *data) dp->plat_data.encoder = encoder; - dp->adp = analogix_dp_bind(dev, dp->drm_dev, &dp->plat_data); - if (IS_ERR(dp->adp)) { + ret = analogix_dp_bind(dp->adp, dp->drm_dev); + if (ret) dp->encoder.funcs->destroy(&dp->encoder); - return PTR_ERR(dp->adp); - } - return 0; + return ret; } static void exynos_dp_unbind(struct device *dev, struct device *master, @@ -222,6 +213,7 @@ static int exynos_dp_probe(struct platform_device *pdev) if (!dp) return -ENOMEM; + dp->dev = dev; /* * We just use the drvdata until driver run into component * add function, and then we would set drvdata to null, so @@ -247,16 +239,29 @@ static int exynos_dp_probe(struct platform_device *pdev) /* The remote port can be either a panel or a bridge */ dp->plat_data.panel = panel; + dp->plat_data.dev_type = EXYNOS_DP; + dp->plat_data.power_on_start = exynos_dp_poweron; + dp->plat_data.power_off = exynos_dp_poweroff; + dp->plat_data.attach = exynos_dp_bridge_attach; + dp->plat_data.get_modes = exynos_dp_get_modes; dp->plat_data.skip_connector = !!bridge; + dp->ptn_bridge = bridge; out: + dp->adp = analogix_dp_probe(dev, &dp->plat_data); + if (IS_ERR(dp->adp)) + return PTR_ERR(dp->adp); + return component_add(&pdev->dev, &exynos_dp_ops); } static int exynos_dp_remove(struct platform_device *pdev) { + struct exynos_dp_device *dp = platform_get_drvdata(pdev); + component_del(&pdev->dev, &exynos_dp_ops); + analogix_dp_remove(dp->adp); return 0; } diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 9f887a86e555..6cd1f6253814 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -28,9 +28,6 @@ subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror CFLAGS_i915_pci.o = $(call cc-disable-warning, override-init) CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init) -subdir-ccflags-y += \ - $(call as-instr,movntdqa (%eax)$(comma)%xmm0,-DCONFIG_AS_MOVNTDQA) - subdir-ccflags-y += -I$(srctree)/$(src) # Please keep these build lists sorted! diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 73d0f4648c06..2c617c98db3a 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -947,7 +947,8 @@ static const struct cnl_ddi_buf_trans * ehl_get_combo_buf_trans(struct drm_i915_private *dev_priv, int type, int rate, int *n_entries) { - if (type == INTEL_OUTPUT_DP && rate > 270000) { + if (type != INTEL_OUTPUT_HDMI && type != INTEL_OUTPUT_EDP && + rate > 270000) { *n_entries = ARRAY_SIZE(ehl_combo_phy_ddi_translations_hbr2_hbr3); return ehl_combo_phy_ddi_translations_hbr2_hbr3; } @@ -959,7 +960,7 @@ static const struct cnl_ddi_buf_trans * tgl_get_combo_buf_trans(struct drm_i915_private *dev_priv, int type, int rate, int *n_entries) { - if (type != INTEL_OUTPUT_DP) { + if (type == INTEL_OUTPUT_HDMI || type == INTEL_OUTPUT_EDP) { return icl_get_combo_buf_trans(dev_priv, type, rate, n_entries); } else if (rate > 270000) { *n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr2); @@ -1869,7 +1870,11 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder, return; dig_port = enc_to_dig_port(encoder); - intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain); + + if (!intel_phy_is_tc(dev_priv, phy) || + dig_port->tc_mode != TC_PORT_TBT_ALT) + intel_display_power_get(dev_priv, + dig_port->ddi_io_power_domain); /* * AUX power is only needed for (e)DP mode, and for HDMI mode on TC diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 36d069504836..b7440f06c5e2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -896,11 +896,13 @@ static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) static void reloc_gpu_flush(struct reloc_cache *cache) { - GEM_BUG_ON(cache->rq_size >= cache->rq->batch->obj->base.size / sizeof(u32)); + struct drm_i915_gem_object *obj = cache->rq->batch->obj; + + GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32)); cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END; - __i915_gem_object_flush_map(cache->rq->batch->obj, 0, cache->rq_size); - i915_gem_object_unpin_map(cache->rq->batch->obj); + __i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1)); + i915_gem_object_unpin_map(obj); intel_gt_chipset_flush(cache->rq->engine->gt); @@ -1477,10 +1479,8 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) * can read from this userspace address. */ offset = gen8_canonical_addr(offset & ~UPDATE); - if (unlikely(__put_user(offset, &urelocs[r-stack].presumed_offset))) { - remain = -EFAULT; - goto out; - } + __put_user(offset, + &urelocs[r - stack].presumed_offset); } } while (r++, --count); urelocs += ARRAY_SIZE(stack); diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index aed498a0d032..4c5a209cb669 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -191,10 +191,11 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, enum i915_cache_level level, u32 flags) { - struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); - struct sgt_iter sgt_iter; - gen8_pte_t __iomem *gtt_entries; const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, 0); + struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); + gen8_pte_t __iomem *gte; + gen8_pte_t __iomem *end; + struct sgt_iter iter; dma_addr_t addr; /* @@ -202,10 +203,17 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, * not to allow the user to override access to a read only page. */ - gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm; - gtt_entries += vma->node.start / I915_GTT_PAGE_SIZE; - for_each_sgt_daddr(addr, sgt_iter, vma->pages) - gen8_set_pte(gtt_entries++, pte_encode | addr); + gte = (gen8_pte_t __iomem *)ggtt->gsm; + gte += vma->node.start / I915_GTT_PAGE_SIZE; + end = gte + vma->node.size / I915_GTT_PAGE_SIZE; + + for_each_sgt_daddr(addr, iter, vma->pages) + gen8_set_pte(gte++, pte_encode | addr); + GEM_BUG_ON(gte > end); + + /* Fill the allocated but "unused" space beyond the end of the buffer */ + while (gte < end) + gen8_set_pte(gte++, vm->scratch[0].encode); /* * We want to flush the TLBs only after we're certain all the PTE @@ -241,13 +249,22 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm, u32 flags) { struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); - gen6_pte_t __iomem *entries = (gen6_pte_t __iomem *)ggtt->gsm; - unsigned int i = vma->node.start / I915_GTT_PAGE_SIZE; + gen6_pte_t __iomem *gte; + gen6_pte_t __iomem *end; struct sgt_iter iter; dma_addr_t addr; + gte = (gen6_pte_t __iomem *)ggtt->gsm; + gte += vma->node.start / I915_GTT_PAGE_SIZE; + end = gte + vma->node.size / I915_GTT_PAGE_SIZE; + for_each_sgt_daddr(addr, iter, vma->pages) - iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]); + iowrite32(vm->pte_encode(addr, level, flags), gte++); + GEM_BUG_ON(gte > end); + + /* Fill the allocated but "unused" space beyond the end of the buffer */ + while (gte < end) + iowrite32(vm->scratch[0].encode, gte++); /* * We want to flush the TLBs only after we're certain all the PTE diff --git a/drivers/gpu/drm/i915/i915_memcpy.c b/drivers/gpu/drm/i915/i915_memcpy.c index fdd550405fd3..7b3b83bd5ab8 100644 --- a/drivers/gpu/drm/i915/i915_memcpy.c +++ b/drivers/gpu/drm/i915/i915_memcpy.c @@ -35,7 +35,6 @@ static DEFINE_STATIC_KEY_FALSE(has_movntdqa); -#ifdef CONFIG_AS_MOVNTDQA static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) { kernel_fpu_begin(); @@ -93,10 +92,6 @@ static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len) kernel_fpu_end(); } -#else -static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) {} -static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len) {} -#endif /** * i915_memcpy_from_wc: perform an accelerated *aligned* read from WC diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 6650f478b226..47b989834af1 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -633,7 +633,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev) if (config->platform.iommu) { iommu_dev = &pdev->dev; - if (!iommu_dev->iommu_fwspec) + if (!dev_iommu_fwspec_get(iommu_dev)) iommu_dev = iommu_dev->parent; aspace = msm_gem_address_space_create(iommu_dev, diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index f38f5e113c6b..ce98c08aa8b4 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -325,15 +325,9 @@ static int rockchip_dp_bind(struct device *dev, struct device *master, void *data) { struct rockchip_dp_device *dp = dev_get_drvdata(dev); - const struct rockchip_dp_chip_data *dp_data; struct drm_device *drm_dev = data; int ret; - dp_data = of_device_get_match_data(dev); - if (!dp_data) - return -ENODEV; - - dp->data = dp_data; dp->drm_dev = drm_dev; ret = rockchip_dp_drm_create_encoder(dp); @@ -344,16 +338,9 @@ static int rockchip_dp_bind(struct device *dev, struct device *master, dp->plat_data.encoder = &dp->encoder; - dp->plat_data.dev_type = dp->data->chip_type; - dp->plat_data.power_on_start = rockchip_dp_poweron_start; - dp->plat_data.power_off = rockchip_dp_powerdown; - dp->plat_data.get_modes = rockchip_dp_get_modes; - - dp->adp = analogix_dp_bind(dev, dp->drm_dev, &dp->plat_data); - if (IS_ERR(dp->adp)) { - ret = PTR_ERR(dp->adp); + ret = analogix_dp_bind(dp->adp, drm_dev); + if (ret) goto err_cleanup_encoder; - } return 0; err_cleanup_encoder: @@ -368,8 +355,6 @@ static void rockchip_dp_unbind(struct device *dev, struct device *master, analogix_dp_unbind(dp->adp); dp->encoder.funcs->destroy(&dp->encoder); - - dp->adp = ERR_PTR(-ENODEV); } static const struct component_ops rockchip_dp_component_ops = { @@ -380,10 +365,15 @@ static const struct component_ops rockchip_dp_component_ops = { static int rockchip_dp_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + const struct rockchip_dp_chip_data *dp_data; struct drm_panel *panel = NULL; struct rockchip_dp_device *dp; int ret; + dp_data = of_device_get_match_data(dev); + if (!dp_data) + return -ENODEV; + ret = drm_of_find_panel_or_bridge(dev->of_node, 1, 0, &panel, NULL); if (ret < 0) return ret; @@ -394,7 +384,12 @@ static int rockchip_dp_probe(struct platform_device *pdev) dp->dev = dev; dp->adp = ERR_PTR(-ENODEV); + dp->data = dp_data; dp->plat_data.panel = panel; + dp->plat_data.dev_type = dp->data->chip_type; + dp->plat_data.power_on_start = rockchip_dp_poweron_start; + dp->plat_data.power_off = rockchip_dp_powerdown; + dp->plat_data.get_modes = rockchip_dp_get_modes; ret = rockchip_dp_of_probe(dp); if (ret < 0) @@ -402,12 +397,19 @@ static int rockchip_dp_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dp); + dp->adp = analogix_dp_probe(dev, &dp->plat_data); + if (IS_ERR(dp->adp)) + return PTR_ERR(dp->adp); + return component_add(dev, &rockchip_dp_component_ops); } static int rockchip_dp_remove(struct platform_device *pdev) { + struct rockchip_dp_device *dp = platform_get_drvdata(pdev); + component_del(&pdev->dev, &rockchip_dp_component_ops); + analogix_dp_remove(dp->adp); return 0; } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 6ee3b96f0d13..0ad30b112982 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -442,66 +442,6 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) } EXPORT_SYMBOL(ttm_bo_vm_fault); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -/** - * ttm_pgprot_is_wrprotecting - Is a page protection value write-protecting? - * @prot: The page protection value - * - * Return: true if @prot is write-protecting. false otherwise. - */ -static bool ttm_pgprot_is_wrprotecting(pgprot_t prot) -{ - /* - * This is meant to say "pgprot_wrprotect(prot) == prot" in a generic - * way. Unfortunately there is no generic pgprot_wrprotect. - */ - return pte_val(pte_wrprotect(__pte(pgprot_val(prot)))) == - pgprot_val(prot); -} - -static vm_fault_t ttm_bo_vm_huge_fault(struct vm_fault *vmf, - enum page_entry_size pe_size) -{ - struct vm_area_struct *vma = vmf->vma; - pgprot_t prot; - struct ttm_buffer_object *bo = vma->vm_private_data; - vm_fault_t ret; - pgoff_t fault_page_size = 0; - bool write = vmf->flags & FAULT_FLAG_WRITE; - - switch (pe_size) { - case PE_SIZE_PMD: - fault_page_size = HPAGE_PMD_SIZE >> PAGE_SHIFT; - break; -#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD - case PE_SIZE_PUD: - fault_page_size = HPAGE_PUD_SIZE >> PAGE_SHIFT; - break; -#endif - default: - WARN_ON_ONCE(1); - return VM_FAULT_FALLBACK; - } - - /* Fallback on write dirty-tracking or COW */ - if (write && ttm_pgprot_is_wrprotecting(vma->vm_page_prot)) - return VM_FAULT_FALLBACK; - - ret = ttm_bo_vm_reserve(bo, vmf); - if (ret) - return ret; - - prot = vm_get_page_prot(vma->vm_flags); - ret = ttm_bo_vm_fault_reserved(vmf, prot, 1, fault_page_size); - if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) - return ret; - - dma_resv_unlock(bo->base.resv); - - return ret; -} -#endif - void ttm_bo_vm_open(struct vm_area_struct *vma) { struct ttm_buffer_object *bo = vma->vm_private_data; @@ -604,9 +544,6 @@ static const struct vm_operations_struct ttm_bo_vm_ops = { .open = ttm_bo_vm_open, .close = ttm_bo_vm_close, .access = ttm_bo_vm_access, -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - .huge_fault = ttm_bo_vm_huge_fault, -#endif }; static struct ttm_buffer_object *ttm_bo_vm_lookup(struct ttm_bo_device *bdev, diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 2bfb13d1932e..d9039bb7c5e3 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -123,15 +123,17 @@ bool virtio_gpu_is_shmem(struct virtio_gpu_object *bo) struct drm_gem_object *virtio_gpu_create_object(struct drm_device *dev, size_t size) { - struct virtio_gpu_object *bo; + struct virtio_gpu_object_shmem *shmem; + struct drm_gem_shmem_object *dshmem; - bo = kzalloc(sizeof(*bo), GFP_KERNEL); - if (!bo) + shmem = kzalloc(sizeof(*shmem), GFP_KERNEL); + if (!shmem) return NULL; - bo->base.base.funcs = &virtio_gpu_shmem_funcs; - bo->base.map_cached = true; - return &bo->base.base; + dshmem = &shmem->base.base; + dshmem->base.funcs = &virtio_gpu_shmem_funcs; + dshmem->map_cached = true; + return &dshmem->base; } static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index d4c83009d625..ab719d372b0d 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -7,7 +7,7 @@ * Hwmon integration: * Copyright (C) 2011 Jean Delvare <jdelvare@suse.de> * Copyright (C) 2013, 2014 Guenter Roeck <linux@roeck-us.net> - * Copyright (C) 2014, 2015 Pali Rohár <pali.rohar@gmail.com> + * Copyright (C) 2014, 2015 Pali Rohár <pali@kernel.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -86,7 +86,7 @@ static unsigned int auto_fan; #define I8K_HWMON_HAVE_FAN3 (1 << 12) MODULE_AUTHOR("Massimo Dal Zotto (dz@debian.org)"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); MODULE_DESCRIPTION("Dell laptop SMM BIOS hwmon driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS("i8k"); diff --git a/drivers/iio/accel/cros_ec_accel_legacy.c b/drivers/iio/accel/cros_ec_accel_legacy.c index 68e847c6255e..2532b9ad3384 100644 --- a/drivers/iio/accel/cros_ec_accel_legacy.c +++ b/drivers/iio/accel/cros_ec_accel_legacy.c @@ -170,7 +170,8 @@ static int cros_ec_accel_legacy_probe(struct platform_device *pdev) if (!indio_dev) return -ENOMEM; - ret = cros_ec_sensors_core_init(pdev, indio_dev, true); + ret = cros_ec_sensors_core_init(pdev, indio_dev, true, + cros_ec_sensors_capture, NULL); if (ret) return ret; @@ -190,11 +191,6 @@ static int cros_ec_accel_legacy_probe(struct platform_device *pdev) state->sign[CROS_EC_SENSOR_Z] = -1; } - ret = devm_iio_triggered_buffer_setup(dev, indio_dev, NULL, - cros_ec_sensors_capture, NULL); - if (ret) - return ret; - return devm_iio_device_register(dev, indio_dev); } diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c b/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c index 1dcc2a16ab2d..af801e203623 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c @@ -97,7 +97,7 @@ static int cros_ec_lid_angle_probe(struct platform_device *pdev) if (!indio_dev) return -ENOMEM; - ret = cros_ec_sensors_core_init(pdev, indio_dev, false); + ret = cros_ec_sensors_core_init(pdev, indio_dev, false, NULL, NULL); if (ret) return ret; @@ -127,7 +127,6 @@ MODULE_DEVICE_TABLE(platform, cros_ec_lid_angle_ids); static struct platform_driver cros_ec_lid_angle_platform_driver = { .driver = { .name = DRV_NAME, - .pm = &cros_ec_sensors_pm_ops, }, .probe = cros_ec_lid_angle_probe, .id_table = cros_ec_lid_angle_ids, diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c index 576e45faafaf..a66941fdb385 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c @@ -230,10 +230,14 @@ static int cros_ec_sensors_probe(struct platform_device *pdev) if (!indio_dev) return -ENOMEM; - ret = cros_ec_sensors_core_init(pdev, indio_dev, true); + ret = cros_ec_sensors_core_init(pdev, indio_dev, true, + cros_ec_sensors_capture, + cros_ec_sensors_push_data); if (ret) return ret; + iio_buffer_set_attrs(indio_dev->buffer, cros_ec_sensor_fifo_attributes); + indio_dev->info = &ec_sensors_info; state = iio_priv(indio_dev); for (channel = state->channels, i = CROS_EC_SENSOR_X; @@ -245,7 +249,6 @@ static int cros_ec_sensors_probe(struct platform_device *pdev) BIT(IIO_CHAN_INFO_CALIBSCALE); channel->info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SCALE) | - BIT(IIO_CHAN_INFO_FREQUENCY) | BIT(IIO_CHAN_INFO_SAMP_FREQ); channel->info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_SAMP_FREQ); @@ -292,11 +295,6 @@ static int cros_ec_sensors_probe(struct platform_device *pdev) else state->core.read_ec_sensors_data = cros_ec_sensors_read_cmd; - ret = devm_iio_triggered_buffer_setup(dev, indio_dev, NULL, - cros_ec_sensors_capture, NULL); - if (ret) - return ret; - return devm_iio_device_register(dev, indio_dev); } @@ -317,7 +315,6 @@ MODULE_DEVICE_TABLE(platform, cros_ec_sensors_ids); static struct platform_driver cros_ec_sensors_platform_driver = { .driver = { .name = "cros-ec-sensors", - .pm = &cros_ec_sensors_pm_ops, }, .probe = cros_ec_sensors_probe, .id_table = cros_ec_sensors_ids, diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index d3a3626c7cd8..c831915ca7e5 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -11,7 +11,9 @@ #include <linux/iio/common/cros_ec_sensors_core.h> #include <linux/iio/iio.h> #include <linux/iio/kfifo_buf.h> +#include <linux/iio/sysfs.h> #include <linux/iio/trigger_consumer.h> +#include <linux/iio/triggered_buffer.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> @@ -20,6 +22,12 @@ #include <linux/platform_data/cros_ec_sensorhub.h> #include <linux/platform_device.h> +/* + * Hard coded to the first device to support sensor fifo. The EC has a 2048 + * byte fifo and will trigger an interrupt when fifo is 2/3 full. + */ +#define CROS_EC_FIFO_SIZE (2048 * 2 / 3) + static char *cros_ec_loc[] = { [MOTIONSENSE_LOC_BASE] = "base", [MOTIONSENSE_LOC_LID] = "lid", @@ -53,8 +61,15 @@ static int cros_ec_get_host_cmd_version_mask(struct cros_ec_device *ec_dev, static void get_default_min_max_freq(enum motionsensor_type type, u32 *min_freq, - u32 *max_freq) + u32 *max_freq, + u32 *max_fifo_events) { + /* + * We don't know fifo size, set to size previously used by older + * hardware. + */ + *max_fifo_events = CROS_EC_FIFO_SIZE; + switch (type) { case MOTIONSENSE_TYPE_ACCEL: case MOTIONSENSE_TYPE_GYRO: @@ -82,9 +97,155 @@ static void get_default_min_max_freq(enum motionsensor_type type, } } +static int cros_ec_sensor_set_ec_rate(struct cros_ec_sensors_core_state *st, + int rate) +{ + int ret; + + if (rate > U16_MAX) + rate = U16_MAX; + + mutex_lock(&st->cmd_lock); + st->param.cmd = MOTIONSENSE_CMD_EC_RATE; + st->param.ec_rate.data = rate; + ret = cros_ec_motion_send_host_cmd(st, 0); + mutex_unlock(&st->cmd_lock); + return ret; +} + +static ssize_t cros_ec_sensor_set_report_latency(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct cros_ec_sensors_core_state *st = iio_priv(indio_dev); + int integer, fract, ret; + int latency; + + ret = iio_str_to_fixpoint(buf, 100000, &integer, &fract); + if (ret) + return ret; + + /* EC rate is in ms. */ + latency = integer * 1000 + fract / 1000; + ret = cros_ec_sensor_set_ec_rate(st, latency); + if (ret < 0) + return ret; + + return len; +} + +static ssize_t cros_ec_sensor_get_report_latency(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct cros_ec_sensors_core_state *st = iio_priv(indio_dev); + int latency, ret; + + mutex_lock(&st->cmd_lock); + st->param.cmd = MOTIONSENSE_CMD_EC_RATE; + st->param.ec_rate.data = EC_MOTION_SENSE_NO_VALUE; + + ret = cros_ec_motion_send_host_cmd(st, 0); + latency = st->resp->ec_rate.ret; + mutex_unlock(&st->cmd_lock); + if (ret < 0) + return ret; + + return sprintf(buf, "%d.%06u\n", + latency / 1000, + (latency % 1000) * 1000); +} + +static IIO_DEVICE_ATTR(hwfifo_timeout, 0644, + cros_ec_sensor_get_report_latency, + cros_ec_sensor_set_report_latency, 0); + +static ssize_t hwfifo_watermark_max_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct cros_ec_sensors_core_state *st = iio_priv(indio_dev); + + return sprintf(buf, "%d\n", st->fifo_max_event_count); +} + +static IIO_DEVICE_ATTR_RO(hwfifo_watermark_max, 0); + +const struct attribute *cros_ec_sensor_fifo_attributes[] = { + &iio_dev_attr_hwfifo_timeout.dev_attr.attr, + &iio_dev_attr_hwfifo_watermark_max.dev_attr.attr, + NULL, +}; +EXPORT_SYMBOL_GPL(cros_ec_sensor_fifo_attributes); + +int cros_ec_sensors_push_data(struct iio_dev *indio_dev, + s16 *data, + s64 timestamp) +{ + struct cros_ec_sensors_core_state *st = iio_priv(indio_dev); + s16 *out; + s64 delta; + unsigned int i; + + /* + * Ignore samples if the buffer is not set: it is needed if the ODR is + * set but the buffer is not enabled yet. + */ + if (!iio_buffer_enabled(indio_dev)) + return 0; + + out = (s16 *)st->samples; + for_each_set_bit(i, + indio_dev->active_scan_mask, + indio_dev->masklength) { + *out = data[i]; + out++; + } + + if (iio_device_get_clock(indio_dev) != CLOCK_BOOTTIME) + delta = iio_get_time_ns(indio_dev) - cros_ec_get_time_ns(); + else + delta = 0; + + iio_push_to_buffers_with_timestamp(indio_dev, st->samples, + timestamp + delta); + + return 0; +} +EXPORT_SYMBOL_GPL(cros_ec_sensors_push_data); + +static void cros_ec_sensors_core_clean(void *arg) +{ + struct platform_device *pdev = (struct platform_device *)arg; + struct cros_ec_sensorhub *sensor_hub = + dev_get_drvdata(pdev->dev.parent); + struct iio_dev *indio_dev = platform_get_drvdata(pdev); + struct cros_ec_sensors_core_state *st = iio_priv(indio_dev); + u8 sensor_num = st->param.info.sensor_num; + + cros_ec_sensorhub_unregister_push_data(sensor_hub, sensor_num); +} + +/** + * cros_ec_sensors_core_init() - basic initialization of the core structure + * @pdev: platform device created for the sensors + * @indio_dev: iio device structure of the device + * @physical_device: true if the device refers to a physical device + * @trigger_capture: function pointer to call buffer is triggered, + * for backward compatibility. + * @push_data: function to call when cros_ec_sensorhub receives + * a sample for that sensor. + * + * Return: 0 on success, -errno on failure. + */ int cros_ec_sensors_core_init(struct platform_device *pdev, struct iio_dev *indio_dev, - bool physical_device) + bool physical_device, + cros_ec_sensors_capture_t trigger_capture, + cros_ec_sensorhub_push_data_cb_t push_data) { struct device *dev = &pdev->dev; struct cros_ec_sensors_core_state *state = iio_priv(indio_dev); @@ -92,6 +253,7 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, struct cros_ec_dev *ec = sensor_hub->ec; struct cros_ec_sensor_platform *sensor_platform = dev_get_platdata(dev); u32 ver_mask; + int frequencies[ARRAY_SIZE(state->frequencies) / 2] = { 0 }; int ret, i; platform_set_drvdata(pdev, indio_dev); @@ -123,8 +285,6 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, indio_dev->name = pdev->name; if (physical_device) { - indio_dev->modes = INDIO_DIRECT_MODE; - state->param.cmd = MOTIONSENSE_CMD_INFO; state->param.info.sensor_num = sensor_platform->sensor_num; ret = cros_ec_motion_send_host_cmd(state, 0); @@ -142,16 +302,63 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, state->calib[i].scale = MOTION_SENSE_DEFAULT_SCALE; /* 0 is a correct value used to stop the device */ - state->frequencies[0] = 0; if (state->msg->version < 3) { get_default_min_max_freq(state->resp->info.type, - &state->frequencies[1], - &state->frequencies[2]); + &frequencies[1], + &frequencies[2], + &state->fifo_max_event_count); } else { - state->frequencies[1] = - state->resp->info_3.min_frequency; - state->frequencies[2] = - state->resp->info_3.max_frequency; + frequencies[1] = state->resp->info_3.min_frequency; + frequencies[2] = state->resp->info_3.max_frequency; + state->fifo_max_event_count = + state->resp->info_3.fifo_max_event_count; + } + for (i = 0; i < ARRAY_SIZE(frequencies); i++) { + state->frequencies[2 * i] = frequencies[i] / 1000; + state->frequencies[2 * i + 1] = + (frequencies[i] % 1000) * 1000; + } + + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { + /* + * Create a software buffer, feed by the EC FIFO. + * We can not use trigger here, as events are generated + * as soon as sample_frequency is set. + */ + struct iio_buffer *buffer; + + buffer = devm_iio_kfifo_allocate(dev); + if (!buffer) + return -ENOMEM; + + iio_device_attach_buffer(indio_dev, buffer); + indio_dev->modes = INDIO_BUFFER_SOFTWARE; + + ret = cros_ec_sensorhub_register_push_data( + sensor_hub, sensor_platform->sensor_num, + indio_dev, push_data); + if (ret) + return ret; + + ret = devm_add_action_or_reset( + dev, cros_ec_sensors_core_clean, pdev); + if (ret) + return ret; + + /* Timestamp coming from FIFO are in ns since boot. */ + ret = iio_device_set_clock(indio_dev, CLOCK_BOOTTIME); + if (ret) + return ret; + } else { + /* + * The only way to get samples in buffer is to set a + * software tigger (systrig, hrtimer). + */ + ret = devm_iio_triggered_buffer_setup( + dev, indio_dev, NULL, trigger_capture, + NULL); + if (ret) + return ret; } } @@ -159,6 +366,16 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, } EXPORT_SYMBOL_GPL(cros_ec_sensors_core_init); +/** + * cros_ec_motion_send_host_cmd() - send motion sense host command + * @state: pointer to state information for device + * @opt_length: optional length to reduce the response size, useful on the data + * path. Otherwise, the maximal allowed response size is used + * + * When called, the sub-command is assumed to be set in param->cmd. + * + * Return: 0 on success, -errno on failure. + */ int cros_ec_motion_send_host_cmd(struct cros_ec_sensors_core_state *state, u16 opt_length) { @@ -421,6 +638,14 @@ int cros_ec_sensors_read_lpc(struct iio_dev *indio_dev, } EXPORT_SYMBOL_GPL(cros_ec_sensors_read_lpc); +/** + * cros_ec_sensors_read_cmd() - retrieve data using the EC command protocol + * @indio_dev: pointer to IIO device + * @scan_mask: bitmap of the sensor indices to scan + * @data: location to store data + * + * Return: 0 on success, -errno on failure. + */ int cros_ec_sensors_read_cmd(struct iio_dev *indio_dev, unsigned long scan_mask, s16 *data) { @@ -445,6 +670,18 @@ int cros_ec_sensors_read_cmd(struct iio_dev *indio_dev, } EXPORT_SYMBOL_GPL(cros_ec_sensors_read_cmd); +/** + * cros_ec_sensors_capture() - the trigger handler function + * @irq: the interrupt number. + * @p: a pointer to the poll function. + * + * On a trigger event occurring, if the pollfunc is attached then this + * handler is called as a threaded interrupt (and hence may sleep). It + * is responsible for grabbing data from the device and pushing it into + * the associated buffer. + * + * Return: IRQ_HANDLED + */ irqreturn_t cros_ec_sensors_capture(int irq, void *p) { struct iio_poll_func *pf = p; @@ -480,26 +717,24 @@ done: } EXPORT_SYMBOL_GPL(cros_ec_sensors_capture); +/** + * cros_ec_sensors_core_read() - function to request a value from the sensor + * @st: pointer to state information for device + * @chan: channel specification structure table + * @val: will contain one element making up the returned value + * @val2: will contain another element making up the returned value + * @mask: specifies which values to be requested + * + * Return: the type of value returned by the device + */ int cros_ec_sensors_core_read(struct cros_ec_sensors_core_state *st, struct iio_chan_spec const *chan, int *val, int *val2, long mask) { - int ret; + int ret, frequency; switch (mask) { case IIO_CHAN_INFO_SAMP_FREQ: - st->param.cmd = MOTIONSENSE_CMD_EC_RATE; - st->param.ec_rate.data = - EC_MOTION_SENSE_NO_VALUE; - - ret = cros_ec_motion_send_host_cmd(st, 0); - if (ret) - break; - - *val = st->resp->ec_rate.ret; - ret = IIO_VAL_INT; - break; - case IIO_CHAN_INFO_FREQUENCY: st->param.cmd = MOTIONSENSE_CMD_SENSOR_ODR; st->param.sensor_odr.data = EC_MOTION_SENSE_NO_VALUE; @@ -508,8 +743,10 @@ int cros_ec_sensors_core_read(struct cros_ec_sensors_core_state *st, if (ret) break; - *val = st->resp->sensor_odr.ret; - ret = IIO_VAL_INT; + frequency = st->resp->sensor_odr.ret; + *val = frequency / 1000; + *val2 = (frequency % 1000) * 1000; + ret = IIO_VAL_INT_PLUS_MICRO; break; default: ret = -EINVAL; @@ -520,6 +757,17 @@ int cros_ec_sensors_core_read(struct cros_ec_sensors_core_state *st, } EXPORT_SYMBOL_GPL(cros_ec_sensors_core_read); +/** + * cros_ec_sensors_core_read_avail() - get available values + * @indio_dev: pointer to state information for device + * @chan: channel specification structure table + * @vals: list of available values + * @type: type of data returned + * @length: number of data returned in the array + * @mask: specifies which values to be requested + * + * Return: an error code, IIO_AVAIL_RANGE or IIO_AVAIL_LIST + */ int cros_ec_sensors_core_read_avail(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, const int **vals, @@ -533,7 +781,7 @@ int cros_ec_sensors_core_read_avail(struct iio_dev *indio_dev, case IIO_CHAN_INFO_SAMP_FREQ: *length = ARRAY_SIZE(state->frequencies); *vals = (const int *)&state->frequencies; - *type = IIO_VAL_INT; + *type = IIO_VAL_INT_PLUS_MICRO; return IIO_AVAIL_LIST; } @@ -541,31 +789,33 @@ int cros_ec_sensors_core_read_avail(struct iio_dev *indio_dev, } EXPORT_SYMBOL_GPL(cros_ec_sensors_core_read_avail); +/** + * cros_ec_sensors_core_write() - function to write a value to the sensor + * @st: pointer to state information for device + * @chan: channel specification structure table + * @val: first part of value to write + * @val2: second part of value to write + * @mask: specifies which values to write + * + * Return: the type of value returned by the device + */ int cros_ec_sensors_core_write(struct cros_ec_sensors_core_state *st, struct iio_chan_spec const *chan, int val, int val2, long mask) { - int ret; + int ret, frequency; switch (mask) { - case IIO_CHAN_INFO_FREQUENCY: + case IIO_CHAN_INFO_SAMP_FREQ: + frequency = val * 1000 + val2 / 1000; st->param.cmd = MOTIONSENSE_CMD_SENSOR_ODR; - st->param.sensor_odr.data = val; + st->param.sensor_odr.data = frequency; /* Always roundup, so caller gets at least what it asks for. */ st->param.sensor_odr.roundup = 1; ret = cros_ec_motion_send_host_cmd(st, 0); break; - case IIO_CHAN_INFO_SAMP_FREQ: - st->param.cmd = MOTIONSENSE_CMD_EC_RATE; - st->param.ec_rate.data = val; - - ret = cros_ec_motion_send_host_cmd(st, 0); - if (ret) - break; - st->curr_sampl_freq = val; - break; default: ret = -EINVAL; break; @@ -574,52 +824,5 @@ int cros_ec_sensors_core_write(struct cros_ec_sensors_core_state *st, } EXPORT_SYMBOL_GPL(cros_ec_sensors_core_write); -static int __maybe_unused cros_ec_sensors_prepare(struct device *dev) -{ - struct iio_dev *indio_dev = dev_get_drvdata(dev); - struct cros_ec_sensors_core_state *st = iio_priv(indio_dev); - - if (st->curr_sampl_freq == 0) - return 0; - - /* - * If the sensors are sampled at high frequency, we will not be able to - * sleep. Set sampling to a long period if necessary. - */ - if (st->curr_sampl_freq < CROS_EC_MIN_SUSPEND_SAMPLING_FREQUENCY) { - mutex_lock(&st->cmd_lock); - st->param.cmd = MOTIONSENSE_CMD_EC_RATE; - st->param.ec_rate.data = CROS_EC_MIN_SUSPEND_SAMPLING_FREQUENCY; - cros_ec_motion_send_host_cmd(st, 0); - mutex_unlock(&st->cmd_lock); - } - return 0; -} - -static void __maybe_unused cros_ec_sensors_complete(struct device *dev) -{ - struct iio_dev *indio_dev = dev_get_drvdata(dev); - struct cros_ec_sensors_core_state *st = iio_priv(indio_dev); - - if (st->curr_sampl_freq == 0) - return; - - if (st->curr_sampl_freq < CROS_EC_MIN_SUSPEND_SAMPLING_FREQUENCY) { - mutex_lock(&st->cmd_lock); - st->param.cmd = MOTIONSENSE_CMD_EC_RATE; - st->param.ec_rate.data = st->curr_sampl_freq; - cros_ec_motion_send_host_cmd(st, 0); - mutex_unlock(&st->cmd_lock); - } -} - -const struct dev_pm_ops cros_ec_sensors_pm_ops = { -#ifdef CONFIG_PM_SLEEP - .prepare = cros_ec_sensors_prepare, - .complete = cros_ec_sensors_complete -#endif -}; -EXPORT_SYMBOL_GPL(cros_ec_sensors_pm_ops); - MODULE_DESCRIPTION("ChromeOS EC sensor hub core functions"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index eac63c1bb8da..2352c426bfb5 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -189,7 +189,12 @@ ssize_t iio_read_const_attr(struct device *dev, } EXPORT_SYMBOL(iio_read_const_attr); -static int iio_device_set_clock(struct iio_dev *indio_dev, clockid_t clock_id) +/** + * iio_device_set_clock() - Set current timestamping clock for the device + * @indio_dev: IIO device structure containing the device + * @clock_id: timestamping clock posix identifier to set. + */ +int iio_device_set_clock(struct iio_dev *indio_dev, clockid_t clock_id) { int ret; const struct iio_event_interface *ev_int = indio_dev->event_interface; @@ -207,6 +212,7 @@ static int iio_device_set_clock(struct iio_dev *indio_dev, clockid_t clock_id) return 0; } +EXPORT_SYMBOL(iio_device_set_clock); /** * iio_get_time_ns() - utility function to get a time stamp for events etc diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c index 7a838e2956f4..2198b50909ed 100644 --- a/drivers/iio/light/cros_ec_light_prox.c +++ b/drivers/iio/light/cros_ec_light_prox.c @@ -177,10 +177,14 @@ static int cros_ec_light_prox_probe(struct platform_device *pdev) if (!indio_dev) return -ENOMEM; - ret = cros_ec_sensors_core_init(pdev, indio_dev, true); + ret = cros_ec_sensors_core_init(pdev, indio_dev, true, + cros_ec_sensors_capture, + cros_ec_sensors_push_data); if (ret) return ret; + iio_buffer_set_attrs(indio_dev->buffer, cros_ec_sensor_fifo_attributes); + indio_dev->info = &cros_ec_light_prox_info; state = iio_priv(indio_dev); state->core.type = state->core.resp->info.type; @@ -189,8 +193,7 @@ static int cros_ec_light_prox_probe(struct platform_device *pdev) /* Common part */ channel->info_mask_shared_by_all = - BIT(IIO_CHAN_INFO_SAMP_FREQ) | - BIT(IIO_CHAN_INFO_FREQUENCY); + BIT(IIO_CHAN_INFO_SAMP_FREQ); channel->info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_SAMP_FREQ); channel->scan_type.realbits = CROS_EC_SENSOR_BITS; @@ -236,11 +239,6 @@ static int cros_ec_light_prox_probe(struct platform_device *pdev) state->core.read_ec_sensors_data = cros_ec_sensors_read_cmd; - ret = devm_iio_triggered_buffer_setup(dev, indio_dev, NULL, - cros_ec_sensors_capture, NULL); - if (ret) - return ret; - return devm_iio_device_register(dev, indio_dev); } @@ -258,7 +256,6 @@ MODULE_DEVICE_TABLE(platform, cros_ec_light_prox_ids); static struct platform_driver cros_ec_light_prox_platform_driver = { .driver = { .name = "cros-ec-light-prox", - .pm = &cros_ec_sensors_pm_ops, }, .probe = cros_ec_light_prox_probe, .id_table = cros_ec_light_prox_ids, diff --git a/drivers/iio/pressure/cros_ec_baro.c b/drivers/iio/pressure/cros_ec_baro.c index b521bebd551c..c079b8960082 100644 --- a/drivers/iio/pressure/cros_ec_baro.c +++ b/drivers/iio/pressure/cros_ec_baro.c @@ -134,10 +134,14 @@ static int cros_ec_baro_probe(struct platform_device *pdev) if (!indio_dev) return -ENOMEM; - ret = cros_ec_sensors_core_init(pdev, indio_dev, true); + ret = cros_ec_sensors_core_init(pdev, indio_dev, true, + cros_ec_sensors_capture, + cros_ec_sensors_push_data); if (ret) return ret; + iio_buffer_set_attrs(indio_dev->buffer, cros_ec_sensor_fifo_attributes); + indio_dev->info = &cros_ec_baro_info; state = iio_priv(indio_dev); state->core.type = state->core.resp->info.type; @@ -147,8 +151,7 @@ static int cros_ec_baro_probe(struct platform_device *pdev) channel->info_mask_separate = BIT(IIO_CHAN_INFO_RAW); channel->info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SCALE) | - BIT(IIO_CHAN_INFO_SAMP_FREQ) | - BIT(IIO_CHAN_INFO_FREQUENCY); + BIT(IIO_CHAN_INFO_SAMP_FREQ); channel->info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_SAMP_FREQ); channel->scan_type.realbits = CROS_EC_SENSOR_BITS; @@ -182,11 +185,6 @@ static int cros_ec_baro_probe(struct platform_device *pdev) state->core.read_ec_sensors_data = cros_ec_sensors_read_cmd; - ret = devm_iio_triggered_buffer_setup(dev, indio_dev, NULL, - cros_ec_sensors_capture, NULL); - if (ret) - return ret; - return devm_iio_device_register(dev, indio_dev); } diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index d2fade984999..58b4a4dbfc78 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -188,6 +188,7 @@ config INTEL_IOMMU select NEED_DMA_MAP_STATE select DMAR_TABLE select SWIOTLB + select IOASID help DMA remapping (DMAR) devices support enables independent address translations for Direct Memory Access (DMA) from devices. @@ -273,7 +274,7 @@ config IRQ_REMAP # OMAP IOMMU support config OMAP_IOMMU bool "OMAP IOMMU Support" - depends on ARM && MMU + depends on ARM && MMU || (COMPILE_TEST && (ARM || ARM64 || IA64 || SPARC)) depends on ARCH_OMAP2PLUS || COMPILE_TEST select IOMMU_API ---help--- @@ -291,7 +292,7 @@ config OMAP_IOMMU_DEBUG config ROCKCHIP_IOMMU bool "Rockchip IOMMU Support" - depends on ARM || ARM64 + depends on ARM || ARM64 || (COMPILE_TEST && (ARM64 || IA64 || SPARC)) depends on ARCH_ROCKCHIP || COMPILE_TEST select IOMMU_API select ARM_DMA_USE_IOMMU @@ -325,7 +326,7 @@ config TEGRA_IOMMU_SMMU config EXYNOS_IOMMU bool "Exynos IOMMU Support" - depends on ARCH_EXYNOS && MMU + depends on ARCH_EXYNOS && MMU || (COMPILE_TEST && (ARM || ARM64 || IA64 || SPARC)) depends on !CPU_BIG_ENDIAN # revisit driver if we can enable big-endian ptes select IOMMU_API select ARM_DMA_USE_IOMMU @@ -361,7 +362,7 @@ config IPMMU_VMSA config SPAPR_TCE_IOMMU bool "sPAPR TCE IOMMU Support" - depends on PPC_POWERNV || PPC_PSERIES + depends on PPC_POWERNV || PPC_PSERIES || (PPC && COMPILE_TEST) select IOMMU_API help Enables bits of IOMMU API required by VFIO. The iommu_ops @@ -370,7 +371,7 @@ config SPAPR_TCE_IOMMU # ARM IOMMU support config ARM_SMMU tristate "ARM Ltd. System MMU (SMMU) Support" - depends on (ARM64 || ARM) && MMU + depends on (ARM64 || ARM || (COMPILE_TEST && !GENERIC_ATOMIC64)) && MMU select IOMMU_API select IOMMU_IO_PGTABLE_LPAE select ARM_DMA_USE_IOMMU if ARM @@ -440,7 +441,7 @@ config S390_IOMMU config S390_CCW_IOMMU bool "S390 CCW IOMMU Support" - depends on S390 && CCW + depends on S390 && CCW || COMPILE_TEST select IOMMU_API help Enables bits of IOMMU API required by VFIO. The iommu_ops @@ -448,7 +449,7 @@ config S390_CCW_IOMMU config S390_AP_IOMMU bool "S390 AP IOMMU Support" - depends on S390 && ZCRYPT + depends on S390 && ZCRYPT || COMPILE_TEST select IOMMU_API help Enables bits of IOMMU API required by VFIO. The iommu_ops @@ -456,7 +457,7 @@ config S390_AP_IOMMU config MTK_IOMMU bool "MTK IOMMU Support" - depends on ARM || ARM64 + depends on ARM || ARM64 || COMPILE_TEST depends on ARCH_MEDIATEK || COMPILE_TEST select ARM_DMA_USE_IOMMU select IOMMU_API @@ -506,8 +507,8 @@ config HYPERV_IOMMU guests to run with x2APIC mode enabled. config VIRTIO_IOMMU - bool "Virtio IOMMU driver" - depends on VIRTIO=y + tristate "Virtio IOMMU driver" + depends on VIRTIO depends on ARM64 select IOMMU_API select INTERVAL_TREE diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index f8d01d6b00da..ca8c4522045b 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -348,7 +348,7 @@ #define DTE_GCR3_VAL_A(x) (((x) >> 12) & 0x00007ULL) #define DTE_GCR3_VAL_B(x) (((x) >> 15) & 0x0ffffULL) -#define DTE_GCR3_VAL_C(x) (((x) >> 31) & 0xfffffULL) +#define DTE_GCR3_VAL_C(x) (((x) >> 31) & 0x1fffffULL) #define DTE_GCR3_INDEX_A 0 #define DTE_GCR3_INDEX_B 1 diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index aa3ac2a03807..82508730feb7 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -69,6 +69,9 @@ #define IDR1_SSIDSIZE GENMASK(10, 6) #define IDR1_SIDSIZE GENMASK(5, 0) +#define ARM_SMMU_IDR3 0xc +#define IDR3_RIL (1 << 10) + #define ARM_SMMU_IDR5 0x14 #define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) @@ -346,9 +349,14 @@ #define CMDQ_CFGI_1_LEAF (1UL << 0) #define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) +#define CMDQ_TLBI_0_NUM GENMASK_ULL(16, 12) +#define CMDQ_TLBI_RANGE_NUM_MAX 31 +#define CMDQ_TLBI_0_SCALE GENMASK_ULL(24, 20) #define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) #define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) #define CMDQ_TLBI_1_LEAF (1UL << 0) +#define CMDQ_TLBI_1_TTL GENMASK_ULL(9, 8) +#define CMDQ_TLBI_1_TG GENMASK_ULL(11, 10) #define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) #define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) @@ -473,9 +481,13 @@ struct arm_smmu_cmdq_ent { #define CMDQ_OP_TLBI_S2_IPA 0x2a #define CMDQ_OP_TLBI_NSNH_ALL 0x30 struct { + u8 num; + u8 scale; u16 asid; u16 vmid; bool leaf; + u8 ttl; + u8 tg; u64 addr; } tlbi; @@ -548,6 +560,11 @@ struct arm_smmu_cmdq { atomic_t lock; }; +struct arm_smmu_cmdq_batch { + u64 cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS]; + int num; +}; + struct arm_smmu_evtq { struct arm_smmu_queue q; u32 max_stalls; @@ -627,6 +644,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_HYP (1 << 12) #define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) #define ARM_SMMU_FEAT_VAX (1 << 14) +#define ARM_SMMU_FEAT_RANGE_INV (1 << 15) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -895,14 +913,22 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31); break; case CMDQ_OP_TLBI_NH_VA: + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; break; case CMDQ_OP_TLBI_S2_IPA: + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; break; case CMDQ_OP_TLBI_NH_ASID: @@ -1482,6 +1508,24 @@ static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu) return arm_smmu_cmdq_issue_cmdlist(smmu, NULL, 0, true); } +static void arm_smmu_cmdq_batch_add(struct arm_smmu_device *smmu, + struct arm_smmu_cmdq_batch *cmds, + struct arm_smmu_cmdq_ent *cmd) +{ + if (cmds->num == CMDQ_BATCH_ENTRIES) { + arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, false); + cmds->num = 0; + } + arm_smmu_cmdq_build_cmd(&cmds->cmds[cmds->num * CMDQ_ENT_DWORDS], cmd); + cmds->num++; +} + +static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu, + struct arm_smmu_cmdq_batch *cmds) +{ + return arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, true); +} + /* Context descriptor manipulation functions */ static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain, int ssid, bool leaf) @@ -1489,6 +1533,7 @@ static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain, size_t i; unsigned long flags; struct arm_smmu_master *master; + struct arm_smmu_cmdq_batch cmds = {}; struct arm_smmu_device *smmu = smmu_domain->smmu; struct arm_smmu_cmdq_ent cmd = { .opcode = CMDQ_OP_CFGI_CD, @@ -1502,12 +1547,12 @@ static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain, list_for_each_entry(master, &smmu_domain->devices, domain_head) { for (i = 0; i < master->num_sids; i++) { cmd.cfgi.sid = master->sids[i]; - arm_smmu_cmdq_issue_cmd(smmu, &cmd); + arm_smmu_cmdq_batch_add(smmu, &cmds, &cmd); } } spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); - arm_smmu_cmdq_issue_sync(smmu); + arm_smmu_cmdq_batch_submit(smmu, &cmds); } static int arm_smmu_alloc_cd_leaf_table(struct arm_smmu_device *smmu, @@ -1531,6 +1576,7 @@ static void arm_smmu_write_cd_l1_desc(__le64 *dst, u64 val = (l1_desc->l2ptr_dma & CTXDESC_L1_DESC_L2PTR_MASK) | CTXDESC_L1_DESC_V; + /* See comment in arm_smmu_write_ctx_desc() */ WRITE_ONCE(*dst, cpu_to_le64(val)); } @@ -1726,7 +1772,8 @@ arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc) val |= FIELD_PREP(STRTAB_L1_DESC_SPAN, desc->span); val |= desc->l2ptr_dma & STRTAB_L1_DESC_L2PTR_MASK; - *dst = cpu_to_le64(val); + /* See comment in arm_smmu_write_ctx_desc() */ + WRITE_ONCE(*dst, cpu_to_le64(val)); } static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid) @@ -2132,17 +2179,16 @@ arm_smmu_atc_inv_to_cmd(int ssid, unsigned long iova, size_t size, cmd->atc.size = log2_span; } -static int arm_smmu_atc_inv_master(struct arm_smmu_master *master, - struct arm_smmu_cmdq_ent *cmd) +static int arm_smmu_atc_inv_master(struct arm_smmu_master *master) { int i; + struct arm_smmu_cmdq_ent cmd; - if (!master->ats_enabled) - return 0; + arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd); for (i = 0; i < master->num_sids; i++) { - cmd->atc.sid = master->sids[i]; - arm_smmu_cmdq_issue_cmd(master->smmu, cmd); + cmd.atc.sid = master->sids[i]; + arm_smmu_cmdq_issue_cmd(master->smmu, &cmd); } return arm_smmu_cmdq_issue_sync(master->smmu); @@ -2151,10 +2197,11 @@ static int arm_smmu_atc_inv_master(struct arm_smmu_master *master, static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid, unsigned long iova, size_t size) { - int ret = 0; + int i; unsigned long flags; struct arm_smmu_cmdq_ent cmd; struct arm_smmu_master *master; + struct arm_smmu_cmdq_batch cmds = {}; if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_ATS)) return 0; @@ -2179,11 +2226,18 @@ static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, arm_smmu_atc_inv_to_cmd(ssid, iova, size, &cmd); spin_lock_irqsave(&smmu_domain->devices_lock, flags); - list_for_each_entry(master, &smmu_domain->devices, domain_head) - ret |= arm_smmu_atc_inv_master(master, &cmd); + list_for_each_entry(master, &smmu_domain->devices, domain_head) { + if (!master->ats_enabled) + continue; + + for (i = 0; i < master->num_sids; i++) { + cmd.atc.sid = master->sids[i]; + arm_smmu_cmdq_batch_add(smmu_domain->smmu, &cmds, &cmd); + } + } spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); - return ret ? -ETIMEDOUT : 0; + return arm_smmu_cmdq_batch_submit(smmu_domain->smmu, &cmds); } /* IO_PGTABLE API */ @@ -2218,10 +2272,10 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, size_t granule, bool leaf, struct arm_smmu_domain *smmu_domain) { - u64 cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS]; struct arm_smmu_device *smmu = smmu_domain->smmu; - unsigned long start = iova, end = iova + size; - int i = 0; + unsigned long start = iova, end = iova + size, num_pages = 0, tg = 0; + size_t inv_range = granule; + struct arm_smmu_cmdq_batch cmds = {}; struct arm_smmu_cmdq_ent cmd = { .tlbi = { .leaf = leaf, @@ -2239,19 +2293,50 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; } + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { + /* Get the leaf page size */ + tg = __ffs(smmu_domain->domain.pgsize_bitmap); + + /* Convert page size of 12,14,16 (log2) to 1,2,3 */ + cmd.tlbi.tg = (tg - 10) / 2; + + /* Determine what level the granule is at */ + cmd.tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); + + num_pages = size >> tg; + } + while (iova < end) { - if (i == CMDQ_BATCH_ENTRIES) { - arm_smmu_cmdq_issue_cmdlist(smmu, cmds, i, false); - i = 0; + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { + /* + * On each iteration of the loop, the range is 5 bits + * worth of the aligned size remaining. + * The range in pages is: + * + * range = (num_pages & (0x1f << __ffs(num_pages))) + */ + unsigned long scale, num; + + /* Determine the power of 2 multiple number of pages */ + scale = __ffs(num_pages); + cmd.tlbi.scale = scale; + + /* Determine how many chunks of 2^scale size we have */ + num = (num_pages >> scale) & CMDQ_TLBI_RANGE_NUM_MAX; + cmd.tlbi.num = num - 1; + + /* range is num * 2^scale * pgsize */ + inv_range = num << (scale + tg); + + /* Clear out the lower order bits for the next iteration */ + num_pages -= num << scale; } cmd.tlbi.addr = iova; - arm_smmu_cmdq_build_cmd(&cmds[i * CMDQ_ENT_DWORDS], &cmd); - iova += granule; - i++; + arm_smmu_cmdq_batch_add(smmu, &cmds, &cmd); + iova += inv_range; } - - arm_smmu_cmdq_issue_cmdlist(smmu, cmds, i, true); + arm_smmu_cmdq_batch_submit(smmu, &cmds); /* * Unfortunately, this can't be leaf-only since we may have @@ -2611,7 +2696,6 @@ static void arm_smmu_enable_ats(struct arm_smmu_master *master) static void arm_smmu_disable_ats(struct arm_smmu_master *master) { - struct arm_smmu_cmdq_ent cmd; struct arm_smmu_domain *smmu_domain = master->domain; if (!master->ats_enabled) @@ -2623,11 +2707,57 @@ static void arm_smmu_disable_ats(struct arm_smmu_master *master) * ATC invalidation via the SMMU. */ wmb(); - arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd); - arm_smmu_atc_inv_master(master, &cmd); + arm_smmu_atc_inv_master(master); atomic_dec(&smmu_domain->nr_ats_masters); } +static int arm_smmu_enable_pasid(struct arm_smmu_master *master) +{ + int ret; + int features; + int num_pasids; + struct pci_dev *pdev; + + if (!dev_is_pci(master->dev)) + return -ENODEV; + + pdev = to_pci_dev(master->dev); + + features = pci_pasid_features(pdev); + if (features < 0) + return features; + + num_pasids = pci_max_pasids(pdev); + if (num_pasids <= 0) + return num_pasids; + + ret = pci_enable_pasid(pdev, features); + if (ret) { + dev_err(&pdev->dev, "Failed to enable PASID\n"); + return ret; + } + + master->ssid_bits = min_t(u8, ilog2(num_pasids), + master->smmu->ssid_bits); + return 0; +} + +static void arm_smmu_disable_pasid(struct arm_smmu_master *master) +{ + struct pci_dev *pdev; + + if (!dev_is_pci(master->dev)) + return; + + pdev = to_pci_dev(master->dev); + + if (!pdev->pasid_enabled) + return; + + master->ssid_bits = 0; + pci_disable_pasid(pdev); +} + static void arm_smmu_detach_dev(struct arm_smmu_master *master) { unsigned long flags; @@ -2659,7 +2789,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) if (!fwspec) return -ENOENT; - master = fwspec->iommu_priv; + master = dev_iommu_priv_get(dev); smmu = master->smmu; arm_smmu_detach_dev(master); @@ -2795,7 +2925,7 @@ static int arm_smmu_add_device(struct device *dev) if (!fwspec || fwspec->ops != &arm_smmu_ops) return -ENODEV; - if (WARN_ON_ONCE(fwspec->iommu_priv)) + if (WARN_ON_ONCE(dev_iommu_priv_get(dev))) return -EBUSY; smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode); @@ -2810,7 +2940,7 @@ static int arm_smmu_add_device(struct device *dev) master->smmu = smmu; master->sids = fwspec->ids; master->num_sids = fwspec->num_ids; - fwspec->iommu_priv = master; + dev_iommu_priv_set(dev, master); /* Check the SIDs are in range of the SMMU and our stream table */ for (i = 0; i < master->num_sids; i++) { @@ -2831,13 +2961,23 @@ static int arm_smmu_add_device(struct device *dev) master->ssid_bits = min(smmu->ssid_bits, fwspec->num_pasid_bits); + /* + * Note that PASID must be enabled before, and disabled after ATS: + * PCI Express Base 4.0r1.0 - 10.5.1.3 ATS Control Register + * + * Behavior is undefined if this bit is Set and the value of the PASID + * Enable, Execute Requested Enable, or Privileged Mode Requested bits + * are changed. + */ + arm_smmu_enable_pasid(master); + if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB)) master->ssid_bits = min_t(u8, master->ssid_bits, CTXDESC_LINEAR_CDMAX); ret = iommu_device_link(&smmu->iommu, dev); if (ret) - goto err_free_master; + goto err_disable_pasid; group = iommu_group_get_for_dev(dev); if (IS_ERR(group)) { @@ -2850,9 +2990,11 @@ static int arm_smmu_add_device(struct device *dev) err_unlink: iommu_device_unlink(&smmu->iommu, dev); +err_disable_pasid: + arm_smmu_disable_pasid(master); err_free_master: kfree(master); - fwspec->iommu_priv = NULL; + dev_iommu_priv_set(dev, NULL); return ret; } @@ -2865,11 +3007,12 @@ static void arm_smmu_remove_device(struct device *dev) if (!fwspec || fwspec->ops != &arm_smmu_ops) return; - master = fwspec->iommu_priv; + master = dev_iommu_priv_get(dev); smmu = master->smmu; arm_smmu_detach_dev(master); iommu_group_remove_device(dev); iommu_device_unlink(&smmu->iommu, dev); + arm_smmu_disable_pasid(master); kfree(master); iommu_fwspec_free(dev); } @@ -3700,6 +3843,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (smmu->sid_bits <= STRTAB_SPLIT) smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; + /* IDR3 */ + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + if (FIELD_GET(IDR3_RIL, reg)) + smmu->features |= ARM_SMMU_FEAT_RANGE_INV; + /* IDR5 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 16c4b87af42b..a6a5796e9c41 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -98,12 +98,10 @@ struct arm_smmu_master_cfg { s16 smendx[]; }; #define INVALID_SMENDX -1 -#define __fwspec_cfg(fw) ((struct arm_smmu_master_cfg *)fw->iommu_priv) -#define fwspec_smmu(fw) (__fwspec_cfg(fw)->smmu) -#define fwspec_smendx(fw, i) \ - (i >= fw->num_ids ? INVALID_SMENDX : __fwspec_cfg(fw)->smendx[i]) -#define for_each_cfg_sme(fw, i, idx) \ - for (i = 0; idx = fwspec_smendx(fw, i), i < fw->num_ids; ++i) +#define cfg_smendx(cfg, fw, i) \ + (i >= fw->num_ids ? INVALID_SMENDX : cfg->smendx[i]) +#define for_each_cfg_sme(cfg, fw, i, idx) \ + for (i = 0; idx = cfg_smendx(cfg, fw, i), i < fw->num_ids; ++i) static bool using_legacy_binding, using_generic_binding; @@ -1061,7 +1059,7 @@ static bool arm_smmu_free_sme(struct arm_smmu_device *smmu, int idx) static int arm_smmu_master_alloc_smes(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct arm_smmu_master_cfg *cfg = fwspec->iommu_priv; + struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev); struct arm_smmu_device *smmu = cfg->smmu; struct arm_smmu_smr *smrs = smmu->smrs; struct iommu_group *group; @@ -1069,7 +1067,7 @@ static int arm_smmu_master_alloc_smes(struct device *dev) mutex_lock(&smmu->stream_map_mutex); /* Figure out a viable stream map entry allocation */ - for_each_cfg_sme(fwspec, i, idx) { + for_each_cfg_sme(cfg, fwspec, i, idx) { u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]); u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]); @@ -1100,7 +1098,7 @@ static int arm_smmu_master_alloc_smes(struct device *dev) iommu_group_put(group); /* It worked! Now, poke the actual hardware */ - for_each_cfg_sme(fwspec, i, idx) { + for_each_cfg_sme(cfg, fwspec, i, idx) { arm_smmu_write_sme(smmu, idx); smmu->s2crs[idx].group = group; } @@ -1117,14 +1115,14 @@ out_err: return ret; } -static void arm_smmu_master_free_smes(struct iommu_fwspec *fwspec) +static void arm_smmu_master_free_smes(struct arm_smmu_master_cfg *cfg, + struct iommu_fwspec *fwspec) { - struct arm_smmu_device *smmu = fwspec_smmu(fwspec); - struct arm_smmu_master_cfg *cfg = fwspec->iommu_priv; + struct arm_smmu_device *smmu = cfg->smmu; int i, idx; mutex_lock(&smmu->stream_map_mutex); - for_each_cfg_sme(fwspec, i, idx) { + for_each_cfg_sme(cfg, fwspec, i, idx) { if (arm_smmu_free_sme(smmu, idx)) arm_smmu_write_sme(smmu, idx); cfg->smendx[i] = INVALID_SMENDX; @@ -1133,6 +1131,7 @@ static void arm_smmu_master_free_smes(struct iommu_fwspec *fwspec) } static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain, + struct arm_smmu_master_cfg *cfg, struct iommu_fwspec *fwspec) { struct arm_smmu_device *smmu = smmu_domain->smmu; @@ -1146,7 +1145,7 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain, else type = S2CR_TYPE_TRANS; - for_each_cfg_sme(fwspec, i, idx) { + for_each_cfg_sme(cfg, fwspec, i, idx) { if (type == s2cr[idx].type && cbndx == s2cr[idx].cbndx) continue; @@ -1160,10 +1159,11 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain, static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) { - int ret; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct arm_smmu_master_cfg *cfg; struct arm_smmu_device *smmu; - struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + int ret; if (!fwspec || fwspec->ops != &arm_smmu_ops) { dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n"); @@ -1177,10 +1177,11 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) * domains, just say no (but more politely than by dereferencing NULL). * This should be at least a WARN_ON once that's sorted. */ - if (!fwspec->iommu_priv) + cfg = dev_iommu_priv_get(dev); + if (!cfg) return -ENODEV; - smmu = fwspec_smmu(fwspec); + smmu = cfg->smmu; ret = arm_smmu_rpm_get(smmu); if (ret < 0) @@ -1204,7 +1205,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) } /* Looks ok, so add the device to the domain */ - ret = arm_smmu_domain_add_master(smmu_domain, fwspec); + ret = arm_smmu_domain_add_master(smmu_domain, cfg, fwspec); /* * Setup an autosuspend delay to avoid bouncing runpm state. @@ -1383,7 +1384,7 @@ struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode) static int arm_smmu_add_device(struct device *dev) { - struct arm_smmu_device *smmu; + struct arm_smmu_device *smmu = NULL; struct arm_smmu_master_cfg *cfg; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); int i, ret; @@ -1429,7 +1430,7 @@ static int arm_smmu_add_device(struct device *dev) goto out_free; cfg->smmu = smmu; - fwspec->iommu_priv = cfg; + dev_iommu_priv_set(dev, cfg); while (i--) cfg->smendx[i] = INVALID_SMENDX; @@ -1467,7 +1468,7 @@ static void arm_smmu_remove_device(struct device *dev) if (!fwspec || fwspec->ops != &arm_smmu_ops) return; - cfg = fwspec->iommu_priv; + cfg = dev_iommu_priv_get(dev); smmu = cfg->smmu; ret = arm_smmu_rpm_get(smmu); @@ -1475,23 +1476,25 @@ static void arm_smmu_remove_device(struct device *dev) return; iommu_device_unlink(&smmu->iommu, dev); - arm_smmu_master_free_smes(fwspec); + arm_smmu_master_free_smes(cfg, fwspec); arm_smmu_rpm_put(smmu); + dev_iommu_priv_set(dev, NULL); iommu_group_remove_device(dev); - kfree(fwspec->iommu_priv); + kfree(cfg); iommu_fwspec_free(dev); } static struct iommu_group *arm_smmu_device_group(struct device *dev) { + struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev); struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct arm_smmu_device *smmu = fwspec_smmu(fwspec); + struct arm_smmu_device *smmu = cfg->smmu; struct iommu_group *group = NULL; int i, idx; - for_each_cfg_sme(fwspec, i, idx) { + for_each_cfg_sme(cfg, fwspec, i, idx) { if (group && smmu->s2crs[idx].group && group != smmu->s2crs[idx].group) return ERR_PTR(-EINVAL); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 4be549478691..ef0a5246700e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4501,7 +4501,8 @@ static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr) struct dmar_atsr_unit *atsru; struct acpi_dmar_atsr *tmp; - list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) { + list_for_each_entry_rcu(atsru, &dmar_atsr_units, list, + dmar_rcu_check()) { tmp = (struct acpi_dmar_atsr *)atsru->hdr; if (atsr->segment != tmp->segment) continue; diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index d7f2a5358900..2998418f0a38 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -531,7 +531,7 @@ struct page_req_dsc { u64 priv_data[2]; }; -#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x10) +#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) static bool access_error(struct vm_area_struct *vma, struct page_req_dsc *req) { @@ -611,14 +611,15 @@ static irqreturn_t prq_event_thread(int irq, void *d) * any faults on kernel addresses. */ if (!svm->mm) goto bad_req; - /* If the mm is already defunct, don't handle faults. */ - if (!mmget_not_zero(svm->mm)) - goto bad_req; /* If address is not canonical, return invalid response */ if (!is_canonical_address(address)) goto bad_req; + /* If the mm is already defunct, don't handle faults. */ + if (!mmget_not_zero(svm->mm)) + goto bad_req; + down_read(&svm->mm->mmap_sem); vma = find_extend_vma(svm->mm, address); if (!vma || address < vma->vm_start) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 3e3528436e0b..2b471419e26c 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -152,9 +152,9 @@ void iommu_device_unregister(struct iommu_device *iommu) } EXPORT_SYMBOL_GPL(iommu_device_unregister); -static struct iommu_param *iommu_get_dev_param(struct device *dev) +static struct dev_iommu *dev_iommu_get(struct device *dev) { - struct iommu_param *param = dev->iommu_param; + struct dev_iommu *param = dev->iommu; if (param) return param; @@ -164,14 +164,14 @@ static struct iommu_param *iommu_get_dev_param(struct device *dev) return NULL; mutex_init(¶m->lock); - dev->iommu_param = param; + dev->iommu = param; return param; } -static void iommu_free_dev_param(struct device *dev) +static void dev_iommu_free(struct device *dev) { - kfree(dev->iommu_param); - dev->iommu_param = NULL; + kfree(dev->iommu); + dev->iommu = NULL; } int iommu_probe_device(struct device *dev) @@ -183,7 +183,7 @@ int iommu_probe_device(struct device *dev) if (!ops) return -EINVAL; - if (!iommu_get_dev_param(dev)) + if (!dev_iommu_get(dev)) return -ENOMEM; if (!try_module_get(ops->owner)) { @@ -200,7 +200,7 @@ int iommu_probe_device(struct device *dev) err_module_put: module_put(ops->owner); err_free_dev_param: - iommu_free_dev_param(dev); + dev_iommu_free(dev); return ret; } @@ -211,9 +211,9 @@ void iommu_release_device(struct device *dev) if (dev->iommu_group) ops->remove_device(dev); - if (dev->iommu_param) { + if (dev->iommu) { module_put(ops->owner); - iommu_free_dev_param(dev); + dev_iommu_free(dev); } } @@ -972,7 +972,7 @@ int iommu_register_device_fault_handler(struct device *dev, iommu_dev_fault_handler_t handler, void *data) { - struct iommu_param *param = dev->iommu_param; + struct dev_iommu *param = dev->iommu; int ret = 0; if (!param) @@ -1015,7 +1015,7 @@ EXPORT_SYMBOL_GPL(iommu_register_device_fault_handler); */ int iommu_unregister_device_fault_handler(struct device *dev) { - struct iommu_param *param = dev->iommu_param; + struct dev_iommu *param = dev->iommu; int ret = 0; if (!param) @@ -1055,7 +1055,7 @@ EXPORT_SYMBOL_GPL(iommu_unregister_device_fault_handler); */ int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt) { - struct iommu_param *param = dev->iommu_param; + struct dev_iommu *param = dev->iommu; struct iommu_fault_event *evt_pending = NULL; struct iommu_fault_param *fparam; int ret = 0; @@ -1104,7 +1104,7 @@ int iommu_page_response(struct device *dev, int ret = -EINVAL; struct iommu_fault_event *evt; struct iommu_fault_page_request *prm; - struct iommu_param *param = dev->iommu_param; + struct dev_iommu *param = dev->iommu; struct iommu_domain *domain = iommu_get_domain_for_dev(dev); if (!domain || !domain->ops->page_response) @@ -2405,7 +2405,11 @@ int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, if (fwspec) return ops == fwspec->ops ? 0 : -EINVAL; - fwspec = kzalloc(sizeof(*fwspec), GFP_KERNEL); + if (!dev_iommu_get(dev)) + return -ENOMEM; + + /* Preallocate for the overwhelmingly common case of 1 ID */ + fwspec = kzalloc(struct_size(fwspec, ids, 1), GFP_KERNEL); if (!fwspec) return -ENOMEM; @@ -2432,15 +2436,15 @@ EXPORT_SYMBOL_GPL(iommu_fwspec_free); int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - size_t size; - int i; + int i, new_num; if (!fwspec) return -EINVAL; - size = offsetof(struct iommu_fwspec, ids[fwspec->num_ids + num_ids]); - if (size > sizeof(*fwspec)) { - fwspec = krealloc(fwspec, size, GFP_KERNEL); + new_num = fwspec->num_ids + num_ids; + if (new_num > 1) { + fwspec = krealloc(fwspec, struct_size(fwspec, ids, new_num), + GFP_KERNEL); if (!fwspec) return -ENOMEM; @@ -2450,7 +2454,7 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids) for (i = 0; i < num_ids; i++) fwspec->ids[fwspec->num_ids + i] = ids[i]; - fwspec->num_ids += num_ids; + fwspec->num_ids = new_num; return 0; } EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids); diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index ecb3f9464dd5..310cf09feea3 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -89,9 +89,7 @@ static struct ipmmu_vmsa_domain *to_vmsa_domain(struct iommu_domain *dom) static struct ipmmu_vmsa_device *to_ipmmu(struct device *dev) { - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - - return fwspec ? fwspec->iommu_priv : NULL; + return dev_iommu_priv_get(dev); } #define TLB_LOOP_TIMEOUT 100 /* 100us */ @@ -727,14 +725,13 @@ static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain, static int ipmmu_init_platform_device(struct device *dev, struct of_phandle_args *args) { - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct platform_device *ipmmu_pdev; ipmmu_pdev = of_find_device_by_node(args->np); if (!ipmmu_pdev) return -ENODEV; - fwspec->iommu_priv = platform_get_drvdata(ipmmu_pdev); + dev_iommu_priv_set(dev, platform_get_drvdata(ipmmu_pdev)); return 0; } diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 95945f467c03..5f4d6df59cf6 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -358,8 +358,8 @@ static void mtk_iommu_domain_free(struct iommu_domain *domain) static int mtk_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { + struct mtk_iommu_data *data = dev_iommu_priv_get(dev); struct mtk_iommu_domain *dom = to_mtk_domain(domain); - struct mtk_iommu_data *data = dev_iommu_fwspec_get(dev)->iommu_priv; if (!data) return -ENODEV; @@ -378,7 +378,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, static void mtk_iommu_detach_device(struct iommu_domain *domain, struct device *dev) { - struct mtk_iommu_data *data = dev_iommu_fwspec_get(dev)->iommu_priv; + struct mtk_iommu_data *data = dev_iommu_priv_get(dev); if (!data) return; @@ -450,7 +450,7 @@ static int mtk_iommu_add_device(struct device *dev) if (!fwspec || fwspec->ops != &mtk_iommu_ops) return -ENODEV; /* Not a iommu client device */ - data = fwspec->iommu_priv; + data = dev_iommu_priv_get(dev); iommu_device_link(&data->iommu, dev); group = iommu_group_get_for_dev(dev); @@ -469,7 +469,7 @@ static void mtk_iommu_remove_device(struct device *dev) if (!fwspec || fwspec->ops != &mtk_iommu_ops) return; - data = fwspec->iommu_priv; + data = dev_iommu_priv_get(dev); iommu_device_unlink(&data->iommu, dev); iommu_group_remove_device(dev); @@ -496,7 +496,6 @@ static struct iommu_group *mtk_iommu_device_group(struct device *dev) static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) { - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct platform_device *m4updev; if (args->args_count != 1) { @@ -505,13 +504,13 @@ static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) return -EINVAL; } - if (!fwspec->iommu_priv) { + if (!dev_iommu_priv_get(dev)) { /* Get the m4u device */ m4updev = of_find_device_by_node(args->np); if (WARN_ON(!m4updev)) return -EINVAL; - fwspec->iommu_priv = platform_get_drvdata(m4updev); + dev_iommu_priv_set(dev, platform_get_drvdata(m4updev)); } return iommu_fwspec_add_ids(dev, args->args, 1); diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index e93b94ecac45..a31be05601c9 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -263,8 +263,8 @@ static void mtk_iommu_domain_free(struct iommu_domain *domain) static int mtk_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { + struct mtk_iommu_data *data = dev_iommu_priv_get(dev); struct mtk_iommu_domain *dom = to_mtk_domain(domain); - struct mtk_iommu_data *data = dev_iommu_fwspec_get(dev)->iommu_priv; int ret; if (!data) @@ -286,7 +286,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, static void mtk_iommu_detach_device(struct iommu_domain *domain, struct device *dev) { - struct mtk_iommu_data *data = dev_iommu_fwspec_get(dev)->iommu_priv; + struct mtk_iommu_data *data = dev_iommu_priv_get(dev); if (!data) return; @@ -387,20 +387,20 @@ static int mtk_iommu_create_mapping(struct device *dev, return -EINVAL; } - if (!fwspec->iommu_priv) { + if (!dev_iommu_priv_get(dev)) { /* Get the m4u device */ m4updev = of_find_device_by_node(args->np); if (WARN_ON(!m4updev)) return -EINVAL; - fwspec->iommu_priv = platform_get_drvdata(m4updev); + dev_iommu_priv_set(dev, platform_get_drvdata(m4updev)); } ret = iommu_fwspec_add_ids(dev, args->args, 1); if (ret) return ret; - data = fwspec->iommu_priv; + data = dev_iommu_priv_get(dev); m4udev = data->dev; mtk_mapping = m4udev->archdata.iommu; if (!mtk_mapping) { @@ -459,7 +459,7 @@ static int mtk_iommu_add_device(struct device *dev) if (err) return err; - data = fwspec->iommu_priv; + data = dev_iommu_priv_get(dev); mtk_mapping = data->dev->archdata.iommu; err = arm_iommu_attach_device(dev, mtk_mapping); if (err) { @@ -478,7 +478,7 @@ static void mtk_iommu_remove_device(struct device *dev) if (!fwspec || fwspec->ops != &mtk_iommu_ops) return; - data = fwspec->iommu_priv; + data = dev_iommu_priv_get(dev); iommu_device_unlink(&data->iommu, dev); iommu_group_remove_device(dev); diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index be551cc34be4..887fefcb03b4 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -167,7 +167,7 @@ static int omap2_iommu_enable(struct omap_iommu *obj) { u32 l, pa; - if (!obj->iopgd || !IS_ALIGNED((u32)obj->iopgd, SZ_16K)) + if (!obj->iopgd || !IS_ALIGNED((unsigned long)obj->iopgd, SZ_16K)) return -EINVAL; pa = virt_to_phys(obj->iopgd); @@ -434,7 +434,7 @@ static void flush_iotlb_page(struct omap_iommu *obj, u32 da) bytes = iopgsz_to_bytes(cr.cam & 3); if ((start <= da) && (da < start + bytes)) { - dev_dbg(obj->dev, "%s: %08x<=%08x(%x)\n", + dev_dbg(obj->dev, "%s: %08x<=%08x(%zx)\n", __func__, start, da, bytes); iotlb_load_cr(obj, &cr); iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY); @@ -1352,11 +1352,11 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da, omap_pgsz = bytes_to_iopgsz(bytes); if (omap_pgsz < 0) { - dev_err(dev, "invalid size to map: %d\n", bytes); + dev_err(dev, "invalid size to map: %zu\n", bytes); return -EINVAL; } - dev_dbg(dev, "mapping da 0x%lx to pa %pa size 0x%x\n", da, &pa, bytes); + dev_dbg(dev, "mapping da 0x%lx to pa %pa size 0x%zx\n", da, &pa, bytes); iotlb_init_entry(&e, da, pa, omap_pgsz); @@ -1393,7 +1393,7 @@ static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da, size_t bytes = 0; int i; - dev_dbg(dev, "unmapping da 0x%lx size %u\n", da, size); + dev_dbg(dev, "unmapping da 0x%lx size %zu\n", da, size); iommu = omap_domain->iommus; for (i = 0; i < omap_domain->num_iommus; i++, iommu++) { diff --git a/drivers/iommu/omap-iopgtable.h b/drivers/iommu/omap-iopgtable.h index 1a4adb59a859..51d74002cc30 100644 --- a/drivers/iommu/omap-iopgtable.h +++ b/drivers/iommu/omap-iopgtable.h @@ -63,7 +63,8 @@ * * va to pa translation */ -static inline phys_addr_t omap_iommu_translate(u32 d, u32 va, u32 mask) +static inline phys_addr_t omap_iommu_translate(unsigned long d, dma_addr_t va, + dma_addr_t mask) { return (d & mask) | (va & (~mask)); } diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 4328da0b0a9f..0e2a96467767 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -48,7 +48,7 @@ struct qcom_iommu_dev { void __iomem *local_base; u32 sec_id; u8 num_ctxs; - struct qcom_iommu_ctx *ctxs[0]; /* indexed by asid-1 */ + struct qcom_iommu_ctx *ctxs[]; /* indexed by asid-1 */ }; struct qcom_iommu_ctx { @@ -74,16 +74,19 @@ static struct qcom_iommu_domain *to_qcom_iommu_domain(struct iommu_domain *dom) static const struct iommu_ops qcom_iommu_ops; -static struct qcom_iommu_dev * to_iommu(struct iommu_fwspec *fwspec) +static struct qcom_iommu_dev * to_iommu(struct device *dev) { + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + if (!fwspec || fwspec->ops != &qcom_iommu_ops) return NULL; - return fwspec->iommu_priv; + + return dev_iommu_priv_get(dev); } -static struct qcom_iommu_ctx * to_ctx(struct iommu_fwspec *fwspec, unsigned asid) +static struct qcom_iommu_ctx * to_ctx(struct device *dev, unsigned asid) { - struct qcom_iommu_dev *qcom_iommu = to_iommu(fwspec); + struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); if (!qcom_iommu) return NULL; return qcom_iommu->ctxs[asid - 1]; @@ -115,11 +118,14 @@ iommu_readq(struct qcom_iommu_ctx *ctx, unsigned reg) static void qcom_iommu_tlb_sync(void *cookie) { - struct iommu_fwspec *fwspec = cookie; + struct iommu_fwspec *fwspec; + struct device *dev = cookie; unsigned i; + fwspec = dev_iommu_fwspec_get(dev); + for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(fwspec, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); unsigned int val, ret; iommu_writel(ctx, ARM_SMMU_CB_TLBSYNC, 0); @@ -133,11 +139,14 @@ static void qcom_iommu_tlb_sync(void *cookie) static void qcom_iommu_tlb_inv_context(void *cookie) { - struct iommu_fwspec *fwspec = cookie; + struct device *dev = cookie; + struct iommu_fwspec *fwspec; unsigned i; + fwspec = dev_iommu_fwspec_get(dev); + for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(fwspec, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); iommu_writel(ctx, ARM_SMMU_CB_S1_TLBIASID, ctx->asid); } @@ -147,13 +156,16 @@ static void qcom_iommu_tlb_inv_context(void *cookie) static void qcom_iommu_tlb_inv_range_nosync(unsigned long iova, size_t size, size_t granule, bool leaf, void *cookie) { - struct iommu_fwspec *fwspec = cookie; + struct device *dev = cookie; + struct iommu_fwspec *fwspec; unsigned i, reg; reg = leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA; + fwspec = dev_iommu_fwspec_get(dev); + for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(fwspec, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); size_t s = size; iova = (iova >> 12) << 12; @@ -222,9 +234,10 @@ static irqreturn_t qcom_iommu_fault(int irq, void *dev) static int qcom_iommu_init_domain(struct iommu_domain *domain, struct qcom_iommu_dev *qcom_iommu, - struct iommu_fwspec *fwspec) + struct device *dev) { struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct io_pgtable_ops *pgtbl_ops; struct io_pgtable_cfg pgtbl_cfg; int i, ret = 0; @@ -243,7 +256,7 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain, }; qcom_domain->iommu = qcom_iommu; - pgtbl_ops = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &pgtbl_cfg, fwspec); + pgtbl_ops = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &pgtbl_cfg, dev); if (!pgtbl_ops) { dev_err(qcom_iommu->dev, "failed to allocate pagetable ops\n"); ret = -ENOMEM; @@ -256,7 +269,7 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain, domain->geometry.force_aperture = true; for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(fwspec, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); if (!ctx->secure_init) { ret = qcom_scm_restore_sec_cfg(qcom_iommu->sec_id, ctx->asid); @@ -363,8 +376,7 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain) static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev) { - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct qcom_iommu_dev *qcom_iommu = to_iommu(fwspec); + struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); int ret; @@ -375,7 +387,7 @@ static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev /* Ensure that the domain is finalized */ pm_runtime_get_sync(qcom_iommu->dev); - ret = qcom_iommu_init_domain(domain, qcom_iommu, fwspec); + ret = qcom_iommu_init_domain(domain, qcom_iommu, dev); pm_runtime_put_sync(qcom_iommu->dev); if (ret < 0) return ret; @@ -397,9 +409,9 @@ static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *dev) { - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct qcom_iommu_dev *qcom_iommu = to_iommu(fwspec); struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); unsigned i; if (WARN_ON(!qcom_domain->iommu)) @@ -407,7 +419,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de pm_runtime_get_sync(qcom_iommu->dev); for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(fwspec, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); /* Disable the context bank: */ iommu_writel(ctx, ARM_SMMU_CB_SCTLR, 0); @@ -514,7 +526,7 @@ static bool qcom_iommu_capable(enum iommu_cap cap) static int qcom_iommu_add_device(struct device *dev) { - struct qcom_iommu_dev *qcom_iommu = to_iommu(dev_iommu_fwspec_get(dev)); + struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); struct iommu_group *group; struct device_link *link; @@ -545,7 +557,7 @@ static int qcom_iommu_add_device(struct device *dev) static void qcom_iommu_remove_device(struct device *dev) { - struct qcom_iommu_dev *qcom_iommu = to_iommu(dev_iommu_fwspec_get(dev)); + struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); if (!qcom_iommu) return; @@ -557,7 +569,6 @@ static void qcom_iommu_remove_device(struct device *dev) static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) { - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct qcom_iommu_dev *qcom_iommu; struct platform_device *iommu_pdev; unsigned asid = args->args[0]; @@ -583,14 +594,14 @@ static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) WARN_ON(asid > qcom_iommu->num_ctxs)) return -EINVAL; - if (!fwspec->iommu_priv) { - fwspec->iommu_priv = qcom_iommu; + if (!dev_iommu_priv_get(dev)) { + dev_iommu_priv_set(dev, qcom_iommu); } else { /* make sure devices iommus dt node isn't referring to * multiple different iommu devices. Multiple context * banks are ok, but multiple devices are not: */ - if (WARN_ON(qcom_iommu != fwspec->iommu_priv)) + if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) return -EINVAL; } diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 3fb7ba72507d..db6559e8336f 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -247,7 +247,7 @@ static int gart_iommu_add_device(struct device *dev) { struct iommu_group *group; - if (!dev->iommu_fwspec) + if (!dev_iommu_fwspec_get(dev)) return -ENODEV; group = iommu_group_get_for_dev(dev); diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index cce329d71fba..d5cac4f46ca5 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -466,7 +466,7 @@ static int viommu_probe_endpoint(struct viommu_dev *viommu, struct device *dev) struct virtio_iommu_req_probe *probe; struct virtio_iommu_probe_property *prop; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct viommu_endpoint *vdev = fwspec->iommu_priv; + struct viommu_endpoint *vdev = dev_iommu_priv_get(dev); if (!fwspec->num_ids) return -EINVAL; @@ -607,24 +607,36 @@ static struct iommu_domain *viommu_domain_alloc(unsigned type) return &vdomain->domain; } -static int viommu_domain_finalise(struct viommu_dev *viommu, +static int viommu_domain_finalise(struct viommu_endpoint *vdev, struct iommu_domain *domain) { int ret; + unsigned long viommu_page_size; + struct viommu_dev *viommu = vdev->viommu; struct viommu_domain *vdomain = to_viommu_domain(domain); - vdomain->viommu = viommu; - vdomain->map_flags = viommu->map_flags; + viommu_page_size = 1UL << __ffs(viommu->pgsize_bitmap); + if (viommu_page_size > PAGE_SIZE) { + dev_err(vdev->dev, + "granule 0x%lx larger than system page size 0x%lx\n", + viommu_page_size, PAGE_SIZE); + return -EINVAL; + } + + ret = ida_alloc_range(&viommu->domain_ids, viommu->first_domain, + viommu->last_domain, GFP_KERNEL); + if (ret < 0) + return ret; + + vdomain->id = (unsigned int)ret; domain->pgsize_bitmap = viommu->pgsize_bitmap; domain->geometry = viommu->geometry; - ret = ida_alloc_range(&viommu->domain_ids, viommu->first_domain, - viommu->last_domain, GFP_KERNEL); - if (ret >= 0) - vdomain->id = (unsigned int)ret; + vdomain->map_flags = viommu->map_flags; + vdomain->viommu = viommu; - return ret > 0 ? 0 : ret; + return 0; } static void viommu_domain_free(struct iommu_domain *domain) @@ -648,7 +660,7 @@ static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev) int ret = 0; struct virtio_iommu_req_attach req; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct viommu_endpoint *vdev = fwspec->iommu_priv; + struct viommu_endpoint *vdev = dev_iommu_priv_get(dev); struct viommu_domain *vdomain = to_viommu_domain(domain); mutex_lock(&vdomain->mutex); @@ -657,7 +669,7 @@ static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev) * Properly initialize the domain now that we know which viommu * owns it. */ - ret = viommu_domain_finalise(vdev->viommu, domain); + ret = viommu_domain_finalise(vdev, domain); } else if (vdomain->viommu != vdev->viommu) { dev_err(dev, "cannot attach to foreign vIOMMU\n"); ret = -EXDEV; @@ -807,8 +819,7 @@ static void viommu_iotlb_sync(struct iommu_domain *domain, static void viommu_get_resv_regions(struct device *dev, struct list_head *head) { struct iommu_resv_region *entry, *new_entry, *msi = NULL; - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct viommu_endpoint *vdev = fwspec->iommu_priv; + struct viommu_endpoint *vdev = dev_iommu_priv_get(dev); int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; list_for_each_entry(entry, &vdev->resv_regions, list) { @@ -876,7 +887,7 @@ static int viommu_add_device(struct device *dev) vdev->dev = dev; vdev->viommu = viommu; INIT_LIST_HEAD(&vdev->resv_regions); - fwspec->iommu_priv = vdev; + dev_iommu_priv_set(dev, vdev); if (viommu->probe_size) { /* Get additional information for this endpoint */ @@ -920,7 +931,7 @@ static void viommu_remove_device(struct device *dev) if (!fwspec || fwspec->ops != &viommu_ops) return; - vdev = fwspec->iommu_priv; + vdev = dev_iommu_priv_get(dev); iommu_group_remove_device(dev); iommu_device_unlink(&vdev->viommu->iommu, dev); @@ -1082,7 +1093,6 @@ static int viommu_probe(struct virtio_device *vdev) #ifdef CONFIG_PCI if (pci_bus_type.iommu_ops != &viommu_ops) { - pci_request_acs(); ret = bus_set_iommu(&pci_bus_type, &viommu_ops); if (ret) goto err_unregister; diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 8d07fdf63a47..e1db43446327 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -201,10 +201,27 @@ static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); } +static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, + size_t nr_pages) +{ + int ret; + struct linear_c *lc = ti->private; + struct block_device *bdev = lc->dev->bdev; + struct dax_device *dax_dev = lc->dev->dax_dev; + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + + dev_sector = linear_map_sector(ti, sector); + ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff); + if (ret) + return ret; + return dax_zero_page_range(dax_dev, pgoff, nr_pages); +} + #else #define linear_dax_direct_access NULL #define linear_dax_copy_from_iter NULL #define linear_dax_copy_to_iter NULL +#define linear_dax_zero_page_range NULL #endif static struct target_type linear_target = { @@ -226,6 +243,7 @@ static struct target_type linear_target = { .direct_access = linear_dax_direct_access, .dax_copy_from_iter = linear_dax_copy_from_iter, .dax_copy_to_iter = linear_dax_copy_to_iter, + .dax_zero_page_range = linear_dax_zero_page_range, }; int __init dm_linear_init(void) diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 99721c76225d..8ea20b56b4d6 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -994,10 +994,26 @@ static size_t log_writes_dax_copy_to_iter(struct dm_target *ti, return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i); } +static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, + size_t nr_pages) +{ + int ret; + struct log_writes_c *lc = ti->private; + sector_t sector = pgoff * PAGE_SECTORS; + + ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages << PAGE_SHIFT, + &pgoff); + if (ret) + return ret; + return dax_zero_page_range(lc->dev->dax_dev, pgoff, + nr_pages << PAGE_SHIFT); +} + #else #define log_writes_dax_direct_access NULL #define log_writes_dax_copy_from_iter NULL #define log_writes_dax_copy_to_iter NULL +#define log_writes_dax_zero_page_range NULL #endif static struct target_type log_writes_target = { @@ -1016,6 +1032,7 @@ static struct target_type log_writes_target = { .direct_access = log_writes_dax_direct_access, .dax_copy_from_iter = log_writes_dax_copy_from_iter, .dax_copy_to_iter = log_writes_dax_copy_to_iter, + .dax_zero_page_range = log_writes_dax_zero_page_range, }; static int __init dm_log_writes_init(void) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 63bbcc20f49a..fa813c0f993d 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -360,10 +360,32 @@ static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); } +static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, + size_t nr_pages) +{ + int ret; + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + struct stripe_c *sc = ti->private; + struct dax_device *dax_dev; + struct block_device *bdev; + uint32_t stripe; + + stripe_map_sector(sc, sector, &stripe, &dev_sector); + dev_sector += sc->stripe[stripe].physical_start; + dax_dev = sc->stripe[stripe].dev->dax_dev; + bdev = sc->stripe[stripe].dev->bdev; + + ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff); + if (ret) + return ret; + return dax_zero_page_range(dax_dev, pgoff, nr_pages); +} + #else #define stripe_dax_direct_access NULL #define stripe_dax_copy_from_iter NULL #define stripe_dax_copy_to_iter NULL +#define stripe_dax_zero_page_range NULL #endif /* @@ -486,6 +508,7 @@ static struct target_type stripe_target = { .direct_access = stripe_dax_direct_access, .dax_copy_from_iter = stripe_dax_copy_from_iter, .dax_copy_to_iter = stripe_dax_copy_to_iter, + .dax_zero_page_range = stripe_dax_zero_page_range, }; int __init dm_stripe_init(void) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 21c0207e3207..db9e46114653 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1199,6 +1199,35 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } +static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, + size_t nr_pages) +{ + struct mapped_device *md = dax_get_private(dax_dev); + sector_t sector = pgoff * PAGE_SECTORS; + struct dm_target *ti; + int ret = -EIO; + int srcu_idx; + + ti = dm_dax_get_live_target(md, sector, &srcu_idx); + + if (!ti) + goto out; + if (WARN_ON(!ti->type->dax_zero_page_range)) { + /* + * ->zero_page_range() is mandatory dax operation. If we are + * here, something is wrong. + */ + dm_put_live_table(md, srcu_idx); + goto out; + } + ret = ti->type->dax_zero_page_range(ti, pgoff, nr_pages); + + out: + dm_put_live_table(md, srcu_idx); + + return ret; +} + /* * A target may call dm_accept_partial_bio only from the map routine. It is * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET, @@ -1969,7 +1998,7 @@ static struct mapped_device *alloc_dev(int minor) if (IS_ENABLED(CONFIG_DAX_DRIVER)) { md->dax_dev = alloc_dax(md, md->disk->disk_name, &dm_dax_ops, 0); - if (!md->dax_dev) + if (IS_ERR(md->dax_dev)) goto bad; } @@ -3200,6 +3229,7 @@ static const struct dax_operations dm_dax_ops = { .dax_supported = dm_dax_supported, .copy_from_iter = dm_dax_copy_from_iter, .copy_to_iter = dm_dax_copy_to_iter, + .zero_page_range = dm_dax_zero_page_range, }; /* diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig index b6841ba6d922..8f201d019f5a 100644 --- a/drivers/misc/mic/Kconfig +++ b/drivers/misc/mic/Kconfig @@ -133,8 +133,4 @@ config VOP OS and tools for MIC to use with this driver are available from <http://software.intel.com/en-us/mic-developer>. -if VOP -source "drivers/vhost/Kconfig.vringh" -endif - endmenu diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig index e74e2bb61236..9db0570c5beb 100644 --- a/drivers/net/caif/Kconfig +++ b/drivers/net/caif/Kconfig @@ -58,8 +58,4 @@ config CAIF_VIRTIO ---help--- The CAIF driver for CAIF over Virtio. -if CAIF_VIRTIO -source "drivers/vhost/Kconfig.vringh" -endif - endif # CAIF_DRIVERS diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index a8b515968569..09087c38fabd 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -1042,8 +1042,10 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, return -EFAULT; } - if (!desc || (desc->out_num + desc->in_num == 0) || - !test_bit(cmd, &cmd_mask)) + if (!desc || + (desc->out_num + desc->in_num == 0) || + cmd > ND_CMD_CALL || + !test_bit(cmd, &cmd_mask)) return -ENOTTY; /* fail write commands (when read-only) */ diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c index 64776ed15bb3..7d4ddc4d9322 100644 --- a/drivers/nvdimm/dimm.c +++ b/drivers/nvdimm/dimm.c @@ -99,7 +99,7 @@ static int nvdimm_probe(struct device *dev) if (ndd->ns_current >= 0) { rc = nd_label_reserve_dpa(ndd); if (rc == 0) - nvdimm_set_aliasing(dev); + nvdimm_set_labeling(dev); } nvdimm_bus_unlock(dev); diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 94ea6dba6b4f..b7b77e8d9027 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -32,7 +32,7 @@ int nvdimm_check_config_data(struct device *dev) if (!nvdimm->cmd_mask || !test_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm->cmd_mask)) { - if (test_bit(NDD_ALIASING, &nvdimm->flags)) + if (test_bit(NDD_LABELING, &nvdimm->flags)) return -ENXIO; else return -ENOTTY; @@ -173,11 +173,11 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset, return rc; } -void nvdimm_set_aliasing(struct device *dev) +void nvdimm_set_labeling(struct device *dev) { struct nvdimm *nvdimm = to_nvdimm(dev); - set_bit(NDD_ALIASING, &nvdimm->flags); + set_bit(NDD_LABELING, &nvdimm->flags); } void nvdimm_set_locked(struct device *dev) @@ -312,8 +312,9 @@ static ssize_t flags_show(struct device *dev, { struct nvdimm *nvdimm = to_nvdimm(dev); - return sprintf(buf, "%s%s\n", + return sprintf(buf, "%s%s%s\n", test_bit(NDD_ALIASING, &nvdimm->flags) ? "alias " : "", + test_bit(NDD_LABELING, &nvdimm->flags) ? "label " : "", test_bit(NDD_LOCKED, &nvdimm->flags) ? "lock " : ""); } static DEVICE_ATTR_RO(flags); @@ -562,6 +563,21 @@ int nvdimm_security_freeze(struct nvdimm *nvdimm) return rc; } +static unsigned long dpa_align(struct nd_region *nd_region) +{ + struct device *dev = &nd_region->dev; + + if (dev_WARN_ONCE(dev, !is_nvdimm_bus_locked(dev), + "bus lock required for capacity provision\n")) + return 0; + if (dev_WARN_ONCE(dev, !nd_region->ndr_mappings || nd_region->align + % nd_region->ndr_mappings, + "invalid region align %#lx mappings: %d\n", + nd_region->align, nd_region->ndr_mappings)) + return 0; + return nd_region->align / nd_region->ndr_mappings; +} + int alias_dpa_busy(struct device *dev, void *data) { resource_size_t map_end, blk_start, new; @@ -570,6 +586,7 @@ int alias_dpa_busy(struct device *dev, void *data) struct nd_region *nd_region; struct nvdimm_drvdata *ndd; struct resource *res; + unsigned long align; int i; if (!is_memory(dev)) @@ -607,13 +624,21 @@ int alias_dpa_busy(struct device *dev, void *data) * Find the free dpa from the end of the last pmem allocation to * the end of the interleave-set mapping. */ + align = dpa_align(nd_region); + if (!align) + return 0; + for_each_dpa_resource(ndd, res) { + resource_size_t start, end; + if (strncmp(res->name, "pmem", 4) != 0) continue; - if ((res->start >= blk_start && res->start < map_end) - || (res->end >= blk_start - && res->end <= map_end)) { - new = max(blk_start, min(map_end + 1, res->end + 1)); + + start = ALIGN_DOWN(res->start, align); + end = ALIGN(res->end + 1, align) - 1; + if ((start >= blk_start && start < map_end) + || (end >= blk_start && end <= map_end)) { + new = max(blk_start, min(map_end, end) + 1); if (new != blk_start) { blk_start = new; goto retry; @@ -653,6 +678,7 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) .res = NULL, }; struct resource *res; + unsigned long align; if (!ndd) return 0; @@ -660,10 +686,20 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy); /* now account for busy blk allocations in unaliased dpa */ + align = dpa_align(nd_region); + if (!align) + return 0; for_each_dpa_resource(ndd, res) { + resource_size_t start, end, size; + if (strncmp(res->name, "blk", 3) != 0) continue; - info.available -= resource_size(res); + start = ALIGN_DOWN(res->start, align); + end = ALIGN(res->end + 1, align) - 1; + size = end - start + 1; + if (size >= info.available) + return 0; + info.available -= size; } return info.available; @@ -682,19 +718,31 @@ resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region, struct nvdimm_bus *nvdimm_bus; resource_size_t max = 0; struct resource *res; + unsigned long align; /* if a dimm is disabled the available capacity is zero */ if (!ndd) return 0; + align = dpa_align(nd_region); + if (!align) + return 0; + nvdimm_bus = walk_to_nvdimm_bus(ndd->dev); if (__reserve_free_pmem(&nd_region->dev, nd_mapping->nvdimm)) return 0; for_each_dpa_resource(ndd, res) { + resource_size_t start, end; + if (strcmp(res->name, "pmem-reserve") != 0) continue; - if (resource_size(res) > max) - max = resource_size(res); + /* trim free space relative to current alignment setting */ + start = ALIGN(res->start, align); + end = ALIGN_DOWN(res->end + 1, align) - 1; + if (end < start) + continue; + if (end - start + 1 > max) + max = end - start + 1; } release_free_pmem(nvdimm_bus, nd_mapping); return max; @@ -722,24 +770,33 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); struct resource *res; const char *reason; + unsigned long align; if (!ndd) return 0; + align = dpa_align(nd_region); + if (!align) + return 0; + map_start = nd_mapping->start; map_end = map_start + nd_mapping->size - 1; blk_start = max(map_start, map_end + 1 - *overlap); for_each_dpa_resource(ndd, res) { - if (res->start >= map_start && res->start < map_end) { + resource_size_t start, end; + + start = ALIGN_DOWN(res->start, align); + end = ALIGN(res->end + 1, align) - 1; + if (start >= map_start && start < map_end) { if (strncmp(res->name, "blk", 3) == 0) blk_start = min(blk_start, - max(map_start, res->start)); - else if (res->end > map_end) { + max(map_start, start)); + else if (end > map_end) { reason = "misaligned to iset"; goto err; } else - busy += resource_size(res); - } else if (res->end >= map_start && res->end <= map_end) { + busy += end - start + 1; + } else if (end >= map_start && end <= map_end) { if (strncmp(res->name, "blk", 3) == 0) { /* * If a BLK allocation overlaps the start of @@ -748,8 +805,8 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, */ blk_start = map_start; } else - busy += resource_size(res); - } else if (map_start > res->start && map_start < res->end) { + busy += end - start + 1; + } else if (map_start > start && map_start < end) { /* total eclipse of the mapping */ busy += nd_mapping->size; blk_start = map_start; @@ -759,7 +816,7 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, *overlap = map_end + 1 - blk_start; available = blk_start - map_start; if (busy < available) - return available - busy; + return ALIGN_DOWN(available - busy, align); return 0; err: diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c index e02f60ad6c99..4cd18be9d0e9 100644 --- a/drivers/nvdimm/e820.c +++ b/drivers/nvdimm/e820.c @@ -7,6 +7,7 @@ #include <linux/memory_hotplug.h> #include <linux/libnvdimm.h> #include <linux/module.h> +#include <linux/numa.h> static int e820_pmem_remove(struct platform_device *pdev) { @@ -16,27 +17,16 @@ static int e820_pmem_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_MEMORY_HOTPLUG -static int e820_range_to_nid(resource_size_t addr) -{ - return memory_add_physaddr_to_nid(addr); -} -#else -static int e820_range_to_nid(resource_size_t addr) -{ - return NUMA_NO_NODE; -} -#endif - static int e820_register_one(struct resource *res, void *data) { struct nd_region_desc ndr_desc; struct nvdimm_bus *nvdimm_bus = data; + int nid = phys_to_target_node(res->start); memset(&ndr_desc, 0, sizeof(ndr_desc)); ndr_desc.res = res; - ndr_desc.numa_node = e820_range_to_nid(res->start); - ndr_desc.target_node = ndr_desc.numa_node; + ndr_desc.numa_node = numa_map_to_online_node(nid); + ndr_desc.target_node = nid; set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags); if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc)) return -ENXIO; diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h index 4c7b775c2811..956b6d1bd8cc 100644 --- a/drivers/nvdimm/label.h +++ b/drivers/nvdimm/label.h @@ -62,7 +62,7 @@ struct nd_namespace_index { __le16 major; __le16 minor; __le64 checksum; - u8 free[0]; + u8 free[]; }; /** diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 032dc61725ff..ae155e860fdc 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -10,6 +10,7 @@ #include <linux/nd.h> #include "nd-core.h" #include "pmem.h" +#include "pfn.h" #include "nd.h" static void namespace_io_release(struct device *dev) @@ -541,6 +542,11 @@ static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd, { bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0; bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0; + unsigned long align; + + align = nd_region->align / nd_region->ndr_mappings; + valid->start = ALIGN(valid->start, align); + valid->end = ALIGN_DOWN(valid->end + 1, align) - 1; if (valid->start >= valid->end) goto invalid; @@ -980,10 +986,10 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) return -ENXIO; } - div_u64_rem(val, PAGE_SIZE * nd_region->ndr_mappings, &remainder); + div_u64_rem(val, nd_region->align, &remainder); if (remainder) { dev_dbg(dev, "%llu is not %ldK aligned\n", val, - (PAGE_SIZE * nd_region->ndr_mappings) / SZ_1K); + nd_region->align / SZ_1K); return -EINVAL; } @@ -1739,6 +1745,22 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev) return ERR_PTR(-ENODEV); } + /* + * Note, alignment validation for fsdax and devdax mode + * namespaces happens in nd_pfn_validate() where infoblock + * padding parameters can be applied. + */ + if (pmem_should_map_pages(dev)) { + struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); + struct resource *res = &nsio->res; + + if (!IS_ALIGNED(res->start | (res->end + 1), + memremap_compat_align())) { + dev_err(&ndns->dev, "%pr misaligned, unable to map\n", res); + return ERR_PTR(-EOPNOTSUPP); + } + } + if (is_namespace_pmem(&ndns->dev)) { struct nd_namespace_pmem *nspm; @@ -2521,7 +2543,7 @@ static int init_active_labels(struct nd_region *nd_region) if (!ndd) { if (test_bit(NDD_LOCKED, &nvdimm->flags)) /* fail, label data may be unreadable */; - else if (test_bit(NDD_ALIASING, &nvdimm->flags)) + else if (test_bit(NDD_LABELING, &nvdimm->flags)) /* fail, labels needed to disambiguate dpa */; else return 0; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index c9f6a5b5253a..85dbb2a322b9 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -39,7 +39,7 @@ struct nd_region_data { int ns_count; int ns_active; unsigned int hints_shift; - void __iomem *flush_wpq[0]; + void __iomem *flush_wpq[]; }; static inline void __iomem *ndrd_get_flush_wpq(struct nd_region_data *ndrd, @@ -146,6 +146,7 @@ struct nd_region { struct device *btt_seed; struct device *pfn_seed; struct device *dax_seed; + unsigned long align; u16 ndr_mappings; u64 ndr_size; u64 ndr_start; @@ -156,7 +157,7 @@ struct nd_region { struct nd_interleave_set *nd_set; struct nd_percpu_lane __percpu *lane; int (*flush)(struct nd_region *nd_region, struct bio *bio); - struct nd_mapping mapping[0]; + struct nd_mapping mapping[]; }; struct nd_blk_region { @@ -252,7 +253,7 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset, void *buf, size_t len); long nvdimm_clear_poison(struct device *dev, phys_addr_t phys, unsigned int len); -void nvdimm_set_aliasing(struct device *dev); +void nvdimm_set_labeling(struct device *dev); void nvdimm_set_locked(struct device *dev); void nvdimm_clear_locked(struct device *dev); int nvdimm_security_setup_events(struct device *dev); diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c index 8224d1431ea9..6826a274a1f1 100644 --- a/drivers/nvdimm/of_pmem.c +++ b/drivers/nvdimm/of_pmem.c @@ -62,8 +62,10 @@ static int of_pmem_region_probe(struct platform_device *pdev) if (is_volatile) region = nvdimm_volatile_region_create(bus, &ndr_desc); - else + else { + set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc.flags); region = nvdimm_pmem_region_create(bus, &ndr_desc); + } if (!region) dev_warn(&pdev->dev, "Unable to register region %pR from %pOF\n", diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h index acb19517f678..37cb1b8a2a39 100644 --- a/drivers/nvdimm/pfn.h +++ b/drivers/nvdimm/pfn.h @@ -24,6 +24,18 @@ struct nd_pfn_sb { __le64 npfns; __le32 mode; /* minor-version-1 additions for section alignment */ + /** + * @start_pad: Deprecated attribute to pad start-misaligned namespaces + * + * start_pad is deprecated because the original definition did + * not comprehend that dataoff is relative to the base address + * of the namespace not the start_pad adjusted base. The result + * is that the dax path is broken, but the block-I/O path is + * not. The kernel will no longer create namespaces using start + * padding, but it still supports block-I/O for legacy + * configurations mainly to allow a backup, reconfigure the + * namespace, and restore flow to repair dax operation. + */ __le32 start_pad; __le32 end_trunc; /* minor-version-2 record the base alignment of the mapping */ diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index b94f7a7e94b8..34db557dbad1 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -446,6 +446,7 @@ static bool nd_supported_alignment(unsigned long align) int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) { u64 checksum, offset; + struct resource *res; enum nd_pfn_mode mode; struct nd_namespace_io *nsio; unsigned long align, start_pad; @@ -561,14 +562,14 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n", nd_pfn->align, align, nd_pfn->mode, mode); - return -EINVAL; + return -EOPNOTSUPP; } } if (align > nvdimm_namespace_capacity(ndns)) { dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n", align, nvdimm_namespace_capacity(ndns)); - return -EINVAL; + return -EOPNOTSUPP; } /* @@ -578,18 +579,31 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) * established. */ nsio = to_nd_namespace_io(&ndns->dev); - if (offset >= resource_size(&nsio->res)) { + res = &nsio->res; + if (offset >= resource_size(res)) { dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n", dev_name(&ndns->dev)); - return -EBUSY; + return -EOPNOTSUPP; } - if ((align && !IS_ALIGNED(nsio->res.start + offset + start_pad, align)) + if ((align && !IS_ALIGNED(res->start + offset + start_pad, align)) || !IS_ALIGNED(offset, PAGE_SIZE)) { dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled align: %#lx\n", offset, align); - return -ENXIO; + return -EOPNOTSUPP; + } + + if (!IS_ALIGNED(res->start + le32_to_cpu(pfn_sb->start_pad), + memremap_compat_align())) { + dev_err(&nd_pfn->dev, "resource start misaligned\n"); + return -EOPNOTSUPP; + } + + if (!IS_ALIGNED(res->end + 1 - le32_to_cpu(pfn_sb->end_trunc), + memremap_compat_align())) { + dev_err(&nd_pfn->dev, "resource end misaligned\n"); + return -EOPNOTSUPP; } return 0; @@ -750,7 +764,19 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) start = nsio->res.start; size = resource_size(&nsio->res); npfns = PHYS_PFN(size - SZ_8K); - align = max(nd_pfn->align, (1UL << SUBSECTION_SHIFT)); + align = max(nd_pfn->align, memremap_compat_align()); + + /* + * When @start is misaligned fail namespace creation. See + * the 'struct nd_pfn_sb' commentary on why ->start_pad is not + * an option. + */ + if (!IS_ALIGNED(start, memremap_compat_align())) { + dev_err(&nd_pfn->dev, "%s: start %pa misaligned to %#lx\n", + dev_name(&ndns->dev), &start, + memremap_compat_align()); + return -EINVAL; + } end_trunc = start + size - ALIGN_DOWN(start + size, align); if (nd_pfn->mode == PFN_MODE_PMEM) { /* diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 4ffc6f7ca131..2df6994acf83 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -136,9 +136,25 @@ static blk_status_t read_pmem(struct page *page, unsigned int off, return BLK_STS_OK; } -static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page, - unsigned int len, unsigned int off, unsigned int op, - sector_t sector) +static blk_status_t pmem_do_read(struct pmem_device *pmem, + struct page *page, unsigned int page_off, + sector_t sector, unsigned int len) +{ + blk_status_t rc; + phys_addr_t pmem_off = sector * 512 + pmem->data_offset; + void *pmem_addr = pmem->virt_addr + pmem_off; + + if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) + return BLK_STS_IOERR; + + rc = read_pmem(page, page_off, pmem_addr, len); + flush_dcache_page(page); + return rc; +} + +static blk_status_t pmem_do_write(struct pmem_device *pmem, + struct page *page, unsigned int page_off, + sector_t sector, unsigned int len) { blk_status_t rc = BLK_STS_OK; bool bad_pmem = false; @@ -148,34 +164,25 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page, if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) bad_pmem = true; - if (!op_is_write(op)) { - if (unlikely(bad_pmem)) - rc = BLK_STS_IOERR; - else { - rc = read_pmem(page, off, pmem_addr, len); - flush_dcache_page(page); - } - } else { - /* - * Note that we write the data both before and after - * clearing poison. The write before clear poison - * handles situations where the latest written data is - * preserved and the clear poison operation simply marks - * the address range as valid without changing the data. - * In this case application software can assume that an - * interrupted write will either return the new good - * data or an error. - * - * However, if pmem_clear_poison() leaves the data in an - * indeterminate state we need to perform the write - * after clear poison. - */ - flush_dcache_page(page); - write_pmem(pmem_addr, page, off, len); - if (unlikely(bad_pmem)) { - rc = pmem_clear_poison(pmem, pmem_off, len); - write_pmem(pmem_addr, page, off, len); - } + /* + * Note that we write the data both before and after + * clearing poison. The write before clear poison + * handles situations where the latest written data is + * preserved and the clear poison operation simply marks + * the address range as valid without changing the data. + * In this case application software can assume that an + * interrupted write will either return the new good + * data or an error. + * + * However, if pmem_clear_poison() leaves the data in an + * indeterminate state we need to perform the write + * after clear poison. + */ + flush_dcache_page(page); + write_pmem(pmem_addr, page, page_off, len); + if (unlikely(bad_pmem)) { + rc = pmem_clear_poison(pmem, pmem_off, len); + write_pmem(pmem_addr, page, page_off, len); } return rc; @@ -197,8 +204,12 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) do_acct = nd_iostat_start(bio, &start); bio_for_each_segment(bvec, bio, iter) { - rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, - bvec.bv_offset, bio_op(bio), iter.bi_sector); + if (op_is_write(bio_op(bio))) + rc = pmem_do_write(pmem, bvec.bv_page, bvec.bv_offset, + iter.bi_sector, bvec.bv_len); + else + rc = pmem_do_read(pmem, bvec.bv_page, bvec.bv_offset, + iter.bi_sector, bvec.bv_len); if (rc) { bio->bi_status = rc; break; @@ -223,9 +234,12 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, struct pmem_device *pmem = bdev->bd_queue->queuedata; blk_status_t rc; - rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE, - 0, op, sector); - + if (op_is_write(op)) + rc = pmem_do_write(pmem, page, 0, sector, + hpage_nr_pages(page) * PAGE_SIZE); + else + rc = pmem_do_read(pmem, page, 0, sector, + hpage_nr_pages(page) * PAGE_SIZE); /* * The ->rw_page interface is subtle and tricky. The core * retries on any error, so we can only invoke page_endio() in @@ -268,6 +282,16 @@ static const struct block_device_operations pmem_fops = { .revalidate_disk = nvdimm_revalidate_disk, }; +static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, + size_t nr_pages) +{ + struct pmem_device *pmem = dax_get_private(dax_dev); + + return blk_status_to_errno(pmem_do_write(pmem, ZERO_PAGE(0), 0, + PFN_PHYS(pgoff) >> SECTOR_SHIFT, + PAGE_SIZE)); +} + static long pmem_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { @@ -299,6 +323,7 @@ static const struct dax_operations pmem_dax_ops = { .dax_supported = generic_fsdax_supported, .copy_from_iter = pmem_copy_from_iter, .copy_to_iter = pmem_copy_to_iter, + .zero_page_range = pmem_dax_zero_page_range, }; static const struct attribute_group *pmem_attribute_groups[] = { @@ -461,9 +486,9 @@ static int pmem_attach_disk(struct device *dev, if (is_nvdimm_sync(nd_region)) flags = DAXDEV_F_SYNC; dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags); - if (!dax_dev) { + if (IS_ERR(dax_dev)) { put_disk(disk); - return -ENOMEM; + return PTR_ERR(dax_dev); } dax_write_cache(dax_dev, nvdimm_has_cache(nd_region)); pmem->dax_dev = dax_dev; diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index a19e535830d9..ccbb5b43b8b2 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -195,16 +195,16 @@ EXPORT_SYMBOL_GPL(nd_blk_region_set_provider_data); int nd_region_to_nstype(struct nd_region *nd_region) { if (is_memory(&nd_region->dev)) { - u16 i, alias; + u16 i, label; - for (i = 0, alias = 0; i < nd_region->ndr_mappings; i++) { + for (i = 0, label = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; struct nvdimm *nvdimm = nd_mapping->nvdimm; - if (test_bit(NDD_ALIASING, &nvdimm->flags)) - alias++; + if (test_bit(NDD_LABELING, &nvdimm->flags)) + label++; } - if (alias) + if (label) return ND_DEVICE_NAMESPACE_PMEM; else return ND_DEVICE_NAMESPACE_IO; @@ -216,21 +216,25 @@ int nd_region_to_nstype(struct nd_region *nd_region) } EXPORT_SYMBOL(nd_region_to_nstype); -static ssize_t size_show(struct device *dev, - struct device_attribute *attr, char *buf) +static unsigned long long region_size(struct nd_region *nd_region) { - struct nd_region *nd_region = to_nd_region(dev); - unsigned long long size = 0; - - if (is_memory(dev)) { - size = nd_region->ndr_size; + if (is_memory(&nd_region->dev)) { + return nd_region->ndr_size; } else if (nd_region->ndr_mappings == 1) { struct nd_mapping *nd_mapping = &nd_region->mapping[0]; - size = nd_mapping->size; + return nd_mapping->size; } - return sprintf(buf, "%llu\n", size); + return 0; +} + +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + + return sprintf(buf, "%llu\n", region_size(nd_region)); } static DEVICE_ATTR_RO(size); @@ -529,6 +533,54 @@ static ssize_t read_only_store(struct device *dev, } static DEVICE_ATTR_RW(read_only); +static ssize_t align_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + + return sprintf(buf, "%#lx\n", nd_region->align); +} + +static ssize_t align_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct nd_region *nd_region = to_nd_region(dev); + unsigned long val, dpa; + u32 remainder; + int rc; + + rc = kstrtoul(buf, 0, &val); + if (rc) + return rc; + + if (!nd_region->ndr_mappings) + return -ENXIO; + + /* + * Ensure space-align is evenly divisible by the region + * interleave-width because the kernel typically has no facility + * to determine which DIMM(s), dimm-physical-addresses, would + * contribute to the tail capacity in system-physical-address + * space for the namespace. + */ + dpa = div_u64_rem(val, nd_region->ndr_mappings, &remainder); + if (!is_power_of_2(dpa) || dpa < PAGE_SIZE + || val > region_size(nd_region) || remainder) + return -EINVAL; + + /* + * Given that space allocation consults this value multiple + * times ensure it does not change for the duration of the + * allocation. + */ + nvdimm_bus_lock(dev); + nd_region->align = val; + nvdimm_bus_unlock(dev); + + return len; +} +static DEVICE_ATTR_RW(align); + static ssize_t region_badblocks_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -571,6 +623,7 @@ static DEVICE_ATTR_RO(persistence_domain); static struct attribute *nd_region_attributes[] = { &dev_attr_size.attr, + &dev_attr_align.attr, &dev_attr_nstype.attr, &dev_attr_mappings.attr, &dev_attr_btt_seed.attr, @@ -626,6 +679,19 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n) return a->mode; } + if (a == &dev_attr_align.attr) { + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + if (test_bit(NDD_LABELING, &nvdimm->flags)) + return a->mode; + } + return 0; + } + if (a != &dev_attr_set_cookie.attr && a != &dev_attr_available_size.attr) return a->mode; @@ -935,6 +1001,41 @@ void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane) } EXPORT_SYMBOL(nd_region_release_lane); +/* + * PowerPC requires this alignment for memremap_pages(). All other archs + * should be ok with SUBSECTION_SIZE (see memremap_compat_align()). + */ +#define MEMREMAP_COMPAT_ALIGN_MAX SZ_16M + +static unsigned long default_align(struct nd_region *nd_region) +{ + unsigned long align; + int i, mappings; + u32 remainder; + + if (is_nd_blk(&nd_region->dev)) + align = PAGE_SIZE; + else + align = MEMREMAP_COMPAT_ALIGN_MAX; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + if (test_bit(NDD_ALIASING, &nvdimm->flags)) { + align = MEMREMAP_COMPAT_ALIGN_MAX; + break; + } + } + + mappings = max_t(u16, 1, nd_region->ndr_mappings); + div_u64_rem(align, mappings, &remainder); + if (remainder) + align *= mappings; + + return align; +} + static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc, const struct device_type *dev_type, const char *caller) @@ -1039,6 +1140,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, dev->of_node = ndr_desc->of_node; nd_region->ndr_size = resource_size(ndr_desc->res); nd_region->ndr_start = ndr_desc->res->start; + nd_region->align = default_align(nd_region); if (ndr_desc->flush) nd_region->flush = ndr_desc->flush; else diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 4f907e3beda1..91c1bd659947 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -6,6 +6,7 @@ #include <linux/blkdev.h> #include <linux/blk-mq.h> +#include <linux/compat.h> #include <linux/delay.h> #include <linux/errno.h> #include <linux/hdreg.h> @@ -1252,6 +1253,18 @@ static void nvme_enable_aen(struct nvme_ctrl *ctrl) queue_work(nvme_wq, &ctrl->async_event_work); } +/* + * Convert integer values from ioctl structures to user pointers, silently + * ignoring the upper bits in the compat case to match behaviour of 32-bit + * kernels. + */ +static void __user *nvme_to_user_ptr(uintptr_t ptrval) +{ + if (in_compat_syscall()) + ptrval = (compat_uptr_t)ptrval; + return (void __user *)ptrval; +} + static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) { struct nvme_user_io io; @@ -1275,7 +1288,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) length = (io.nblocks + 1) << ns->lba_shift; meta_len = (io.nblocks + 1) * ns->ms; - metadata = (void __user *)(uintptr_t)io.metadata; + metadata = nvme_to_user_ptr(io.metadata); if (ns->ext) { length += meta_len; @@ -1298,7 +1311,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) c.rw.appmask = cpu_to_le16(io.appmask); return nvme_submit_user_cmd(ns->queue, &c, - (void __user *)(uintptr_t)io.addr, length, + nvme_to_user_ptr(io.addr), length, metadata, meta_len, lower_32_bits(io.slba), NULL, 0); } @@ -1418,9 +1431,9 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, effects = nvme_passthru_start(ctrl, ns, cmd.opcode); status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, - (void __user *)(uintptr_t)cmd.addr, cmd.data_len, - (void __user *)(uintptr_t)cmd.metadata, - cmd.metadata_len, 0, &result, timeout); + nvme_to_user_ptr(cmd.addr), cmd.data_len, + nvme_to_user_ptr(cmd.metadata), cmd.metadata_len, + 0, &result, timeout); nvme_passthru_end(ctrl, effects); if (status >= 0) { @@ -1465,8 +1478,8 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, effects = nvme_passthru_start(ctrl, ns, cmd.opcode); status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, - (void __user *)(uintptr_t)cmd.addr, cmd.data_len, - (void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len, + nvme_to_user_ptr(cmd.addr), cmd.data_len, + nvme_to_user_ptr(cmd.metadata), cmd.metadata_len, 0, &cmd.result, timeout); nvme_passthru_end(ctrl, effects); @@ -1884,6 +1897,13 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); blk_queue_stack_limits(ns->head->disk->queue, ns->queue); + if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) { + struct backing_dev_info *info = + ns->head->disk->queue->backing_dev_info; + + info->capabilities |= BDI_CAP_STABLE_WRITES; + } + revalidate_disk(ns->head->disk); } #endif diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index a8bf2fb1287b..7dfc4a2ecf1e 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -342,8 +342,7 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, !template->ls_req || !template->fcp_io || !template->ls_abort || !template->fcp_abort || !template->max_hw_queues || !template->max_sgl_segments || - !template->max_dif_sgl_segments || !template->dma_boundary || - !template->module) { + !template->max_dif_sgl_segments || !template->dma_boundary) { ret = -EINVAL; goto out_reghost_failed; } @@ -2016,7 +2015,6 @@ nvme_fc_ctrl_free(struct kref *ref) { struct nvme_fc_ctrl *ctrl = container_of(ref, struct nvme_fc_ctrl, ref); - struct nvme_fc_lport *lport = ctrl->lport; unsigned long flags; if (ctrl->ctrl.tagset) { @@ -2043,7 +2041,6 @@ nvme_fc_ctrl_free(struct kref *ref) if (ctrl->ctrl.opts) nvmf_free_options(ctrl->ctrl.opts); kfree(ctrl); - module_put(lport->ops->module); } static void @@ -3074,15 +3071,10 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, goto out_fail; } - if (!try_module_get(lport->ops->module)) { - ret = -EUNATCH; - goto out_free_ctrl; - } - idx = ida_simple_get(&nvme_fc_ctrl_cnt, 0, 0, GFP_KERNEL); if (idx < 0) { ret = -ENOSPC; - goto out_mod_put; + goto out_free_ctrl; } ctrl->ctrl.opts = opts; @@ -3232,8 +3224,6 @@ out_free_queues: out_free_ida: put_device(ctrl->dev); ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum); -out_mod_put: - module_put(lport->ops->module); out_free_ctrl: kfree(ctrl); out_fail: diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 61bf87592570..54603bd3e02d 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -510,7 +510,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl, if (!nr_nsids) return 0; - down_write(&ctrl->namespaces_rwsem); + down_read(&ctrl->namespaces_rwsem); list_for_each_entry(ns, &ctrl->namespaces, list) { unsigned nsid = le32_to_cpu(desc->nsids[n]); @@ -521,7 +521,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl, if (++n == nr_nsids) break; } - up_write(&ctrl->namespaces_rwsem); + up_read(&ctrl->namespaces_rwsem); return 0; } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 76dbb55625ac..cac8a930396a 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1342,7 +1342,7 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue, int ret; sge->addr = qe->dma; - sge->length = sizeof(struct nvme_command), + sge->length = sizeof(struct nvme_command); sge->lkey = queue->device->pd->local_dma_lkey; wr.next = NULL; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 0ef14f0fad86..c15a92163c1f 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -174,16 +174,14 @@ static inline bool nvme_tcp_async_req(struct nvme_tcp_request *req) static inline bool nvme_tcp_has_inline_data(struct nvme_tcp_request *req) { struct request *rq; - unsigned int bytes; if (unlikely(nvme_tcp_async_req(req))) return false; /* async events don't have a request */ rq = blk_mq_rq_from_pdu(req); - bytes = blk_rq_payload_bytes(rq); - return rq_data_dir(rq) == WRITE && bytes && - bytes <= nvme_tcp_inline_data_size(req->queue); + return rq_data_dir(rq) == WRITE && req->data_len && + req->data_len <= nvme_tcp_inline_data_size(req->queue); } static inline struct page *nvme_tcp_req_cur_page(struct nvme_tcp_request *req) @@ -1075,7 +1073,7 @@ static void nvme_tcp_io_work(struct work_struct *w) if (result > 0) pending = true; else if (unlikely(result < 0)) - break; + return; if (!pending) return; @@ -2164,7 +2162,9 @@ static blk_status_t nvme_tcp_map_data(struct nvme_tcp_queue *queue, c->common.flags |= NVME_CMD_SGL_METABUF; - if (rq_data_dir(rq) == WRITE && req->data_len && + if (!blk_rq_nr_phys_segments(rq)) + nvme_tcp_set_sg_null(c); + else if (rq_data_dir(rq) == WRITE && req->data_len <= nvme_tcp_inline_data_size(queue)) nvme_tcp_set_sg_inline(queue, c, req->data_len); else @@ -2191,7 +2191,8 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns, req->data_sent = 0; req->pdu_len = 0; req->pdu_sent = 0; - req->data_len = blk_rq_payload_bytes(rq); + req->data_len = blk_rq_nr_phys_segments(rq) ? + blk_rq_payload_bytes(rq) : 0; req->curr_bio = rq->bio; if (rq_data_dir(rq) == WRITE && @@ -2298,6 +2299,9 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx) struct nvme_tcp_queue *queue = hctx->driver_data; struct sock *sk = queue->sock->sk; + if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags)) + return 0; + if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue)) sk_busy_loop(sk, true); nvme_tcp_try_recv(queue); diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 7aa10788b7c8..58cabd7b6fc5 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1098,12 +1098,19 @@ static struct configfs_attribute *nvmet_referral_attrs[] = { NULL, }; -static void nvmet_referral_release(struct config_item *item) +static void nvmet_referral_notify(struct config_group *group, + struct config_item *item) { struct nvmet_port *parent = to_nvmet_port(item->ci_parent->ci_parent); struct nvmet_port *port = to_nvmet_port(item); nvmet_referral_disable(parent, port); +} + +static void nvmet_referral_release(struct config_item *item) +{ + struct nvmet_port *port = to_nvmet_port(item); + kfree(port); } @@ -1134,6 +1141,7 @@ static struct config_group *nvmet_referral_make( static struct configfs_group_operations nvmet_referral_group_ops = { .make_group = nvmet_referral_make, + .disconnect_notify = nvmet_referral_notify, }; static const struct config_item_type nvmet_referrals_type = { diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index a0db6371b43e..a8ceb7721640 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -684,7 +684,7 @@ nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue) disconnect = atomic_xchg(&queue->connected, 0); spin_lock_irqsave(&queue->qlock, flags); - /* about outstanding io's */ + /* abort outstanding io's */ for (i = 0; i < queue->sqsize; fod++, i++) { if (fod->active) { spin_lock(&fod->flock); diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 1c50af6219f3..f69ce66e2d44 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -198,10 +198,13 @@ struct fcloop_lport_priv { }; struct fcloop_rport { - struct nvme_fc_remote_port *remoteport; - struct nvmet_fc_target_port *targetport; - struct fcloop_nport *nport; - struct fcloop_lport *lport; + struct nvme_fc_remote_port *remoteport; + struct nvmet_fc_target_port *targetport; + struct fcloop_nport *nport; + struct fcloop_lport *lport; + spinlock_t lock; + struct list_head ls_list; + struct work_struct ls_work; }; struct fcloop_tport { @@ -224,11 +227,10 @@ struct fcloop_nport { }; struct fcloop_lsreq { - struct fcloop_tport *tport; struct nvmefc_ls_req *lsreq; - struct work_struct work; struct nvmefc_tgt_ls_req tgt_ls_req; int status; + struct list_head ls_list; /* fcloop_rport->ls_list */ }; struct fcloop_rscn { @@ -292,21 +294,32 @@ fcloop_delete_queue(struct nvme_fc_local_port *localport, { } - -/* - * Transmit of LS RSP done (e.g. buffers all set). call back up - * initiator "done" flows. - */ static void -fcloop_tgt_lsrqst_done_work(struct work_struct *work) +fcloop_rport_lsrqst_work(struct work_struct *work) { - struct fcloop_lsreq *tls_req = - container_of(work, struct fcloop_lsreq, work); - struct fcloop_tport *tport = tls_req->tport; - struct nvmefc_ls_req *lsreq = tls_req->lsreq; + struct fcloop_rport *rport = + container_of(work, struct fcloop_rport, ls_work); + struct fcloop_lsreq *tls_req; - if (!tport || tport->remoteport) - lsreq->done(lsreq, tls_req->status); + spin_lock(&rport->lock); + for (;;) { + tls_req = list_first_entry_or_null(&rport->ls_list, + struct fcloop_lsreq, ls_list); + if (!tls_req) + break; + + list_del(&tls_req->ls_list); + spin_unlock(&rport->lock); + + tls_req->lsreq->done(tls_req->lsreq, tls_req->status); + /* + * callee may free memory containing tls_req. + * do not reference lsreq after this. + */ + + spin_lock(&rport->lock); + } + spin_unlock(&rport->lock); } static int @@ -319,17 +332,18 @@ fcloop_ls_req(struct nvme_fc_local_port *localport, int ret = 0; tls_req->lsreq = lsreq; - INIT_WORK(&tls_req->work, fcloop_tgt_lsrqst_done_work); + INIT_LIST_HEAD(&tls_req->ls_list); if (!rport->targetport) { tls_req->status = -ECONNREFUSED; - tls_req->tport = NULL; - schedule_work(&tls_req->work); + spin_lock(&rport->lock); + list_add_tail(&rport->ls_list, &tls_req->ls_list); + spin_unlock(&rport->lock); + schedule_work(&rport->ls_work); return ret; } tls_req->status = 0; - tls_req->tport = rport->targetport->private; ret = nvmet_fc_rcv_ls_req(rport->targetport, &tls_req->tgt_ls_req, lsreq->rqstaddr, lsreq->rqstlen); @@ -337,18 +351,28 @@ fcloop_ls_req(struct nvme_fc_local_port *localport, } static int -fcloop_xmt_ls_rsp(struct nvmet_fc_target_port *tport, +fcloop_xmt_ls_rsp(struct nvmet_fc_target_port *targetport, struct nvmefc_tgt_ls_req *tgt_lsreq) { struct fcloop_lsreq *tls_req = tgt_ls_req_to_lsreq(tgt_lsreq); struct nvmefc_ls_req *lsreq = tls_req->lsreq; + struct fcloop_tport *tport = targetport->private; + struct nvme_fc_remote_port *remoteport = tport->remoteport; + struct fcloop_rport *rport; memcpy(lsreq->rspaddr, tgt_lsreq->rspbuf, ((lsreq->rsplen < tgt_lsreq->rsplen) ? lsreq->rsplen : tgt_lsreq->rsplen)); + tgt_lsreq->done(tgt_lsreq); - schedule_work(&tls_req->work); + if (remoteport) { + rport = remoteport->private; + spin_lock(&rport->lock); + list_add_tail(&rport->ls_list, &tls_req->ls_list); + spin_unlock(&rport->lock); + schedule_work(&rport->ls_work); + } return 0; } @@ -834,6 +858,7 @@ fcloop_remoteport_delete(struct nvme_fc_remote_port *remoteport) { struct fcloop_rport *rport = remoteport->private; + flush_work(&rport->ls_work); fcloop_nport_put(rport->nport); } @@ -850,7 +875,6 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) #define FCLOOP_DMABOUND_4G 0xFFFFFFFF static struct nvme_fc_port_template fctemplate = { - .module = THIS_MODULE, .localport_delete = fcloop_localport_delete, .remoteport_delete = fcloop_remoteport_delete, .create_queue = fcloop_create_queue, @@ -1136,6 +1160,9 @@ fcloop_create_remote_port(struct device *dev, struct device_attribute *attr, rport->nport = nport; rport->lport = nport->lport; nport->rport = rport; + spin_lock_init(&rport->lock); + INIT_WORK(&rport->ls_work, fcloop_rport_lsrqst_work); + INIT_LIST_HEAD(&rport->ls_list); return count; } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index c90c06839d64..fd47de0e4e4e 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -78,6 +78,7 @@ enum nvmet_rdma_queue_state { struct nvmet_rdma_queue { struct rdma_cm_id *cm_id; + struct ib_qp *qp; struct nvmet_port *port; struct ib_cq *cq; atomic_t sq_wr_avail; @@ -105,6 +106,13 @@ struct nvmet_rdma_queue { struct list_head queue_list; }; +struct nvmet_rdma_port { + struct nvmet_port *nport; + struct sockaddr_storage addr; + struct rdma_cm_id *cm_id; + struct delayed_work repair_work; +}; + struct nvmet_rdma_device { struct ib_device *device; struct ib_pd *pd; @@ -461,7 +469,7 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev, if (ndev->srq) ret = ib_post_srq_recv(ndev->srq, &cmd->wr, NULL); else - ret = ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, NULL); + ret = ib_post_recv(cmd->queue->qp, &cmd->wr, NULL); if (unlikely(ret)) pr_err("post_recv cmd failed\n"); @@ -500,7 +508,7 @@ static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp) atomic_add(1 + rsp->n_rdma, &queue->sq_wr_avail); if (rsp->n_rdma) { - rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp, + rdma_rw_ctx_destroy(&rsp->rw, queue->qp, queue->cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, nvmet_data_dir(&rsp->req)); } @@ -584,7 +592,7 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc) WARN_ON(rsp->n_rdma <= 0); atomic_add(rsp->n_rdma, &queue->sq_wr_avail); - rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp, + rdma_rw_ctx_destroy(&rsp->rw, queue->qp, queue->cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, nvmet_data_dir(&rsp->req)); rsp->n_rdma = 0; @@ -739,7 +747,7 @@ static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp) } if (nvmet_rdma_need_data_in(rsp)) { - if (rdma_rw_ctx_post(&rsp->rw, queue->cm_id->qp, + if (rdma_rw_ctx_post(&rsp->rw, queue->qp, queue->cm_id->port_num, &rsp->read_cqe, NULL)) nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR); } else { @@ -911,7 +919,8 @@ static void nvmet_rdma_free_dev(struct kref *ref) static struct nvmet_rdma_device * nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id) { - struct nvmet_port *port = cm_id->context; + struct nvmet_rdma_port *port = cm_id->context; + struct nvmet_port *nport = port->nport; struct nvmet_rdma_device *ndev; int inline_page_count; int inline_sge_count; @@ -928,17 +937,17 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id) if (!ndev) goto out_err; - inline_page_count = num_pages(port->inline_data_size); + inline_page_count = num_pages(nport->inline_data_size); inline_sge_count = max(cm_id->device->attrs.max_sge_rd, cm_id->device->attrs.max_recv_sge) - 1; if (inline_page_count > inline_sge_count) { pr_warn("inline_data_size %d cannot be supported by device %s. Reducing to %lu.\n", - port->inline_data_size, cm_id->device->name, + nport->inline_data_size, cm_id->device->name, inline_sge_count * PAGE_SIZE); - port->inline_data_size = inline_sge_count * PAGE_SIZE; + nport->inline_data_size = inline_sge_count * PAGE_SIZE; inline_page_count = inline_sge_count; } - ndev->inline_data_size = port->inline_data_size; + ndev->inline_data_size = nport->inline_data_size; ndev->inline_page_count = inline_page_count; ndev->device = cm_id->device; kref_init(&ndev->ref); @@ -1024,6 +1033,7 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue) pr_err("failed to create_qp ret= %d\n", ret); goto err_destroy_cq; } + queue->qp = queue->cm_id->qp; atomic_set(&queue->sq_wr_avail, qp_attr.cap.max_send_wr); @@ -1052,11 +1062,10 @@ err_destroy_cq: static void nvmet_rdma_destroy_queue_ib(struct nvmet_rdma_queue *queue) { - struct ib_qp *qp = queue->cm_id->qp; - - ib_drain_qp(qp); - rdma_destroy_id(queue->cm_id); - ib_destroy_qp(qp); + ib_drain_qp(queue->qp); + if (queue->cm_id) + rdma_destroy_id(queue->cm_id); + ib_destroy_qp(queue->qp); ib_free_cq(queue->cq); } @@ -1266,6 +1275,7 @@ static int nvmet_rdma_cm_accept(struct rdma_cm_id *cm_id, static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, struct rdma_cm_event *event) { + struct nvmet_rdma_port *port = cm_id->context; struct nvmet_rdma_device *ndev; struct nvmet_rdma_queue *queue; int ret = -EINVAL; @@ -1281,7 +1291,7 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, ret = -ENOMEM; goto put_device; } - queue->port = cm_id->context; + queue->port = port->nport; if (queue->host_qid == 0) { /* Let inflight controller teardown complete */ @@ -1290,9 +1300,12 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); if (ret) { - schedule_work(&queue->release_work); - /* Destroying rdma_cm id is not needed here */ - return 0; + /* + * Don't destroy the cm_id in free path, as we implicitly + * destroy the cm_id here with non-zero ret code. + */ + queue->cm_id = NULL; + goto free_queue; } mutex_lock(&nvmet_rdma_queue_mutex); @@ -1301,6 +1314,8 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, return 0; +free_queue: + nvmet_rdma_free_queue(queue); put_device: kref_put(&ndev->ref, nvmet_rdma_free_dev); @@ -1406,7 +1421,7 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id, struct nvmet_rdma_queue *queue) { - struct nvmet_port *port; + struct nvmet_rdma_port *port; if (queue) { /* @@ -1425,7 +1440,7 @@ static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id, * cm_id destroy. use atomic xchg to make sure * we don't compete with remove_port. */ - if (xchg(&port->priv, NULL) != cm_id) + if (xchg(&port->cm_id, NULL) != cm_id) return 0; /* @@ -1456,6 +1471,13 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, nvmet_rdma_queue_established(queue); break; case RDMA_CM_EVENT_ADDR_CHANGE: + if (!queue) { + struct nvmet_rdma_port *port = cm_id->context; + + schedule_delayed_work(&port->repair_work, 0); + break; + } + /* FALLTHROUGH */ case RDMA_CM_EVENT_DISCONNECTED: case RDMA_CM_EVENT_TIMEWAIT_EXIT: nvmet_rdma_queue_disconnect(queue); @@ -1498,42 +1520,19 @@ restart: mutex_unlock(&nvmet_rdma_queue_mutex); } -static int nvmet_rdma_add_port(struct nvmet_port *port) +static void nvmet_rdma_disable_port(struct nvmet_rdma_port *port) { - struct rdma_cm_id *cm_id; - struct sockaddr_storage addr = { }; - __kernel_sa_family_t af; - int ret; + struct rdma_cm_id *cm_id = xchg(&port->cm_id, NULL); - switch (port->disc_addr.adrfam) { - case NVMF_ADDR_FAMILY_IP4: - af = AF_INET; - break; - case NVMF_ADDR_FAMILY_IP6: - af = AF_INET6; - break; - default: - pr_err("address family %d not supported\n", - port->disc_addr.adrfam); - return -EINVAL; - } - - if (port->inline_data_size < 0) { - port->inline_data_size = NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE; - } else if (port->inline_data_size > NVMET_RDMA_MAX_INLINE_DATA_SIZE) { - pr_warn("inline_data_size %u is too large, reducing to %u\n", - port->inline_data_size, - NVMET_RDMA_MAX_INLINE_DATA_SIZE); - port->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE; - } + if (cm_id) + rdma_destroy_id(cm_id); +} - ret = inet_pton_with_scope(&init_net, af, port->disc_addr.traddr, - port->disc_addr.trsvcid, &addr); - if (ret) { - pr_err("malformed ip/port passed: %s:%s\n", - port->disc_addr.traddr, port->disc_addr.trsvcid); - return ret; - } +static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port) +{ + struct sockaddr *addr = (struct sockaddr *)&port->addr; + struct rdma_cm_id *cm_id; + int ret; cm_id = rdma_create_id(&init_net, nvmet_rdma_cm_handler, port, RDMA_PS_TCP, IB_QPT_RC); @@ -1552,23 +1551,19 @@ static int nvmet_rdma_add_port(struct nvmet_port *port) goto out_destroy_id; } - ret = rdma_bind_addr(cm_id, (struct sockaddr *)&addr); + ret = rdma_bind_addr(cm_id, addr); if (ret) { - pr_err("binding CM ID to %pISpcs failed (%d)\n", - (struct sockaddr *)&addr, ret); + pr_err("binding CM ID to %pISpcs failed (%d)\n", addr, ret); goto out_destroy_id; } ret = rdma_listen(cm_id, 128); if (ret) { - pr_err("listening to %pISpcs failed (%d)\n", - (struct sockaddr *)&addr, ret); + pr_err("listening to %pISpcs failed (%d)\n", addr, ret); goto out_destroy_id; } - pr_info("enabling port %d (%pISpcs)\n", - le16_to_cpu(port->disc_addr.portid), (struct sockaddr *)&addr); - port->priv = cm_id; + port->cm_id = cm_id; return 0; out_destroy_id: @@ -1576,18 +1571,92 @@ out_destroy_id: return ret; } -static void nvmet_rdma_remove_port(struct nvmet_port *port) +static void nvmet_rdma_repair_port_work(struct work_struct *w) { - struct rdma_cm_id *cm_id = xchg(&port->priv, NULL); + struct nvmet_rdma_port *port = container_of(to_delayed_work(w), + struct nvmet_rdma_port, repair_work); + int ret; - if (cm_id) - rdma_destroy_id(cm_id); + nvmet_rdma_disable_port(port); + ret = nvmet_rdma_enable_port(port); + if (ret) + schedule_delayed_work(&port->repair_work, 5 * HZ); +} + +static int nvmet_rdma_add_port(struct nvmet_port *nport) +{ + struct nvmet_rdma_port *port; + __kernel_sa_family_t af; + int ret; + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + nport->priv = port; + port->nport = nport; + INIT_DELAYED_WORK(&port->repair_work, nvmet_rdma_repair_port_work); + + switch (nport->disc_addr.adrfam) { + case NVMF_ADDR_FAMILY_IP4: + af = AF_INET; + break; + case NVMF_ADDR_FAMILY_IP6: + af = AF_INET6; + break; + default: + pr_err("address family %d not supported\n", + nport->disc_addr.adrfam); + ret = -EINVAL; + goto out_free_port; + } + + if (nport->inline_data_size < 0) { + nport->inline_data_size = NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE; + } else if (nport->inline_data_size > NVMET_RDMA_MAX_INLINE_DATA_SIZE) { + pr_warn("inline_data_size %u is too large, reducing to %u\n", + nport->inline_data_size, + NVMET_RDMA_MAX_INLINE_DATA_SIZE); + nport->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE; + } + + ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr, + nport->disc_addr.trsvcid, &port->addr); + if (ret) { + pr_err("malformed ip/port passed: %s:%s\n", + nport->disc_addr.traddr, nport->disc_addr.trsvcid); + goto out_free_port; + } + + ret = nvmet_rdma_enable_port(port); + if (ret) + goto out_free_port; + + pr_info("enabling port %d (%pISpcs)\n", + le16_to_cpu(nport->disc_addr.portid), + (struct sockaddr *)&port->addr); + + return 0; + +out_free_port: + kfree(port); + return ret; +} + +static void nvmet_rdma_remove_port(struct nvmet_port *nport) +{ + struct nvmet_rdma_port *port = nport->priv; + + cancel_delayed_work_sync(&port->repair_work); + nvmet_rdma_disable_port(port); + kfree(port); } static void nvmet_rdma_disc_port_addr(struct nvmet_req *req, - struct nvmet_port *port, char *traddr) + struct nvmet_port *nport, char *traddr) { - struct rdma_cm_id *cm_id = port->priv; + struct nvmet_rdma_port *port = nport->priv; + struct rdma_cm_id *cm_id = port->cm_id; if (inet_addr_is_any((struct sockaddr *)&cm_id->route.addr.src_addr)) { struct nvmet_rdma_rsp *rsp = @@ -1597,7 +1666,7 @@ static void nvmet_rdma_disc_port_addr(struct nvmet_req *req, sprintf(traddr, "%pISc", addr); } else { - memcpy(traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE); + memcpy(traddr, nport->disc_addr.traddr, NVMF_TRADDR_SIZE); } } diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 3ef0bb281e7c..390e92f2d8d1 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -366,6 +366,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features) return 0; } +EXPORT_SYMBOL_GPL(pci_enable_pasid); /** * pci_disable_pasid - Disable the PASID capability @@ -390,6 +391,7 @@ void pci_disable_pasid(struct pci_dev *pdev) pdev->pasid_enabled = 0; } +EXPORT_SYMBOL_GPL(pci_disable_pasid); /** * pci_restore_pasid_state - Restore PASID capabilities @@ -441,6 +443,7 @@ int pci_pasid_features(struct pci_dev *pdev) return supported; } +EXPORT_SYMBOL_GPL(pci_pasid_features); #define PASID_NUMBER_SHIFT 8 #define PASID_NUMBER_MASK (0x1f << PASID_NUMBER_SHIFT) @@ -469,4 +472,5 @@ int pci_max_pasids(struct pci_dev *pdev) return (1 << supported); } +EXPORT_SYMBOL_GPL(pci_max_pasids); #endif /* CONFIG_PCI_PASID */ diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index 5f57282a28da..03ea5129ed0c 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -7,7 +7,7 @@ config MFD_CROS_EC tristate "Platform support for Chrome hardware (transitional)" select CHROME_PLATFORMS select CROS_EC - select CONFIG_MFD_CROS_EC_DEV + select MFD_CROS_EC_DEV depends on X86 || ARM || ARM64 || COMPILE_TEST help This is a transitional Kconfig option and will be removed after @@ -214,6 +214,17 @@ config CROS_EC_SYSFS To compile this driver as a module, choose M here: the module will be called cros_ec_sysfs. +config CROS_EC_TYPEC + tristate "ChromeOS EC Type-C Connector Control" + depends on MFD_CROS_EC_DEV && TYPEC + default MFD_CROS_EC_DEV + help + If you say Y here, you get support for accessing Type C connector + information from the Chrome OS EC. + + To compile this driver as a module, choose M here: the module will be + called cros_ec_typec. + config CROS_USBPD_LOGGER tristate "Logging driver for USB PD charger" depends on CHARGER_CROS_USBPD @@ -226,6 +237,20 @@ config CROS_USBPD_LOGGER To compile this driver as a module, choose M here: the module will be called cros_usbpd_logger. +config CROS_USBPD_NOTIFY + tristate "ChromeOS Type-C power delivery event notifier" + depends on MFD_CROS_EC_DEV + default MFD_CROS_EC_DEV + help + If you say Y here, you get support for Type-C PD event notifications + from the ChromeOS EC. On ACPI platorms this driver will bind to the + GOOG0003 ACPI device, and on platforms which don't have this device it + will get initialized on ECs which support the feature + EC_FEATURE_USB_PD. + + To compile this driver as a module, choose M here: the + module will be called cros_usbpd_notify. + source "drivers/platform/chrome/wilco_ec/Kconfig" endif # CHROMEOS_PLATFORMS diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index aacd5920d8a1..41baccba033f 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_CROS_EC_ISHTP) += cros_ec_ishtp.o obj-$(CONFIG_CROS_EC_RPMSG) += cros_ec_rpmsg.o obj-$(CONFIG_CROS_EC_SPI) += cros_ec_spi.o cros_ec_lpcs-objs := cros_ec_lpc.o cros_ec_lpc_mec.o +obj-$(CONFIG_CROS_EC_TYPEC) += cros_ec_typec.o obj-$(CONFIG_CROS_EC_LPC) += cros_ec_lpcs.o obj-$(CONFIG_CROS_EC_PROTO) += cros_ec_proto.o cros_ec_trace.o obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT) += cros_kbd_led_backlight.o @@ -19,8 +20,10 @@ obj-$(CONFIG_CROS_EC_CHARDEV) += cros_ec_chardev.o obj-$(CONFIG_CROS_EC_LIGHTBAR) += cros_ec_lightbar.o obj-$(CONFIG_CROS_EC_VBC) += cros_ec_vbc.o obj-$(CONFIG_CROS_EC_DEBUGFS) += cros_ec_debugfs.o -obj-$(CONFIG_CROS_EC_SENSORHUB) += cros_ec_sensorhub.o +cros-ec-sensorhub-objs := cros_ec_sensorhub.o cros_ec_sensorhub_ring.o +obj-$(CONFIG_CROS_EC_SENSORHUB) += cros-ec-sensorhub.o obj-$(CONFIG_CROS_EC_SYSFS) += cros_ec_sysfs.o obj-$(CONFIG_CROS_USBPD_LOGGER) += cros_usbpd_logger.o +obj-$(CONFIG_CROS_USBPD_NOTIFY) += cros_usbpd_notify.o obj-$(CONFIG_WILCO_EC) += wilco_ec/ diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c index 4f3651fcd9fe..472a03daa869 100644 --- a/drivers/platform/chrome/chromeos_laptop.c +++ b/drivers/platform/chrome/chromeos_laptop.c @@ -103,7 +103,7 @@ chromes_laptop_instantiate_i2c_device(struct i2c_adapter *adapter, pr_debug("%d-%02x is probed at %02x\n", adapter->nr, info->addr, dummy->addr); i2c_unregister_device(dummy); - client = i2c_new_device(adapter, info); + client = i2c_new_client_device(adapter, info); } } diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index 6fc8f2c3ac51..3104680b7485 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -120,7 +120,7 @@ static int cros_ec_sleep_event(struct cros_ec_device *ec_dev, u8 sleep_event) buf.msg.command = EC_CMD_HOST_SLEEP_EVENT; - ret = cros_ec_cmd_xfer(ec_dev, &buf.msg); + ret = cros_ec_cmd_xfer_status(ec_dev, &buf.msg); /* For now, report failure to transition to S0ix with a warning. */ if (ret >= 0 && ec_dev->host_sleep_v1 && @@ -138,6 +138,24 @@ static int cros_ec_sleep_event(struct cros_ec_device *ec_dev, u8 sleep_event) return ret; } +static int cros_ec_ready_event(struct notifier_block *nb, + unsigned long queued_during_suspend, + void *_notify) +{ + struct cros_ec_device *ec_dev = container_of(nb, struct cros_ec_device, + notifier_ready); + u32 host_event = cros_ec_get_host_event(ec_dev); + + if (host_event & EC_HOST_EVENT_MASK(EC_HOST_EVENT_INTERFACE_READY)) { + mutex_lock(&ec_dev->lock); + cros_ec_query_all(ec_dev); + mutex_unlock(&ec_dev->lock); + return NOTIFY_OK; + } + + return NOTIFY_DONE; +} + /** * cros_ec_register() - Register a new ChromeOS EC, using the provided info. * @ec_dev: Device to register. @@ -237,6 +255,18 @@ int cros_ec_register(struct cros_ec_device *ec_dev) dev_dbg(ec_dev->dev, "Error %d clearing sleep event to ec", err); + if (ec_dev->mkbp_event_supported) { + /* + * Register the notifier for EC_HOST_EVENT_INTERFACE_READY + * event. + */ + ec_dev->notifier_ready.notifier_call = cros_ec_ready_event; + err = blocking_notifier_chain_register(&ec_dev->event_notifier, + &ec_dev->notifier_ready); + if (err) + return err; + } + dev_info(dev, "Chrome EC device registered\n"); return 0; diff --git a/drivers/platform/chrome/cros_ec_chardev.c b/drivers/platform/chrome/cros_ec_chardev.c index c65e70bc168d..e0bce869c49a 100644 --- a/drivers/platform/chrome/cros_ec_chardev.c +++ b/drivers/platform/chrome/cros_ec_chardev.c @@ -48,7 +48,7 @@ struct ec_event { struct list_head node; size_t size; u8 event_type; - u8 data[0]; + u8 data[]; }; static int ec_get_version(struct cros_ec_dev *ec, char *str, int maxlen) @@ -301,7 +301,7 @@ static long cros_ec_chardev_ioctl_xcmd(struct cros_ec_dev *ec, void __user *arg) } s_cmd->command += ec->cmd_offset; - ret = cros_ec_cmd_xfer(ec->ec_dev, s_cmd); + ret = cros_ec_cmd_xfer_status(ec->ec_dev, s_cmd); /* Only copy data to userland if data was received. */ if (ret < 0) goto exit; diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c index b4c110c5fee0..b59180bff5a3 100644 --- a/drivers/platform/chrome/cros_ec_lightbar.c +++ b/drivers/platform/chrome/cros_ec_lightbar.c @@ -116,7 +116,7 @@ static int get_lightbar_version(struct cros_ec_dev *ec, param = (struct ec_params_lightbar *)msg->data; param->cmd = LIGHTBAR_CMD_VERSION; - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) { ret = 0; goto exit; @@ -193,15 +193,10 @@ static ssize_t brightness_store(struct device *dev, if (ret) goto exit; - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) goto exit; - if (msg->result != EC_RES_SUCCESS) { - ret = -EINVAL; - goto exit; - } - ret = count; exit: kfree(msg); @@ -258,13 +253,10 @@ static ssize_t led_rgb_store(struct device *dev, struct device_attribute *attr, goto exit; } - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) goto exit; - if (msg->result != EC_RES_SUCCESS) - goto exit; - i = 0; ok = 1; } @@ -305,14 +297,13 @@ static ssize_t sequence_show(struct device *dev, if (ret) goto exit; - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); - if (ret < 0) - goto exit; - - if (msg->result != EC_RES_SUCCESS) { + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); + if (ret == -EPROTO) { ret = scnprintf(buf, PAGE_SIZE, "ERROR: EC returned %d\n", msg->result); goto exit; + } else if (ret < 0) { + goto exit; } resp = (struct ec_response_lightbar *)msg->data; @@ -344,13 +335,10 @@ static int lb_send_empty_cmd(struct cros_ec_dev *ec, uint8_t cmd) if (ret) goto error; - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) goto error; - if (msg->result != EC_RES_SUCCESS) { - ret = -EINVAL; - goto error; - } + ret = 0; error: kfree(msg); @@ -377,13 +365,10 @@ static int lb_manual_suspend_ctrl(struct cros_ec_dev *ec, uint8_t enable) if (ret) goto error; - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) goto error; - if (msg->result != EC_RES_SUCCESS) { - ret = -EINVAL; - goto error; - } + ret = 0; error: kfree(msg); @@ -425,15 +410,10 @@ static ssize_t sequence_store(struct device *dev, struct device_attribute *attr, if (ret) goto exit; - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) goto exit; - if (msg->result != EC_RES_SUCCESS) { - ret = -EINVAL; - goto exit; - } - ret = count; exit: kfree(msg); @@ -487,13 +467,9 @@ static ssize_t program_store(struct device *dev, struct device_attribute *attr, */ msg->outsize = count + extra_bytes; - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) goto exit; - if (msg->result != EC_RES_SUCCESS) { - ret = -EINVAL; - goto exit; - } ret = count; exit: diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 3cfa643f1d07..3e745e0fe092 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -553,7 +553,10 @@ EXPORT_SYMBOL(cros_ec_cmd_xfer); * replied with success status. It's not necessary to check msg->result when * using this function. * - * Return: The number of bytes transferred on success or negative error code. + * Return: + * >=0 - The number of bytes transferred + * -ENOTSUPP - Operation not supported + * -EPROTO - Protocol error */ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) @@ -563,6 +566,10 @@ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, ret = cros_ec_cmd_xfer(ec_dev, msg); if (ret < 0) { dev_err(ec_dev->dev, "Command xfer error (err:%d)\n", ret); + } else if (msg->result == EC_RES_INVALID_VERSION) { + dev_dbg(ec_dev->dev, "Command invalid version (err:%d)\n", + msg->result); + return -ENOTSUPP; } else if (msg->result != EC_RES_SUCCESS) { dev_dbg(ec_dev->dev, "Command result (err: %d)\n", msg->result); return -EPROTO; diff --git a/drivers/platform/chrome/cros_ec_rpmsg.c b/drivers/platform/chrome/cros_ec_rpmsg.c index dbc3f5523b83..7e8629e3db74 100644 --- a/drivers/platform/chrome/cros_ec_rpmsg.c +++ b/drivers/platform/chrome/cros_ec_rpmsg.c @@ -44,6 +44,8 @@ struct cros_ec_rpmsg { struct completion xfer_ack; struct work_struct host_event_work; struct rpmsg_endpoint *ept; + bool has_pending_host_event; + bool probe_done; }; /** @@ -177,7 +179,14 @@ static int cros_ec_rpmsg_callback(struct rpmsg_device *rpdev, void *data, memcpy(ec_dev->din, resp->data, len); complete(&ec_rpmsg->xfer_ack); } else if (resp->type == HOST_EVENT_MARK) { - schedule_work(&ec_rpmsg->host_event_work); + /* + * If the host event is sent before cros_ec_register is + * finished, queue the host event. + */ + if (ec_rpmsg->probe_done) + schedule_work(&ec_rpmsg->host_event_work); + else + ec_rpmsg->has_pending_host_event = true; } else { dev_warn(ec_dev->dev, "rpmsg received invalid type = %d", resp->type); @@ -240,6 +249,11 @@ static int cros_ec_rpmsg_probe(struct rpmsg_device *rpdev) return ret; } + ec_rpmsg->probe_done = true; + + if (ec_rpmsg->has_pending_host_event) + schedule_work(&ec_rpmsg->host_event_work); + return 0; } diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c index 79fefd3bb0fa..b7f2c00db5e1 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub.c +++ b/drivers/platform/chrome/cros_ec_sensorhub.c @@ -50,10 +50,8 @@ static int cros_ec_sensorhub_register(struct device *dev, struct cros_ec_sensorhub *sensorhub) { int sensor_type[MOTIONSENSE_TYPE_MAX] = { 0 }; + struct cros_ec_command *msg = sensorhub->msg; struct cros_ec_dev *ec = sensorhub->ec; - struct ec_params_motion_sense *params; - struct ec_response_motion_sense *resp; - struct cros_ec_command *msg; int ret, i, sensor_num; char *name; @@ -65,27 +63,19 @@ static int cros_ec_sensorhub_register(struct device *dev, return sensor_num; } + sensorhub->sensor_num = sensor_num; if (sensor_num == 0) { dev_err(dev, "Zero sensors reported.\n"); return -EINVAL; } - /* Prepare a message to send INFO command to each sensor. */ - msg = kzalloc(sizeof(*msg) + max(sizeof(*params), sizeof(*resp)), - GFP_KERNEL); - if (!msg) - return -ENOMEM; - msg->version = 1; - msg->command = EC_CMD_MOTION_SENSE_CMD + ec->cmd_offset; - msg->outsize = sizeof(*params); - msg->insize = sizeof(*resp); - params = (struct ec_params_motion_sense *)msg->data; - resp = (struct ec_response_motion_sense *)msg->data; + msg->insize = sizeof(struct ec_response_motion_sense); + msg->outsize = sizeof(struct ec_params_motion_sense); for (i = 0; i < sensor_num; i++) { - params->cmd = MOTIONSENSE_CMD_INFO; - params->info.sensor_num = i; + sensorhub->params->cmd = MOTIONSENSE_CMD_INFO; + sensorhub->params->info.sensor_num = i; ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) { @@ -94,7 +84,7 @@ static int cros_ec_sensorhub_register(struct device *dev, continue; } - switch (resp->info.type) { + switch (sensorhub->resp->info.type) { case MOTIONSENSE_TYPE_ACCEL: name = "cros-ec-accel"; break; @@ -117,15 +107,16 @@ static int cros_ec_sensorhub_register(struct device *dev, name = "cros-ec-activity"; break; default: - dev_warn(dev, "unknown type %d\n", resp->info.type); + dev_warn(dev, "unknown type %d\n", + sensorhub->resp->info.type); continue; } ret = cros_ec_sensorhub_allocate_sensor(dev, name, i); if (ret) - goto error; + return ret; - sensor_type[resp->info.type]++; + sensor_type[sensorhub->resp->info.type]++; } if (sensor_type[MOTIONSENSE_TYPE_ACCEL] >= 2) @@ -137,29 +128,41 @@ static int cros_ec_sensorhub_register(struct device *dev, "cros-ec-lid-angle", 0); if (ret) - goto error; + return ret; } - kfree(msg); return 0; - -error: - kfree(msg); - return ret; } static int cros_ec_sensorhub_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct cros_ec_dev *ec = dev_get_drvdata(dev->parent); struct cros_ec_sensorhub *data; + struct cros_ec_command *msg; int ret; int i; + msg = devm_kzalloc(dev, sizeof(struct cros_ec_command) + + max((u16)sizeof(struct ec_params_motion_sense), + ec->ec_dev->max_response), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->command = EC_CMD_MOTION_SENSE_CMD + ec->cmd_offset; + data = devm_kzalloc(dev, sizeof(struct cros_ec_sensorhub), GFP_KERNEL); if (!data) return -ENOMEM; - data->ec = dev_get_drvdata(dev->parent); + mutex_init(&data->cmd_lock); + + data->dev = dev; + data->ec = ec; + data->msg = msg; + data->params = (struct ec_params_motion_sense *)msg->data; + data->resp = (struct ec_response_motion_sense *)msg->data; + dev_set_drvdata(dev, data); /* Check whether this EC is a sensor hub. */ @@ -172,7 +175,8 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) * If the device has sensors but does not claim to * be a sensor hub, we are in legacy mode. */ - for (i = 0; i < 2; i++) { + data->sensor_num = 2; + for (i = 0; i < data->sensor_num; i++) { ret = cros_ec_sensorhub_allocate_sensor(dev, "cros-ec-accel-legacy", i); if (ret) @@ -180,12 +184,63 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) } } + /* + * If the EC does not have a FIFO, the sensors will query their data + * themselves via sysfs or a software trigger. + */ + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { + ret = cros_ec_sensorhub_ring_add(data); + if (ret) + return ret; + /* + * The msg and its data is not under the control of the ring + * handler. + */ + return devm_add_action_or_reset(dev, + cros_ec_sensorhub_ring_remove, + data); + } + + return 0; +} + +#ifdef CONFIG_PM_SLEEP +/* + * When the EC is suspending, we must stop sending interrupt, + * we may use the same interrupt line for waking up the device. + * Tell the EC to stop sending non-interrupt event on the iio ring. + */ +static int cros_ec_sensorhub_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct cros_ec_sensorhub *sensorhub = platform_get_drvdata(pdev); + struct cros_ec_dev *ec = sensorhub->ec; + + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) + return cros_ec_sensorhub_ring_fifo_enable(sensorhub, false); return 0; } +static int cros_ec_sensorhub_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct cros_ec_sensorhub *sensorhub = platform_get_drvdata(pdev); + struct cros_ec_dev *ec = sensorhub->ec; + + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) + return cros_ec_sensorhub_ring_fifo_enable(sensorhub, true); + return 0; +} +#endif + +static SIMPLE_DEV_PM_OPS(cros_ec_sensorhub_pm_ops, + cros_ec_sensorhub_suspend, + cros_ec_sensorhub_resume); + static struct platform_driver cros_ec_sensorhub_driver = { .driver = { .name = DRV_NAME, + .pm = &cros_ec_sensorhub_pm_ops, }, .probe = cros_ec_sensorhub_probe, }; diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c new file mode 100644 index 000000000000..230e6cf3da2f --- /dev/null +++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c @@ -0,0 +1,1046 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Driver for Chrome OS EC Sensor hub FIFO. + * + * Copyright 2020 Google LLC + */ + +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/iio/iio.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/platform_data/cros_ec_commands.h> +#include <linux/platform_data/cros_ec_proto.h> +#include <linux/platform_data/cros_ec_sensorhub.h> +#include <linux/platform_device.h> +#include <linux/sort.h> +#include <linux/slab.h> + +/* Precision of fixed point for the m values from the filter */ +#define M_PRECISION BIT(23) + +/* Only activate the filter once we have at least this many elements. */ +#define TS_HISTORY_THRESHOLD 8 + +/* + * If we don't have any history entries for this long, empty the filter to + * make sure there are no big discontinuities. + */ +#define TS_HISTORY_BORED_US 500000 + +/* To measure by how much the filter is overshooting, if it happens. */ +#define FUTURE_TS_ANALYTICS_COUNT_MAX 100 + +static inline int +cros_sensorhub_send_sample(struct cros_ec_sensorhub *sensorhub, + struct cros_ec_sensors_ring_sample *sample) +{ + cros_ec_sensorhub_push_data_cb_t cb; + int id = sample->sensor_id; + struct iio_dev *indio_dev; + + if (id > sensorhub->sensor_num) + return -EINVAL; + + cb = sensorhub->push_data[id].push_data_cb; + if (!cb) + return 0; + + indio_dev = sensorhub->push_data[id].indio_dev; + + if (sample->flag & MOTIONSENSE_SENSOR_FLAG_FLUSH) + return 0; + + return cb(indio_dev, sample->vector, sample->timestamp); +} + +/** + * cros_ec_sensorhub_register_push_data() - register the callback to the hub. + * + * @sensorhub : Sensor Hub object + * @sensor_num : The sensor the caller is interested in. + * @indio_dev : The iio device to use when a sample arrives. + * @cb : The callback to call when a sample arrives. + * + * The callback cb will be used by cros_ec_sensorhub_ring to distribute events + * from the EC. + * + * Return: 0 when callback is registered. + * EINVAL is the sensor number is invalid or the slot already used. + */ +int cros_ec_sensorhub_register_push_data(struct cros_ec_sensorhub *sensorhub, + u8 sensor_num, + struct iio_dev *indio_dev, + cros_ec_sensorhub_push_data_cb_t cb) +{ + if (sensor_num >= sensorhub->sensor_num) + return -EINVAL; + if (sensorhub->push_data[sensor_num].indio_dev) + return -EINVAL; + + sensorhub->push_data[sensor_num].indio_dev = indio_dev; + sensorhub->push_data[sensor_num].push_data_cb = cb; + + return 0; +} +EXPORT_SYMBOL_GPL(cros_ec_sensorhub_register_push_data); + +void cros_ec_sensorhub_unregister_push_data(struct cros_ec_sensorhub *sensorhub, + u8 sensor_num) +{ + sensorhub->push_data[sensor_num].indio_dev = NULL; + sensorhub->push_data[sensor_num].push_data_cb = NULL; +} +EXPORT_SYMBOL_GPL(cros_ec_sensorhub_unregister_push_data); + +/** + * cros_ec_sensorhub_ring_fifo_enable() - Enable or disable interrupt generation + * for FIFO events. + * @sensorhub: Sensor Hub object + * @on: true when events are requested. + * + * To be called before sleeping or when noone is listening. + * Return: 0 on success, or an error when we can not communicate with the EC. + * + */ +int cros_ec_sensorhub_ring_fifo_enable(struct cros_ec_sensorhub *sensorhub, + bool on) +{ + int ret, i; + + mutex_lock(&sensorhub->cmd_lock); + if (sensorhub->tight_timestamps) + for (i = 0; i < sensorhub->sensor_num; i++) + sensorhub->batch_state[i].last_len = 0; + + sensorhub->params->cmd = MOTIONSENSE_CMD_FIFO_INT_ENABLE; + sensorhub->params->fifo_int_enable.enable = on; + + sensorhub->msg->outsize = sizeof(struct ec_params_motion_sense); + sensorhub->msg->insize = sizeof(struct ec_response_motion_sense); + + ret = cros_ec_cmd_xfer_status(sensorhub->ec->ec_dev, sensorhub->msg); + mutex_unlock(&sensorhub->cmd_lock); + + /* We expect to receive a payload of 4 bytes, ignore. */ + if (ret > 0) + ret = 0; + + return ret; +} + +static int cros_ec_sensor_ring_median_cmp(const void *pv1, const void *pv2) +{ + s64 v1 = *(s64 *)pv1; + s64 v2 = *(s64 *)pv2; + + if (v1 > v2) + return 1; + else if (v1 < v2) + return -1; + else + return 0; +} + +/* + * cros_ec_sensor_ring_median: Gets median of an array of numbers + * + * For now it's implemented using an inefficient > O(n) sort then return + * the middle element. A more optimal method would be something like + * quickselect, but given that n = 64 we can probably live with it in the + * name of clarity. + * + * Warning: the input array gets modified (sorted)! + */ +static s64 cros_ec_sensor_ring_median(s64 *array, size_t length) +{ + sort(array, length, sizeof(s64), cros_ec_sensor_ring_median_cmp, NULL); + return array[length / 2]; +} + +/* + * IRQ Timestamp Filtering + * + * Lower down in cros_ec_sensor_ring_process_event(), for each sensor event + * we have to calculate it's timestamp in the AP timebase. There are 3 time + * points: + * a - EC timebase, sensor event + * b - EC timebase, IRQ + * c - AP timebase, IRQ + * a' - what we want: sensor even in AP timebase + * + * While a and b are recorded at accurate times (due to the EC real time + * nature); c is pretty untrustworthy, even though it's recorded the + * first thing in ec_irq_handler(). There is a very good change we'll get + * added lantency due to: + * other irqs + * ddrfreq + * cpuidle + * + * Normally a' = c - b + a, but if we do that naive math any jitter in c + * will get coupled in a', which we don't want. We want a function + * a' = cros_ec_sensor_ring_ts_filter(a) which will filter out outliers in c. + * + * Think of a graph of AP time(b) on the y axis vs EC time(c) on the x axis. + * The slope of the line won't be exactly 1, there will be some clock drift + * between the 2 chips for various reasons (mechanical stress, temperature, + * voltage). We need to extrapolate values for a future x, without trusting + * recent y values too much. + * + * We use a median filter for the slope, then another median filter for the + * y-intercept to calculate this function: + * dx[n] = x[n-1] - x[n] + * dy[n] = x[n-1] - x[n] + * m[n] = dy[n] / dx[n] + * median_m = median(m[n-k:n]) + * error[i] = y[n-i] - median_m * x[n-i] + * median_error = median(error[:k]) + * predicted_y = median_m * x + median_error + * + * Implementation differences from above: + * - Redefined y to be actually c - b, this gives us a lot more precision + * to do the math. (c-b)/b variations are more obvious than c/b variations. + * - Since we don't have floating point, any operations involving slope are + * done using fixed point math (*M_PRECISION) + * - Since x and y grow with time, we keep zeroing the graph (relative to + * the last sample), this way math involving *x[n-i] will not overflow + * - EC timestamps are kept in us, it improves the slope calculation precision + */ + +/** + * cros_ec_sensor_ring_ts_filter_update() - Update filter history. + * + * @state: Filter information. + * @b: IRQ timestamp, EC timebase (us) + * @c: IRQ timestamp, AP timebase (ns) + * + * Given a new IRQ timestamp pair (EC and AP timebases), add it to the filter + * history. + */ +static void +cros_ec_sensor_ring_ts_filter_update(struct cros_ec_sensors_ts_filter_state + *state, + s64 b, s64 c) +{ + s64 x, y; + s64 dx, dy; + s64 m; /* stored as *M_PRECISION */ + s64 *m_history_copy = state->temp_buf; + s64 *error = state->temp_buf; + int i; + + /* we trust b the most, that'll be our independent variable */ + x = b; + /* y is the offset between AP and EC times, in ns */ + y = c - b * 1000; + + dx = (state->x_history[0] + state->x_offset) - x; + if (dx == 0) + return; /* we already have this irq in the history */ + dy = (state->y_history[0] + state->y_offset) - y; + m = div64_s64(dy * M_PRECISION, dx); + + /* Empty filter if we haven't seen any action in a while. */ + if (-dx > TS_HISTORY_BORED_US) + state->history_len = 0; + + /* Move everything over, also update offset to all absolute coords .*/ + for (i = state->history_len - 1; i >= 1; i--) { + state->x_history[i] = state->x_history[i - 1] + dx; + state->y_history[i] = state->y_history[i - 1] + dy; + + state->m_history[i] = state->m_history[i - 1]; + /* + * Also use the same loop to copy m_history for future + * median extraction. + */ + m_history_copy[i] = state->m_history[i - 1]; + } + + /* Store the x and y, but remember offset is actually last sample. */ + state->x_offset = x; + state->y_offset = y; + state->x_history[0] = 0; + state->y_history[0] = 0; + + state->m_history[0] = m; + m_history_copy[0] = m; + + if (state->history_len < CROS_EC_SENSORHUB_TS_HISTORY_SIZE) + state->history_len++; + + /* Precalculate things for the filter. */ + if (state->history_len > TS_HISTORY_THRESHOLD) { + state->median_m = + cros_ec_sensor_ring_median(m_history_copy, + state->history_len - 1); + + /* + * Calculate y-intercepts as if m_median is the slope and + * points in the history are on the line. median_error will + * still be in the offset coordinate system. + */ + for (i = 0; i < state->history_len; i++) + error[i] = state->y_history[i] - + div_s64(state->median_m * state->x_history[i], + M_PRECISION); + state->median_error = + cros_ec_sensor_ring_median(error, state->history_len); + } else { + state->median_m = 0; + state->median_error = 0; + } +} + +/** + * cros_ec_sensor_ring_ts_filter() - Translate EC timebase timestamp to AP + * timebase + * + * @state: filter information. + * @x: any ec timestamp (us): + * + * cros_ec_sensor_ring_ts_filter(a) => a' event timestamp, AP timebase + * cros_ec_sensor_ring_ts_filter(b) => calculated timestamp when the EC IRQ + * should have happened on the AP, with low jitter + * + * Note: The filter will only activate once state->history_len goes + * over TS_HISTORY_THRESHOLD. Otherwise it'll just do the naive c - b + a + * transform. + * + * How to derive the formula, starting from: + * f(x) = median_m * x + median_error + * That's the calculated AP - EC offset (at the x point in time) + * Undo the coordinate system transform: + * f(x) = median_m * (x - x_offset) + median_error + y_offset + * Remember to undo the "y = c - b * 1000" modification: + * f(x) = median_m * (x - x_offset) + median_error + y_offset + x * 1000 + * + * Return: timestamp in AP timebase (ns) + */ +static s64 +cros_ec_sensor_ring_ts_filter(struct cros_ec_sensors_ts_filter_state *state, + s64 x) +{ + return div_s64(state->median_m * (x - state->x_offset), M_PRECISION) + + state->median_error + state->y_offset + x * 1000; +} + +/* + * Since a and b were originally 32 bit values from the EC, + * they overflow relatively often, casting is not enough, so we need to + * add an offset. + */ +static void +cros_ec_sensor_ring_fix_overflow(s64 *ts, + const s64 overflow_period, + struct cros_ec_sensors_ec_overflow_state + *state) +{ + s64 adjust; + + *ts += state->offset; + if (abs(state->last - *ts) > (overflow_period / 2)) { + adjust = state->last > *ts ? overflow_period : -overflow_period; + state->offset += adjust; + *ts += adjust; + } + state->last = *ts; +} + +static void +cros_ec_sensor_ring_check_for_past_timestamp(struct cros_ec_sensorhub + *sensorhub, + struct cros_ec_sensors_ring_sample + *sample) +{ + const u8 sensor_id = sample->sensor_id; + + /* If this event is earlier than one we saw before... */ + if (sensorhub->batch_state[sensor_id].newest_sensor_event > + sample->timestamp) + /* mark it for spreading. */ + sample->timestamp = + sensorhub->batch_state[sensor_id].last_ts; + else + sensorhub->batch_state[sensor_id].newest_sensor_event = + sample->timestamp; +} + +/** + * cros_ec_sensor_ring_process_event() - Process one EC FIFO event + * + * @sensorhub: Sensor Hub object. + * @fifo_info: FIFO information from the EC (includes b point, EC timebase). + * @fifo_timestamp: EC IRQ, kernel timebase (aka c). + * @current_timestamp: calculated event timestamp, kernel timebase (aka a'). + * @in: incoming FIFO event from EC (includes a point, EC timebase). + * @out: outgoing event to user space (includes a'). + * + * Process one EC event, add it in the ring if necessary. + * + * Return: true if out event has been populated. + */ +static bool +cros_ec_sensor_ring_process_event(struct cros_ec_sensorhub *sensorhub, + const struct ec_response_motion_sense_fifo_info + *fifo_info, + const ktime_t fifo_timestamp, + ktime_t *current_timestamp, + struct ec_response_motion_sensor_data *in, + struct cros_ec_sensors_ring_sample *out) +{ + const s64 now = cros_ec_get_time_ns(); + int axis, async_flags; + + /* Do not populate the filter based on asynchronous events. */ + async_flags = in->flags & + (MOTIONSENSE_SENSOR_FLAG_ODR | MOTIONSENSE_SENSOR_FLAG_FLUSH); + + if (in->flags & MOTIONSENSE_SENSOR_FLAG_TIMESTAMP && !async_flags) { + s64 a = in->timestamp; + s64 b = fifo_info->timestamp; + s64 c = fifo_timestamp; + + cros_ec_sensor_ring_fix_overflow(&a, 1LL << 32, + &sensorhub->overflow_a); + cros_ec_sensor_ring_fix_overflow(&b, 1LL << 32, + &sensorhub->overflow_b); + + if (sensorhub->tight_timestamps) { + cros_ec_sensor_ring_ts_filter_update( + &sensorhub->filter, b, c); + *current_timestamp = cros_ec_sensor_ring_ts_filter( + &sensorhub->filter, a); + } else { + s64 new_timestamp; + + /* + * Disable filtering since we might add more jitter + * if b is in a random point in time. + */ + new_timestamp = fifo_timestamp - + fifo_info->timestamp * 1000 + + in->timestamp * 1000; + /* + * The timestamp can be stale if we had to use the fifo + * info timestamp. + */ + if (new_timestamp - *current_timestamp > 0) + *current_timestamp = new_timestamp; + } + } + + if (in->flags & MOTIONSENSE_SENSOR_FLAG_ODR) { + if (sensorhub->tight_timestamps) { + sensorhub->batch_state[in->sensor_num].last_len = 0; + sensorhub->batch_state[in->sensor_num].penul_len = 0; + } + /* + * ODR change is only useful for the sensor_ring, it does not + * convey information to clients. + */ + return false; + } + + if (in->flags & MOTIONSENSE_SENSOR_FLAG_FLUSH) { + out->sensor_id = in->sensor_num; + out->timestamp = *current_timestamp; + out->flag = in->flags; + if (sensorhub->tight_timestamps) + sensorhub->batch_state[out->sensor_id].last_len = 0; + /* + * No other payload information provided with + * flush ack. + */ + return true; + } + + if (in->flags & MOTIONSENSE_SENSOR_FLAG_TIMESTAMP) + /* If we just have a timestamp, skip this entry. */ + return false; + + /* Regular sample */ + out->sensor_id = in->sensor_num; + if (*current_timestamp - now > 0) { + /* + * This fix is needed to overcome the timestamp filter putting + * events in the future. + */ + sensorhub->future_timestamp_total_ns += + *current_timestamp - now; + if (++sensorhub->future_timestamp_count == + FUTURE_TS_ANALYTICS_COUNT_MAX) { + s64 avg = div_s64(sensorhub->future_timestamp_total_ns, + sensorhub->future_timestamp_count); + dev_warn_ratelimited(sensorhub->dev, + "100 timestamps in the future, %lldns shaved on average\n", + avg); + sensorhub->future_timestamp_count = 0; + sensorhub->future_timestamp_total_ns = 0; + } + out->timestamp = now; + } else { + out->timestamp = *current_timestamp; + } + + out->flag = in->flags; + for (axis = 0; axis < 3; axis++) + out->vector[axis] = in->data[axis]; + + if (sensorhub->tight_timestamps) + cros_ec_sensor_ring_check_for_past_timestamp(sensorhub, out); + return true; +} + +/* + * cros_ec_sensor_ring_spread_add: Calculate proper timestamps then add to + * ringbuffer. + * + * This is the new spreading code, assumes every sample's timestamp + * preceeds the sample. Run if tight_timestamps == true. + * + * Sometimes the EC receives only one interrupt (hence timestamp) for + * a batch of samples. Only the first sample will have the correct + * timestamp. So we must interpolate the other samples. + * We use the previous batch timestamp and our current batch timestamp + * as a way to calculate period, then spread the samples evenly. + * + * s0 int, 0ms + * s1 int, 10ms + * s2 int, 20ms + * 30ms point goes by, no interrupt, previous one is still asserted + * downloading s2 and s3 + * s3 sample, 20ms (incorrect timestamp) + * s4 int, 40ms + * + * The batches are [(s0), (s1), (s2, s3), (s4)]. Since the 3rd batch + * has 2 samples in them, we adjust the timestamp of s3. + * s2 - s1 = 10ms, so s3 must be s2 + 10ms => 20ms. If s1 would have + * been part of a bigger batch things would have gotten a little + * more complicated. + * + * Note: we also assume another sensor sample doesn't break up a batch + * in 2 or more partitions. Example, there can't ever be a sync sensor + * in between S2 and S3. This simplifies the following code. + */ +static void +cros_ec_sensor_ring_spread_add(struct cros_ec_sensorhub *sensorhub, + unsigned long sensor_mask, + struct cros_ec_sensors_ring_sample *last_out) +{ + struct cros_ec_sensors_ring_sample *batch_start, *next_batch_start; + int id; + + for_each_set_bit(id, &sensor_mask, sensorhub->sensor_num) { + for (batch_start = sensorhub->ring; batch_start < last_out; + batch_start = next_batch_start) { + /* + * For each batch (where all samples have the same + * timestamp). + */ + int batch_len, sample_idx; + struct cros_ec_sensors_ring_sample *batch_end = + batch_start; + struct cros_ec_sensors_ring_sample *s; + s64 batch_timestamp = batch_start->timestamp; + s64 sample_period; + + /* + * Skip over batches that start with the sensor types + * we're not looking at right now. + */ + if (batch_start->sensor_id != id) { + next_batch_start = batch_start + 1; + continue; + } + + /* + * Do not start a batch + * from a flush, as it happens asynchronously to the + * regular flow of events. + */ + if (batch_start->flag & MOTIONSENSE_SENSOR_FLAG_FLUSH) { + cros_sensorhub_send_sample(sensorhub, + batch_start); + next_batch_start = batch_start + 1; + continue; + } + + if (batch_start->timestamp <= + sensorhub->batch_state[id].last_ts) { + batch_timestamp = + sensorhub->batch_state[id].last_ts; + batch_len = sensorhub->batch_state[id].last_len; + + sample_idx = batch_len; + + sensorhub->batch_state[id].last_ts = + sensorhub->batch_state[id].penul_ts; + sensorhub->batch_state[id].last_len = + sensorhub->batch_state[id].penul_len; + } else { + /* + * Push first sample in the batch to the, + * kifo, it's guaranteed to be correct, the + * rest will follow later on. + */ + sample_idx = 1; + batch_len = 1; + cros_sensorhub_send_sample(sensorhub, + batch_start); + batch_start++; + } + + /* Find all samples have the same timestamp. */ + for (s = batch_start; s < last_out; s++) { + if (s->sensor_id != id) + /* + * Skip over other sensor types that + * are interleaved, don't count them. + */ + continue; + if (s->timestamp != batch_timestamp) + /* we discovered the next batch */ + break; + if (s->flag & MOTIONSENSE_SENSOR_FLAG_FLUSH) + /* break on flush packets */ + break; + batch_end = s; + batch_len++; + } + + if (batch_len == 1) + goto done_with_this_batch; + + /* Can we calculate period? */ + if (sensorhub->batch_state[id].last_len == 0) { + dev_warn(sensorhub->dev, "Sensor %d: lost %d samples when spreading\n", + id, batch_len - 1); + goto done_with_this_batch; + /* + * Note: we're dropping the rest of the samples + * in this batch since we have no idea where + * they're supposed to go without a period + * calculation. + */ + } + + sample_period = div_s64(batch_timestamp - + sensorhub->batch_state[id].last_ts, + sensorhub->batch_state[id].last_len); + dev_dbg(sensorhub->dev, + "Adjusting %d samples, sensor %d last_batch @%lld (%d samples) batch_timestamp=%lld => period=%lld\n", + batch_len, id, + sensorhub->batch_state[id].last_ts, + sensorhub->batch_state[id].last_len, + batch_timestamp, + sample_period); + + /* + * Adjust timestamps of the samples then push them to + * kfifo. + */ + for (s = batch_start; s <= batch_end; s++) { + if (s->sensor_id != id) + /* + * Skip over other sensor types that + * are interleaved, don't change them. + */ + continue; + + s->timestamp = batch_timestamp + + sample_period * sample_idx; + sample_idx++; + + cros_sensorhub_send_sample(sensorhub, s); + } + +done_with_this_batch: + sensorhub->batch_state[id].penul_ts = + sensorhub->batch_state[id].last_ts; + sensorhub->batch_state[id].penul_len = + sensorhub->batch_state[id].last_len; + + sensorhub->batch_state[id].last_ts = + batch_timestamp; + sensorhub->batch_state[id].last_len = batch_len; + + next_batch_start = batch_end + 1; + } + } +} + +/* + * cros_ec_sensor_ring_spread_add_legacy: Calculate proper timestamps then + * add to ringbuffer (legacy). + * + * Note: This assumes we're running old firmware, where every sample's timestamp + * is after the sample. Run if tight_timestamps == false. + * + * If there is a sample with a proper timestamp + * + * timestamp | count + * ----------------- + * older_unprocess_out --> TS1 | 1 + * TS1 | 2 + * out --> TS1 | 3 + * next_out --> TS2 | + * + * We spread time for the samples [older_unprocess_out .. out] + * between TS1 and TS2: [TS1+1/4, TS1+2/4, TS1+3/4, TS2]. + * + * If we reach the end of the samples, we compare with the + * current timestamp: + * + * older_unprocess_out --> TS1 | 1 + * TS1 | 2 + * out --> TS1 | 3 + * + * We know have [TS1+1/3, TS1+2/3, current timestamp] + */ +static void +cros_ec_sensor_ring_spread_add_legacy(struct cros_ec_sensorhub *sensorhub, + unsigned long sensor_mask, + s64 current_timestamp, + struct cros_ec_sensors_ring_sample + *last_out) +{ + struct cros_ec_sensors_ring_sample *out; + int i; + + for_each_set_bit(i, &sensor_mask, sensorhub->sensor_num) { + s64 older_timestamp; + s64 timestamp; + struct cros_ec_sensors_ring_sample *older_unprocess_out = + sensorhub->ring; + struct cros_ec_sensors_ring_sample *next_out; + int count = 1; + + for (out = sensorhub->ring; out < last_out; out = next_out) { + s64 time_period; + + next_out = out + 1; + if (out->sensor_id != i) + continue; + + /* Timestamp to start with */ + older_timestamp = out->timestamp; + + /* Find next sample. */ + while (next_out < last_out && next_out->sensor_id != i) + next_out++; + + if (next_out >= last_out) { + timestamp = current_timestamp; + } else { + timestamp = next_out->timestamp; + if (timestamp == older_timestamp) { + count++; + continue; + } + } + + /* + * The next sample has a new timestamp, spread the + * unprocessed samples. + */ + if (next_out < last_out) + count++; + time_period = div_s64(timestamp - older_timestamp, + count); + + for (; older_unprocess_out <= out; + older_unprocess_out++) { + if (older_unprocess_out->sensor_id != i) + continue; + older_timestamp += time_period; + older_unprocess_out->timestamp = + older_timestamp; + } + count = 1; + /* The next_out sample has a valid timestamp, skip. */ + next_out++; + older_unprocess_out = next_out; + } + } + + /* Push the event into the kfifo */ + for (out = sensorhub->ring; out < last_out; out++) + cros_sensorhub_send_sample(sensorhub, out); +} + +/** + * cros_ec_sensorhub_ring_handler() - The trigger handler function + * + * @sensorhub: Sensor Hub object. + * + * Called by the notifier, process the EC sensor FIFO queue. + */ +static void cros_ec_sensorhub_ring_handler(struct cros_ec_sensorhub *sensorhub) +{ + struct ec_response_motion_sense_fifo_info *fifo_info = + sensorhub->fifo_info; + struct cros_ec_dev *ec = sensorhub->ec; + ktime_t fifo_timestamp, current_timestamp; + int i, j, number_data, ret; + unsigned long sensor_mask = 0; + struct ec_response_motion_sensor_data *in; + struct cros_ec_sensors_ring_sample *out, *last_out; + + mutex_lock(&sensorhub->cmd_lock); + + /* Get FIFO information if there are lost vectors. */ + if (fifo_info->total_lost) { + int fifo_info_length = + sizeof(struct ec_response_motion_sense_fifo_info) + + sizeof(u16) * sensorhub->sensor_num; + + /* Need to retrieve the number of lost vectors per sensor */ + sensorhub->params->cmd = MOTIONSENSE_CMD_FIFO_INFO; + sensorhub->msg->outsize = 1; + sensorhub->msg->insize = fifo_info_length; + + if (cros_ec_cmd_xfer_status(ec->ec_dev, sensorhub->msg) < 0) + goto error; + + memcpy(fifo_info, &sensorhub->resp->fifo_info, + fifo_info_length); + + /* + * Update collection time, will not be as precise as the + * non-error case. + */ + fifo_timestamp = cros_ec_get_time_ns(); + } else { + fifo_timestamp = sensorhub->fifo_timestamp[ + CROS_EC_SENSOR_NEW_TS]; + } + + if (fifo_info->count > sensorhub->fifo_size || + fifo_info->size != sensorhub->fifo_size) { + dev_warn(sensorhub->dev, + "Mismatch EC data: count %d, size %d - expected %d", + fifo_info->count, fifo_info->size, + sensorhub->fifo_size); + goto error; + } + + /* Copy elements in the main fifo */ + current_timestamp = sensorhub->fifo_timestamp[CROS_EC_SENSOR_LAST_TS]; + out = sensorhub->ring; + for (i = 0; i < fifo_info->count; i += number_data) { + sensorhub->params->cmd = MOTIONSENSE_CMD_FIFO_READ; + sensorhub->params->fifo_read.max_data_vector = + fifo_info->count - i; + sensorhub->msg->outsize = + sizeof(struct ec_params_motion_sense); + sensorhub->msg->insize = + sizeof(sensorhub->resp->fifo_read) + + sensorhub->params->fifo_read.max_data_vector * + sizeof(struct ec_response_motion_sensor_data); + ret = cros_ec_cmd_xfer_status(ec->ec_dev, sensorhub->msg); + if (ret < 0) { + dev_warn(sensorhub->dev, "Fifo error: %d\n", ret); + break; + } + number_data = sensorhub->resp->fifo_read.number_data; + if (number_data == 0) { + dev_dbg(sensorhub->dev, "Unexpected empty FIFO\n"); + break; + } + if (number_data > fifo_info->count - i) { + dev_warn(sensorhub->dev, + "Invalid EC data: too many entry received: %d, expected %d", + number_data, fifo_info->count - i); + break; + } + if (out + number_data > + sensorhub->ring + fifo_info->count) { + dev_warn(sensorhub->dev, + "Too many samples: %d (%zd data) to %d entries for expected %d entries", + i, out - sensorhub->ring, i + number_data, + fifo_info->count); + break; + } + + for (in = sensorhub->resp->fifo_read.data, j = 0; + j < number_data; j++, in++) { + if (cros_ec_sensor_ring_process_event( + sensorhub, fifo_info, + fifo_timestamp, + ¤t_timestamp, + in, out)) { + sensor_mask |= BIT(in->sensor_num); + out++; + } + } + } + mutex_unlock(&sensorhub->cmd_lock); + last_out = out; + + if (out == sensorhub->ring) + /* Unexpected empty FIFO. */ + goto ring_handler_end; + + /* + * Check if current_timestamp is ahead of the last sample. Normally, + * the EC appends a timestamp after the last sample, but if the AP + * is slow to respond to the IRQ, the EC may have added new samples. + * Use the FIFO info timestamp as last timestamp then. + */ + if (!sensorhub->tight_timestamps && + (last_out - 1)->timestamp == current_timestamp) + current_timestamp = fifo_timestamp; + + /* Warn on lost samples. */ + if (fifo_info->total_lost) + for (i = 0; i < sensorhub->sensor_num; i++) { + if (fifo_info->lost[i]) { + dev_warn_ratelimited(sensorhub->dev, + "Sensor %d: lost: %d out of %d\n", + i, fifo_info->lost[i], + fifo_info->total_lost); + if (sensorhub->tight_timestamps) + sensorhub->batch_state[i].last_len = 0; + } + } + + /* + * Spread samples in case of batching, then add them to the + * ringbuffer. + */ + if (sensorhub->tight_timestamps) + cros_ec_sensor_ring_spread_add(sensorhub, sensor_mask, + last_out); + else + cros_ec_sensor_ring_spread_add_legacy(sensorhub, sensor_mask, + current_timestamp, + last_out); + +ring_handler_end: + sensorhub->fifo_timestamp[CROS_EC_SENSOR_LAST_TS] = current_timestamp; + return; + +error: + mutex_unlock(&sensorhub->cmd_lock); +} + +static int cros_ec_sensorhub_event(struct notifier_block *nb, + unsigned long queued_during_suspend, + void *_notify) +{ + struct cros_ec_sensorhub *sensorhub; + struct cros_ec_device *ec_dev; + + sensorhub = container_of(nb, struct cros_ec_sensorhub, notifier); + ec_dev = sensorhub->ec->ec_dev; + + if (ec_dev->event_data.event_type != EC_MKBP_EVENT_SENSOR_FIFO) + return NOTIFY_DONE; + + if (ec_dev->event_size != sizeof(ec_dev->event_data.data.sensor_fifo)) { + dev_warn(ec_dev->dev, "Invalid fifo info size\n"); + return NOTIFY_DONE; + } + + if (queued_during_suspend) + return NOTIFY_OK; + + memcpy(sensorhub->fifo_info, &ec_dev->event_data.data.sensor_fifo.info, + sizeof(*sensorhub->fifo_info)); + sensorhub->fifo_timestamp[CROS_EC_SENSOR_NEW_TS] = + ec_dev->last_event_time; + cros_ec_sensorhub_ring_handler(sensorhub); + + return NOTIFY_OK; +} + +/** + * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC + * supports it. + * + * @sensorhub : Sensor Hub object. + * + * Return: 0 on success. + */ +int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) +{ + struct cros_ec_dev *ec = sensorhub->ec; + int ret; + int fifo_info_length = + sizeof(struct ec_response_motion_sense_fifo_info) + + sizeof(u16) * sensorhub->sensor_num; + + /* Allocate the array for lost events. */ + sensorhub->fifo_info = devm_kzalloc(sensorhub->dev, fifo_info_length, + GFP_KERNEL); + if (!sensorhub->fifo_info) + return -ENOMEM; + + /* Retrieve FIFO information */ + sensorhub->msg->version = 2; + sensorhub->params->cmd = MOTIONSENSE_CMD_FIFO_INFO; + sensorhub->msg->outsize = 1; + sensorhub->msg->insize = fifo_info_length; + + ret = cros_ec_cmd_xfer_status(ec->ec_dev, sensorhub->msg); + if (ret < 0) + return ret; + + /* + * Allocate the full fifo. We need to copy the whole FIFO to set + * timestamps properly. + */ + sensorhub->fifo_size = sensorhub->resp->fifo_info.size; + sensorhub->ring = devm_kcalloc(sensorhub->dev, sensorhub->fifo_size, + sizeof(*sensorhub->ring), GFP_KERNEL); + if (!sensorhub->ring) + return -ENOMEM; + + /* + * Allocate the callback area based on the number of sensors. + */ + sensorhub->push_data = devm_kcalloc( + sensorhub->dev, sensorhub->sensor_num, + sizeof(*sensorhub->push_data), + GFP_KERNEL); + if (!sensorhub->push_data) + return -ENOMEM; + + sensorhub->fifo_timestamp[CROS_EC_SENSOR_LAST_TS] = + cros_ec_get_time_ns(); + + sensorhub->tight_timestamps = cros_ec_check_features( + ec, EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS); + + if (sensorhub->tight_timestamps) { + sensorhub->batch_state = devm_kcalloc(sensorhub->dev, + sensorhub->sensor_num, + sizeof(*sensorhub->batch_state), + GFP_KERNEL); + if (!sensorhub->batch_state) + return -ENOMEM; + } + + /* Register the notifier that will act as a top half interrupt. */ + sensorhub->notifier.notifier_call = cros_ec_sensorhub_event; + ret = blocking_notifier_chain_register(&ec->ec_dev->event_notifier, + &sensorhub->notifier); + if (ret < 0) + return ret; + + /* Start collection samples. */ + return cros_ec_sensorhub_ring_fifo_enable(sensorhub, true); +} + +void cros_ec_sensorhub_ring_remove(void *arg) +{ + struct cros_ec_sensorhub *sensorhub = arg; + struct cros_ec_device *ec_dev = sensorhub->ec->ec_dev; + + /* Disable the ring, prevent EC interrupt to the AP for nothing. */ + cros_ec_sensorhub_ring_fifo_enable(sensorhub, false); + blocking_notifier_chain_unregister(&ec_dev->event_notifier, + &sensorhub->notifier); +} diff --git a/drivers/platform/chrome/cros_ec_spi.c b/drivers/platform/chrome/cros_ec_spi.c index 46786d2d679a..debea5c4c829 100644 --- a/drivers/platform/chrome/cros_ec_spi.c +++ b/drivers/platform/chrome/cros_ec_spi.c @@ -127,7 +127,8 @@ static int terminate_request(struct cros_ec_device *ec_dev) */ spi_message_init(&msg); memset(&trans, 0, sizeof(trans)); - trans.delay_usecs = ec_spi->end_of_msg_delay; + trans.delay.value = ec_spi->end_of_msg_delay; + trans.delay.unit = SPI_DELAY_UNIT_USECS; spi_message_add_tail(&trans, &msg); ret = spi_sync_locked(ec_spi->spi, &msg); @@ -416,7 +417,8 @@ static int do_cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev, spi_message_init(&msg); if (ec_spi->start_of_msg_delay) { memset(&trans_delay, 0, sizeof(trans_delay)); - trans_delay.delay_usecs = ec_spi->start_of_msg_delay; + trans_delay.delay.value = ec_spi->start_of_msg_delay; + trans_delay.delay.unit = SPI_DELAY_UNIT_USECS; spi_message_add_tail(&trans_delay, &msg); } diff --git a/drivers/platform/chrome/cros_ec_sysfs.c b/drivers/platform/chrome/cros_ec_sysfs.c index 07dac97ad57c..d45ea5d5bfa4 100644 --- a/drivers/platform/chrome/cros_ec_sysfs.c +++ b/drivers/platform/chrome/cros_ec_sysfs.c @@ -149,14 +149,14 @@ static ssize_t version_show(struct device *dev, /* Get build info. */ msg->command = EC_CMD_GET_BUILD_INFO + ec->cmd_offset; msg->insize = EC_HOST_PARAM_SIZE; - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); - if (ret < 0) - count += scnprintf(buf + count, PAGE_SIZE - count, - "Build info: XFER ERROR %d\n", ret); - else if (msg->result != EC_RES_SUCCESS) + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); + if (ret == -EPROTO) { count += scnprintf(buf + count, PAGE_SIZE - count, "Build info: EC error %d\n", msg->result); - else { + } else if (ret < 0) { + count += scnprintf(buf + count, PAGE_SIZE - count, + "Build info: XFER ERROR %d\n", ret); + } else { msg->data[EC_HOST_PARAM_SIZE - 1] = '\0'; count += scnprintf(buf + count, PAGE_SIZE - count, "Build info: %s\n", msg->data); @@ -165,14 +165,14 @@ static ssize_t version_show(struct device *dev, /* Get chip info. */ msg->command = EC_CMD_GET_CHIP_INFO + ec->cmd_offset; msg->insize = sizeof(*r_chip); - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); - if (ret < 0) - count += scnprintf(buf + count, PAGE_SIZE - count, - "Chip info: XFER ERROR %d\n", ret); - else if (msg->result != EC_RES_SUCCESS) + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); + if (ret == -EPROTO) { count += scnprintf(buf + count, PAGE_SIZE - count, "Chip info: EC error %d\n", msg->result); - else { + } else if (ret < 0) { + count += scnprintf(buf + count, PAGE_SIZE - count, + "Chip info: XFER ERROR %d\n", ret); + } else { r_chip = (struct ec_response_get_chip_info *)msg->data; r_chip->vendor[sizeof(r_chip->vendor) - 1] = '\0'; @@ -189,14 +189,14 @@ static ssize_t version_show(struct device *dev, /* Get board version */ msg->command = EC_CMD_GET_BOARD_VERSION + ec->cmd_offset; msg->insize = sizeof(*r_board); - ret = cros_ec_cmd_xfer(ec->ec_dev, msg); - if (ret < 0) - count += scnprintf(buf + count, PAGE_SIZE - count, - "Board version: XFER ERROR %d\n", ret); - else if (msg->result != EC_RES_SUCCESS) + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); + if (ret == -EPROTO) { count += scnprintf(buf + count, PAGE_SIZE - count, "Board version: EC error %d\n", msg->result); - else { + } else if (ret < 0) { + count += scnprintf(buf + count, PAGE_SIZE - count, + "Board version: XFER ERROR %d\n", ret); + } else { r_board = (struct ec_response_board_version *)msg->data; count += scnprintf(buf + count, PAGE_SIZE - count, diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c new file mode 100644 index 000000000000..874269c07073 --- /dev/null +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -0,0 +1,357 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2020 Google LLC + * + * This driver provides the ability to view and manage Type C ports through the + * Chrome OS EC. + */ + +#include <linux/acpi.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_data/cros_ec_commands.h> +#include <linux/platform_data/cros_ec_proto.h> +#include <linux/platform_device.h> +#include <linux/usb/typec.h> + +#define DRV_NAME "cros-ec-typec" + +/* Platform-specific data for the Chrome OS EC Type C controller. */ +struct cros_typec_data { + struct device *dev; + struct cros_ec_device *ec; + int num_ports; + unsigned int cmd_ver; + /* Array of ports, indexed by port number. */ + struct typec_port *ports[EC_USB_PD_MAX_PORTS]; + /* Initial capabilities for each port. */ + struct typec_capability *caps[EC_USB_PD_MAX_PORTS]; +}; + +static int cros_typec_parse_port_props(struct typec_capability *cap, + struct fwnode_handle *fwnode, + struct device *dev) +{ + const char *buf; + int ret; + + memset(cap, 0, sizeof(*cap)); + ret = fwnode_property_read_string(fwnode, "power-role", &buf); + if (ret) { + dev_err(dev, "power-role not found: %d\n", ret); + return ret; + } + + ret = typec_find_port_power_role(buf); + if (ret < 0) + return ret; + cap->type = ret; + + ret = fwnode_property_read_string(fwnode, "data-role", &buf); + if (ret) { + dev_err(dev, "data-role not found: %d\n", ret); + return ret; + } + + ret = typec_find_port_data_role(buf); + if (ret < 0) + return ret; + cap->data = ret; + + ret = fwnode_property_read_string(fwnode, "try-power-role", &buf); + if (ret) { + dev_err(dev, "try-power-role not found: %d\n", ret); + return ret; + } + + ret = typec_find_power_role(buf); + if (ret < 0) + return ret; + cap->prefer_role = ret; + + cap->fwnode = fwnode; + + return 0; +} + +static int cros_typec_init_ports(struct cros_typec_data *typec) +{ + struct device *dev = typec->dev; + struct typec_capability *cap; + struct fwnode_handle *fwnode; + const char *port_prop; + int ret; + int i; + int nports; + u32 port_num = 0; + + nports = device_get_child_node_count(dev); + if (nports == 0) { + dev_err(dev, "No port entries found.\n"); + return -ENODEV; + } + + if (nports > typec->num_ports) { + dev_err(dev, "More ports listed than can be supported.\n"); + return -EINVAL; + } + + /* DT uses "reg" to specify port number. */ + port_prop = dev->of_node ? "reg" : "port-number"; + device_for_each_child_node(dev, fwnode) { + if (fwnode_property_read_u32(fwnode, port_prop, &port_num)) { + ret = -EINVAL; + dev_err(dev, "No port-number for port, aborting.\n"); + goto unregister_ports; + } + + if (port_num >= typec->num_ports) { + dev_err(dev, "Invalid port number.\n"); + ret = -EINVAL; + goto unregister_ports; + } + + dev_dbg(dev, "Registering port %d\n", port_num); + + cap = devm_kzalloc(dev, sizeof(*cap), GFP_KERNEL); + if (!cap) { + ret = -ENOMEM; + goto unregister_ports; + } + + typec->caps[port_num] = cap; + + ret = cros_typec_parse_port_props(cap, fwnode, dev); + if (ret < 0) + goto unregister_ports; + + typec->ports[port_num] = typec_register_port(dev, cap); + if (IS_ERR(typec->ports[port_num])) { + dev_err(dev, "Failed to register port %d\n", port_num); + ret = PTR_ERR(typec->ports[port_num]); + goto unregister_ports; + } + } + + return 0; + +unregister_ports: + for (i = 0; i < typec->num_ports; i++) + typec_unregister_port(typec->ports[i]); + return ret; +} + +static int cros_typec_ec_command(struct cros_typec_data *typec, + unsigned int version, + unsigned int command, + void *outdata, + unsigned int outsize, + void *indata, + unsigned int insize) +{ + struct cros_ec_command *msg; + int ret; + + msg = kzalloc(sizeof(*msg) + max(outsize, insize), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->version = version; + msg->command = command; + msg->outsize = outsize; + msg->insize = insize; + + if (outsize) + memcpy(msg->data, outdata, outsize); + + ret = cros_ec_cmd_xfer_status(typec->ec, msg); + if (ret >= 0 && insize) + memcpy(indata, msg->data, insize); + + kfree(msg); + return ret; +} + +static void cros_typec_set_port_params_v0(struct cros_typec_data *typec, + int port_num, struct ec_response_usb_pd_control *resp) +{ + struct typec_port *port = typec->ports[port_num]; + enum typec_orientation polarity; + + if (!resp->enabled) + polarity = TYPEC_ORIENTATION_NONE; + else if (!resp->polarity) + polarity = TYPEC_ORIENTATION_NORMAL; + else + polarity = TYPEC_ORIENTATION_REVERSE; + + typec_set_pwr_role(port, resp->role ? TYPEC_SOURCE : TYPEC_SINK); + typec_set_orientation(port, polarity); +} + +static void cros_typec_set_port_params_v1(struct cros_typec_data *typec, + int port_num, struct ec_response_usb_pd_control_v1 *resp) +{ + struct typec_port *port = typec->ports[port_num]; + enum typec_orientation polarity; + + if (!(resp->enabled & PD_CTRL_RESP_ENABLED_CONNECTED)) + polarity = TYPEC_ORIENTATION_NONE; + else if (!resp->polarity) + polarity = TYPEC_ORIENTATION_NORMAL; + else + polarity = TYPEC_ORIENTATION_REVERSE; + typec_set_orientation(port, polarity); + typec_set_data_role(port, resp->role & PD_CTRL_RESP_ROLE_DATA ? + TYPEC_HOST : TYPEC_DEVICE); + typec_set_pwr_role(port, resp->role & PD_CTRL_RESP_ROLE_POWER ? + TYPEC_SOURCE : TYPEC_SINK); + typec_set_vconn_role(port, resp->role & PD_CTRL_RESP_ROLE_VCONN ? + TYPEC_SOURCE : TYPEC_SINK); +} + +static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) +{ + struct ec_params_usb_pd_control req; + struct ec_response_usb_pd_control_v1 resp; + int ret; + + if (port_num < 0 || port_num >= typec->num_ports) { + dev_err(typec->dev, "cannot get status for invalid port %d\n", + port_num); + return -EINVAL; + } + + req.port = port_num; + req.role = USB_PD_CTRL_ROLE_NO_CHANGE; + req.mux = USB_PD_CTRL_MUX_NO_CHANGE; + req.swap = USB_PD_CTRL_SWAP_NONE; + + ret = cros_typec_ec_command(typec, typec->cmd_ver, + EC_CMD_USB_PD_CONTROL, &req, sizeof(req), + &resp, sizeof(resp)); + if (ret < 0) + return ret; + + dev_dbg(typec->dev, "Enabled %d: 0x%hhx\n", port_num, resp.enabled); + dev_dbg(typec->dev, "Role %d: 0x%hhx\n", port_num, resp.role); + dev_dbg(typec->dev, "Polarity %d: 0x%hhx\n", port_num, resp.polarity); + dev_dbg(typec->dev, "State %d: %s\n", port_num, resp.state); + + if (typec->cmd_ver == 1) + cros_typec_set_port_params_v1(typec, port_num, &resp); + else + cros_typec_set_port_params_v0(typec, port_num, + (struct ec_response_usb_pd_control *) &resp); + + return 0; +} + +static int cros_typec_get_cmd_version(struct cros_typec_data *typec) +{ + struct ec_params_get_cmd_versions_v1 req_v1; + struct ec_response_get_cmd_versions resp; + int ret; + + /* We're interested in the PD control command version. */ + req_v1.cmd = EC_CMD_USB_PD_CONTROL; + ret = cros_typec_ec_command(typec, 1, EC_CMD_GET_CMD_VERSIONS, + &req_v1, sizeof(req_v1), &resp, + sizeof(resp)); + if (ret < 0) + return ret; + + if (resp.version_mask & EC_VER_MASK(1)) + typec->cmd_ver = 1; + else + typec->cmd_ver = 0; + + dev_dbg(typec->dev, "PD Control has version mask 0x%hhx\n", + typec->cmd_ver); + + return 0; +} + +#ifdef CONFIG_ACPI +static const struct acpi_device_id cros_typec_acpi_id[] = { + { "GOOG0014", 0 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, cros_typec_acpi_id); +#endif + +#ifdef CONFIG_OF +static const struct of_device_id cros_typec_of_match[] = { + { .compatible = "google,cros-ec-typec", }, + {} +}; +MODULE_DEVICE_TABLE(of, cros_typec_of_match); +#endif + +static int cros_typec_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cros_typec_data *typec; + struct ec_response_usb_pd_ports resp; + int ret, i; + + typec = devm_kzalloc(dev, sizeof(*typec), GFP_KERNEL); + if (!typec) + return -ENOMEM; + + typec->dev = dev; + typec->ec = dev_get_drvdata(pdev->dev.parent); + platform_set_drvdata(pdev, typec); + + ret = cros_typec_get_cmd_version(typec); + if (ret < 0) { + dev_err(dev, "failed to get PD command version info\n"); + return ret; + } + + ret = cros_typec_ec_command(typec, 0, EC_CMD_USB_PD_PORTS, NULL, 0, + &resp, sizeof(resp)); + if (ret < 0) + return ret; + + typec->num_ports = resp.num_ports; + if (typec->num_ports > EC_USB_PD_MAX_PORTS) { + dev_warn(typec->dev, + "Too many ports reported: %d, limiting to max: %d\n", + typec->num_ports, EC_USB_PD_MAX_PORTS); + typec->num_ports = EC_USB_PD_MAX_PORTS; + } + + ret = cros_typec_init_ports(typec); + if (ret < 0) + return ret; + + for (i = 0; i < typec->num_ports; i++) { + ret = cros_typec_port_update(typec, i); + if (ret < 0) + goto unregister_ports; + } + + return 0; + +unregister_ports: + for (i = 0; i < typec->num_ports; i++) + if (typec->ports[i]) + typec_unregister_port(typec->ports[i]); + return ret; +} + +static struct platform_driver cros_typec_driver = { + .driver = { + .name = DRV_NAME, + .acpi_match_table = ACPI_PTR(cros_typec_acpi_id), + .of_match_table = of_match_ptr(cros_typec_of_match), + }, + .probe = cros_typec_probe, +}; + +module_platform_driver(cros_typec_driver); + +MODULE_AUTHOR("Prashant Malani <pmalani@chromium.org>"); +MODULE_DESCRIPTION("Chrome OS EC Type C control"); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/chrome/cros_ec_vbc.c b/drivers/platform/chrome/cros_ec_vbc.c index 8edae465105c..46482d12cffe 100644 --- a/drivers/platform/chrome/cros_ec_vbc.c +++ b/drivers/platform/chrome/cros_ec_vbc.c @@ -40,7 +40,7 @@ static ssize_t vboot_context_read(struct file *filp, struct kobject *kobj, msg->outsize = para_sz; msg->insize = resp_sz; - err = cros_ec_cmd_xfer(ecdev, msg); + err = cros_ec_cmd_xfer_status(ecdev, msg); if (err < 0) { dev_err(dev, "Error sending read request: %d\n", err); kfree(msg); @@ -83,7 +83,7 @@ static ssize_t vboot_context_write(struct file *filp, struct kobject *kobj, msg->outsize = para_sz; msg->insize = 0; - err = cros_ec_cmd_xfer(ecdev, msg); + err = cros_ec_cmd_xfer_status(ecdev, msg); if (err < 0) { dev_err(dev, "Error sending write request: %d\n", err); kfree(msg); diff --git a/drivers/platform/chrome/cros_usbpd_notify.c b/drivers/platform/chrome/cros_usbpd_notify.c new file mode 100644 index 000000000000..7f36142ab12a --- /dev/null +++ b/drivers/platform/chrome/cros_usbpd_notify.c @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2020 Google LLC + * + * This driver serves as the receiver of cros_ec PD host events. + */ + +#include <linux/acpi.h> +#include <linux/module.h> +#include <linux/platform_data/cros_ec_proto.h> +#include <linux/platform_data/cros_usbpd_notify.h> +#include <linux/platform_device.h> + +#define DRV_NAME "cros-usbpd-notify" +#define DRV_NAME_PLAT_ACPI "cros-usbpd-notify-acpi" +#define ACPI_DRV_NAME "GOOG0003" + +static BLOCKING_NOTIFIER_HEAD(cros_usbpd_notifier_list); + +struct cros_usbpd_notify_data { + struct device *dev; + struct cros_ec_device *ec; + struct notifier_block nb; +}; + +/** + * cros_usbpd_register_notify - Register a notifier callback for PD events. + * @nb: Notifier block pointer to register + * + * On ACPI platforms this corresponds to host events on the ECPD + * "GOOG0003" ACPI device. On non-ACPI platforms this will filter mkbp events + * for USB PD events. + * + * Return: 0 on success or negative error code. + */ +int cros_usbpd_register_notify(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&cros_usbpd_notifier_list, + nb); +} +EXPORT_SYMBOL_GPL(cros_usbpd_register_notify); + +/** + * cros_usbpd_unregister_notify - Unregister notifier callback for PD events. + * @nb: Notifier block pointer to unregister + * + * Unregister a notifier callback that was previously registered with + * cros_usbpd_register_notify(). + */ +void cros_usbpd_unregister_notify(struct notifier_block *nb) +{ + blocking_notifier_chain_unregister(&cros_usbpd_notifier_list, nb); +} +EXPORT_SYMBOL_GPL(cros_usbpd_unregister_notify); + +/** + * cros_ec_pd_command - Send a command to the EC. + * + * @ec_dev: EC device + * @command: EC command + * @outdata: EC command output data + * @outsize: Size of outdata + * @indata: EC command input data + * @insize: Size of indata + * + * Return: >= 0 on success, negative error number on failure. + */ +static int cros_ec_pd_command(struct cros_ec_device *ec_dev, + int command, + uint8_t *outdata, + int outsize, + uint8_t *indata, + int insize) +{ + struct cros_ec_command *msg; + int ret; + + msg = kzalloc(sizeof(*msg) + max(insize, outsize), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->command = command; + msg->outsize = outsize; + msg->insize = insize; + + if (outsize) + memcpy(msg->data, outdata, outsize); + + ret = cros_ec_cmd_xfer_status(ec_dev, msg); + if (ret < 0) + goto error; + + if (insize) + memcpy(indata, msg->data, insize); +error: + kfree(msg); + return ret; +} + +static void cros_usbpd_get_event_and_notify(struct device *dev, + struct cros_ec_device *ec_dev) +{ + struct ec_response_host_event_status host_event_status; + u32 event = 0; + int ret; + + /* + * We still send a 0 event out to older devices which don't + * have the updated device heirarchy. + */ + if (!ec_dev) { + dev_dbg(dev, + "EC device inaccessible; sending 0 event status.\n"); + goto send_notify; + } + + /* Check for PD host events on EC. */ + ret = cros_ec_pd_command(ec_dev, EC_CMD_PD_HOST_EVENT_STATUS, + NULL, 0, + (uint8_t *)&host_event_status, + sizeof(host_event_status)); + if (ret < 0) { + dev_warn(dev, "Can't get host event status (err: %d)\n", ret); + goto send_notify; + } + + event = host_event_status.status; + +send_notify: + blocking_notifier_call_chain(&cros_usbpd_notifier_list, event, NULL); +} + +#ifdef CONFIG_ACPI + +static void cros_usbpd_notify_acpi(acpi_handle device, u32 event, void *data) +{ + struct cros_usbpd_notify_data *pdnotify = data; + + cros_usbpd_get_event_and_notify(pdnotify->dev, pdnotify->ec); +} + +static int cros_usbpd_notify_probe_acpi(struct platform_device *pdev) +{ + struct cros_usbpd_notify_data *pdnotify; + struct device *dev = &pdev->dev; + struct acpi_device *adev; + struct cros_ec_device *ec_dev; + acpi_status status; + + adev = ACPI_COMPANION(dev); + + pdnotify = devm_kzalloc(dev, sizeof(*pdnotify), GFP_KERNEL); + if (!pdnotify) + return -ENOMEM; + + /* Get the EC device pointer needed to talk to the EC. */ + ec_dev = dev_get_drvdata(dev->parent); + if (!ec_dev) { + /* + * We continue even for older devices which don't have the + * correct device heirarchy, namely, GOOG0003 is a child + * of GOOG0004. + */ + dev_warn(dev, "Couldn't get Chrome EC device pointer.\n"); + } + + pdnotify->dev = dev; + pdnotify->ec = ec_dev; + + status = acpi_install_notify_handler(adev->handle, + ACPI_ALL_NOTIFY, + cros_usbpd_notify_acpi, + pdnotify); + if (ACPI_FAILURE(status)) { + dev_warn(dev, "Failed to register notify handler %08x\n", + status); + return -EINVAL; + } + + return 0; +} + +static int cros_usbpd_notify_remove_acpi(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct acpi_device *adev = ACPI_COMPANION(dev); + + acpi_remove_notify_handler(adev->handle, ACPI_ALL_NOTIFY, + cros_usbpd_notify_acpi); + + return 0; +} + +static const struct acpi_device_id cros_usbpd_notify_acpi_device_ids[] = { + { ACPI_DRV_NAME, 0 }, + { } +}; +MODULE_DEVICE_TABLE(acpi, cros_usbpd_notify_acpi_device_ids); + +static struct platform_driver cros_usbpd_notify_acpi_driver = { + .driver = { + .name = DRV_NAME_PLAT_ACPI, + .acpi_match_table = cros_usbpd_notify_acpi_device_ids, + }, + .probe = cros_usbpd_notify_probe_acpi, + .remove = cros_usbpd_notify_remove_acpi, +}; + +#endif /* CONFIG_ACPI */ + +static int cros_usbpd_notify_plat(struct notifier_block *nb, + unsigned long queued_during_suspend, + void *data) +{ + struct cros_usbpd_notify_data *pdnotify = container_of(nb, + struct cros_usbpd_notify_data, nb); + struct cros_ec_device *ec_dev = (struct cros_ec_device *)data; + u32 host_event = cros_ec_get_host_event(ec_dev); + + if (!host_event) + return NOTIFY_DONE; + + if (host_event & EC_HOST_EVENT_MASK(EC_HOST_EVENT_PD_MCU)) { + cros_usbpd_get_event_and_notify(pdnotify->dev, ec_dev); + return NOTIFY_OK; + } + return NOTIFY_DONE; +} + +static int cros_usbpd_notify_probe_plat(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cros_ec_dev *ecdev = dev_get_drvdata(dev->parent); + struct cros_usbpd_notify_data *pdnotify; + int ret; + + pdnotify = devm_kzalloc(dev, sizeof(*pdnotify), GFP_KERNEL); + if (!pdnotify) + return -ENOMEM; + + pdnotify->dev = dev; + pdnotify->ec = ecdev->ec_dev; + pdnotify->nb.notifier_call = cros_usbpd_notify_plat; + + dev_set_drvdata(dev, pdnotify); + + ret = blocking_notifier_chain_register(&ecdev->ec_dev->event_notifier, + &pdnotify->nb); + if (ret < 0) { + dev_err(dev, "Failed to register notifier\n"); + return ret; + } + + return 0; +} + +static int cros_usbpd_notify_remove_plat(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cros_ec_dev *ecdev = dev_get_drvdata(dev->parent); + struct cros_usbpd_notify_data *pdnotify = + (struct cros_usbpd_notify_data *)dev_get_drvdata(dev); + + blocking_notifier_chain_unregister(&ecdev->ec_dev->event_notifier, + &pdnotify->nb); + + return 0; +} + +static struct platform_driver cros_usbpd_notify_plat_driver = { + .driver = { + .name = DRV_NAME, + }, + .probe = cros_usbpd_notify_probe_plat, + .remove = cros_usbpd_notify_remove_plat, +}; + +static int __init cros_usbpd_notify_init(void) +{ + int ret; + + ret = platform_driver_register(&cros_usbpd_notify_plat_driver); + if (ret < 0) + return ret; + +#ifdef CONFIG_ACPI + platform_driver_register(&cros_usbpd_notify_acpi_driver); +#endif + return 0; +} + +static void __exit cros_usbpd_notify_exit(void) +{ +#ifdef CONFIG_ACPI + platform_driver_unregister(&cros_usbpd_notify_acpi_driver); +#endif + platform_driver_unregister(&cros_usbpd_notify_plat_driver); +} + +module_init(cros_usbpd_notify_init); +module_exit(cros_usbpd_notify_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("ChromeOS power delivery notifier device"); +MODULE_AUTHOR("Jon Flatley <jflat@chromium.org>"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/platform/chrome/wilco_ec/event.c b/drivers/platform/chrome/wilco_ec/event.c index dba3d445623f..814518509739 100644 --- a/drivers/platform/chrome/wilco_ec/event.c +++ b/drivers/platform/chrome/wilco_ec/event.c @@ -79,7 +79,7 @@ static DEFINE_IDA(event_ida); struct ec_event { u16 size; u16 type; - u16 event[0]; + u16 event[]; } __packed; #define ec_event_num_words(ev) (ev->size - 1) @@ -96,7 +96,7 @@ struct ec_event_queue { int capacity; int head; int tail; - struct ec_event *entries[0]; + struct ec_event *entries[]; }; /* Maximum number of events to store in ec_event_queue */ diff --git a/drivers/platform/chrome/wilco_ec/properties.c b/drivers/platform/chrome/wilco_ec/properties.c index 62f27610dd33..c2bf4c95c5d2 100644 --- a/drivers/platform/chrome/wilco_ec/properties.c +++ b/drivers/platform/chrome/wilco_ec/properties.c @@ -3,8 +3,11 @@ * Copyright 2019 Google LLC */ +#include <linux/errno.h> +#include <linux/export.h> #include <linux/platform_data/wilco-ec.h> #include <linux/string.h> +#include <linux/types.h> #include <asm/unaligned.h> /* Operation code; what the EC should do with the property */ diff --git a/drivers/platform/chrome/wilco_ec/sysfs.c b/drivers/platform/chrome/wilco_ec/sysfs.c index f0d174b6bb21..3c587b4054a5 100644 --- a/drivers/platform/chrome/wilco_ec/sysfs.c +++ b/drivers/platform/chrome/wilco_ec/sysfs.c @@ -8,8 +8,12 @@ * See Documentation/ABI/testing/sysfs-platform-wilco-ec for more information. */ +#include <linux/device.h> +#include <linux/kernel.h> #include <linux/platform_data/wilco-ec.h> +#include <linux/string.h> #include <linux/sysfs.h> +#include <linux/types.h> #define CMD_KB_CMOS 0x7C #define SUB_CMD_KB_CMOS_AUTO_ON 0x03 diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index 74e988f839e8..f8d3e3bd1bb5 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -4,7 +4,7 @@ * * Copyright (c) Red Hat <mjg@redhat.com> * Copyright (c) 2014 Gabriele Mazzotta <gabriele.mzt@gmail.com> - * Copyright (c) 2014 Pali Rohár <pali.rohar@gmail.com> + * Copyright (c) 2014 Pali Rohár <pali@kernel.org> * * Based on documentation in the libsmbios package: * Copyright (C) 2005-2014 Dell Inc. @@ -2295,6 +2295,6 @@ module_exit(dell_exit); MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); MODULE_AUTHOR("Gabriele Mazzotta <gabriele.mzt@gmail.com>"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); MODULE_DESCRIPTION("Dell laptop driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-rbtn.c b/drivers/platform/x86/dell-rbtn.c index a6b856cd86bd..a89fad47ff13 100644 --- a/drivers/platform/x86/dell-rbtn.c +++ b/drivers/platform/x86/dell-rbtn.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* Dell Airplane Mode Switch driver - Copyright (C) 2014-2015 Pali Rohár <pali.rohar@gmail.com> + Copyright (C) 2014-2015 Pali Rohár <pali@kernel.org> */ @@ -495,5 +495,5 @@ MODULE_PARM_DESC(auto_remove_rfkill, "Automatically remove rfkill devices when " "(default true)"); MODULE_DEVICE_TABLE(acpi, rbtn_ids); MODULE_DESCRIPTION("Dell Airplane Mode Switch driver"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-rbtn.h b/drivers/platform/x86/dell-rbtn.h index 0fdc81644458..5e030f926c58 100644 --- a/drivers/platform/x86/dell-rbtn.h +++ b/drivers/platform/x86/dell-rbtn.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Dell Airplane Mode Switch driver - Copyright (C) 2014-2015 Pali Rohár <pali.rohar@gmail.com> + Copyright (C) 2014-2015 Pali Rohár <pali@kernel.org> */ diff --git a/drivers/platform/x86/dell-smbios-base.c b/drivers/platform/x86/dell-smbios-base.c index fe59b0ebff31..2e2cd565926a 100644 --- a/drivers/platform/x86/dell-smbios-base.c +++ b/drivers/platform/x86/dell-smbios-base.c @@ -4,7 +4,7 @@ * * Copyright (c) Red Hat <mjg@redhat.com> * Copyright (c) 2014 Gabriele Mazzotta <gabriele.mzt@gmail.com> - * Copyright (c) 2014 Pali Rohár <pali.rohar@gmail.com> + * Copyright (c) 2014 Pali Rohár <pali@kernel.org> * * Based on documentation in the libsmbios package: * Copyright (C) 2005-2014 Dell Inc. @@ -645,7 +645,7 @@ module_exit(dell_smbios_exit); MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); MODULE_AUTHOR("Gabriele Mazzotta <gabriele.mzt@gmail.com>"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); MODULE_DESCRIPTION("Common functions for kernel modules using Dell SMBIOS"); MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios-smm.c b/drivers/platform/x86/dell-smbios-smm.c index d6854d1c4119..97c52a839a3e 100644 --- a/drivers/platform/x86/dell-smbios-smm.c +++ b/drivers/platform/x86/dell-smbios-smm.c @@ -4,7 +4,7 @@ * * Copyright (c) Red Hat <mjg@redhat.com> * Copyright (c) 2014 Gabriele Mazzotta <gabriele.mzt@gmail.com> - * Copyright (c) 2014 Pali Rohár <pali.rohar@gmail.com> + * Copyright (c) 2014 Pali Rohár <pali@kernel.org> * Copyright (c) 2017 Dell Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/platform/x86/dell-smbios.h b/drivers/platform/x86/dell-smbios.h index a7ff9803f41a..75fa8ea0476d 100644 --- a/drivers/platform/x86/dell-smbios.h +++ b/drivers/platform/x86/dell-smbios.h @@ -4,7 +4,7 @@ * * Copyright (c) Red Hat <mjg@redhat.com> * Copyright (c) 2014 Gabriele Mazzotta <gabriele.mzt@gmail.com> - * Copyright (c) 2014 Pali Rohár <pali.rohar@gmail.com> + * Copyright (c) 2014 Pali Rohár <pali@kernel.org> * * Based on documentation in the libsmbios package: * Copyright (C) 2005-2014 Dell Inc. diff --git a/drivers/platform/x86/dell-smo8800.c b/drivers/platform/x86/dell-smo8800.c index b531fe8ab7e0..5d9304a7de1b 100644 --- a/drivers/platform/x86/dell-smo8800.c +++ b/drivers/platform/x86/dell-smo8800.c @@ -3,7 +3,7 @@ * dell-smo8800.c - Dell Latitude ACPI SMO88XX freefall sensor driver * * Copyright (C) 2012 Sonal Santan <sonal.santan@gmail.com> - * Copyright (C) 2014 Pali Rohár <pali.rohar@gmail.com> + * Copyright (C) 2014 Pali Rohár <pali@kernel.org> * * This is loosely based on lis3lv02d driver. */ diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index 6669db2555fb..86e8dd6a8b33 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -3,7 +3,7 @@ * Dell WMI hotkeys * * Copyright (C) 2008 Red Hat <mjg@redhat.com> - * Copyright (C) 2014-2015 Pali Rohár <pali.rohar@gmail.com> + * Copyright (C) 2014-2015 Pali Rohár <pali@kernel.org> * * Portions based on wistron_btns.c: * Copyright (C) 2005 Miloslav Trmac <mitr@volny.cz> @@ -29,7 +29,7 @@ #include "dell-wmi-descriptor.h" MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); MODULE_DESCRIPTION("Dell laptop WMI hotkeys driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index 195bc0462d3e..f3424fdce341 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -659,7 +659,7 @@ config CHARGER_RT9455 config CHARGER_CROS_USBPD tristate "ChromeOS EC based USBPD charger" - depends on CROS_EC + depends on CROS_USBPD_NOTIFY default n help Say Y here to enable ChromeOS EC based USBPD charger diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c index 532f6e4fcafb..a1f00ae1c180 100644 --- a/drivers/power/supply/bq2415x_charger.c +++ b/drivers/power/supply/bq2415x_charger.c @@ -2,7 +2,7 @@ /* * bq2415x charger driver * - * Copyright (C) 2011-2013 Pali Rohár <pali.rohar@gmail.com> + * Copyright (C) 2011-2013 Pali Rohár <pali@kernel.org> * * Datasheets: * http://www.ti.com/product/bq24150 @@ -1788,6 +1788,6 @@ static struct i2c_driver bq2415x_driver = { }; module_i2c_driver(bq2415x_driver); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); MODULE_DESCRIPTION("bq2415x charger driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 664e50103eaa..942c92127b6d 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -4,7 +4,7 @@ * Copyright (C) 2008 Rodolfo Giometti <giometti@linux.it> * Copyright (C) 2008 Eurotech S.p.A. <info@eurotech.it> * Copyright (C) 2010-2011 Lars-Peter Clausen <lars@metafoo.de> - * Copyright (C) 2011 Pali Rohár <pali.rohar@gmail.com> + * Copyright (C) 2011 Pali Rohár <pali@kernel.org> * Copyright (C) 2017 Liam Breck <kernel@networkimprov.net> * * Based on a previous work by Copyright (C) 2008 Texas Instruments, Inc. diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c index 30c3d37511c9..2a45e84447fe 100644 --- a/drivers/power/supply/cros_usbpd-charger.c +++ b/drivers/power/supply/cros_usbpd-charger.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/platform_data/cros_ec_commands.h> #include <linux/platform_data/cros_ec_proto.h> +#include <linux/platform_data/cros_usbpd_notify.h> #include <linux/platform_device.h> #include <linux/power_supply.h> #include <linux/slab.h> @@ -517,32 +518,21 @@ static int cros_usbpd_charger_property_is_writeable(struct power_supply *psy, } static int cros_usbpd_charger_ec_event(struct notifier_block *nb, - unsigned long queued_during_suspend, + unsigned long host_event, void *_notify) { - struct cros_ec_device *ec_device; - struct charger_data *charger; - u32 host_event; + struct charger_data *charger = container_of(nb, struct charger_data, + notifier); - charger = container_of(nb, struct charger_data, notifier); - ec_device = charger->ec_device; - - host_event = cros_ec_get_host_event(ec_device); - if (host_event & EC_HOST_EVENT_MASK(EC_HOST_EVENT_PD_MCU)) { - cros_usbpd_charger_power_changed(charger->ports[0]->psy); - return NOTIFY_OK; - } else { - return NOTIFY_DONE; - } + cros_usbpd_charger_power_changed(charger->ports[0]->psy); + return NOTIFY_OK; } static void cros_usbpd_charger_unregister_notifier(void *data) { struct charger_data *charger = data; - struct cros_ec_device *ec_device = charger->ec_device; - blocking_notifier_chain_unregister(&ec_device->event_notifier, - &charger->notifier); + cros_usbpd_unregister_notify(&charger->notifier); } static int cros_usbpd_charger_probe(struct platform_device *pd) @@ -676,21 +666,17 @@ static int cros_usbpd_charger_probe(struct platform_device *pd) goto fail; } - if (ec_device->mkbp_event_supported) { - /* Get PD events from the EC */ - charger->notifier.notifier_call = cros_usbpd_charger_ec_event; - ret = blocking_notifier_chain_register( - &ec_device->event_notifier, - &charger->notifier); - if (ret < 0) { - dev_warn(dev, "failed to register notifier\n"); - } else { - ret = devm_add_action_or_reset(dev, - cros_usbpd_charger_unregister_notifier, - charger); - if (ret < 0) - goto fail; - } + /* Get PD events from the EC */ + charger->notifier.notifier_call = cros_usbpd_charger_ec_event; + ret = cros_usbpd_register_notify(&charger->notifier); + if (ret < 0) { + dev_warn(dev, "failed to register notifier\n"); + } else { + ret = devm_add_action_or_reset(dev, + cros_usbpd_charger_unregister_notifier, + charger); + if (ret < 0) + goto fail; } return 0; diff --git a/drivers/power/supply/isp1704_charger.c b/drivers/power/supply/isp1704_charger.c index 4812ac1ff2df..b6efc454e4f0 100644 --- a/drivers/power/supply/isp1704_charger.c +++ b/drivers/power/supply/isp1704_charger.c @@ -3,7 +3,7 @@ * ISP1704 USB Charger Detection driver * * Copyright (C) 2010 Nokia Corporation - * Copyright (C) 2012 - 2013 Pali Rohár <pali.rohar@gmail.com> + * Copyright (C) 2012 - 2013 Pali Rohár <pali@kernel.org> */ #include <linux/kernel.h> diff --git a/drivers/power/supply/rx51_battery.c b/drivers/power/supply/rx51_battery.c index 8548b639ff2f..6e488ecf4dcb 100644 --- a/drivers/power/supply/rx51_battery.c +++ b/drivers/power/supply/rx51_battery.c @@ -2,7 +2,7 @@ /* * Nokia RX-51 battery driver * - * Copyright (C) 2012 Pali Rohár <pali.rohar@gmail.com> + * Copyright (C) 2012 Pali Rohár <pali@kernel.org> */ #include <linux/module.h> @@ -278,6 +278,6 @@ static struct platform_driver rx51_battery_driver = { module_platform_driver(rx51_battery_driver); MODULE_ALIAS("platform:rx51-battery"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); MODULE_DESCRIPTION("Nokia RX-51 battery driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/ps3/sys-manager-core.c b/drivers/ps3/sys-manager-core.c index 24709c572c0c..e061b7d0632b 100644 --- a/drivers/ps3/sys-manager-core.c +++ b/drivers/ps3/sys-manager-core.c @@ -31,7 +31,7 @@ void ps3_sys_manager_register_ops(const struct ps3_sys_manager_ops *ops) { BUG_ON(!ops); BUG_ON(!ops->dev); - ps3_sys_manager_ops = ops ? *ops : ps3_sys_manager_ops; + ps3_sys_manager_ops = *ops; } EXPORT_SYMBOL_GPL(ps3_sys_manager_register_ops); diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig index 30190beeb6e9..eebbc917ac97 100644 --- a/drivers/pwm/Kconfig +++ b/drivers/pwm/Kconfig @@ -33,6 +33,15 @@ config PWM_SYSFS bool default y if SYSFS +config PWM_DEBUG + bool "PWM lowlevel drivers additional checks and debug messages" + depends on DEBUG_KERNEL + help + This option enables some additional checks to help lowlevel driver + authors to get their callbacks implemented correctly. + It is expected to introduce some runtime overhead and diagnostic + output to the kernel log, so only enable while working on a driver. + config PWM_AB8500 tristate "AB8500 PWM support" depends on AB8500_CORE && ARCH_U8500 @@ -44,7 +53,8 @@ config PWM_AB8500 config PWM_ATMEL tristate "Atmel PWM support" - depends on ARCH_AT91 && OF + depends on OF + depends on ARCH_AT91 || COMPILE_TEST help Generic PWM framework driver for Atmel SoC. @@ -100,7 +110,7 @@ config PWM_BCM_KONA config PWM_BCM2835 tristate "BCM2835 PWM support" - depends on ARCH_BCM2835 || ARCH_BRCMSTB + depends on ARCH_BCM2835 || ARCH_BRCMSTB || COMPILE_TEST help PWM framework driver for BCM2835 controller (Raspberry Pi) @@ -109,7 +119,7 @@ config PWM_BCM2835 config PWM_BERLIN tristate "Marvell Berlin PWM support" - depends on ARCH_BERLIN + depends on ARCH_BERLIN || COMPILE_TEST help PWM framework driver for Marvell Berlin SoCs. @@ -118,7 +128,7 @@ config PWM_BERLIN config PWM_BRCMSTB tristate "Broadcom STB PWM support" - depends on ARCH_BRCMSTB || BMIPS_GENERIC + depends on ARCH_BRCMSTB || BMIPS_GENERIC || COMPILE_TEST help Generic PWM framework driver for the Broadcom Set-top-Box SoCs (BCM7xxx). @@ -152,7 +162,7 @@ config PWM_CROS_EC config PWM_EP93XX tristate "Cirrus Logic EP93xx PWM support" - depends on ARCH_EP93XX + depends on ARCH_EP93XX || COMPILE_TEST help Generic PWM framework driver for Cirrus Logic EP93xx. @@ -195,7 +205,7 @@ config PWM_IMG config PWM_IMX1 tristate "i.MX1 PWM support" - depends on ARCH_MXC + depends on ARCH_MXC || COMPILE_TEST help Generic PWM framework driver for i.MX1 and i.MX21 @@ -204,7 +214,7 @@ config PWM_IMX1 config PWM_IMX27 tristate "i.MX27 PWM support" - depends on ARCH_MXC + depends on ARCH_MXC || COMPILE_TEST help Generic PWM framework driver for i.MX27 and later i.MX SoCs. @@ -225,6 +235,8 @@ config PWM_IMX_TPM config PWM_JZ4740 tristate "Ingenic JZ47xx PWM support" depends on MACH_INGENIC + depends on COMMON_CLK + select MFD_SYSCON help Generic PWM framework driver for Ingenic JZ47xx based machines. @@ -244,7 +256,7 @@ config PWM_LP3943 config PWM_LPC18XX_SCT tristate "LPC18xx/43xx PWM/SCT support" - depends on ARCH_LPC18XX + depends on ARCH_LPC18XX || COMPILE_TEST help Generic PWM framework driver for NXP LPC18xx PWM/SCT which supports 16 channels. @@ -256,7 +268,7 @@ config PWM_LPC18XX_SCT config PWM_LPC32XX tristate "LPC32XX PWM support" - depends on ARCH_LPC32XX + depends on ARCH_LPC32XX || COMPILE_TEST help Generic PWM framework driver for LPC32XX. The LPC32XX SOC has two PWM controllers. @@ -289,7 +301,8 @@ config PWM_LPSS_PLATFORM config PWM_MESON tristate "Amlogic Meson PWM driver" - depends on ARCH_MESON + depends on ARCH_MESON || COMPILE_TEST + depends on COMMON_CLK help The platform driver for Amlogic Meson PWM controller. @@ -318,7 +331,8 @@ config PWM_MEDIATEK config PWM_MXS tristate "Freescale MXS PWM support" - depends on ARCH_MXS && OF + depends on OF + depends on ARCH_MXS || COMPILE_TEST select STMP_DEVICE help Generic PWM framework driver for Freescale MXS. @@ -357,7 +371,7 @@ config PWM_PUV3 config PWM_PXA tristate "PXA PWM support" - depends on ARCH_PXA + depends on ARCH_PXA || COMPILE_TEST help Generic PWM framework driver for PXA. @@ -388,14 +402,14 @@ config PWM_RENESAS_TPU config PWM_ROCKCHIP tristate "Rockchip PWM support" - depends on ARCH_ROCKCHIP + depends on ARCH_ROCKCHIP || COMPILE_TEST help Generic PWM framework driver for the PWM controller found on Rockchip SoCs. config PWM_SAMSUNG tristate "Samsung PWM support" - depends on PLAT_SAMSUNG || ARCH_EXYNOS + depends on PLAT_SAMSUNG || ARCH_EXYNOS || COMPILE_TEST help Generic PWM framework driver for Samsung. @@ -415,7 +429,7 @@ config PWM_SIFIVE config PWM_SPEAR tristate "STMicroelectronics SPEAr PWM support" - depends on PLAT_SPEAR + depends on PLAT_SPEAR || COMPILE_TEST depends on OF help Generic PWM framework driver for the PWM controller on ST @@ -437,7 +451,7 @@ config PWM_SPRD config PWM_STI tristate "STiH4xx PWM support" - depends on ARCH_STI + depends on ARCH_STI || COMPILE_TEST depends on OF help Generic PWM framework driver for STiH4xx SoCs. @@ -447,7 +461,7 @@ config PWM_STI config PWM_STM32 tristate "STMicroelectronics STM32 PWM" - depends on MFD_STM32_TIMERS + depends on MFD_STM32_TIMERS || COMPILE_TEST help Generic PWM framework driver for STM32 SoCs. @@ -483,7 +497,7 @@ config PWM_SUN4I config PWM_TEGRA tristate "NVIDIA Tegra PWM support" - depends on ARCH_TEGRA + depends on ARCH_TEGRA || COMPILE_TEST help Generic PWM framework driver for the PWFM controller found on NVIDIA Tegra SoCs. @@ -493,7 +507,7 @@ config PWM_TEGRA config PWM_TIECAP tristate "ECAP PWM support" - depends on ARCH_OMAP2PLUS || ARCH_DAVINCI_DA8XX || ARCH_KEYSTONE || ARCH_K3 + depends on ARCH_OMAP2PLUS || ARCH_DAVINCI_DA8XX || ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST help PWM driver support for the ECAP APWM controller found on TI SOCs @@ -502,7 +516,7 @@ config PWM_TIECAP config PWM_TIEHRPWM tristate "EHRPWM PWM support" - depends on ARCH_OMAP2PLUS || ARCH_DAVINCI_DA8XX || ARCH_K3 + depends on ARCH_OMAP2PLUS || ARCH_DAVINCI_DA8XX || ARCH_K3 || COMPILE_TEST help PWM driver support for the EHRPWM controller found on TI SOCs @@ -529,7 +543,7 @@ config PWM_TWL_LED config PWM_VT8500 tristate "vt8500 PWM support" - depends on ARCH_VT8500 + depends on ARCH_VT8500 || COMPILE_TEST help Generic PWM framework driver for vt8500. @@ -538,7 +552,7 @@ config PWM_VT8500 config PWM_ZX tristate "ZTE ZX PWM support" - depends on ARCH_ZX + depends on ARCH_ZX || COMPILE_TEST help Generic PWM framework driver for ZTE ZX family SoCs. diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 5a7f6598c05f..9973c442b455 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -120,6 +120,9 @@ static int pwm_device_request(struct pwm_device *pwm, const char *label) if (pwm->chip->ops->get_state) { pwm->chip->ops->get_state(pwm->chip, pwm, &pwm->state); trace_pwm_get(pwm, &pwm->state); + + if (IS_ENABLED(PWM_DEBUG)) + pwm->last = pwm->state; } set_bit(PWMF_REQUESTED, &pwm->flags); @@ -232,17 +235,28 @@ void *pwm_get_chip_data(struct pwm_device *pwm) } EXPORT_SYMBOL_GPL(pwm_get_chip_data); -static bool pwm_ops_check(const struct pwm_ops *ops) +static bool pwm_ops_check(const struct pwm_chip *chip) { + + const struct pwm_ops *ops = chip->ops; + /* driver supports legacy, non-atomic operation */ - if (ops->config && ops->enable && ops->disable) - return true; + if (ops->config && ops->enable && ops->disable) { + if (IS_ENABLED(CONFIG_PWM_DEBUG)) + dev_warn(chip->dev, + "Driver needs updating to atomic API\n"); - /* driver supports atomic operation */ - if (ops->apply) return true; + } - return false; + if (!ops->apply) + return false; + + if (IS_ENABLED(CONFIG_PWM_DEBUG) && !ops->get_state) + dev_warn(chip->dev, + "Please implement the .get_state() callback\n"); + + return true; } /** @@ -266,7 +280,7 @@ int pwmchip_add_with_polarity(struct pwm_chip *chip, if (!chip || !chip->dev || !chip->ops || !chip->npwm) return -EINVAL; - if (!pwm_ops_check(chip->ops)) + if (!pwm_ops_check(chip)) return -EINVAL; mutex_lock(&pwm_lock); @@ -450,6 +464,107 @@ void pwm_free(struct pwm_device *pwm) } EXPORT_SYMBOL_GPL(pwm_free); +static void pwm_apply_state_debug(struct pwm_device *pwm, + const struct pwm_state *state) +{ + struct pwm_state *last = &pwm->last; + struct pwm_chip *chip = pwm->chip; + struct pwm_state s1, s2; + int err; + + if (!IS_ENABLED(CONFIG_PWM_DEBUG)) + return; + + /* No reasonable diagnosis possible without .get_state() */ + if (!chip->ops->get_state) + return; + + /* + * *state was just applied. Read out the hardware state and do some + * checks. + */ + + chip->ops->get_state(chip, pwm, &s1); + trace_pwm_get(pwm, &s1); + + /* + * The lowlevel driver either ignored .polarity (which is a bug) or as + * best effort inverted .polarity and fixed .duty_cycle respectively. + * Undo this inversion and fixup for further tests. + */ + if (s1.enabled && s1.polarity != state->polarity) { + s2.polarity = state->polarity; + s2.duty_cycle = s1.period - s1.duty_cycle; + s2.period = s1.period; + s2.enabled = s1.enabled; + } else { + s2 = s1; + } + + if (s2.polarity != state->polarity && + state->duty_cycle < state->period) + dev_warn(chip->dev, ".apply ignored .polarity\n"); + + if (state->enabled && + last->polarity == state->polarity && + last->period > s2.period && + last->period <= state->period) + dev_warn(chip->dev, + ".apply didn't pick the best available period (requested: %u, applied: %u, possible: %u)\n", + state->period, s2.period, last->period); + + if (state->enabled && state->period < s2.period) + dev_warn(chip->dev, + ".apply is supposed to round down period (requested: %u, applied: %u)\n", + state->period, s2.period); + + if (state->enabled && + last->polarity == state->polarity && + last->period == s2.period && + last->duty_cycle > s2.duty_cycle && + last->duty_cycle <= state->duty_cycle) + dev_warn(chip->dev, + ".apply didn't pick the best available duty cycle (requested: %u/%u, applied: %u/%u, possible: %u/%u)\n", + state->duty_cycle, state->period, + s2.duty_cycle, s2.period, + last->duty_cycle, last->period); + + if (state->enabled && state->duty_cycle < s2.duty_cycle) + dev_warn(chip->dev, + ".apply is supposed to round down duty_cycle (requested: %u/%u, applied: %u/%u)\n", + state->duty_cycle, state->period, + s2.duty_cycle, s2.period); + + if (!state->enabled && s2.enabled && s2.duty_cycle > 0) + dev_warn(chip->dev, + "requested disabled, but yielded enabled with duty > 0"); + + /* reapply the state that the driver reported being configured. */ + err = chip->ops->apply(chip, pwm, &s1); + if (err) { + *last = s1; + dev_err(chip->dev, "failed to reapply current setting\n"); + return; + } + + trace_pwm_apply(pwm, &s1); + + chip->ops->get_state(chip, pwm, last); + trace_pwm_get(pwm, last); + + /* reapplication of the current state should give an exact match */ + if (s1.enabled != last->enabled || + s1.polarity != last->polarity || + (s1.enabled && s1.period != last->period) || + (s1.enabled && s1.duty_cycle != last->duty_cycle)) { + dev_err(chip->dev, + ".apply is not idempotent (ena=%d pol=%d %u/%u) -> (ena=%d pol=%d %u/%u)\n", + s1.enabled, s1.polarity, s1.duty_cycle, s1.period, + last->enabled, last->polarity, last->duty_cycle, + last->period); + } +} + /** * pwm_apply_state() - atomically apply a new state to a PWM device * @pwm: PWM device @@ -480,6 +595,12 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state) trace_pwm_apply(pwm, state); pwm->state = *state; + + /* + * only do this after pwm->state was applied as some + * implementations of .get_state depend on this + */ + pwm_apply_state_debug(pwm, state); } else { /* * FIXME: restore the initial state in case of error. diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c index 91e24f01b54e..d78f86f8e462 100644 --- a/drivers/pwm/pwm-bcm2835.c +++ b/drivers/pwm/pwm-bcm2835.c @@ -166,6 +166,7 @@ static int bcm2835_pwm_probe(struct platform_device *pdev) pc->chip.dev = &pdev->dev; pc->chip.ops = &bcm2835_pwm_ops; + pc->chip.base = -1; pc->chip.npwm = 2; pc->chip.of_xlate = of_pwm_xlate_with_flags; pc->chip.of_pwm_n_cells = 3; diff --git a/drivers/pwm/pwm-imx-tpm.c b/drivers/pwm/pwm-imx-tpm.c index 9145f6160649..5f3d7f7e6aef 100644 --- a/drivers/pwm/pwm-imx-tpm.c +++ b/drivers/pwm/pwm-imx-tpm.c @@ -18,10 +18,8 @@ #include <linux/clk.h> #include <linux/err.h> #include <linux/io.h> -#include <linux/log2.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_address.h> #include <linux/platform_device.h> #include <linux/pwm.h> #include <linux/slab.h> diff --git a/drivers/pwm/pwm-imx27.c b/drivers/pwm/pwm-imx27.c index 35a7ac42269c..a6e40d4c485f 100644 --- a/drivers/pwm/pwm-imx27.c +++ b/drivers/pwm/pwm-imx27.c @@ -18,7 +18,6 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/pwm.h> #include <linux/slab.h> @@ -96,9 +95,8 @@ struct pwm_imx27_chip { #define to_pwm_imx27_chip(chip) container_of(chip, struct pwm_imx27_chip, chip) -static int pwm_imx27_clk_prepare_enable(struct pwm_chip *chip) +static int pwm_imx27_clk_prepare_enable(struct pwm_imx27_chip *imx) { - struct pwm_imx27_chip *imx = to_pwm_imx27_chip(chip); int ret; ret = clk_prepare_enable(imx->clk_ipg); @@ -114,10 +112,8 @@ static int pwm_imx27_clk_prepare_enable(struct pwm_chip *chip) return 0; } -static void pwm_imx27_clk_disable_unprepare(struct pwm_chip *chip) +static void pwm_imx27_clk_disable_unprepare(struct pwm_imx27_chip *imx) { - struct pwm_imx27_chip *imx = to_pwm_imx27_chip(chip); - clk_disable_unprepare(imx->clk_per); clk_disable_unprepare(imx->clk_ipg); } @@ -130,7 +126,7 @@ static void pwm_imx27_get_state(struct pwm_chip *chip, u64 tmp; int ret; - ret = pwm_imx27_clk_prepare_enable(chip); + ret = pwm_imx27_clk_prepare_enable(imx); if (ret < 0) return; @@ -174,8 +170,7 @@ static void pwm_imx27_get_state(struct pwm_chip *chip, tmp = NSEC_PER_SEC * (u64)(val); state->duty_cycle = DIV_ROUND_CLOSEST_ULL(tmp, pwm_clk); - if (!state->enabled) - pwm_imx27_clk_disable_unprepare(chip); + pwm_imx27_clk_disable_unprepare(imx); } static void pwm_imx27_sw_reset(struct pwm_chip *chip) @@ -259,7 +254,7 @@ static int pwm_imx27_apply(struct pwm_chip *chip, struct pwm_device *pwm, if (cstate.enabled) { pwm_imx27_wait_fifo_slot(chip, pwm); } else { - ret = pwm_imx27_clk_prepare_enable(chip); + ret = pwm_imx27_clk_prepare_enable(imx); if (ret) return ret; @@ -289,8 +284,8 @@ static int pwm_imx27_apply(struct pwm_chip *chip, struct pwm_device *pwm, writel(cr, imx->mmio_base + MX3_PWMCR); - if (!state->enabled && cstate.enabled) - pwm_imx27_clk_disable_unprepare(chip); + if (!state->enabled) + pwm_imx27_clk_disable_unprepare(imx); return 0; } @@ -310,6 +305,8 @@ MODULE_DEVICE_TABLE(of, pwm_imx27_dt_ids); static int pwm_imx27_probe(struct platform_device *pdev) { struct pwm_imx27_chip *imx; + int ret; + u32 pwmcr; imx = devm_kzalloc(&pdev->dev, sizeof(*imx), GFP_KERNEL); if (imx == NULL) @@ -352,6 +349,15 @@ static int pwm_imx27_probe(struct platform_device *pdev) if (IS_ERR(imx->mmio_base)) return PTR_ERR(imx->mmio_base); + ret = pwm_imx27_clk_prepare_enable(imx); + if (ret) + return ret; + + /* keep clks on if pwm is running */ + pwmcr = readl(imx->mmio_base + MX3_PWMCR); + if (!(pwmcr & MX3_PWMCR_EN)) + pwm_imx27_clk_disable_unprepare(imx); + return pwmchip_add(&imx->chip); } @@ -361,8 +367,6 @@ static int pwm_imx27_remove(struct platform_device *pdev) imx = platform_get_drvdata(pdev); - pwm_imx27_clk_disable_unprepare(&imx->chip); - return pwmchip_remove(&imx->chip); } diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c index 9d78cc21cb12..3cd5c054ad9a 100644 --- a/drivers/pwm/pwm-jz4740.c +++ b/drivers/pwm/pwm-jz4740.c @@ -13,18 +13,19 @@ #include <linux/err.h> #include <linux/gpio.h> #include <linux/kernel.h> +#include <linux/mfd/ingenic-tcu.h> +#include <linux/mfd/syscon.h> #include <linux/module.h> #include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/pwm.h> - -#include <asm/mach-jz4740/timer.h> +#include <linux/regmap.h> #define NUM_PWM 8 struct jz4740_pwm_chip { struct pwm_chip chip; - struct clk *clk; + struct regmap *map; }; static inline struct jz4740_pwm_chip *to_jz4740(struct pwm_chip *chip) @@ -32,82 +33,134 @@ static inline struct jz4740_pwm_chip *to_jz4740(struct pwm_chip *chip) return container_of(chip, struct jz4740_pwm_chip, chip); } +static bool jz4740_pwm_can_use_chn(struct jz4740_pwm_chip *jz, + unsigned int channel) +{ + /* Enable all TCU channels for PWM use by default except channels 0/1 */ + u32 pwm_channels_mask = GENMASK(NUM_PWM - 1, 2); + + device_property_read_u32(jz->chip.dev->parent, + "ingenic,pwm-channels-mask", + &pwm_channels_mask); + + return !!(pwm_channels_mask & BIT(channel)); +} + static int jz4740_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) { - /* - * Timers 0 and 1 are used for system tasks, so they are unavailable - * for use as PWMs. - */ - if (pwm->hwpwm < 2) + struct jz4740_pwm_chip *jz = to_jz4740(chip); + struct clk *clk; + char name[16]; + int err; + + if (!jz4740_pwm_can_use_chn(jz, pwm->hwpwm)) return -EBUSY; - jz4740_timer_start(pwm->hwpwm); + snprintf(name, sizeof(name), "timer%u", pwm->hwpwm); + + clk = clk_get(chip->dev, name); + if (IS_ERR(clk)) { + if (PTR_ERR(clk) != -EPROBE_DEFER) + dev_err(chip->dev, "Failed to get clock: %pe", clk); + + return PTR_ERR(clk); + } + + err = clk_prepare_enable(clk); + if (err < 0) { + clk_put(clk); + return err; + } + + pwm_set_chip_data(pwm, clk); return 0; } static void jz4740_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm) { - jz4740_timer_set_ctrl(pwm->hwpwm, 0); + struct clk *clk = pwm_get_chip_data(pwm); - jz4740_timer_stop(pwm->hwpwm); + clk_disable_unprepare(clk); + clk_put(clk); } static int jz4740_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm) { - uint32_t ctrl = jz4740_timer_get_ctrl(pwm->pwm); + struct jz4740_pwm_chip *jz = to_jz4740(chip); + + /* Enable PWM output */ + regmap_update_bits(jz->map, TCU_REG_TCSRc(pwm->hwpwm), + TCU_TCSR_PWM_EN, TCU_TCSR_PWM_EN); - ctrl |= JZ_TIMER_CTRL_PWM_ENABLE; - jz4740_timer_set_ctrl(pwm->hwpwm, ctrl); - jz4740_timer_enable(pwm->hwpwm); + /* Start counter */ + regmap_write(jz->map, TCU_REG_TESR, BIT(pwm->hwpwm)); return 0; } static void jz4740_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm) { - uint32_t ctrl = jz4740_timer_get_ctrl(pwm->hwpwm); + struct jz4740_pwm_chip *jz = to_jz4740(chip); /* * Set duty > period. This trick allows the TCU channels in TCU2 mode to * properly return to their init level. */ - jz4740_timer_set_duty(pwm->hwpwm, 0xffff); - jz4740_timer_set_period(pwm->hwpwm, 0x0); + regmap_write(jz->map, TCU_REG_TDHRc(pwm->hwpwm), 0xffff); + regmap_write(jz->map, TCU_REG_TDFRc(pwm->hwpwm), 0x0); /* * Disable PWM output. * In TCU2 mode (channel 1/2 on JZ4750+), this must be done before the * counter is stopped, while in TCU1 mode the order does not matter. */ - ctrl &= ~JZ_TIMER_CTRL_PWM_ENABLE; - jz4740_timer_set_ctrl(pwm->hwpwm, ctrl); + regmap_update_bits(jz->map, TCU_REG_TCSRc(pwm->hwpwm), + TCU_TCSR_PWM_EN, 0); /* Stop counter */ - jz4740_timer_disable(pwm->hwpwm); + regmap_write(jz->map, TCU_REG_TECR, BIT(pwm->hwpwm)); } static int jz4740_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { struct jz4740_pwm_chip *jz4740 = to_jz4740(pwm->chip); - unsigned long long tmp; + unsigned long long tmp = 0xffffull * NSEC_PER_SEC; + struct clk *clk = pwm_get_chip_data(pwm); unsigned long period, duty; - unsigned int prescaler = 0; - uint16_t ctrl; + long rate; + int err; - tmp = (unsigned long long)clk_get_rate(jz4740->clk) * state->period; - do_div(tmp, 1000000000); - period = tmp; + /* + * Limit the clock to a maximum rate that still gives us a period value + * which fits in 16 bits. + */ + do_div(tmp, state->period); - while (period > 0xffff && prescaler < 6) { - period >>= 2; - ++prescaler; + /* + * /!\ IMPORTANT NOTE: + * ------------------- + * This code relies on the fact that clk_round_rate() will always round + * down, which is not a valid assumption given by the clk API, but only + * happens to be true with the clk drivers used for Ingenic SoCs. + * + * Right now, there is no alternative as the clk API does not have a + * round-down function (and won't have one for a while), but if it ever + * comes to light, a round-down function should be used instead. + */ + rate = clk_round_rate(clk, tmp); + if (rate < 0) { + dev_err(chip->dev, "Unable to round rate: %ld", rate); + return rate; } - if (prescaler == 6) - return -EINVAL; + /* Calculate period value */ + tmp = (unsigned long long)rate * state->period; + do_div(tmp, NSEC_PER_SEC); + period = (unsigned long)tmp; + /* Calculate duty value */ tmp = (unsigned long long)period * state->duty_cycle; do_div(tmp, state->period); duty = period - tmp; @@ -117,26 +170,38 @@ static int jz4740_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, jz4740_pwm_disable(chip, pwm); - jz4740_timer_set_count(pwm->hwpwm, 0); - jz4740_timer_set_duty(pwm->hwpwm, duty); - jz4740_timer_set_period(pwm->hwpwm, period); + err = clk_set_rate(clk, rate); + if (err) { + dev_err(chip->dev, "Unable to set rate: %d", err); + return err; + } + + /* Reset counter to 0 */ + regmap_write(jz4740->map, TCU_REG_TCNTc(pwm->hwpwm), 0); - ctrl = JZ_TIMER_CTRL_PRESCALER(prescaler) | JZ_TIMER_CTRL_SRC_EXT | - JZ_TIMER_CTRL_PWM_ABBRUPT_SHUTDOWN; + /* Set duty */ + regmap_write(jz4740->map, TCU_REG_TDHRc(pwm->hwpwm), duty); - jz4740_timer_set_ctrl(pwm->hwpwm, ctrl); + /* Set period */ + regmap_write(jz4740->map, TCU_REG_TDFRc(pwm->hwpwm), period); + /* Set abrupt shutdown */ + regmap_update_bits(jz4740->map, TCU_REG_TCSRc(pwm->hwpwm), + TCU_TCSR_PWM_SD, TCU_TCSR_PWM_SD); + + /* Set polarity */ switch (state->polarity) { case PWM_POLARITY_NORMAL: - ctrl &= ~JZ_TIMER_CTRL_PWM_ACTIVE_LOW; + regmap_update_bits(jz4740->map, TCU_REG_TCSRc(pwm->hwpwm), + TCU_TCSR_PWM_INITL_HIGH, 0); break; case PWM_POLARITY_INVERSED: - ctrl |= JZ_TIMER_CTRL_PWM_ACTIVE_LOW; + regmap_update_bits(jz4740->map, TCU_REG_TCSRc(pwm->hwpwm), + TCU_TCSR_PWM_INITL_HIGH, + TCU_TCSR_PWM_INITL_HIGH); break; } - jz4740_timer_set_ctrl(pwm->hwpwm, ctrl); - if (state->enabled) jz4740_pwm_enable(chip, pwm); @@ -152,17 +217,20 @@ static const struct pwm_ops jz4740_pwm_ops = { static int jz4740_pwm_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; struct jz4740_pwm_chip *jz4740; - jz4740 = devm_kzalloc(&pdev->dev, sizeof(*jz4740), GFP_KERNEL); + jz4740 = devm_kzalloc(dev, sizeof(*jz4740), GFP_KERNEL); if (!jz4740) return -ENOMEM; - jz4740->clk = devm_clk_get(&pdev->dev, "ext"); - if (IS_ERR(jz4740->clk)) - return PTR_ERR(jz4740->clk); + jz4740->map = device_node_to_regmap(dev->parent->of_node); + if (IS_ERR(jz4740->map)) { + dev_err(dev, "regmap not found: %ld\n", PTR_ERR(jz4740->map)); + return PTR_ERR(jz4740->map); + } - jz4740->chip.dev = &pdev->dev; + jz4740->chip.dev = dev; jz4740->chip.ops = &jz4740_pwm_ops; jz4740->chip.npwm = NUM_PWM; jz4740->chip.base = -1; diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 6245bbdb6e6c..bd0d7336b898 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -136,7 +136,7 @@ static int meson_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) dev_err(dev, "failed to set parent %s for %s: %d\n", __clk_get_name(channel->clk_parent), __clk_get_name(channel->clk), err); - return err; + return err; } } @@ -163,7 +163,7 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm, { struct meson_pwm_channel *channel = pwm_get_chip_data(pwm); unsigned int duty, period, pre_div, cnt, duty_cnt; - unsigned long fin_freq = -1; + unsigned long fin_freq; duty = state->duty_cycle; period = state->period; diff --git a/drivers/pwm/pwm-mxs.c b/drivers/pwm/pwm-mxs.c index f2e57fcf8f8b..7ce616923c52 100644 --- a/drivers/pwm/pwm-mxs.c +++ b/drivers/pwm/pwm-mxs.c @@ -9,7 +9,6 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_address.h> #include <linux/platform_device.h> #include <linux/pwm.h> #include <linux/slab.h> diff --git a/drivers/pwm/pwm-omap-dmtimer.c b/drivers/pwm/pwm-omap-dmtimer.c index 9e4378dc6897..0d31833db2e2 100644 --- a/drivers/pwm/pwm-omap-dmtimer.c +++ b/drivers/pwm/pwm-omap-dmtimer.c @@ -10,7 +10,27 @@ * * Description: * This file is the core OMAP support for the generic, Linux - * PWM driver / controller, using the OMAP's dual-mode timers. + * PWM driver / controller, using the OMAP's dual-mode timers + * with a timer counter that goes up. When it overflows it gets + * reloaded with the load value and the pwm output goes up. + * When counter matches with match register, the output goes down. + * Reference Manual: http://www.ti.com/lit/ug/spruh73q/spruh73q.pdf + * + * Limitations: + * - When PWM is stopped, timer counter gets stopped immediately. This + * doesn't allow the current PWM period to complete and stops abruptly. + * - When PWM is running and changing both duty cycle and period, + * we cannot prevent in software that the output might produce + * a period with mixed settings. Especially when period/duty_cyle + * is updated while the pwm pin is high, current pwm period/duty_cycle + * can get updated as below based on the current timer counter: + * - period for current cycle = current_period + new period + * - duty_cycle for current period = current period + new duty_cycle. + * - PWM OMAP DM timer cannot change the polarity when pwm is active. When + * user requests a change in polarity when in active state: + * - PWM is stopped abruptly(without completing the current cycle) + * - Polarity is changed + * - A fresh cycle is started. */ #include <linux/clk.h> @@ -20,8 +40,8 @@ #include <linux/mutex.h> #include <linux/of.h> #include <linux/of_platform.h> +#include <clocksource/timer-ti-dm.h> #include <linux/platform_data/dmtimer-omap.h> -#include <linux/platform_data/pwm_omap_dmtimer.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/pwm.h> @@ -31,10 +51,20 @@ #define DM_TIMER_LOAD_MIN 0xfffffffe #define DM_TIMER_MAX 0xffffffff +/** + * struct pwm_omap_dmtimer_chip - Structure representing a pwm chip + * corresponding to omap dmtimer. + * @chip: PWM chip structure representing PWM controller + * @mutex: Mutex to protect pwm apply state + * @dm_timer: Pointer to omap dm timer. + * @pdata: Pointer to omap dm timer ops. + * dm_timer_pdev: Pointer to omap dm timer platform device + */ struct pwm_omap_dmtimer_chip { struct pwm_chip chip; + /* Mutex to protect pwm apply state */ struct mutex mutex; - pwm_omap_dmtimer *dm_timer; + struct omap_dm_timer *dm_timer; const struct omap_dm_timer_ops *pdata; struct platform_device *dm_timer_pdev; }; @@ -45,11 +75,22 @@ to_pwm_omap_dmtimer_chip(struct pwm_chip *chip) return container_of(chip, struct pwm_omap_dmtimer_chip, chip); } +/** + * pwm_omap_dmtimer_get_clock_cycles() - Get clock cycles in a time frame + * @clk_rate: pwm timer clock rate + * @ns: time frame in nano seconds. + * + * Return number of clock cycles in a given period(ins ns). + */ static u32 pwm_omap_dmtimer_get_clock_cycles(unsigned long clk_rate, int ns) { return DIV_ROUND_CLOSEST_ULL((u64)clk_rate * ns, NSEC_PER_SEC); } +/** + * pwm_omap_dmtimer_start() - Start the pwm omap dm timer in pwm mode + * @omap: Pointer to pwm omap dm timer chip + */ static void pwm_omap_dmtimer_start(struct pwm_omap_dmtimer_chip *omap) { /* @@ -67,28 +108,46 @@ static void pwm_omap_dmtimer_start(struct pwm_omap_dmtimer_chip *omap) omap->pdata->start(omap->dm_timer); } -static int pwm_omap_dmtimer_enable(struct pwm_chip *chip, - struct pwm_device *pwm) +/** + * pwm_omap_dmtimer_is_enabled() - Detect if the pwm is enabled. + * @omap: Pointer to pwm omap dm timer chip + * + * Return true if pwm is enabled else false. + */ +static bool pwm_omap_dmtimer_is_enabled(struct pwm_omap_dmtimer_chip *omap) { - struct pwm_omap_dmtimer_chip *omap = to_pwm_omap_dmtimer_chip(chip); + u32 status; - mutex_lock(&omap->mutex); - pwm_omap_dmtimer_start(omap); - mutex_unlock(&omap->mutex); + status = omap->pdata->get_pwm_status(omap->dm_timer); - return 0; + return !!(status & OMAP_TIMER_CTRL_ST); } -static void pwm_omap_dmtimer_disable(struct pwm_chip *chip, - struct pwm_device *pwm) +/** + * pwm_omap_dmtimer_polarity() - Detect the polarity of pwm. + * @omap: Pointer to pwm omap dm timer chip + * + * Return the polarity of pwm. + */ +static int pwm_omap_dmtimer_polarity(struct pwm_omap_dmtimer_chip *omap) { - struct pwm_omap_dmtimer_chip *omap = to_pwm_omap_dmtimer_chip(chip); + u32 status; - mutex_lock(&omap->mutex); - omap->pdata->stop(omap->dm_timer); - mutex_unlock(&omap->mutex); + status = omap->pdata->get_pwm_status(omap->dm_timer); + + return !!(status & OMAP_TIMER_CTRL_SCPWM); } +/** + * pwm_omap_dmtimer_config() - Update the configuration of pwm omap dm timer + * @chip: Pointer to PWM controller + * @pwm: Pointer to PWM channel + * @duty_ns: New duty cycle in nano seconds + * @period_ns: New period in nano seconds + * + * Return 0 if successfully changed the period/duty_cycle else appropriate + * error. + */ static int pwm_omap_dmtimer_config(struct pwm_chip *chip, struct pwm_device *pwm, int duty_ns, int period_ns) @@ -96,31 +155,26 @@ static int pwm_omap_dmtimer_config(struct pwm_chip *chip, struct pwm_omap_dmtimer_chip *omap = to_pwm_omap_dmtimer_chip(chip); u32 period_cycles, duty_cycles; u32 load_value, match_value; - struct clk *fclk; unsigned long clk_rate; - bool timer_active; + struct clk *fclk; dev_dbg(chip->dev, "requested duty cycle: %d ns, period: %d ns\n", duty_ns, period_ns); - mutex_lock(&omap->mutex); if (duty_ns == pwm_get_duty_cycle(pwm) && - period_ns == pwm_get_period(pwm)) { - /* No change - don't cause any transients. */ - mutex_unlock(&omap->mutex); + period_ns == pwm_get_period(pwm)) return 0; - } fclk = omap->pdata->get_fclk(omap->dm_timer); if (!fclk) { dev_err(chip->dev, "invalid pmtimer fclk\n"); - goto err_einval; + return -EINVAL; } clk_rate = clk_get_rate(fclk); if (!clk_rate) { dev_err(chip->dev, "invalid pmtimer fclk rate\n"); - goto err_einval; + return -EINVAL; } dev_dbg(chip->dev, "clk rate: %luHz\n", clk_rate); @@ -148,7 +202,7 @@ static int pwm_omap_dmtimer_config(struct pwm_chip *chip, dev_info(chip->dev, "period %d ns too short for clock rate %lu Hz\n", period_ns, clk_rate); - goto err_einval; + return -EINVAL; } if (duty_cycles < 1) { @@ -174,81 +228,103 @@ static int pwm_omap_dmtimer_config(struct pwm_chip *chip, load_value = (DM_TIMER_MAX - period_cycles) + 1; match_value = load_value + duty_cycles - 1; - /* - * We MUST stop the associated dual-mode timer before attempting to - * write its registers, but calls to omap_dm_timer_start/stop must - * be balanced so check if timer is active before calling timer_stop. - */ - timer_active = pm_runtime_active(&omap->dm_timer_pdev->dev); - if (timer_active) - omap->pdata->stop(omap->dm_timer); - omap->pdata->set_load(omap->dm_timer, load_value); omap->pdata->set_match(omap->dm_timer, true, match_value); dev_dbg(chip->dev, "load value: %#08x (%d), match value: %#08x (%d)\n", load_value, load_value, match_value, match_value); - omap->pdata->set_pwm(omap->dm_timer, - pwm_get_polarity(pwm) == PWM_POLARITY_INVERSED, - true, - PWM_OMAP_DMTIMER_TRIGGER_OVERFLOW_AND_COMPARE, - true); - - /* If config was called while timer was running it must be reenabled. */ - if (timer_active) - pwm_omap_dmtimer_start(omap); + return 0; +} - mutex_unlock(&omap->mutex); +/** + * pwm_omap_dmtimer_set_polarity() - Changes the polarity of the pwm dm timer. + * @chip: Pointer to PWM controller + * @pwm: Pointer to PWM channel + * @polarity: New pwm polarity to be set + */ +static void pwm_omap_dmtimer_set_polarity(struct pwm_chip *chip, + struct pwm_device *pwm, + enum pwm_polarity polarity) +{ + struct pwm_omap_dmtimer_chip *omap = to_pwm_omap_dmtimer_chip(chip); + bool enabled; - return 0; + /* Disable the PWM before changing the polarity. */ + enabled = pwm_omap_dmtimer_is_enabled(omap); + if (enabled) + omap->pdata->stop(omap->dm_timer); -err_einval: - mutex_unlock(&omap->mutex); + omap->pdata->set_pwm(omap->dm_timer, + polarity == PWM_POLARITY_INVERSED, + true, OMAP_TIMER_TRIGGER_OVERFLOW_AND_COMPARE, + true); - return -EINVAL; + if (enabled) + pwm_omap_dmtimer_start(omap); } -static int pwm_omap_dmtimer_set_polarity(struct pwm_chip *chip, - struct pwm_device *pwm, - enum pwm_polarity polarity) +/** + * pwm_omap_dmtimer_apply() - Changes the state of the pwm omap dm timer. + * @chip: Pointer to PWM controller + * @pwm: Pointer to PWM channel + * @state: New state to apply + * + * Return 0 if successfully changed the state else appropriate error. + */ +static int pwm_omap_dmtimer_apply(struct pwm_chip *chip, + struct pwm_device *pwm, + const struct pwm_state *state) { struct pwm_omap_dmtimer_chip *omap = to_pwm_omap_dmtimer_chip(chip); + int ret = 0; - /* - * PWM core will not call set_polarity while PWM is enabled so it's - * safe to reconfigure the timer here without stopping it first. - */ mutex_lock(&omap->mutex); - omap->pdata->set_pwm(omap->dm_timer, - polarity == PWM_POLARITY_INVERSED, - true, - PWM_OMAP_DMTIMER_TRIGGER_OVERFLOW_AND_COMPARE, - true); + + if (pwm_omap_dmtimer_is_enabled(omap) && !state->enabled) { + omap->pdata->stop(omap->dm_timer); + goto unlock_mutex; + } + + if (pwm_omap_dmtimer_polarity(omap) != state->polarity) + pwm_omap_dmtimer_set_polarity(chip, pwm, state->polarity); + + ret = pwm_omap_dmtimer_config(chip, pwm, state->duty_cycle, + state->period); + if (ret) + goto unlock_mutex; + + if (!pwm_omap_dmtimer_is_enabled(omap) && state->enabled) { + omap->pdata->set_pwm(omap->dm_timer, + state->polarity == PWM_POLARITY_INVERSED, + true, + OMAP_TIMER_TRIGGER_OVERFLOW_AND_COMPARE, + true); + pwm_omap_dmtimer_start(omap); + } + +unlock_mutex: mutex_unlock(&omap->mutex); - return 0; + return ret; } static const struct pwm_ops pwm_omap_dmtimer_ops = { - .enable = pwm_omap_dmtimer_enable, - .disable = pwm_omap_dmtimer_disable, - .config = pwm_omap_dmtimer_config, - .set_polarity = pwm_omap_dmtimer_set_polarity, + .apply = pwm_omap_dmtimer_apply, .owner = THIS_MODULE, }; static int pwm_omap_dmtimer_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - struct device_node *timer; - struct platform_device *timer_pdev; - struct pwm_omap_dmtimer_chip *omap; struct dmtimer_platform_data *timer_pdata; const struct omap_dm_timer_ops *pdata; - pwm_omap_dmtimer *dm_timer; - u32 v; + struct platform_device *timer_pdev; + struct pwm_omap_dmtimer_chip *omap; + struct omap_dm_timer *dm_timer; + struct device_node *timer; int ret = 0; + u32 v; timer = of_parse_phandle(np, "ti,timers", 0); if (!timer) @@ -281,6 +357,7 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev) !pdata->set_load || !pdata->set_match || !pdata->set_pwm || + !pdata->get_pwm_status || !pdata->set_prescaler || !pdata->write_counter) { dev_err(&pdev->dev, "Incomplete dmtimer pdata structure\n"); diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c index b07bdca3d510..76cd22bd6614 100644 --- a/drivers/pwm/pwm-pca9685.c +++ b/drivers/pwm/pwm-pca9685.c @@ -20,6 +20,7 @@ #include <linux/slab.h> #include <linux/delay.h> #include <linux/pm_runtime.h> +#include <linux/bitmap.h> /* * Because the PCA9685 has only one prescaler per chip, changing the period of @@ -69,11 +70,11 @@ struct pca9685 { struct pwm_chip chip; struct regmap *regmap; - int duty_ns; int period_ns; #if IS_ENABLED(CONFIG_GPIOLIB) struct mutex lock; struct gpio_chip gpio; + DECLARE_BITMAP(pwms_inuse, PCA9685_MAXCHAN + 1); #endif }; @@ -83,51 +84,51 @@ static inline struct pca9685 *to_pca(struct pwm_chip *chip) } #if IS_ENABLED(CONFIG_GPIOLIB) -static int pca9685_pwm_gpio_request(struct gpio_chip *gpio, unsigned int offset) +static bool pca9685_pwm_test_and_set_inuse(struct pca9685 *pca, int pwm_idx) { - struct pca9685 *pca = gpiochip_get_data(gpio); - struct pwm_device *pwm; + bool is_inuse; mutex_lock(&pca->lock); - - pwm = &pca->chip.pwms[offset]; - - if (pwm->flags & (PWMF_REQUESTED | PWMF_EXPORTED)) { - mutex_unlock(&pca->lock); - return -EBUSY; + if (pwm_idx >= PCA9685_MAXCHAN) { + /* + * "all LEDs" channel: + * pretend already in use if any of the PWMs are requested + */ + if (!bitmap_empty(pca->pwms_inuse, PCA9685_MAXCHAN)) { + is_inuse = true; + goto out; + } + } else { + /* + * regular channel: + * pretend already in use if the "all LEDs" channel is requested + */ + if (test_bit(PCA9685_MAXCHAN, pca->pwms_inuse)) { + is_inuse = true; + goto out; + } } - - pwm_set_chip_data(pwm, (void *)1); - + is_inuse = test_and_set_bit(pwm_idx, pca->pwms_inuse); +out: mutex_unlock(&pca->lock); - pm_runtime_get_sync(pca->chip.dev); - return 0; + return is_inuse; } -static bool pca9685_pwm_is_gpio(struct pca9685 *pca, struct pwm_device *pwm) +static void pca9685_pwm_clear_inuse(struct pca9685 *pca, int pwm_idx) { - bool is_gpio = false; - mutex_lock(&pca->lock); + clear_bit(pwm_idx, pca->pwms_inuse); + mutex_unlock(&pca->lock); +} - if (pwm->hwpwm >= PCA9685_MAXCHAN) { - unsigned int i; - - /* - * Check if any of the GPIOs are requested and in that case - * prevent using the "all LEDs" channel. - */ - for (i = 0; i < pca->gpio.ngpio; i++) - if (gpiochip_is_requested(&pca->gpio, i)) { - is_gpio = true; - break; - } - } else if (pwm_get_chip_data(pwm)) { - is_gpio = true; - } +static int pca9685_pwm_gpio_request(struct gpio_chip *gpio, unsigned int offset) +{ + struct pca9685 *pca = gpiochip_get_data(gpio); - mutex_unlock(&pca->lock); - return is_gpio; + if (pca9685_pwm_test_and_set_inuse(pca, offset)) + return -EBUSY; + pm_runtime_get_sync(pca->chip.dev); + return 0; } static int pca9685_pwm_gpio_get(struct gpio_chip *gpio, unsigned int offset) @@ -162,13 +163,14 @@ static void pca9685_pwm_gpio_free(struct gpio_chip *gpio, unsigned int offset) pca9685_pwm_gpio_set(gpio, offset, 0); pm_runtime_put(pca->chip.dev); + pca9685_pwm_clear_inuse(pca, offset); } static int pca9685_pwm_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) { /* Always out */ - return 0; + return GPIO_LINE_DIRECTION_OUT; } static int pca9685_pwm_gpio_direction_input(struct gpio_chip *gpio, @@ -213,12 +215,17 @@ static int pca9685_pwm_gpio_probe(struct pca9685 *pca) return devm_gpiochip_add_data(dev, &pca->gpio, pca); } #else -static inline bool pca9685_pwm_is_gpio(struct pca9685 *pca, - struct pwm_device *pwm) +static inline bool pca9685_pwm_test_and_set_inuse(struct pca9685 *pca, + int pwm_idx) { return false; } +static inline void +pca9685_pwm_clear_inuse(struct pca9685 *pca, int pwm_idx) +{ +} + static inline int pca9685_pwm_gpio_probe(struct pca9685 *pca) { return 0; @@ -272,8 +279,6 @@ static int pca9685_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, } } - pca->duty_ns = duty_ns; - if (duty_ns < 1) { if (pwm->hwpwm >= PCA9685_MAXCHAN) reg = PCA9685_ALL_LED_OFF_H; @@ -402,7 +407,7 @@ static int pca9685_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) { struct pca9685 *pca = to_pca(chip); - if (pca9685_pwm_is_gpio(pca, pwm)) + if (pca9685_pwm_test_and_set_inuse(pca, pwm->hwpwm)) return -EBUSY; pm_runtime_get_sync(chip->dev); @@ -411,8 +416,11 @@ static int pca9685_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) static void pca9685_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm) { + struct pca9685 *pca = to_pca(chip); + pca9685_pwm_disable(chip, pwm); pm_runtime_put(chip->dev); + pca9685_pwm_clear_inuse(pca, pwm->hwpwm); } static const struct pwm_ops pca9685_pwm_ops = { @@ -449,7 +457,6 @@ static int pca9685_pwm_probe(struct i2c_client *client, ret); return ret; } - pca->duty_ns = 0; pca->period_ns = PCA9685_DEFAULT_PERIOD; i2c_set_clientdata(client, pca); @@ -512,8 +519,7 @@ static int pca9685_pwm_remove(struct i2c_client *client) return 0; } -#ifdef CONFIG_PM -static int pca9685_pwm_runtime_suspend(struct device *dev) +static int __maybe_unused pca9685_pwm_runtime_suspend(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); struct pca9685 *pca = i2c_get_clientdata(client); @@ -522,7 +528,7 @@ static int pca9685_pwm_runtime_suspend(struct device *dev) return 0; } -static int pca9685_pwm_runtime_resume(struct device *dev) +static int __maybe_unused pca9685_pwm_runtime_resume(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); struct pca9685 *pca = i2c_get_clientdata(client); @@ -530,7 +536,6 @@ static int pca9685_pwm_runtime_resume(struct device *dev) pca9685_set_sleep_mode(pca, false); return 0; } -#endif static const struct i2c_device_id pca9685_id[] = { { "pca9685", 0 }, diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c index 2685577b6dd4..7ab9eb6616d9 100644 --- a/drivers/pwm/pwm-rcar.c +++ b/drivers/pwm/pwm-rcar.c @@ -229,24 +229,28 @@ static int rcar_pwm_probe(struct platform_device *pdev) rcar_pwm->chip.base = -1; rcar_pwm->chip.npwm = 1; + pm_runtime_enable(&pdev->dev); + ret = pwmchip_add(&rcar_pwm->chip); if (ret < 0) { dev_err(&pdev->dev, "failed to register PWM chip: %d\n", ret); + pm_runtime_disable(&pdev->dev); return ret; } - pm_runtime_enable(&pdev->dev); - return 0; } static int rcar_pwm_remove(struct platform_device *pdev) { struct rcar_pwm_chip *rcar_pwm = platform_get_drvdata(pdev); + int ret; + + ret = pwmchip_remove(&rcar_pwm->chip); pm_runtime_disable(&pdev->dev); - return pwmchip_remove(&rcar_pwm->chip); + return ret; } static const struct of_device_id rcar_pwm_of_table[] = { diff --git a/drivers/pwm/pwm-renesas-tpu.c b/drivers/pwm/pwm-renesas-tpu.c index 4a855a21b782..81ad5a551455 100644 --- a/drivers/pwm/pwm-renesas-tpu.c +++ b/drivers/pwm/pwm-renesas-tpu.c @@ -415,16 +415,15 @@ static int tpu_probe(struct platform_device *pdev) tpu->chip.base = -1; tpu->chip.npwm = TPU_CHANNEL_MAX; + pm_runtime_enable(&pdev->dev); + ret = pwmchip_add(&tpu->chip); if (ret < 0) { dev_err(&pdev->dev, "failed to register PWM chip\n"); + pm_runtime_disable(&pdev->dev); return ret; } - dev_info(&pdev->dev, "TPU PWM %d registered\n", tpu->pdev->id); - - pm_runtime_enable(&pdev->dev); - return 0; } @@ -434,12 +433,10 @@ static int tpu_remove(struct platform_device *pdev) int ret; ret = pwmchip_remove(&tpu->chip); - if (ret) - return ret; pm_runtime_disable(&pdev->dev); - return 0; + return ret; } #ifdef CONFIG_OF diff --git a/drivers/pwm/pwm-sun4i.c b/drivers/pwm/pwm-sun4i.c index 3e3efa6c768f..5c677c563349 100644 --- a/drivers/pwm/pwm-sun4i.c +++ b/drivers/pwm/pwm-sun4i.c @@ -90,7 +90,6 @@ struct sun4i_pwm_chip { spinlock_t ctrl_lock; const struct sun4i_pwm_data *data; unsigned long next_period[2]; - bool needs_delay[2]; }; static inline struct sun4i_pwm_chip *to_sun4i_pwm_chip(struct pwm_chip *chip) @@ -287,7 +286,6 @@ static int sun4i_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, sun4i_pwm_writel(sun4i_pwm, val, PWM_CH_PRD(pwm->hwpwm)); sun4i_pwm->next_period[pwm->hwpwm] = jiffies + usecs_to_jiffies(cstate.period / 1000 + 1); - sun4i_pwm->needs_delay[pwm->hwpwm] = true; if (state->polarity != PWM_POLARITY_NORMAL) ctrl &= ~BIT_CH(PWM_ACT_STATE, pwm->hwpwm); @@ -298,7 +296,7 @@ static int sun4i_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, if (state->enabled) { ctrl |= BIT_CH(PWM_EN, pwm->hwpwm); - } else if (!sun4i_pwm->needs_delay[pwm->hwpwm]) { + } else { ctrl &= ~BIT_CH(PWM_EN, pwm->hwpwm); ctrl &= ~BIT_CH(PWM_CLK_GATING, pwm->hwpwm); } @@ -310,15 +308,9 @@ static int sun4i_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, if (state->enabled) return 0; - if (!sun4i_pwm->needs_delay[pwm->hwpwm]) { - clk_disable_unprepare(sun4i_pwm->clk); - return 0; - } - /* We need a full period to elapse before disabling the channel. */ now = jiffies; - if (sun4i_pwm->needs_delay[pwm->hwpwm] && - time_before(now, sun4i_pwm->next_period[pwm->hwpwm])) { + if (time_before(now, sun4i_pwm->next_period[pwm->hwpwm])) { delay_us = jiffies_to_usecs(sun4i_pwm->next_period[pwm->hwpwm] - now); if ((delay_us / 500) > MAX_UDELAY_MS) @@ -326,7 +318,6 @@ static int sun4i_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, else usleep_range(delay_us, delay_us * 2); } - sun4i_pwm->needs_delay[pwm->hwpwm] = false; spin_lock(&sun4i_pwm->ctrl_lock); ctrl = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); diff --git a/drivers/pwm/pwm-tegra.c b/drivers/pwm/pwm-tegra.c index aa12fb3ed92e..d26ed8f579ff 100644 --- a/drivers/pwm/pwm-tegra.c +++ b/drivers/pwm/pwm-tegra.c @@ -282,9 +282,15 @@ static const struct tegra_pwm_soc tegra186_pwm_soc = { .max_frequency = 102000000UL, }; +static const struct tegra_pwm_soc tegra194_pwm_soc = { + .num_channels = 1, + .max_frequency = 408000000UL, +}; + static const struct of_device_id tegra_pwm_of_match[] = { { .compatible = "nvidia,tegra20-pwm", .data = &tegra20_pwm_soc }, { .compatible = "nvidia,tegra186-pwm", .data = &tegra186_pwm_soc }, + { .compatible = "nvidia,tegra194-pwm", .data = &tegra194_pwm_soc }, { } }; MODULE_DEVICE_TABLE(of, tegra_pwm_of_match); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 80d22290f268..384edffe5cb4 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -57,11 +57,26 @@ static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev, return copy_to_iter(addr, bytes, i); } +static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev, + pgoff_t pgoff, size_t nr_pages) +{ + long rc; + void *kaddr; + + rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL); + if (rc < 0) + return rc; + memset(kaddr, 0, nr_pages << PAGE_SHIFT); + dax_flush(dax_dev, kaddr, nr_pages << PAGE_SHIFT); + return 0; +} + static const struct dax_operations dcssblk_dax_ops = { .direct_access = dcssblk_dax_direct_access, .dax_supported = generic_fsdax_supported, .copy_from_iter = dcssblk_dax_copy_from_iter, .copy_to_iter = dcssblk_dax_copy_to_iter, + .zero_page_range = dcssblk_dax_zero_page_range, }; struct dcssblk_dev_info { @@ -680,8 +695,9 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char dev_info->dax_dev = alloc_dax(dev_info, dev_info->gd->disk_name, &dcssblk_dax_ops, DAXDEV_F_SYNC); - if (!dev_info->dax_dev) { - rc = -ENOMEM; + if (IS_ERR(dev_info->dax_dev)) { + rc = PTR_ERR(dev_info->dax_dev); + dev_info->dax_dev = NULL; goto put_dev; } diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 50007cb9be5b..b29fe8d50baf 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -849,8 +849,10 @@ static void io_subchannel_register(struct ccw_device *cdev) * Now we know this subchannel will stay, we can throw * our delayed uevent. */ - dev_set_uevent_suppress(&sch->dev, 0); - kobject_uevent(&sch->dev.kobj, KOBJ_ADD); + if (dev_get_uevent_suppress(&sch->dev)) { + dev_set_uevent_suppress(&sch->dev, 0); + kobject_uevent(&sch->dev.kobj, KOBJ_ADD); + } /* make it known to the system */ ret = ccw_device_add(cdev); if (ret) { @@ -1058,8 +1060,11 @@ static int io_subchannel_probe(struct subchannel *sch) * Throw the delayed uevent for the subchannel, register * the ccw_device and exit. */ - dev_set_uevent_suppress(&sch->dev, 0); - kobject_uevent(&sch->dev.kobj, KOBJ_ADD); + if (dev_get_uevent_suppress(&sch->dev)) { + /* should always be the case for the console */ + dev_set_uevent_suppress(&sch->dev, 0); + kobject_uevent(&sch->dev.kobj, KOBJ_ADD); + } cdev = sch_get_cdev(sch); rc = ccw_device_add(cdev); if (rc) { diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index b0beafc43d37..b8453b594679 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -374,7 +374,6 @@ int tiqdio_allocate_memory(void); void tiqdio_free_memory(void); int tiqdio_register_thinints(void); void tiqdio_unregister_thinints(void); -void clear_nonshared_ind(struct qdio_irq *); int test_nonshared_ind(struct qdio_irq *); /* prototypes for setup */ diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c index 5a3d9ee90a7f..286b044fb027 100644 --- a/drivers/s390/cio/qdio_debug.c +++ b/drivers/s390/cio/qdio_debug.c @@ -58,25 +58,11 @@ static void qdio_clear_dbf_list(void) mutex_unlock(&qdio_dbf_list_mutex); } -int qdio_allocate_dbf(struct qdio_initialize *init_data, - struct qdio_irq *irq_ptr) +int qdio_allocate_dbf(struct qdio_irq *irq_ptr) { char text[QDIO_DBF_NAME_LEN]; struct qdio_dbf_entry *new_entry; - DBF_EVENT("qfmt:%1d", init_data->q_format); - DBF_HEX(init_data->adapter_name, 8); - DBF_EVENT("qpff%4x", init_data->qib_param_field_format); - DBF_HEX(&init_data->qib_param_field, sizeof(void *)); - DBF_HEX(&init_data->input_slib_elements, sizeof(void *)); - DBF_HEX(&init_data->output_slib_elements, sizeof(void *)); - DBF_EVENT("niq:%1d noq:%1d", init_data->no_input_qs, - init_data->no_output_qs); - DBF_HEX(&init_data->input_handler, sizeof(void *)); - DBF_HEX(&init_data->output_handler, sizeof(void *)); - DBF_HEX(&init_data->int_parm, sizeof(long)); - DBF_HEX(&init_data->input_sbal_addr_array, sizeof(void *)); - DBF_HEX(&init_data->output_sbal_addr_array, sizeof(void *)); DBF_EVENT("irq:%8lx", (unsigned long)irq_ptr); /* allocate trace view for the interface */ diff --git a/drivers/s390/cio/qdio_debug.h b/drivers/s390/cio/qdio_debug.h index 122450ba6b90..0dfba085f360 100644 --- a/drivers/s390/cio/qdio_debug.h +++ b/drivers/s390/cio/qdio_debug.h @@ -64,8 +64,7 @@ static inline void DBF_DEV_HEX(struct qdio_irq *dev, void *addr, debug_event(dev->debug_area, level, addr, len); } -int qdio_allocate_dbf(struct qdio_initialize *init_data, - struct qdio_irq *irq_ptr); +int qdio_allocate_dbf(struct qdio_irq *irq_ptr); void qdio_setup_debug_entries(struct qdio_irq *irq_ptr); void qdio_shutdown_debug_entries(struct qdio_irq *irq_ptr); int qdio_debug_init(void); diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index c890848064fe..bcc3ab14e72d 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -1220,27 +1220,21 @@ EXPORT_SYMBOL_GPL(qdio_free); /** * qdio_allocate - allocate qdio queues and associated data - * @init_data: initialization data + * @cdev: associated ccw device + * @no_input_qs: allocate this number of Input Queues + * @no_output_qs: allocate this number of Output Queues */ -int qdio_allocate(struct qdio_initialize *init_data) +int qdio_allocate(struct ccw_device *cdev, unsigned int no_input_qs, + unsigned int no_output_qs) { - struct ccw_device *cdev = init_data->cdev; struct subchannel_id schid; struct qdio_irq *irq_ptr; ccw_device_get_schid(cdev, &schid); DBF_EVENT("qallocate:%4x", schid.sch_no); - if ((init_data->no_input_qs && !init_data->input_handler) || - (init_data->no_output_qs && !init_data->output_handler)) - return -EINVAL; - - if ((init_data->no_input_qs > QDIO_MAX_QUEUES_PER_IRQ) || - (init_data->no_output_qs > QDIO_MAX_QUEUES_PER_IRQ)) - return -EINVAL; - - if ((!init_data->input_sbal_addr_array) || - (!init_data->output_sbal_addr_array)) + if (no_input_qs > QDIO_MAX_QUEUES_PER_IRQ || + no_output_qs > QDIO_MAX_QUEUES_PER_IRQ) return -EINVAL; /* irq_ptr must be in GFP_DMA since it contains ccw1.cda */ @@ -1250,9 +1244,12 @@ int qdio_allocate(struct qdio_initialize *init_data) irq_ptr->cdev = cdev; mutex_init(&irq_ptr->setup_mutex); - if (qdio_allocate_dbf(init_data, irq_ptr)) + if (qdio_allocate_dbf(irq_ptr)) goto out_rel; + DBF_DEV_EVENT(DBF_ERR, irq_ptr, "alloc niq:%1u noq:%1u", no_input_qs, + no_output_qs); + /* * Allocate a page for the chsc calls in qdio_establish. * Must be pre-allocated since a zfcp recovery will call @@ -1268,8 +1265,7 @@ int qdio_allocate(struct qdio_initialize *init_data) if (!irq_ptr->qdr) goto out_rel; - if (qdio_allocate_qs(irq_ptr, init_data->no_input_qs, - init_data->no_output_qs)) + if (qdio_allocate_qs(irq_ptr, no_input_qs, no_output_qs)) goto out_rel; INIT_LIST_HEAD(&irq_ptr->entry); @@ -1305,13 +1301,33 @@ static void qdio_detect_hsicq(struct qdio_irq *irq_ptr) DBF_EVENT("use_cq:%d", use_cq); } +static void qdio_trace_init_data(struct qdio_irq *irq, + struct qdio_initialize *data) +{ + DBF_DEV_EVENT(DBF_ERR, irq, "qfmt:%1u", data->q_format); + DBF_DEV_HEX(irq, data->adapter_name, 8, DBF_ERR); + DBF_DEV_EVENT(DBF_ERR, irq, "qpff%4x", data->qib_param_field_format); + DBF_DEV_HEX(irq, &data->qib_param_field, sizeof(void *), DBF_ERR); + DBF_DEV_HEX(irq, &data->input_slib_elements, sizeof(void *), DBF_ERR); + DBF_DEV_HEX(irq, &data->output_slib_elements, sizeof(void *), DBF_ERR); + DBF_DEV_EVENT(DBF_ERR, irq, "niq:%1u noq:%1u", data->no_input_qs, + data->no_output_qs); + DBF_DEV_HEX(irq, &data->input_handler, sizeof(void *), DBF_ERR); + DBF_DEV_HEX(irq, &data->output_handler, sizeof(void *), DBF_ERR); + DBF_DEV_HEX(irq, &data->int_parm, sizeof(long), DBF_ERR); + DBF_DEV_HEX(irq, &data->input_sbal_addr_array, sizeof(void *), DBF_ERR); + DBF_DEV_HEX(irq, &data->output_sbal_addr_array, sizeof(void *), + DBF_ERR); +} + /** * qdio_establish - establish queues on a qdio subchannel + * @cdev: associated ccw device * @init_data: initialization data */ -int qdio_establish(struct qdio_initialize *init_data) +int qdio_establish(struct ccw_device *cdev, + struct qdio_initialize *init_data) { - struct ccw_device *cdev = init_data->cdev; struct qdio_irq *irq_ptr = cdev->private->qdio_data; struct subchannel_id schid; int rc; @@ -1322,7 +1338,16 @@ int qdio_establish(struct qdio_initialize *init_data) if (!irq_ptr) return -ENODEV; + if ((init_data->no_input_qs && !init_data->input_handler) || + (init_data->no_output_qs && !init_data->output_handler)) + return -EINVAL; + + if (!init_data->input_sbal_addr_array || + !init_data->output_sbal_addr_array) + return -EINVAL; + mutex_lock(&irq_ptr->setup_mutex); + qdio_trace_init_data(irq_ptr, init_data); qdio_setup_irq(irq_ptr, init_data); rc = qdio_establish_thinint(irq_ptr); @@ -1618,8 +1643,6 @@ int qdio_start_irq(struct ccw_device *cdev) if (!irq_ptr) return -ENODEV; - clear_nonshared_ind(irq_ptr); - for_each_input_queue(irq_ptr, q, i) qdio_stop_polling(q); diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index bbbefc9f9e04..3083edd61f0c 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -213,8 +213,6 @@ static void setup_queues(struct qdio_irq *irq_ptr, struct qdio_initialize *qdio_init) { struct qdio_q *q; - struct qdio_buffer **input_sbal_array = qdio_init->input_sbal_addr_array; - struct qdio_buffer **output_sbal_array = qdio_init->output_sbal_addr_array; struct qdio_outbuf_state *output_sbal_state_array = qdio_init->output_sbal_state_array; int i; @@ -225,8 +223,8 @@ static void setup_queues(struct qdio_irq *irq_ptr, q->is_input_q = 1; - setup_storage_lists(q, irq_ptr, input_sbal_array, i); - input_sbal_array += QDIO_MAX_BUFFERS_PER_Q; + setup_storage_lists(q, irq_ptr, + qdio_init->input_sbal_addr_array[i], i); if (is_thinint_irq(irq_ptr)) { tasklet_init(&q->tasklet, tiqdio_inbound_processing, @@ -245,8 +243,8 @@ static void setup_queues(struct qdio_irq *irq_ptr, output_sbal_state_array += QDIO_MAX_BUFFERS_PER_Q; q->is_input_q = 0; - setup_storage_lists(q, irq_ptr, output_sbal_array, i); - output_sbal_array += QDIO_MAX_BUFFERS_PER_Q; + setup_storage_lists(q, irq_ptr, + qdio_init->output_sbal_addr_array[i], i); tasklet_init(&q->tasklet, qdio_outbound_processing, (unsigned long) q); diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c index ea09df7209f0..ae50373617cd 100644 --- a/drivers/s390/cio/qdio_thinint.c +++ b/drivers/s390/cio/qdio_thinint.c @@ -82,36 +82,16 @@ void tiqdio_remove_device(struct qdio_irq *irq_ptr) INIT_LIST_HEAD(&irq_ptr->entry); } -static inline int has_multiple_inq_on_dsci(struct qdio_irq *irq_ptr) -{ - return irq_ptr->nr_input_qs > 1; -} - static inline int references_shared_dsci(struct qdio_irq *irq_ptr) { return irq_ptr->dsci == &q_indicators[TIQDIO_SHARED_IND].ind; } -static inline int shared_ind(struct qdio_irq *irq_ptr) -{ - return references_shared_dsci(irq_ptr) || - has_multiple_inq_on_dsci(irq_ptr); -} - -void clear_nonshared_ind(struct qdio_irq *irq_ptr) -{ - if (!is_thinint_irq(irq_ptr)) - return; - if (shared_ind(irq_ptr)) - return; - xchg(irq_ptr->dsci, 0); -} - int test_nonshared_ind(struct qdio_irq *irq_ptr) { if (!is_thinint_irq(irq_ptr)) return 0; - if (shared_ind(irq_ptr)) + if (references_shared_dsci(irq_ptr)) return 0; if (*irq_ptr->dsci) return 1; @@ -131,8 +111,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq) struct qdio_q *q; int i; - if (!references_shared_dsci(irq) && - has_multiple_inq_on_dsci(irq)) + if (!references_shared_dsci(irq)) xchg(irq->dsci, 0); if (irq->irq_poll) { @@ -145,9 +124,6 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq) } for_each_input_queue(irq, q, i) { - if (!shared_ind(irq)) - xchg(irq->dsci, 0); - /* * Call inbound processing but not directly * since that could starve other thinint queues. diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index e401a3d0aa57..339a6bc0339b 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -167,6 +167,11 @@ static int vfio_ccw_sch_probe(struct subchannel *sch) if (ret) goto out_disable; + if (dev_get_uevent_suppress(&sch->dev)) { + dev_set_uevent_suppress(&sch->dev, 0); + kobject_uevent(&sch->dev.kobj, KOBJ_ADD); + } + VFIO_CCW_MSG_EVENT(4, "bound to subchannel %x.%x.%04x\n", sch->schid.cssid, sch->schid.ssid, sch->schid.sch_no); diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index acda230323d5..e0b26310ecab 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -181,11 +181,12 @@ struct qeth_vnicc_info { /*****************************************************************************/ /* QDIO queue and buffer handling */ /*****************************************************************************/ -#define QETH_MAX_QUEUES 4 +#define QETH_MAX_OUT_QUEUES 4 #define QETH_IQD_MIN_TXQ 2 /* One for ucast, one for mcast. */ #define QETH_IQD_MCAST_TXQ 0 #define QETH_IQD_MIN_UCAST_TXQ 1 +#define QETH_MAX_IN_QUEUES 2 #define QETH_RX_COPYBREAK (PAGE_SIZE >> 1) #define QETH_IN_BUF_SIZE_DEFAULT 65536 #define QETH_IN_BUF_COUNT_DEFAULT 64 @@ -539,7 +540,7 @@ struct qeth_qdio_info { /* output */ int no_out_queues; - struct qeth_qdio_out_q *out_qs[QETH_MAX_QUEUES]; + struct qeth_qdio_out_q *out_qs[QETH_MAX_OUT_QUEUES]; struct qdio_outbuf_state *out_bufstates; /* priority queueing */ diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 24fd17b347fe..f7689461c242 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4812,28 +4812,13 @@ out: return; } -static void qeth_qdio_establish_cq(struct qeth_card *card, - struct qdio_buffer **in_sbal_ptrs) -{ - int i; - - if (card->options.cq == QETH_CQ_ENABLED) { - int offset = QDIO_MAX_BUFFERS_PER_Q * - (card->qdio.no_in_queues - 1); - - for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) - in_sbal_ptrs[offset + i] = - card->qdio.c_q->bufs[i].buffer; - } -} - static int qeth_qdio_establish(struct qeth_card *card) { + struct qdio_buffer **out_sbal_ptrs[QETH_MAX_OUT_QUEUES]; + struct qdio_buffer **in_sbal_ptrs[QETH_MAX_IN_QUEUES]; struct qdio_initialize init_data; char *qib_param_field; - struct qdio_buffer **in_sbal_ptrs; - struct qdio_buffer **out_sbal_ptrs; - int i, j, k; + unsigned int i; int rc = 0; QETH_CARD_TEXT(card, 2, "qdioest"); @@ -4847,35 +4832,14 @@ static int qeth_qdio_establish(struct qeth_card *card) qeth_create_qib_param_field(card, qib_param_field); qeth_create_qib_param_field_blkt(card, qib_param_field); - in_sbal_ptrs = kcalloc(card->qdio.no_in_queues * QDIO_MAX_BUFFERS_PER_Q, - sizeof(void *), - GFP_KERNEL); - if (!in_sbal_ptrs) { - rc = -ENOMEM; - goto out_free_qib_param; - } - - for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) - in_sbal_ptrs[i] = card->qdio.in_q->bufs[i].buffer; - - qeth_qdio_establish_cq(card, in_sbal_ptrs); - - out_sbal_ptrs = - kcalloc(card->qdio.no_out_queues * QDIO_MAX_BUFFERS_PER_Q, - sizeof(void *), - GFP_KERNEL); - if (!out_sbal_ptrs) { - rc = -ENOMEM; - goto out_free_in_sbals; - } + in_sbal_ptrs[0] = card->qdio.in_q->qdio_bufs; + if (card->options.cq == QETH_CQ_ENABLED) + in_sbal_ptrs[1] = card->qdio.c_q->qdio_bufs; - for (i = 0, k = 0; i < card->qdio.no_out_queues; ++i) - for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++, k++) - out_sbal_ptrs[k] = - card->qdio.out_qs[i]->bufs[j]->buffer; + for (i = 0; i < card->qdio.no_out_queues; i++) + out_sbal_ptrs[i] = card->qdio.out_qs[i]->qdio_bufs; memset(&init_data, 0, sizeof(struct qdio_initialize)); - init_data.cdev = CARD_DDEV(card); init_data.q_format = IS_IQD(card) ? QDIO_IQDIO_QFMT : QDIO_QETH_QFMT; init_data.qib_param_field_format = 0; @@ -4893,12 +4857,13 @@ static int qeth_qdio_establish(struct qeth_card *card) if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_ALLOCATED, QETH_QDIO_ESTABLISHED) == QETH_QDIO_ALLOCATED) { - rc = qdio_allocate(&init_data); + rc = qdio_allocate(CARD_DDEV(card), init_data.no_input_qs, + init_data.no_output_qs); if (rc) { atomic_set(&card->qdio.state, QETH_QDIO_ALLOCATED); goto out; } - rc = qdio_establish(&init_data); + rc = qdio_establish(CARD_DDEV(card), &init_data); if (rc) { atomic_set(&card->qdio.state, QETH_QDIO_ALLOCATED); qdio_free(CARD_DDEV(card)); @@ -4916,10 +4881,6 @@ static int qeth_qdio_establish(struct qeth_card *card) break; } out: - kfree(out_sbal_ptrs); -out_free_in_sbals: - kfree(in_sbal_ptrs); -out_free_qib_param: kfree(qib_param_field); out_free_nothing: return rc; @@ -5985,7 +5946,7 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card) switch (card->info.type) { case QETH_CARD_TYPE_IQD: dev = alloc_netdev_mqs(sizeof(*priv), "hsi%d", NET_NAME_UNKNOWN, - ether_setup, QETH_MAX_QUEUES, 1); + ether_setup, QETH_MAX_OUT_QUEUES, 1); break; case QETH_CARD_TYPE_OSM: dev = alloc_etherdev(sizeof(*priv)); @@ -5995,7 +5956,7 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card) ether_setup); break; default: - dev = alloc_etherdev_mqs(sizeof(*priv), QETH_MAX_QUEUES, 1); + dev = alloc_etherdev_mqs(sizeof(*priv), QETH_MAX_OUT_QUEUES, 1); } if (!dev) diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 18a6751299f9..3d0bc000f500 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -178,12 +178,12 @@ static enum zfcp_erp_act_type zfcp_erp_required_act(enum zfcp_erp_act_type want, return 0; if (!(p_status & ZFCP_STATUS_COMMON_UNBLOCKED)) need = ZFCP_ERP_ACTION_REOPEN_PORT; - /* fall through */ + fallthrough; case ZFCP_ERP_ACTION_REOPEN_PORT_FORCED: p_status = atomic_read(&port->status); if (!(p_status & ZFCP_STATUS_COMMON_OPEN)) need = ZFCP_ERP_ACTION_REOPEN_PORT; - /* fall through */ + fallthrough; case ZFCP_ERP_ACTION_REOPEN_PORT: p_status = atomic_read(&port->status); if (p_status & ZFCP_STATUS_COMMON_ERP_INUSE) @@ -196,7 +196,7 @@ static enum zfcp_erp_act_type zfcp_erp_required_act(enum zfcp_erp_act_type want, return need; if (!(a_status & ZFCP_STATUS_COMMON_UNBLOCKED)) need = ZFCP_ERP_ACTION_REOPEN_ADAPTER; - /* fall through */ + fallthrough; case ZFCP_ERP_ACTION_REOPEN_ADAPTER: a_status = atomic_read(&adapter->status); if (a_status & ZFCP_STATUS_COMMON_ERP_INUSE) @@ -1086,7 +1086,7 @@ static enum zfcp_erp_act_result zfcp_erp_lun_strategy( if (atomic_read(&zfcp_sdev->status) & ZFCP_STATUS_COMMON_OPEN) return zfcp_erp_lun_strategy_close(erp_action); /* already closed */ - /* fall through */ + fallthrough; case ZFCP_ERP_STEP_LUN_CLOSING: if (atomic_read(&zfcp_sdev->status) & ZFCP_STATUS_COMMON_OPEN) return ZFCP_ERP_FAILED; @@ -1415,7 +1415,7 @@ static void zfcp_erp_action_cleanup(struct zfcp_erp_action *act, if (act->step != ZFCP_ERP_STEP_UNINITIALIZED) if (result == ZFCP_ERP_SUCCEEDED) zfcp_erp_try_rport_unblock(port); - /* fall through */ + fallthrough; case ZFCP_ERP_ACTION_REOPEN_PORT_FORCED: put_device(&port->dev); break; diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 7c603e5b5b19..111fe3fc32d7 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -564,7 +564,7 @@ static int zfcp_fsf_exchange_config_evaluate(struct zfcp_fsf_req *req) case FSF_TOPO_AL: fc_host_port_type(shost) = FC_PORTTYPE_NLPORT; fc_host_fabric_name(shost) = 0; - /* fall through */ + fallthrough; default: fc_host_fabric_name(shost) = 0; dev_err(&adapter->ccw_device->dev, @@ -1032,7 +1032,7 @@ static void zfcp_fsf_abort_fcp_command_handler(struct zfcp_fsf_req *req) switch (fsq->word[0]) { case FSF_SQ_INVOKE_LINK_TEST_PROCEDURE: zfcp_fc_test_link(zfcp_sdev->port); - /* fall through */ + fallthrough; case FSF_SQ_ULP_DEPENDENT_ERP_REQUIRED: req->status |= ZFCP_STATUS_FSFREQ_ERROR; break; @@ -1127,7 +1127,7 @@ static void zfcp_fsf_send_ct_handler(struct zfcp_fsf_req *req) break; case FSF_PORT_HANDLE_NOT_VALID: zfcp_erp_adapter_reopen(adapter, 0, "fsscth1"); - /* fall through */ + fallthrough; case FSF_GENERIC_COMMAND_REJECTED: case FSF_PAYLOAD_SIZE_MISMATCH: case FSF_REQUEST_SIZE_TOO_LARGE: @@ -1313,7 +1313,7 @@ static void zfcp_fsf_send_els_handler(struct zfcp_fsf_req *req) break; case FSF_SBAL_MISMATCH: /* should never occur, avoided in zfcp_fsf_send_els */ - /* fall through */ + fallthrough; default: req->status |= ZFCP_STATUS_FSFREQ_ERROR; break; @@ -1736,7 +1736,7 @@ static void zfcp_fsf_open_port_handler(struct zfcp_fsf_req *req) switch (header->fsf_status_qual.word[0]) { case FSF_SQ_INVOKE_LINK_TEST_PROCEDURE: /* no zfcp_fc_test_link() with failed open port */ - /* fall through */ + fallthrough; case FSF_SQ_ULP_DEPENDENT_ERP_REQUIRED: case FSF_SQ_NO_RETRY_POSSIBLE: req->status |= ZFCP_STATUS_FSFREQ_ERROR; @@ -1909,14 +1909,14 @@ static void zfcp_fsf_open_wka_port_handler(struct zfcp_fsf_req *req) case FSF_MAXIMUM_NUMBER_OF_PORTS_EXCEEDED: dev_warn(&req->adapter->ccw_device->dev, "Opening WKA port 0x%x failed\n", wka_port->d_id); - /* fall through */ + fallthrough; case FSF_ADAPTER_STATUS_AVAILABLE: req->status |= ZFCP_STATUS_FSFREQ_ERROR; wka_port->status = ZFCP_FC_WKA_PORT_OFFLINE; break; case FSF_GOOD: wka_port->handle = header->port_handle; - /* fall through */ + fallthrough; case FSF_PORT_ALREADY_OPEN: wka_port->status = ZFCP_FC_WKA_PORT_ONLINE; } @@ -2059,7 +2059,6 @@ static void zfcp_fsf_close_physical_port_handler(struct zfcp_fsf_req *req) case FSF_ADAPTER_STATUS_AVAILABLE: switch (header->fsf_status_qual.word[0]) { case FSF_SQ_INVOKE_LINK_TEST_PROCEDURE: - /* fall through */ case FSF_SQ_ULP_DEPENDENT_ERP_REQUIRED: req->status |= ZFCP_STATUS_FSFREQ_ERROR; break; @@ -2144,7 +2143,7 @@ static void zfcp_fsf_open_lun_handler(struct zfcp_fsf_req *req) case FSF_PORT_HANDLE_NOT_VALID: zfcp_erp_adapter_reopen(adapter, 0, "fsouh_1"); - /* fall through */ + fallthrough; case FSF_LUN_ALREADY_OPEN: break; case FSF_PORT_BOXED: @@ -2175,7 +2174,7 @@ static void zfcp_fsf_open_lun_handler(struct zfcp_fsf_req *req) (unsigned long long)zfcp_scsi_dev_lun(sdev), (unsigned long long)zfcp_sdev->port->wwpn); zfcp_erp_set_lun_status(sdev, ZFCP_STATUS_COMMON_ERP_FAILED); - /* fall through */ + fallthrough; case FSF_INVALID_COMMAND_OPTION: req->status |= ZFCP_STATUS_FSFREQ_ERROR; break; @@ -2183,7 +2182,7 @@ static void zfcp_fsf_open_lun_handler(struct zfcp_fsf_req *req) switch (header->fsf_status_qual.word[0]) { case FSF_SQ_INVOKE_LINK_TEST_PROCEDURE: zfcp_fc_test_link(zfcp_sdev->port); - /* fall through */ + fallthrough; case FSF_SQ_ULP_DEPENDENT_ERP_REQUIRED: req->status |= ZFCP_STATUS_FSFREQ_ERROR; break; @@ -2277,7 +2276,7 @@ static void zfcp_fsf_close_lun_handler(struct zfcp_fsf_req *req) switch (req->qtcb->header.fsf_status_qual.word[0]) { case FSF_SQ_INVOKE_LINK_TEST_PROCEDURE: zfcp_fc_test_link(zfcp_sdev->port); - /* fall through */ + fallthrough; case FSF_SQ_ULP_DEPENDENT_ERP_REQUIRED: req->status |= ZFCP_STATUS_FSFREQ_ERROR; break; diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c index f0d6296e673b..26702b56a7ab 100644 --- a/drivers/s390/scsi/zfcp_qdio.c +++ b/drivers/s390/scsi/zfcp_qdio.c @@ -277,29 +277,6 @@ int zfcp_qdio_send(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req) return 0; } - -static void zfcp_qdio_setup_init_data(struct qdio_initialize *id, - struct zfcp_qdio *qdio) -{ - memset(id, 0, sizeof(*id)); - id->cdev = qdio->adapter->ccw_device; - id->q_format = QDIO_ZFCP_QFMT; - memcpy(id->adapter_name, dev_name(&id->cdev->dev), 8); - ASCEBC(id->adapter_name, 8); - id->qib_rflags = QIB_RFLAGS_ENABLE_DATA_DIV; - if (enable_multibuffer) - id->qdr_ac |= QDR_AC_MULTI_BUFFER_ENABLE; - id->no_input_qs = 1; - id->no_output_qs = 1; - id->input_handler = zfcp_qdio_int_resp; - id->output_handler = zfcp_qdio_int_req; - id->int_parm = (unsigned long) qdio; - id->input_sbal_addr_array = qdio->res_q; - id->output_sbal_addr_array = qdio->req_q; - id->scan_threshold = - QDIO_MAX_BUFFERS_PER_Q - ZFCP_QDIO_MAX_SBALS_PER_REQ * 2; -} - /** * zfcp_qdio_allocate - allocate queue memory and initialize QDIO data * @qdio: pointer to struct zfcp_qdio @@ -308,7 +285,6 @@ static void zfcp_qdio_setup_init_data(struct qdio_initialize *id, */ static int zfcp_qdio_allocate(struct zfcp_qdio *qdio) { - struct qdio_initialize init_data; int ret; ret = qdio_alloc_buffers(qdio->req_q, QDIO_MAX_BUFFERS_PER_Q); @@ -319,10 +295,9 @@ static int zfcp_qdio_allocate(struct zfcp_qdio *qdio) if (ret) goto free_req_q; - zfcp_qdio_setup_init_data(&init_data, qdio); init_waitqueue_head(&qdio->req_q_wq); - ret = qdio_allocate(&init_data); + ret = qdio_allocate(qdio->adapter->ccw_device, 1, 1); if (ret) goto free_res_q; @@ -374,8 +349,10 @@ void zfcp_qdio_close(struct zfcp_qdio *qdio) */ int zfcp_qdio_open(struct zfcp_qdio *qdio) { + struct qdio_buffer **input_sbals[1] = {qdio->res_q}; + struct qdio_buffer **output_sbals[1] = {qdio->req_q}; struct qdio_buffer_element *sbale; - struct qdio_initialize init_data; + struct qdio_initialize init_data = {0}; struct zfcp_adapter *adapter = qdio->adapter; struct ccw_device *cdev = adapter->ccw_device; struct qdio_ssqd_desc ssqd; @@ -387,12 +364,26 @@ int zfcp_qdio_open(struct zfcp_qdio *qdio) atomic_andnot(ZFCP_STATUS_ADAPTER_SIOSL_ISSUED, &qdio->adapter->status); - zfcp_qdio_setup_init_data(&init_data, qdio); + init_data.q_format = QDIO_ZFCP_QFMT; + memcpy(init_data.adapter_name, dev_name(&cdev->dev), 8); + ASCEBC(init_data.adapter_name, 8); + init_data.qib_rflags = QIB_RFLAGS_ENABLE_DATA_DIV; + if (enable_multibuffer) + init_data.qdr_ac |= QDR_AC_MULTI_BUFFER_ENABLE; + init_data.no_input_qs = 1; + init_data.no_output_qs = 1; + init_data.input_handler = zfcp_qdio_int_resp; + init_data.output_handler = zfcp_qdio_int_req; + init_data.int_parm = (unsigned long) qdio; + init_data.input_sbal_addr_array = input_sbals; + init_data.output_sbal_addr_array = output_sbals; + init_data.scan_threshold = + QDIO_MAX_BUFFERS_PER_Q - ZFCP_QDIO_MAX_SBALS_PER_REQ * 2; - if (qdio_establish(&init_data)) + if (qdio_establish(cdev, &init_data)) goto failed_establish; - if (qdio_get_ssqd_desc(init_data.cdev, &ssqd)) + if (qdio_get_ssqd_desc(cdev, &ssqd)) goto failed_qdio; if (ssqd.qdioac2 & CHSC_AC2_DATA_DIV_ENABLED) diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 4725e4c763cf..ddd73f6798af 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -1626,7 +1626,7 @@ out: int aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type) { unsigned long flagv = 0; - int retval; + int retval, unblock_retval; struct Scsi_Host *host = aac->scsi_host_ptr; int bled; @@ -1656,8 +1656,9 @@ int aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type) retval = _aac_reset_adapter(aac, bled, reset_type); spin_unlock_irqrestore(host->host_lock, flagv); - retval = scsi_host_unblock(host, SDEV_RUNNING); - + unblock_retval = scsi_host_unblock(host, SDEV_RUNNING); + if (!retval) + retval = unblock_retval; if ((forced < 2) && (retval == -ENODEV)) { /* Unwind aac_send_shutdown() IOP_RESET unsupported/disabled */ struct fib * fibctx = aac_fib_alloc(aac); diff --git a/drivers/scsi/aic7xxx/aic7xxx_core.c b/drivers/scsi/aic7xxx/aic7xxx_core.c index 4190a025381a..84fc499cb1e6 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_core.c +++ b/drivers/scsi/aic7xxx/aic7xxx_core.c @@ -1834,21 +1834,6 @@ ahc_handle_scsiint(struct ahc_softc *ahc, u_int intstat) printerror = 0; } else if (ahc_sent_msg(ahc, AHCMSG_1B, MSG_BUS_DEV_RESET, TRUE)) { -#ifdef __FreeBSD__ - /* - * Don't mark the user's request for this BDR - * as completing with CAM_BDR_SENT. CAM3 - * specifies CAM_REQ_CMP. - */ - if (scb != NULL - && scb->io_ctx->ccb_h.func_code== XPT_RESET_DEV - && ahc_match_scb(ahc, scb, target, channel, - CAM_LUN_WILDCARD, - SCB_LIST_NULL, - ROLE_INITIATOR)) { - ahc_set_transaction_status(scb, CAM_REQ_CMP); - } -#endif ahc_compile_devinfo(&devinfo, initiator_role_id, target, @@ -4399,22 +4384,16 @@ ahc_alloc(void *platform_arg, char *name) struct ahc_softc *ahc; int i; -#ifndef __FreeBSD__ ahc = kmalloc(sizeof(*ahc), GFP_ATOMIC); if (!ahc) { printk("aic7xxx: cannot malloc softc!\n"); kfree(name); return NULL; } -#else - ahc = device_get_softc((device_t)platform_arg); -#endif memset(ahc, 0, sizeof(*ahc)); ahc->seep_config = kmalloc(sizeof(*ahc->seep_config), GFP_ATOMIC); if (ahc->seep_config == NULL) { -#ifndef __FreeBSD__ kfree(ahc); -#endif kfree(name); return (NULL); } @@ -4540,9 +4519,7 @@ ahc_free(struct ahc_softc *ahc) kfree(ahc->name); if (ahc->seep_config != NULL) kfree(ahc->seep_config); -#ifndef __FreeBSD__ kfree(ahc); -#endif return; } diff --git a/drivers/scsi/bnx2fc/bnx2fc.h b/drivers/scsi/bnx2fc/bnx2fc.h index 3b84db8d13a9..b6e8ed757252 100644 --- a/drivers/scsi/bnx2fc/bnx2fc.h +++ b/drivers/scsi/bnx2fc/bnx2fc.h @@ -66,7 +66,7 @@ #include "bnx2fc_constants.h" #define BNX2FC_NAME "bnx2fc" -#define BNX2FC_VERSION "2.12.10" +#define BNX2FC_VERSION "2.12.13" #define PFX "bnx2fc: " @@ -482,7 +482,10 @@ struct io_bdt { struct bnx2fc_work { struct list_head list; struct bnx2fc_rport *tgt; + struct fcoe_task_ctx_entry *task; + unsigned char rq_data[BNX2FC_RQ_BUF_SZ]; u16 wqe; + u8 num_rq; }; struct bnx2fc_unsol_els { struct fc_lport *lport; @@ -550,7 +553,7 @@ void bnx2fc_rport_event_handler(struct fc_lport *lport, enum fc_rport_event event); void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req, struct fcoe_task_ctx_entry *task, - u8 num_rq); + u8 num_rq, unsigned char *rq_data); void bnx2fc_process_cleanup_compl(struct bnx2fc_cmd *io_req, struct fcoe_task_ctx_entry *task, u8 num_rq); @@ -559,7 +562,7 @@ void bnx2fc_process_abts_compl(struct bnx2fc_cmd *io_req, u8 num_rq); void bnx2fc_process_tm_compl(struct bnx2fc_cmd *io_req, struct fcoe_task_ctx_entry *task, - u8 num_rq); + u8 num_rq, unsigned char *rq_data); void bnx2fc_process_els_compl(struct bnx2fc_cmd *els_req, struct fcoe_task_ctx_entry *task, u8 num_rq); @@ -577,7 +580,9 @@ struct fc_seq *bnx2fc_elsct_send(struct fc_lport *lport, u32 did, void *arg, u32 timeout); void bnx2fc_arm_cq(struct bnx2fc_rport *tgt); int bnx2fc_process_new_cqes(struct bnx2fc_rport *tgt); -void bnx2fc_process_cq_compl(struct bnx2fc_rport *tgt, u16 wqe); +void bnx2fc_process_cq_compl(struct bnx2fc_rport *tgt, u16 wqe, + unsigned char *rq_data, u8 num_rq, + struct fcoe_task_ctx_entry *task); struct bnx2fc_rport *bnx2fc_tgt_lookup(struct fcoe_port *port, u32 port_id); void bnx2fc_process_l2_frame_compl(struct bnx2fc_rport *tgt, diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index b4bfab5edf8f..1cbb431fa682 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -660,7 +660,10 @@ static int bnx2fc_percpu_io_thread(void *arg) list_for_each_entry_safe(work, tmp, &work_list, list) { list_del_init(&work->list); - bnx2fc_process_cq_compl(work->tgt, work->wqe); + bnx2fc_process_cq_compl(work->tgt, work->wqe, + work->rq_data, + work->num_rq, + work->task); kfree(work); } @@ -2655,7 +2658,8 @@ static int bnx2fc_cpu_offline(unsigned int cpu) /* Free all work in the list */ list_for_each_entry_safe(work, tmp, &p->work_list, list) { list_del_init(&work->list); - bnx2fc_process_cq_compl(work->tgt, work->wqe); + bnx2fc_process_cq_compl(work->tgt, work->wqe, work->rq_data, + work->num_rq, work->task); kfree(work); } diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index 6f8335ddb1f2..1f7c58b4c535 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -863,36 +863,22 @@ ret_warn_rqe: } } -void bnx2fc_process_cq_compl(struct bnx2fc_rport *tgt, u16 wqe) +void bnx2fc_process_cq_compl(struct bnx2fc_rport *tgt, u16 wqe, + unsigned char *rq_data, u8 num_rq, + struct fcoe_task_ctx_entry *task) { - struct fcoe_task_ctx_entry *task; - struct fcoe_task_ctx_entry *task_page; struct fcoe_port *port = tgt->port; struct bnx2fc_interface *interface = port->priv; struct bnx2fc_hba *hba = interface->hba; struct bnx2fc_cmd *io_req; - int task_idx, index; + u16 xid; u8 cmd_type; u8 rx_state = 0; - u8 num_rq; spin_lock_bh(&tgt->tgt_lock); - xid = wqe & FCOE_PEND_WQ_CQE_TASK_ID; - if (xid >= hba->max_tasks) { - printk(KERN_ERR PFX "ERROR:xid out of range\n"); - spin_unlock_bh(&tgt->tgt_lock); - return; - } - task_idx = xid / BNX2FC_TASKS_PER_PAGE; - index = xid % BNX2FC_TASKS_PER_PAGE; - task_page = (struct fcoe_task_ctx_entry *)hba->task_ctx[task_idx]; - task = &(task_page[index]); - - num_rq = ((task->rxwr_txrd.var_ctx.rx_flags & - FCOE_TCE_RX_WR_TX_RD_VAR_NUM_RQ_WQE) >> - FCOE_TCE_RX_WR_TX_RD_VAR_NUM_RQ_WQE_SHIFT); + xid = wqe & FCOE_PEND_WQ_CQE_TASK_ID; io_req = (struct bnx2fc_cmd *)hba->cmd_mgr->cmds[xid]; if (io_req == NULL) { @@ -912,7 +898,8 @@ void bnx2fc_process_cq_compl(struct bnx2fc_rport *tgt, u16 wqe) switch (cmd_type) { case BNX2FC_SCSI_CMD: if (rx_state == FCOE_TASK_RX_STATE_COMPLETED) { - bnx2fc_process_scsi_cmd_compl(io_req, task, num_rq); + bnx2fc_process_scsi_cmd_compl(io_req, task, num_rq, + rq_data); spin_unlock_bh(&tgt->tgt_lock); return; } @@ -929,7 +916,7 @@ void bnx2fc_process_cq_compl(struct bnx2fc_rport *tgt, u16 wqe) case BNX2FC_TASK_MGMT_CMD: BNX2FC_IO_DBG(io_req, "Processing TM complete\n"); - bnx2fc_process_tm_compl(io_req, task, num_rq); + bnx2fc_process_tm_compl(io_req, task, num_rq, rq_data); break; case BNX2FC_ABTS: @@ -987,7 +974,9 @@ void bnx2fc_arm_cq(struct bnx2fc_rport *tgt) } -static struct bnx2fc_work *bnx2fc_alloc_work(struct bnx2fc_rport *tgt, u16 wqe) +static struct bnx2fc_work *bnx2fc_alloc_work(struct bnx2fc_rport *tgt, u16 wqe, + unsigned char *rq_data, u8 num_rq, + struct fcoe_task_ctx_entry *task) { struct bnx2fc_work *work; work = kzalloc(sizeof(struct bnx2fc_work), GFP_ATOMIC); @@ -997,29 +986,87 @@ static struct bnx2fc_work *bnx2fc_alloc_work(struct bnx2fc_rport *tgt, u16 wqe) INIT_LIST_HEAD(&work->list); work->tgt = tgt; work->wqe = wqe; + work->num_rq = num_rq; + work->task = task; + if (rq_data) + memcpy(work->rq_data, rq_data, BNX2FC_RQ_BUF_SZ); + return work; } /* Pending work request completion */ -static void bnx2fc_pending_work(struct bnx2fc_rport *tgt, unsigned int wqe) +static bool bnx2fc_pending_work(struct bnx2fc_rport *tgt, unsigned int wqe) { unsigned int cpu = wqe % num_possible_cpus(); struct bnx2fc_percpu_s *fps; struct bnx2fc_work *work; + struct fcoe_task_ctx_entry *task; + struct fcoe_task_ctx_entry *task_page; + struct fcoe_port *port = tgt->port; + struct bnx2fc_interface *interface = port->priv; + struct bnx2fc_hba *hba = interface->hba; + unsigned char *rq_data = NULL; + unsigned char rq_data_buff[BNX2FC_RQ_BUF_SZ]; + int task_idx, index; + unsigned char *dummy; + u16 xid; + u8 num_rq; + int i; + + xid = wqe & FCOE_PEND_WQ_CQE_TASK_ID; + if (xid >= hba->max_tasks) { + pr_err(PFX "ERROR:xid out of range\n"); + return false; + } + + task_idx = xid / BNX2FC_TASKS_PER_PAGE; + index = xid % BNX2FC_TASKS_PER_PAGE; + task_page = (struct fcoe_task_ctx_entry *)hba->task_ctx[task_idx]; + task = &task_page[index]; + + num_rq = ((task->rxwr_txrd.var_ctx.rx_flags & + FCOE_TCE_RX_WR_TX_RD_VAR_NUM_RQ_WQE) >> + FCOE_TCE_RX_WR_TX_RD_VAR_NUM_RQ_WQE_SHIFT); + + memset(rq_data_buff, 0, BNX2FC_RQ_BUF_SZ); + + if (!num_rq) + goto num_rq_zero; + + rq_data = bnx2fc_get_next_rqe(tgt, 1); + + if (num_rq > 1) { + /* We do not need extra sense data */ + for (i = 1; i < num_rq; i++) + dummy = bnx2fc_get_next_rqe(tgt, 1); + } + + if (rq_data) + memcpy(rq_data_buff, rq_data, BNX2FC_RQ_BUF_SZ); + + /* return RQ entries */ + for (i = 0; i < num_rq; i++) + bnx2fc_return_rqe(tgt, 1); + +num_rq_zero: fps = &per_cpu(bnx2fc_percpu, cpu); spin_lock_bh(&fps->fp_work_lock); if (fps->iothread) { - work = bnx2fc_alloc_work(tgt, wqe); + work = bnx2fc_alloc_work(tgt, wqe, rq_data_buff, + num_rq, task); if (work) { list_add_tail(&work->list, &fps->work_list); wake_up_process(fps->iothread); spin_unlock_bh(&fps->fp_work_lock); - return; + return true; } } spin_unlock_bh(&fps->fp_work_lock); - bnx2fc_process_cq_compl(tgt, wqe); + bnx2fc_process_cq_compl(tgt, wqe, + rq_data_buff, num_rq, task); + + return true; } int bnx2fc_process_new_cqes(struct bnx2fc_rport *tgt) @@ -1056,8 +1103,8 @@ int bnx2fc_process_new_cqes(struct bnx2fc_rport *tgt) /* Unsolicited event notification */ bnx2fc_process_unsol_compl(tgt, wqe); } else { - bnx2fc_pending_work(tgt, wqe); - num_free_sqes++; + if (bnx2fc_pending_work(tgt, wqe)) + num_free_sqes++; } cqe++; tgt->cq_cons_idx++; diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index 4c8122a82322..2b070f0835df 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -24,7 +24,7 @@ static void bnx2fc_unmap_sg_list(struct bnx2fc_cmd *io_req); static void bnx2fc_free_mp_resc(struct bnx2fc_cmd *io_req); static void bnx2fc_parse_fcp_rsp(struct bnx2fc_cmd *io_req, struct fcoe_fcp_rsp_payload *fcp_rsp, - u8 num_rq); + u8 num_rq, unsigned char *rq_data); void bnx2fc_cmd_timer_set(struct bnx2fc_cmd *io_req, unsigned int timer_msec) @@ -1518,7 +1518,8 @@ static void bnx2fc_tgt_reset_cmpl(struct bnx2fc_cmd *io_req) } void bnx2fc_process_tm_compl(struct bnx2fc_cmd *io_req, - struct fcoe_task_ctx_entry *task, u8 num_rq) + struct fcoe_task_ctx_entry *task, u8 num_rq, + unsigned char *rq_data) { struct bnx2fc_mp_req *tm_req; struct fc_frame_header *fc_hdr; @@ -1557,7 +1558,7 @@ void bnx2fc_process_tm_compl(struct bnx2fc_cmd *io_req, if (fc_hdr->fh_r_ctl == FC_RCTL_DD_CMD_STATUS) { bnx2fc_parse_fcp_rsp(io_req, (struct fcoe_fcp_rsp_payload *) - rsp_buf, num_rq); + rsp_buf, num_rq, rq_data); if (io_req->fcp_rsp_code == 0) { /* TM successful */ if (tm_req->tm_flags & FCP_TMF_LUN_RESET) @@ -1755,15 +1756,11 @@ void bnx2fc_build_fcp_cmnd(struct bnx2fc_cmd *io_req, static void bnx2fc_parse_fcp_rsp(struct bnx2fc_cmd *io_req, struct fcoe_fcp_rsp_payload *fcp_rsp, - u8 num_rq) + u8 num_rq, unsigned char *rq_data) { struct scsi_cmnd *sc_cmd = io_req->sc_cmd; - struct bnx2fc_rport *tgt = io_req->tgt; u8 rsp_flags = fcp_rsp->fcp_flags.flags; u32 rq_buff_len = 0; - int i; - unsigned char *rq_data; - unsigned char *dummy; int fcp_sns_len = 0; int fcp_rsp_len = 0; @@ -1809,14 +1806,6 @@ static void bnx2fc_parse_fcp_rsp(struct bnx2fc_cmd *io_req, rq_buff_len = num_rq * BNX2FC_RQ_BUF_SZ; } - rq_data = bnx2fc_get_next_rqe(tgt, 1); - - if (num_rq > 1) { - /* We do not need extra sense data */ - for (i = 1; i < num_rq; i++) - dummy = bnx2fc_get_next_rqe(tgt, 1); - } - /* fetch fcp_rsp_code */ if ((fcp_rsp_len == 4) || (fcp_rsp_len == 8)) { /* Only for task management function */ @@ -1837,9 +1826,6 @@ static void bnx2fc_parse_fcp_rsp(struct bnx2fc_cmd *io_req, if (fcp_sns_len) memcpy(sc_cmd->sense_buffer, rq_data, fcp_sns_len); - /* return RQ entries */ - for (i = 0; i < num_rq; i++) - bnx2fc_return_rqe(tgt, 1); } } @@ -1918,7 +1904,7 @@ exit_qcmd: void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req, struct fcoe_task_ctx_entry *task, - u8 num_rq) + u8 num_rq, unsigned char *rq_data) { struct fcoe_fcp_rsp_payload *fcp_rsp; struct bnx2fc_rport *tgt = io_req->tgt; @@ -1931,6 +1917,12 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req, /* we will not receive ABTS response for this IO */ BNX2FC_IO_DBG(io_req, "Timer context finished processing " "this scsi cmd\n"); + if (test_and_clear_bit(BNX2FC_FLAG_IO_CLEANUP, + &io_req->req_flags)) { + BNX2FC_IO_DBG(io_req, + "Actual completion after cleanup request cleaning up\n"); + bnx2fc_process_cleanup_compl(io_req, task, num_rq); + } return; } @@ -1950,7 +1942,7 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req, &(task->rxwr_only.union_ctx.comp_info.fcp_rsp.payload); /* parse fcp_rsp and obtain sense data from RQ if available */ - bnx2fc_parse_fcp_rsp(io_req, fcp_rsp, num_rq); + bnx2fc_parse_fcp_rsp(io_req, fcp_rsp, num_rq, rq_data); if (!sc_cmd->SCp.ptr) { printk(KERN_ERR PFX "SCp.ptr is NULL\n"); diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c index d4c2a2e4c5d4..84d73f57292b 100644 --- a/drivers/scsi/constants.c +++ b/drivers/scsi/constants.c @@ -404,7 +404,7 @@ static const char * const hostbyte_table[]={ "DID_ABORT", "DID_PARITY", "DID_ERROR", "DID_RESET", "DID_BAD_INTR", "DID_PASSTHROUGH", "DID_SOFT_ERROR", "DID_IMM_RETRY", "DID_REQUEUE", "DID_TRANSPORT_DISRUPTED", "DID_TRANSPORT_FAILFAST", "DID_TARGET_FAILURE", -"DID_NEXUS_FAILURE" }; +"DID_NEXUS_FAILURE", "DID_ALLOC_FAILURE", "DID_MEDIUM_ERROR" }; static const char * const driverbyte_table[]={ "DRIVER_OK", "DRIVER_BUSY", "DRIVER_SOFT", "DRIVER_MEDIA", "DRIVER_ERROR", diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index da6e97d8dc3b..773c45af9387 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -632,6 +632,8 @@ static void fc_rport_error(struct fc_rport_priv *rdata, int err) fc_rport_enter_ready(rdata); break; case RPORT_ST_PRLI: + fc_rport_enter_plogi(rdata); + break; case RPORT_ST_ADISC: fc_rport_enter_logo(rdata); break; @@ -1208,9 +1210,15 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp, rjt = fc_frame_payload_get(fp, sizeof(*rjt)); if (!rjt) FC_RPORT_DBG(rdata, "PRLI bad response\n"); - else + else { FC_RPORT_DBG(rdata, "PRLI ELS rejected, reason %x expl %x\n", rjt->er_reason, rjt->er_explan); + if (rjt->er_reason == ELS_RJT_UNAB && + rjt->er_explan == ELS_EXPL_PLOGI_REQD) { + fc_rport_enter_plogi(rdata); + goto out; + } + } fc_rport_error_retry(rdata, FC_EX_ELS_RJT); } diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 357fdec06bae..8e2a356911a9 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -207,8 +207,7 @@ typedef struct lpfc_vpd { } rev; struct { #ifdef __BIG_ENDIAN_BITFIELD - uint32_t rsvd3 :19; /* Reserved */ - uint32_t cdss : 1; /* Configure Data Security SLI */ + uint32_t rsvd3 :20; /* Reserved */ uint32_t rsvd2 : 3; /* Reserved */ uint32_t cbg : 1; /* Configure BlockGuard */ uint32_t cmv : 1; /* Configure Max VPIs */ @@ -230,8 +229,7 @@ typedef struct lpfc_vpd { uint32_t cmv : 1; /* Configure Max VPIs */ uint32_t cbg : 1; /* Configure BlockGuard */ uint32_t rsvd2 : 3; /* Reserved */ - uint32_t cdss : 1; /* Configure Data Security SLI */ - uint32_t rsvd3 :19; /* Reserved */ + uint32_t rsvd3 :20; /* Reserved */ #endif } sli3Feat; } lpfc_vpd_t; @@ -480,8 +478,8 @@ struct lpfc_vport { struct dentry *debug_nodelist; struct dentry *debug_nvmestat; struct dentry *debug_scsistat; - struct dentry *debug_nvmektime; - struct dentry *debug_cpucheck; + struct dentry *debug_ioktime; + struct dentry *debug_hdwqstat; struct dentry *vport_debugfs_root; struct lpfc_debugfs_trc *disc_trc; atomic_t disc_trc_cnt; @@ -887,7 +885,6 @@ struct lpfc_hba { #define LPFC_INITIALIZE_LINK 0 /* do normal init_link mbox */ #define LPFC_DELAY_INIT_LINK 1 /* layered driver hold off */ #define LPFC_DELAY_INIT_LINK_INDEFINITELY 2 /* wait, manual intervention */ - uint32_t cfg_enable_dss; uint32_t cfg_fdmi_on; #define LPFC_FDMI_NO_SUPPORT 0 /* FDMI not supported */ #define LPFC_FDMI_SUPPORT 1 /* FDMI supported? */ @@ -1156,8 +1153,6 @@ struct lpfc_hba { uint32_t iocb_cnt; uint32_t iocb_max; atomic_t sdev_cnt; - uint8_t fips_spec_rev; - uint8_t fips_level; spinlock_t devicelock; /* lock for luns list */ mempool_t *device_data_mem_pool; struct list_head luns; @@ -1175,12 +1170,11 @@ struct lpfc_hba { uint16_t sfp_warning; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS - uint16_t cpucheck_on; + uint16_t hdwqstat_on; #define LPFC_CHECK_OFF 0 #define LPFC_CHECK_NVME_IO 1 -#define LPFC_CHECK_NVMET_RCV 2 -#define LPFC_CHECK_NVMET_IO 4 -#define LPFC_CHECK_SCSI_IO 8 +#define LPFC_CHECK_NVMET_IO 2 +#define LPFC_CHECK_SCSI_IO 4 uint16_t ktime_on; uint64_t ktime_data_samples; uint64_t ktime_status_samples; @@ -1225,6 +1219,11 @@ struct lpfc_hba { #define LPFC_POLL_SLOWPATH 1 /* called from slowpath */ char os_host_name[MAXHOSTNAMELEN]; + + /* SCSI host template information - for physical port */ + struct scsi_host_template port_template; + /* SCSI host template information - for all vports */ + struct scsi_host_template vport_template; }; static inline struct Scsi_Host * diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index be3b0ccbac78..1354c141d614 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -2231,66 +2231,6 @@ lpfc_poll_store(struct device *dev, struct device_attribute *attr, } /** - * lpfc_fips_level_show - Return the current FIPS level for the HBA - * @dev: class unused variable. - * @attr: device attribute, not used. - * @buf: on return contains the module description text. - * - * Returns: size of formatted string. - **/ -static ssize_t -lpfc_fips_level_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct Scsi_Host *shost = class_to_shost(dev); - struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata; - struct lpfc_hba *phba = vport->phba; - - return scnprintf(buf, PAGE_SIZE, "%d\n", phba->fips_level); -} - -/** - * lpfc_fips_rev_show - Return the FIPS Spec revision for the HBA - * @dev: class unused variable. - * @attr: device attribute, not used. - * @buf: on return contains the module description text. - * - * Returns: size of formatted string. - **/ -static ssize_t -lpfc_fips_rev_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct Scsi_Host *shost = class_to_shost(dev); - struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata; - struct lpfc_hba *phba = vport->phba; - - return scnprintf(buf, PAGE_SIZE, "%d\n", phba->fips_spec_rev); -} - -/** - * lpfc_dss_show - Return the current state of dss and the configured state - * @dev: class converted to a Scsi_host structure. - * @attr: device attribute, not used. - * @buf: on return contains the formatted text. - * - * Returns: size of formatted string. - **/ -static ssize_t -lpfc_dss_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct Scsi_Host *shost = class_to_shost(dev); - struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata; - struct lpfc_hba *phba = vport->phba; - - return scnprintf(buf, PAGE_SIZE, "%s - %sOperational\n", - (phba->cfg_enable_dss) ? "Enabled" : "Disabled", - (phba->sli3_options & LPFC_SLI3_DSS_ENABLED) ? - "" : "Not "); -} - -/** * lpfc_sriov_hw_max_virtfn_show - Return maximum number of virtual functions * @dev: class converted to a Scsi_host structure. * @attr: device attribute, not used. @@ -2705,9 +2645,6 @@ static DEVICE_ATTR(max_xri, S_IRUGO, lpfc_max_xri_show, NULL); static DEVICE_ATTR(used_xri, S_IRUGO, lpfc_used_xri_show, NULL); static DEVICE_ATTR(npiv_info, S_IRUGO, lpfc_npiv_info_show, NULL); static DEVICE_ATTR_RO(lpfc_temp_sensor); -static DEVICE_ATTR_RO(lpfc_fips_level); -static DEVICE_ATTR_RO(lpfc_fips_rev); -static DEVICE_ATTR_RO(lpfc_dss); static DEVICE_ATTR_RO(lpfc_sriov_hw_max_virtfn); static DEVICE_ATTR(protocol, S_IRUGO, lpfc_sli4_protocol_show, NULL); static DEVICE_ATTR(lpfc_xlane_supported, S_IRUGO, lpfc_oas_supported_show, @@ -3868,9 +3805,9 @@ LPFC_VPORT_ATTR_R(enable_da_id, 1, 0, 1, /* # lun_queue_depth: This parameter is used to limit the number of outstanding -# commands per FCP LUN. Value range is [1,512]. Default value is 30. +# commands per FCP LUN. */ -LPFC_VPORT_ATTR_R(lun_queue_depth, 30, 1, 512, +LPFC_VPORT_ATTR_R(lun_queue_depth, 64, 1, 512, "Max number of FCP commands we can queue to a specific LUN"); /* @@ -6251,9 +6188,6 @@ struct device_attribute *lpfc_hba_attrs[] = { &dev_attr_pt, &dev_attr_txq_hw, &dev_attr_txcmplq_hw, - &dev_attr_lpfc_fips_level, - &dev_attr_lpfc_fips_rev, - &dev_attr_lpfc_dss, &dev_attr_lpfc_sriov_hw_max_virtfn, &dev_attr_protocol, &dev_attr_lpfc_xlane_supported, @@ -6289,8 +6223,6 @@ struct device_attribute *lpfc_vport_attrs[] = { &dev_attr_lpfc_max_scsicmpl_time, &dev_attr_lpfc_stat_data_ctrl, &dev_attr_lpfc_static_vport, - &dev_attr_lpfc_fips_level, - &dev_attr_lpfc_fips_rev, NULL, }; @@ -7399,7 +7331,6 @@ lpfc_get_cfgparam(struct lpfc_hba *phba) lpfc_suppress_link_up_init(phba, lpfc_suppress_link_up); lpfc_delay_discovery_init(phba, lpfc_delay_discovery); lpfc_sli_mode_init(phba, lpfc_sli_mode); - phba->cfg_enable_dss = 1; lpfc_enable_mds_diags_init(phba, lpfc_enable_mds_diags); lpfc_ras_fwlog_buffsize_init(phba, lpfc_ras_fwlog_buffsize); lpfc_ras_fwlog_level_init(phba, lpfc_ras_fwlog_level); diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index a450477a7e00..76dc8d9493d2 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -404,9 +404,7 @@ void lpfc_free_sysfs_attr(struct lpfc_vport *); extern struct device_attribute *lpfc_hba_attrs[]; extern struct device_attribute *lpfc_vport_attrs[]; extern struct scsi_host_template lpfc_template; -extern struct scsi_host_template lpfc_template_no_hr; extern struct scsi_host_template lpfc_template_nvme; -extern struct scsi_host_template lpfc_vport_template; extern struct fc_function_template lpfc_transport_functions; extern struct fc_function_template lpfc_vport_transport_functions; @@ -590,6 +588,7 @@ struct lpfc_io_buf *lpfc_get_io_buf(struct lpfc_hba *phba, int); void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *ncmd, struct lpfc_sli4_hdw_queue *qp); +void lpfc_io_ktime(struct lpfc_hba *phba, struct lpfc_io_buf *ncmd); void lpfc_nvme_cmd_template(void); void lpfc_nvmet_cmd_template(void); void lpfc_nvme_cancel_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn); diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 819335b16c2e..8a6e02aa553f 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -1300,8 +1300,88 @@ buffer_done: return len; } +void +lpfc_io_ktime(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd) +{ + uint64_t seg1, seg2, seg3, seg4; + uint64_t segsum; + + if (!lpfc_cmd->ts_last_cmd || + !lpfc_cmd->ts_cmd_start || + !lpfc_cmd->ts_cmd_wqput || + !lpfc_cmd->ts_isr_cmpl || + !lpfc_cmd->ts_data_io) + return; + + if (lpfc_cmd->ts_data_io < lpfc_cmd->ts_cmd_start) + return; + if (lpfc_cmd->ts_cmd_start < lpfc_cmd->ts_last_cmd) + return; + if (lpfc_cmd->ts_cmd_wqput < lpfc_cmd->ts_cmd_start) + return; + if (lpfc_cmd->ts_isr_cmpl < lpfc_cmd->ts_cmd_wqput) + return; + if (lpfc_cmd->ts_data_io < lpfc_cmd->ts_isr_cmpl) + return; + /* + * Segment 1 - Time from Last FCP command cmpl is handed + * off to NVME Layer to start of next command. + * Segment 2 - Time from Driver receives a IO cmd start + * from NVME Layer to WQ put is done on IO cmd. + * Segment 3 - Time from Driver WQ put is done on IO cmd + * to MSI-X ISR for IO cmpl. + * Segment 4 - Time from MSI-X ISR for IO cmpl to when + * cmpl is handled off to the NVME Layer. + */ + seg1 = lpfc_cmd->ts_cmd_start - lpfc_cmd->ts_last_cmd; + if (seg1 > 5000000) /* 5 ms - for sequential IOs only */ + seg1 = 0; + + /* Calculate times relative to start of IO */ + seg2 = (lpfc_cmd->ts_cmd_wqput - lpfc_cmd->ts_cmd_start); + segsum = seg2; + seg3 = lpfc_cmd->ts_isr_cmpl - lpfc_cmd->ts_cmd_start; + if (segsum > seg3) + return; + seg3 -= segsum; + segsum += seg3; + + seg4 = lpfc_cmd->ts_data_io - lpfc_cmd->ts_cmd_start; + if (segsum > seg4) + return; + seg4 -= segsum; + + phba->ktime_data_samples++; + phba->ktime_seg1_total += seg1; + if (seg1 < phba->ktime_seg1_min) + phba->ktime_seg1_min = seg1; + else if (seg1 > phba->ktime_seg1_max) + phba->ktime_seg1_max = seg1; + phba->ktime_seg2_total += seg2; + if (seg2 < phba->ktime_seg2_min) + phba->ktime_seg2_min = seg2; + else if (seg2 > phba->ktime_seg2_max) + phba->ktime_seg2_max = seg2; + phba->ktime_seg3_total += seg3; + if (seg3 < phba->ktime_seg3_min) + phba->ktime_seg3_min = seg3; + else if (seg3 > phba->ktime_seg3_max) + phba->ktime_seg3_max = seg3; + phba->ktime_seg4_total += seg4; + if (seg4 < phba->ktime_seg4_min) + phba->ktime_seg4_min = seg4; + else if (seg4 > phba->ktime_seg4_max) + phba->ktime_seg4_max = seg4; + + lpfc_cmd->ts_last_cmd = 0; + lpfc_cmd->ts_cmd_start = 0; + lpfc_cmd->ts_cmd_wqput = 0; + lpfc_cmd->ts_isr_cmpl = 0; + lpfc_cmd->ts_data_io = 0; +} + /** - * lpfc_debugfs_nvmektime_data - Dump target node list to a buffer + * lpfc_debugfs_ioktime_data - Dump target node list to a buffer * @vport: The vport to gather target node info from. * @buf: The buffer to dump log into. * @size: The maximum amount of data to process. @@ -1314,13 +1394,13 @@ buffer_done: * not exceed @size. **/ static int -lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size) +lpfc_debugfs_ioktime_data(struct lpfc_vport *vport, char *buf, int size) { struct lpfc_hba *phba = vport->phba; int len = 0; if (phba->nvmet_support == 0) { - /* NVME Initiator */ + /* Initiator */ len += scnprintf(buf + len, PAGE_SIZE - len, "ktime %s: Total Samples: %lld\n", (phba->ktime_on ? "Enabled" : "Disabled"), @@ -1330,8 +1410,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size) len += scnprintf( buf + len, PAGE_SIZE - len, - "Segment 1: Last NVME Cmd cmpl " - "done -to- Start of next NVME cnd (in driver)\n"); + "Segment 1: Last Cmd cmpl " + "done -to- Start of next Cmd (in driver)\n"); len += scnprintf( buf + len, PAGE_SIZE - len, "avg:%08lld min:%08lld max %08lld\n", @@ -1341,7 +1421,7 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size) phba->ktime_seg1_max); len += scnprintf( buf + len, PAGE_SIZE - len, - "Segment 2: Driver start of NVME cmd " + "Segment 2: Driver start of Cmd " "-to- Firmware WQ doorbell\n"); len += scnprintf( buf + len, PAGE_SIZE - len, @@ -1364,7 +1444,7 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size) len += scnprintf( buf + len, PAGE_SIZE - len, "Segment 4: MSI-X ISR cmpl -to- " - "NVME cmpl done\n"); + "Cmd cmpl done\n"); len += scnprintf( buf + len, PAGE_SIZE - len, "avg:%08lld min:%08lld max %08lld\n", @@ -1603,42 +1683,50 @@ out: } /** - * lpfc_debugfs_cpucheck_data - Dump target node list to a buffer + * lpfc_debugfs_hdwqstat_data - Dump I/O stats to a buffer * @vport: The vport to gather target node info from. * @buf: The buffer to dump log into. * @size: The maximum amount of data to process. * * Description: - * This routine dumps the NVME statistics associated with @vport + * This routine dumps the NVME + SCSI statistics associated with @vport * * Return Value: * This routine returns the amount of bytes that were dumped into @buf and will * not exceed @size. **/ static int -lpfc_debugfs_cpucheck_data(struct lpfc_vport *vport, char *buf, int size) +lpfc_debugfs_hdwqstat_data(struct lpfc_vport *vport, char *buf, int size) { struct lpfc_hba *phba = vport->phba; struct lpfc_sli4_hdw_queue *qp; - int i, j, max_cnt; - int len = 0; + struct lpfc_hdwq_stat *c_stat; + int i, j, len; uint32_t tot_xmt; uint32_t tot_rcv; uint32_t tot_cmpl; + char tmp[LPFC_MAX_SCSI_INFO_TMP_LEN] = {0}; - len += scnprintf(buf + len, PAGE_SIZE - len, - "CPUcheck %s ", - (phba->cpucheck_on & LPFC_CHECK_NVME_IO ? - "Enabled" : "Disabled")); - if (phba->nvmet_support) { - len += scnprintf(buf + len, PAGE_SIZE - len, - "%s\n", - (phba->cpucheck_on & LPFC_CHECK_NVMET_RCV ? - "Rcv Enabled\n" : "Rcv Disabled\n")); - } else { - len += scnprintf(buf + len, PAGE_SIZE - len, "\n"); - } - max_cnt = size - LPFC_DEBUG_OUT_LINE_SZ; + scnprintf(tmp, sizeof(tmp), "HDWQ Stats:\n\n"); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; + + scnprintf(tmp, sizeof(tmp), "(NVME Accounting: %s) ", + (phba->hdwqstat_on & + (LPFC_CHECK_NVME_IO | LPFC_CHECK_NVMET_IO) ? + "Enabled" : "Disabled")); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; + + scnprintf(tmp, sizeof(tmp), "(SCSI Accounting: %s) ", + (phba->hdwqstat_on & LPFC_CHECK_SCSI_IO ? + "Enabled" : "Disabled")); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; + + scnprintf(tmp, sizeof(tmp), "\n\n"); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; for (i = 0; i < phba->cfg_hdw_queue; i++) { qp = &phba->sli4_hba.hdwq[i]; @@ -1646,46 +1734,76 @@ lpfc_debugfs_cpucheck_data(struct lpfc_vport *vport, char *buf, int size) tot_rcv = 0; tot_xmt = 0; tot_cmpl = 0; - for (j = 0; j < LPFC_CHECK_CPU_CNT; j++) { - tot_xmt += qp->cpucheck_xmt_io[j]; - tot_cmpl += qp->cpucheck_cmpl_io[j]; - if (phba->nvmet_support) - tot_rcv += qp->cpucheck_rcv_io[j]; - } - /* Only display Hardware Qs with something */ - if (!tot_xmt && !tot_cmpl && !tot_rcv) - continue; + for_each_present_cpu(j) { + c_stat = per_cpu_ptr(phba->sli4_hba.c_stat, j); + + /* Only display for this HDWQ */ + if (i != c_stat->hdwq_no) + continue; - len += scnprintf(buf + len, PAGE_SIZE - len, - "HDWQ %03d: ", i); - for (j = 0; j < LPFC_CHECK_CPU_CNT; j++) { /* Only display non-zero counters */ - if (!qp->cpucheck_xmt_io[j] && - !qp->cpucheck_cmpl_io[j] && - !qp->cpucheck_rcv_io[j]) + if (!c_stat->xmt_io && !c_stat->cmpl_io && + !c_stat->rcv_io) continue; + + if (!tot_xmt && !tot_cmpl && !tot_rcv) { + /* Print HDWQ string only the first time */ + scnprintf(tmp, sizeof(tmp), "[HDWQ %d]:\t", i); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; + } + + tot_xmt += c_stat->xmt_io; + tot_cmpl += c_stat->cmpl_io; + if (phba->nvmet_support) + tot_rcv += c_stat->rcv_io; + + scnprintf(tmp, sizeof(tmp), "| [CPU %d]: ", j); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; + if (phba->nvmet_support) { - len += scnprintf(buf + len, PAGE_SIZE - len, - "CPU %03d: %x/%x/%x ", j, - qp->cpucheck_rcv_io[j], - qp->cpucheck_xmt_io[j], - qp->cpucheck_cmpl_io[j]); + scnprintf(tmp, sizeof(tmp), + "XMT 0x%x CMPL 0x%x RCV 0x%x |", + c_stat->xmt_io, c_stat->cmpl_io, + c_stat->rcv_io); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; } else { - len += scnprintf(buf + len, PAGE_SIZE - len, - "CPU %03d: %x/%x ", j, - qp->cpucheck_xmt_io[j], - qp->cpucheck_cmpl_io[j]); + scnprintf(tmp, sizeof(tmp), + "XMT 0x%x CMPL 0x%x |", + c_stat->xmt_io, c_stat->cmpl_io); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; } } - len += scnprintf(buf + len, PAGE_SIZE - len, - "Total: %x\n", tot_xmt); - if (len >= max_cnt) { - len += scnprintf(buf + len, PAGE_SIZE - len, - "Truncated ...\n"); - return len; + + /* Check if nothing to display */ + if (!tot_xmt && !tot_cmpl && !tot_rcv) + continue; + + scnprintf(tmp, sizeof(tmp), "\t->\t[HDWQ Total: "); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; + + if (phba->nvmet_support) { + scnprintf(tmp, sizeof(tmp), + "XMT 0x%x CMPL 0x%x RCV 0x%x]\n\n", + tot_xmt, tot_cmpl, tot_rcv); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; + } else { + scnprintf(tmp, sizeof(tmp), + "XMT 0x%x CMPL 0x%x]\n\n", + tot_xmt, tot_cmpl); + if (strlcat(buf, tmp, size) >= size) + goto buffer_done; } } + +buffer_done: + len = strnlen(buf, size); return len; } @@ -2689,7 +2807,7 @@ lpfc_debugfs_scsistat_write(struct file *file, const char __user *buf, } static int -lpfc_debugfs_nvmektime_open(struct inode *inode, struct file *file) +lpfc_debugfs_ioktime_open(struct inode *inode, struct file *file) { struct lpfc_vport *vport = inode->i_private; struct lpfc_debug *debug; @@ -2700,14 +2818,14 @@ lpfc_debugfs_nvmektime_open(struct inode *inode, struct file *file) goto out; /* Round to page boundary */ - debug->buffer = kmalloc(LPFC_NVMEKTIME_SIZE, GFP_KERNEL); + debug->buffer = kmalloc(LPFC_IOKTIME_SIZE, GFP_KERNEL); if (!debug->buffer) { kfree(debug); goto out; } - debug->len = lpfc_debugfs_nvmektime_data(vport, debug->buffer, - LPFC_NVMEKTIME_SIZE); + debug->len = lpfc_debugfs_ioktime_data(vport, debug->buffer, + LPFC_IOKTIME_SIZE); debug->i_private = inode->i_private; file->private_data = debug; @@ -2718,8 +2836,8 @@ out: } static ssize_t -lpfc_debugfs_nvmektime_write(struct file *file, const char __user *buf, - size_t nbytes, loff_t *ppos) +lpfc_debugfs_ioktime_write(struct file *file, const char __user *buf, + size_t nbytes, loff_t *ppos) { struct lpfc_debug *debug = file->private_data; struct lpfc_vport *vport = (struct lpfc_vport *)debug->i_private; @@ -2921,7 +3039,7 @@ lpfc_debugfs_nvmeio_trc_write(struct file *file, const char __user *buf, } static int -lpfc_debugfs_cpucheck_open(struct inode *inode, struct file *file) +lpfc_debugfs_hdwqstat_open(struct inode *inode, struct file *file) { struct lpfc_vport *vport = inode->i_private; struct lpfc_debug *debug; @@ -2932,14 +3050,14 @@ lpfc_debugfs_cpucheck_open(struct inode *inode, struct file *file) goto out; /* Round to page boundary */ - debug->buffer = kmalloc(LPFC_CPUCHECK_SIZE, GFP_KERNEL); + debug->buffer = kcalloc(1, LPFC_SCSISTAT_SIZE, GFP_KERNEL); if (!debug->buffer) { kfree(debug); goto out; } - debug->len = lpfc_debugfs_cpucheck_data(vport, debug->buffer, - LPFC_CPUCHECK_SIZE); + debug->len = lpfc_debugfs_hdwqstat_data(vport, debug->buffer, + LPFC_SCSISTAT_SIZE); debug->i_private = inode->i_private; file->private_data = debug; @@ -2950,16 +3068,16 @@ out: } static ssize_t -lpfc_debugfs_cpucheck_write(struct file *file, const char __user *buf, +lpfc_debugfs_hdwqstat_write(struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos) { struct lpfc_debug *debug = file->private_data; struct lpfc_vport *vport = (struct lpfc_vport *)debug->i_private; struct lpfc_hba *phba = vport->phba; - struct lpfc_sli4_hdw_queue *qp; + struct lpfc_hdwq_stat *c_stat; char mybuf[64]; char *pbuf; - int i, j; + int i; if (nbytes > 64) nbytes = 64; @@ -2972,41 +3090,39 @@ lpfc_debugfs_cpucheck_write(struct file *file, const char __user *buf, if ((strncmp(pbuf, "on", sizeof("on") - 1) == 0)) { if (phba->nvmet_support) - phba->cpucheck_on |= LPFC_CHECK_NVMET_IO; + phba->hdwqstat_on |= LPFC_CHECK_NVMET_IO; else - phba->cpucheck_on |= (LPFC_CHECK_NVME_IO | + phba->hdwqstat_on |= (LPFC_CHECK_NVME_IO | LPFC_CHECK_SCSI_IO); return strlen(pbuf); } else if ((strncmp(pbuf, "nvme_on", sizeof("nvme_on") - 1) == 0)) { if (phba->nvmet_support) - phba->cpucheck_on |= LPFC_CHECK_NVMET_IO; + phba->hdwqstat_on |= LPFC_CHECK_NVMET_IO; else - phba->cpucheck_on |= LPFC_CHECK_NVME_IO; + phba->hdwqstat_on |= LPFC_CHECK_NVME_IO; return strlen(pbuf); } else if ((strncmp(pbuf, "scsi_on", sizeof("scsi_on") - 1) == 0)) { - phba->cpucheck_on |= LPFC_CHECK_SCSI_IO; + if (!phba->nvmet_support) + phba->hdwqstat_on |= LPFC_CHECK_SCSI_IO; return strlen(pbuf); - } else if ((strncmp(pbuf, "rcv", - sizeof("rcv") - 1) == 0)) { - if (phba->nvmet_support) - phba->cpucheck_on |= LPFC_CHECK_NVMET_RCV; - else - return -EINVAL; + } else if ((strncmp(pbuf, "nvme_off", sizeof("nvme_off") - 1) == 0)) { + phba->hdwqstat_on &= ~(LPFC_CHECK_NVME_IO | + LPFC_CHECK_NVMET_IO); + return strlen(pbuf); + } else if ((strncmp(pbuf, "scsi_off", sizeof("scsi_off") - 1) == 0)) { + phba->hdwqstat_on &= ~LPFC_CHECK_SCSI_IO; return strlen(pbuf); } else if ((strncmp(pbuf, "off", sizeof("off") - 1) == 0)) { - phba->cpucheck_on = LPFC_CHECK_OFF; + phba->hdwqstat_on = LPFC_CHECK_OFF; return strlen(pbuf); } else if ((strncmp(pbuf, "zero", sizeof("zero") - 1) == 0)) { - for (i = 0; i < phba->cfg_hdw_queue; i++) { - qp = &phba->sli4_hba.hdwq[i]; - - for (j = 0; j < LPFC_CHECK_CPU_CNT; j++) { - qp->cpucheck_rcv_io[j] = 0; - qp->cpucheck_xmt_io[j] = 0; - qp->cpucheck_cmpl_io[j] = 0; - } + for_each_present_cpu(i) { + c_stat = per_cpu_ptr(phba->sli4_hba.c_stat, i); + c_stat->xmt_io = 0; + c_stat->cmpl_io = 0; + c_stat->rcv_io = 0; } return strlen(pbuf); } @@ -5431,13 +5547,13 @@ static const struct file_operations lpfc_debugfs_op_scsistat = { .release = lpfc_debugfs_release, }; -#undef lpfc_debugfs_op_nvmektime -static const struct file_operations lpfc_debugfs_op_nvmektime = { +#undef lpfc_debugfs_op_ioktime +static const struct file_operations lpfc_debugfs_op_ioktime = { .owner = THIS_MODULE, - .open = lpfc_debugfs_nvmektime_open, + .open = lpfc_debugfs_ioktime_open, .llseek = lpfc_debugfs_lseek, .read = lpfc_debugfs_read, - .write = lpfc_debugfs_nvmektime_write, + .write = lpfc_debugfs_ioktime_write, .release = lpfc_debugfs_release, }; @@ -5451,13 +5567,13 @@ static const struct file_operations lpfc_debugfs_op_nvmeio_trc = { .release = lpfc_debugfs_release, }; -#undef lpfc_debugfs_op_cpucheck -static const struct file_operations lpfc_debugfs_op_cpucheck = { +#undef lpfc_debugfs_op_hdwqstat +static const struct file_operations lpfc_debugfs_op_hdwqstat = { .owner = THIS_MODULE, - .open = lpfc_debugfs_cpucheck_open, + .open = lpfc_debugfs_hdwqstat_open, .llseek = lpfc_debugfs_lseek, .read = lpfc_debugfs_read, - .write = lpfc_debugfs_cpucheck_write, + .write = lpfc_debugfs_hdwqstat_write, .release = lpfc_debugfs_release, }; @@ -6075,17 +6191,22 @@ nvmeio_off: goto debug_failed; } - snprintf(name, sizeof(name), "nvmektime"); - vport->debug_nvmektime = + snprintf(name, sizeof(name), "ioktime"); + vport->debug_ioktime = debugfs_create_file(name, 0644, vport->vport_debugfs_root, - vport, &lpfc_debugfs_op_nvmektime); + vport, &lpfc_debugfs_op_ioktime); + if (!vport->debug_ioktime) { + lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, + "0815 Cannot create debugfs ioktime\n"); + goto debug_failed; + } - snprintf(name, sizeof(name), "cpucheck"); - vport->debug_cpucheck = + snprintf(name, sizeof(name), "hdwqstat"); + vport->debug_hdwqstat = debugfs_create_file(name, 0644, vport->vport_debugfs_root, - vport, &lpfc_debugfs_op_cpucheck); + vport, &lpfc_debugfs_op_hdwqstat); /* * The following section is for additional directories/files for the @@ -6216,11 +6337,11 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport) debugfs_remove(vport->debug_scsistat); /* scsistat */ vport->debug_scsistat = NULL; - debugfs_remove(vport->debug_nvmektime); /* nvmektime */ - vport->debug_nvmektime = NULL; + debugfs_remove(vport->debug_ioktime); /* ioktime */ + vport->debug_ioktime = NULL; - debugfs_remove(vport->debug_cpucheck); /* cpucheck */ - vport->debug_cpucheck = NULL; + debugfs_remove(vport->debug_hdwqstat); /* hdwqstat */ + vport->debug_hdwqstat = NULL; if (vport->vport_debugfs_root) { debugfs_remove(vport->vport_debugfs_root); /* vportX */ diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h index 20f2537af511..7ab6d3b08698 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.h +++ b/drivers/scsi/lpfc/lpfc_debugfs.h @@ -46,8 +46,7 @@ /* nvmestat output buffer size */ #define LPFC_NVMESTAT_SIZE 8192 -#define LPFC_NVMEKTIME_SIZE 8192 -#define LPFC_CPUCHECK_SIZE 8192 +#define LPFC_IOKTIME_SIZE 8192 #define LPFC_NVMEIO_TRC_SIZE 8192 /* scsistat output buffer size */ diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h index ae51c0dbba0a..c20034b3101c 100644 --- a/drivers/scsi/lpfc/lpfc_hw.h +++ b/drivers/scsi/lpfc/lpfc_hw.h @@ -3262,8 +3262,7 @@ typedef struct { #endif #ifdef __BIG_ENDIAN_BITFIELD - uint32_t rsvd1 : 19; /* Reserved */ - uint32_t cdss : 1; /* Configure Data Security SLI */ + uint32_t rsvd1 : 20; /* Reserved */ uint32_t casabt : 1; /* Configure async abts status notice */ uint32_t rsvd2 : 2; /* Reserved */ uint32_t cbg : 1; /* Configure BlockGuard */ @@ -3287,12 +3286,10 @@ typedef struct { uint32_t cbg : 1; /* Configure BlockGuard */ uint32_t rsvd2 : 2; /* Reserved */ uint32_t casabt : 1; /* Configure async abts status notice */ - uint32_t cdss : 1; /* Configure Data Security SLI */ - uint32_t rsvd1 : 19; /* Reserved */ + uint32_t rsvd1 : 20; /* Reserved */ #endif #ifdef __BIG_ENDIAN_BITFIELD - uint32_t rsvd3 : 19; /* Reserved */ - uint32_t gdss : 1; /* Configure Data Security SLI */ + uint32_t rsvd3 : 20; /* Reserved */ uint32_t gasabt : 1; /* Grant async abts status notice */ uint32_t rsvd4 : 2; /* Reserved */ uint32_t gbg : 1; /* Grant BlockGuard */ @@ -3316,8 +3313,7 @@ typedef struct { uint32_t gbg : 1; /* Grant BlockGuard */ uint32_t rsvd4 : 2; /* Reserved */ uint32_t gasabt : 1; /* Grant async abts status notice */ - uint32_t gdss : 1; /* Configure Data Security SLI */ - uint32_t rsvd3 : 19; /* Reserved */ + uint32_t rsvd3 : 20; /* Reserved */ #endif #ifdef __BIG_ENDIAN_BITFIELD @@ -3339,15 +3335,11 @@ typedef struct { uint32_t rsvd6; /* Reserved */ #ifdef __BIG_ENDIAN_BITFIELD - uint32_t fips_rev : 3; /* FIPS Spec Revision */ - uint32_t fips_level : 4; /* FIPS Level */ - uint32_t sec_err : 9; /* security crypto error */ + uint32_t rsvd7 : 16; uint32_t max_vpi : 16; /* Max number of virt N-Ports */ #else /* __LITTLE_ENDIAN */ uint32_t max_vpi : 16; /* Max number of virt N-Ports */ - uint32_t sec_err : 9; /* security crypto error */ - uint32_t fips_level : 4; /* FIPS Level */ - uint32_t fips_rev : 3; /* FIPS Spec Revision */ + uint32_t rsvd7 : 16; #endif } CONFIG_PORT_VAR; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 9d03e9b71efb..4104bdcdbb6f 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -4231,6 +4231,7 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) { struct lpfc_vport *vport; struct Scsi_Host *shost = NULL; + struct scsi_host_template *template; int error = 0; int i; uint64_t wwn; @@ -4259,22 +4260,50 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) } } - if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) { - if (dev != &phba->pcidev->dev) { - shost = scsi_host_alloc(&lpfc_vport_template, - sizeof(struct lpfc_vport)); + /* Seed template for SCSI host registration */ + if (dev == &phba->pcidev->dev) { + template = &phba->port_template; + + if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) { + /* Seed physical port template */ + memcpy(template, &lpfc_template, sizeof(*template)); + + if (use_no_reset_hba) { + /* template is for a no reset SCSI Host */ + template->max_sectors = 0xffff; + template->eh_host_reset_handler = NULL; + } + + /* Template for all vports this physical port creates */ + memcpy(&phba->vport_template, &lpfc_template, + sizeof(*template)); + phba->vport_template.max_sectors = 0xffff; + phba->vport_template.shost_attrs = lpfc_vport_attrs; + phba->vport_template.eh_bus_reset_handler = NULL; + phba->vport_template.eh_host_reset_handler = NULL; + phba->vport_template.vendor_id = 0; + + /* Initialize the host templates with updated value */ + if (phba->sli_rev == LPFC_SLI_REV4) { + template->sg_tablesize = phba->cfg_scsi_seg_cnt; + phba->vport_template.sg_tablesize = + phba->cfg_scsi_seg_cnt; + } else { + template->sg_tablesize = phba->cfg_sg_seg_cnt; + phba->vport_template.sg_tablesize = + phba->cfg_sg_seg_cnt; + } + } else { - if (!use_no_reset_hba) - shost = scsi_host_alloc(&lpfc_template, - sizeof(struct lpfc_vport)); - else - shost = scsi_host_alloc(&lpfc_template_no_hr, - sizeof(struct lpfc_vport)); + /* NVMET is for physical port only */ + memcpy(template, &lpfc_template_nvme, + sizeof(*template)); } - } else if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { - shost = scsi_host_alloc(&lpfc_template_nvme, - sizeof(struct lpfc_vport)); + } else { + template = &phba->vport_template; } + + shost = scsi_host_alloc(template, sizeof(struct lpfc_vport)); if (!shost) goto out; @@ -4329,6 +4358,12 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) vport->port_type = LPFC_PHYSICAL_PORT; } + lpfc_printf_log(phba, KERN_INFO, LOG_INIT | LOG_FCP, + "9081 CreatePort TMPLATE type %x TBLsize %d " + "SEGcnt %d/%d\n", + vport->port_type, shost->sg_tablesize, + phba->cfg_scsi_seg_cnt, phba->cfg_sg_seg_cnt); + /* Initialize all internally managed lists. */ INIT_LIST_HEAD(&vport->fc_nodes); INIT_LIST_HEAD(&vport->rcv_buffer_list); @@ -6301,11 +6336,6 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba) * used to create the sg_dma_buf_pool must be dynamically calculated. */ - /* Initialize the host templates the configured values. */ - lpfc_vport_template.sg_tablesize = phba->cfg_sg_seg_cnt; - lpfc_template_no_hr.sg_tablesize = phba->cfg_sg_seg_cnt; - lpfc_template.sg_tablesize = phba->cfg_sg_seg_cnt; - if (phba->sli_rev == LPFC_SLI_REV4) entry_sz = sizeof(struct sli4_sge); else @@ -6346,7 +6376,7 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba) } lpfc_printf_log(phba, KERN_INFO, LOG_INIT | LOG_FCP, - "9088 sg_tablesize:%d dmabuf_size:%d total_bde:%d\n", + "9088 INIT sg_tablesize:%d dmabuf_size:%d total_bde:%d\n", phba->cfg_sg_seg_cnt, phba->cfg_sg_dma_buf_size, phba->cfg_total_seg_cnt); @@ -6816,11 +6846,6 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) phba->cfg_nvme_seg_cnt = phba->cfg_sg_seg_cnt; } - /* Initialize the host templates with the updated values. */ - lpfc_vport_template.sg_tablesize = phba->cfg_scsi_seg_cnt; - lpfc_template.sg_tablesize = phba->cfg_scsi_seg_cnt; - lpfc_template_no_hr.sg_tablesize = phba->cfg_scsi_seg_cnt; - lpfc_printf_log(phba, KERN_INFO, LOG_INIT | LOG_FCP, "9087 sg_seg_cnt:%d dmabuf_size:%d " "total:%d scsi:%d nvme:%d\n", @@ -6926,6 +6951,17 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) rc = -ENOMEM; goto out_free_hba_cpu_map; } + +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + phba->sli4_hba.c_stat = alloc_percpu(struct lpfc_hdwq_stat); + if (!phba->sli4_hba.c_stat) { + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "3332 Failed allocating per cpu hdwq stats\n"); + rc = -ENOMEM; + goto out_free_hba_eq_info; + } +#endif + /* * Enable sr-iov virtual functions if supported and configured * through the module parameter. @@ -6945,6 +6981,10 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) return 0; +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS +out_free_hba_eq_info: + free_percpu(phba->sli4_hba.eq_info); +#endif out_free_hba_cpu_map: kfree(phba->sli4_hba.cpu_map); out_free_hba_eq_hdl: @@ -6983,6 +7023,9 @@ lpfc_sli4_driver_resource_unset(struct lpfc_hba *phba) struct lpfc_fcf_conn_entry *conn_entry, *next_conn_entry; free_percpu(phba->sli4_hba.eq_info); +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + free_percpu(phba->sli4_hba.c_stat); +#endif /* Free memory allocated for msi-x interrupt vector to CPU mapping */ kfree(phba->sli4_hba.cpu_map); @@ -10823,6 +10866,9 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors) #ifdef CONFIG_X86 struct cpuinfo_x86 *cpuinfo; #endif +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + struct lpfc_hdwq_stat *c_stat; +#endif max_phys_id = 0; min_phys_id = LPFC_VECTOR_MAP_EMPTY; @@ -11074,10 +11120,17 @@ found_any: idx = 0; for_each_possible_cpu(cpu) { cpup = &phba->sli4_hba.cpu_map[cpu]; +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + c_stat = per_cpu_ptr(phba->sli4_hba.c_stat, cpu); + c_stat->hdwq_no = cpup->hdwq; +#endif if (cpup->hdwq != LPFC_VECTOR_MAP_EMPTY) continue; cpup->hdwq = idx++ % phba->cfg_hdw_queue; +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + c_stat->hdwq_no = cpup->hdwq; +#endif lpfc_printf_log(phba, KERN_INFO, LOG_INIT, "3340 Set Affinity: not present " "CPU %d hdwq %d\n", @@ -11173,11 +11226,9 @@ static void lpfc_cpuhp_add(struct lpfc_hba *phba) rcu_read_lock(); - if (!list_empty(&phba->poll_list)) { - timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0); + if (!list_empty(&phba->poll_list)) mod_timer(&phba->cpuhp_poll_timer, jiffies + msecs_to_jiffies(LPFC_POLL_HB)); - } rcu_read_unlock(); @@ -13145,6 +13196,7 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid) lpfc_sli4_ras_setup(phba); INIT_LIST_HEAD(&phba->poll_list); + timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0); cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, &phba->cpuhp); return 0; diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c index d1773c01d2b3..e35b52b66d6c 100644 --- a/drivers/scsi/lpfc/lpfc_mbox.c +++ b/drivers/scsi/lpfc/lpfc_mbox.c @@ -1299,8 +1299,6 @@ lpfc_config_port(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) if (phba->sli_rev == LPFC_SLI_REV3 && phba->vpd.sli3Feat.cerbm) { if (phba->cfg_enable_bg) mb->un.varCfgPort.cbg = 1; /* configure BlockGuard */ - if (phba->cfg_enable_dss) - mb->un.varCfgPort.cdss = 1; /* Configure Security */ mb->un.varCfgPort.cerbm = 1; /* Request HBQs */ mb->un.varCfgPort.ccrp = 1; /* Command Ring Polling */ mb->un.varCfgPort.max_hbq = lpfc_sli_hbq_count(); diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index f6c8963c915d..a45936e08031 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -382,13 +382,15 @@ lpfc_nvme_remoteport_delete(struct nvme_fc_remote_port *remoteport) if (ndlp->upcall_flags & NLP_WAIT_FOR_UNREG) { ndlp->nrport = NULL; ndlp->upcall_flags &= ~NLP_WAIT_FOR_UNREG; - } - spin_unlock_irq(&vport->phba->hbalock); + spin_unlock_irq(&vport->phba->hbalock); - /* Remove original register reference. The host transport - * won't reference this rport/remoteport any further. - */ - lpfc_nlp_put(ndlp); + /* Remove original register reference. The host transport + * won't reference this rport/remoteport any further. + */ + lpfc_nlp_put(ndlp); + } else { + spin_unlock_irq(&vport->phba->hbalock); + } rport_err: return; @@ -897,88 +899,6 @@ lpfc_nvme_adj_fcp_sgls(struct lpfc_vport *vport, sgl->sge_len = cpu_to_le32(nCmd->rsplen); } -#ifdef CONFIG_SCSI_LPFC_DEBUG_FS -static void -lpfc_nvme_ktime(struct lpfc_hba *phba, - struct lpfc_io_buf *lpfc_ncmd) -{ - uint64_t seg1, seg2, seg3, seg4; - uint64_t segsum; - - if (!lpfc_ncmd->ts_last_cmd || - !lpfc_ncmd->ts_cmd_start || - !lpfc_ncmd->ts_cmd_wqput || - !lpfc_ncmd->ts_isr_cmpl || - !lpfc_ncmd->ts_data_nvme) - return; - - if (lpfc_ncmd->ts_data_nvme < lpfc_ncmd->ts_cmd_start) - return; - if (lpfc_ncmd->ts_cmd_start < lpfc_ncmd->ts_last_cmd) - return; - if (lpfc_ncmd->ts_cmd_wqput < lpfc_ncmd->ts_cmd_start) - return; - if (lpfc_ncmd->ts_isr_cmpl < lpfc_ncmd->ts_cmd_wqput) - return; - if (lpfc_ncmd->ts_data_nvme < lpfc_ncmd->ts_isr_cmpl) - return; - /* - * Segment 1 - Time from Last FCP command cmpl is handed - * off to NVME Layer to start of next command. - * Segment 2 - Time from Driver receives a IO cmd start - * from NVME Layer to WQ put is done on IO cmd. - * Segment 3 - Time from Driver WQ put is done on IO cmd - * to MSI-X ISR for IO cmpl. - * Segment 4 - Time from MSI-X ISR for IO cmpl to when - * cmpl is handled off to the NVME Layer. - */ - seg1 = lpfc_ncmd->ts_cmd_start - lpfc_ncmd->ts_last_cmd; - if (seg1 > 5000000) /* 5 ms - for sequential IOs only */ - seg1 = 0; - - /* Calculate times relative to start of IO */ - seg2 = (lpfc_ncmd->ts_cmd_wqput - lpfc_ncmd->ts_cmd_start); - segsum = seg2; - seg3 = lpfc_ncmd->ts_isr_cmpl - lpfc_ncmd->ts_cmd_start; - if (segsum > seg3) - return; - seg3 -= segsum; - segsum += seg3; - - seg4 = lpfc_ncmd->ts_data_nvme - lpfc_ncmd->ts_cmd_start; - if (segsum > seg4) - return; - seg4 -= segsum; - - phba->ktime_data_samples++; - phba->ktime_seg1_total += seg1; - if (seg1 < phba->ktime_seg1_min) - phba->ktime_seg1_min = seg1; - else if (seg1 > phba->ktime_seg1_max) - phba->ktime_seg1_max = seg1; - phba->ktime_seg2_total += seg2; - if (seg2 < phba->ktime_seg2_min) - phba->ktime_seg2_min = seg2; - else if (seg2 > phba->ktime_seg2_max) - phba->ktime_seg2_max = seg2; - phba->ktime_seg3_total += seg3; - if (seg3 < phba->ktime_seg3_min) - phba->ktime_seg3_min = seg3; - else if (seg3 > phba->ktime_seg3_max) - phba->ktime_seg3_max = seg3; - phba->ktime_seg4_total += seg4; - if (seg4 < phba->ktime_seg4_min) - phba->ktime_seg4_min = seg4; - else if (seg4 > phba->ktime_seg4_max) - phba->ktime_seg4_max = seg4; - - lpfc_ncmd->ts_last_cmd = 0; - lpfc_ncmd->ts_cmd_start = 0; - lpfc_ncmd->ts_cmd_wqput = 0; - lpfc_ncmd->ts_isr_cmpl = 0; - lpfc_ncmd->ts_data_nvme = 0; -} -#endif /** * lpfc_nvme_io_cmd_wqe_cmpl - Complete an NVME-over-FCP IO @@ -1010,6 +930,9 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn, uint32_t code, status, idx; uint16_t cid, sqhd, data; uint32_t *ptr; +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + int cpu; +#endif /* Sanity check on return of outstanding command */ if (!lpfc_ncmd) { @@ -1178,23 +1101,19 @@ out_err: #ifdef CONFIG_SCSI_LPFC_DEBUG_FS if (lpfc_ncmd->ts_cmd_start) { lpfc_ncmd->ts_isr_cmpl = pwqeIn->isr_timestamp; - lpfc_ncmd->ts_data_nvme = ktime_get_ns(); - phba->ktime_last_cmd = lpfc_ncmd->ts_data_nvme; - lpfc_nvme_ktime(phba, lpfc_ncmd); + lpfc_ncmd->ts_data_io = ktime_get_ns(); + phba->ktime_last_cmd = lpfc_ncmd->ts_data_io; + lpfc_io_ktime(phba, lpfc_ncmd); } - if (unlikely(phba->cpucheck_on & LPFC_CHECK_NVME_IO)) { - uint32_t cpu; - idx = lpfc_ncmd->cur_iocbq.hba_wqidx; + if (unlikely(phba->hdwqstat_on & LPFC_CHECK_NVME_IO)) { cpu = raw_smp_processor_id(); - if (cpu < LPFC_CHECK_CPU_CNT) { - if (lpfc_ncmd->cpu != cpu) - lpfc_printf_vlog(vport, - KERN_INFO, LOG_NVME_IOERR, - "6701 CPU Check cmpl: " - "cpu %d expect %d\n", - cpu, lpfc_ncmd->cpu); - phba->sli4_hba.hdwq[idx].cpucheck_cmpl_io[cpu]++; - } + this_cpu_inc(phba->sli4_hba.c_stat->cmpl_io); + if (lpfc_ncmd->cpu != cpu) + lpfc_printf_vlog(vport, + KERN_INFO, LOG_NVME_IOERR, + "6701 CPU Check cmpl: " + "cpu %d expect %d\n", + cpu, lpfc_ncmd->cpu); } #endif @@ -1743,19 +1662,17 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, if (lpfc_ncmd->ts_cmd_start) lpfc_ncmd->ts_cmd_wqput = ktime_get_ns(); - if (phba->cpucheck_on & LPFC_CHECK_NVME_IO) { + if (phba->hdwqstat_on & LPFC_CHECK_NVME_IO) { cpu = raw_smp_processor_id(); - if (cpu < LPFC_CHECK_CPU_CNT) { - lpfc_ncmd->cpu = cpu; - if (idx != cpu) - lpfc_printf_vlog(vport, - KERN_INFO, LOG_NVME_IOERR, - "6702 CPU Check cmd: " - "cpu %d wq %d\n", - lpfc_ncmd->cpu, - lpfc_queue_info->index); - phba->sli4_hba.hdwq[idx].cpucheck_xmt_io[cpu]++; - } + this_cpu_inc(phba->sli4_hba.c_stat->xmt_io); + lpfc_ncmd->cpu = cpu; + if (idx != cpu) + lpfc_printf_vlog(vport, + KERN_INFO, LOG_NVME_IOERR, + "6702 CPU Check cmd: " + "cpu %d wq %d\n", + lpfc_ncmd->cpu, + lpfc_queue_info->index); } #endif return 0; @@ -1985,8 +1902,6 @@ out_unlock: /* Declare and initialization an instance of the FC NVME template. */ static struct nvme_fc_port_template lpfc_nvme_template = { - .module = THIS_MODULE, - /* initiator-based functions */ .localport_delete = lpfc_nvme_localport_delete, .remoteport_delete = lpfc_nvme_remoteport_delete, diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index 9dc9afe1c255..565419bf8d74 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -707,7 +707,7 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe, struct lpfc_nvmet_rcv_ctx *ctxp; uint32_t status, result, op, start_clean, logerr; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS - uint32_t id; + int id; #endif ctxp = cmdwqe->context2; @@ -814,16 +814,14 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe, rsp->done(rsp); } #ifdef CONFIG_SCSI_LPFC_DEBUG_FS - if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) { + if (phba->hdwqstat_on & LPFC_CHECK_NVMET_IO) { id = raw_smp_processor_id(); - if (id < LPFC_CHECK_CPU_CNT) { - if (ctxp->cpu != id) - lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR, - "6704 CPU Check cmdcmpl: " - "cpu %d expect %d\n", - id, ctxp->cpu); - phba->sli4_hba.hdwq[rsp->hwqid].cpucheck_cmpl_io[id]++; - } + this_cpu_inc(phba->sli4_hba.c_stat->cmpl_io); + if (ctxp->cpu != id) + lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR, + "6704 CPU Check cmdcmpl: " + "cpu %d expect %d\n", + id, ctxp->cpu); } #endif } @@ -931,6 +929,9 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport, struct lpfc_sli_ring *pring; unsigned long iflags; int rc; +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + int id; +#endif if (phba->pport->load_flag & FC_UNLOADING) { rc = -ENODEV; @@ -954,16 +955,14 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport, if (!ctxp->hdwq) ctxp->hdwq = &phba->sli4_hba.hdwq[rsp->hwqid]; - if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) { - int id = raw_smp_processor_id(); - if (id < LPFC_CHECK_CPU_CNT) { - if (rsp->hwqid != id) - lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR, - "6705 CPU Check OP: " - "cpu %d expect %d\n", - id, rsp->hwqid); - phba->sli4_hba.hdwq[rsp->hwqid].cpucheck_xmt_io[id]++; - } + if (phba->hdwqstat_on & LPFC_CHECK_NVMET_IO) { + id = raw_smp_processor_id(); + this_cpu_inc(phba->sli4_hba.c_stat->xmt_io); + if (rsp->hwqid != id) + lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR, + "6705 CPU Check OP: " + "cpu %d expect %d\n", + id, rsp->hwqid); ctxp->cpu = id; /* Setup cpu for cmpl check */ } #endif @@ -2270,15 +2269,13 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba, size = nvmebuf->bytes_recv; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS - if (phba->cpucheck_on & LPFC_CHECK_NVMET_RCV) { - if (current_cpu < LPFC_CHECK_CPU_CNT) { - if (idx != current_cpu) - lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR, - "6703 CPU Check rcv: " - "cpu %d expect %d\n", - current_cpu, idx); - phba->sli4_hba.hdwq[idx].cpucheck_rcv_io[current_cpu]++; - } + if (phba->hdwqstat_on & LPFC_CHECK_NVMET_IO) { + this_cpu_inc(phba->sli4_hba.c_stat->rcv_io); + if (idx != current_cpu) + lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR, + "6703 CPU Check rcv: " + "cpu %d expect %d\n", + current_cpu, idx); } #endif @@ -2598,7 +2595,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba, union lpfc_wqe128 *wqe; struct ulp_bde64 *bde; dma_addr_t physaddr; - int i, cnt; + int i, cnt, nsegs; int do_pbde; int xc = 1; @@ -2629,6 +2626,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba, phba->cfg_nvme_seg_cnt); return NULL; } + nsegs = rsp->sg_cnt; tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private; nvmewqe = ctxp->wqeq; @@ -2868,7 +2866,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba, wqe->fcp_trsp.rsvd_12_15[0] = 0; /* Use rspbuf, NOT sg list */ - rsp->sg_cnt = 0; + nsegs = 0; sgl->word2 = 0; atomic_inc(&tgtp->xmt_fcp_rsp); break; @@ -2885,7 +2883,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba, nvmewqe->drvrTimeout = (phba->fc_ratov * 3) + LPFC_DRVR_TIMEOUT; nvmewqe->context1 = ndlp; - for_each_sg(rsp->sg, sgel, rsp->sg_cnt, i) { + for_each_sg(rsp->sg, sgel, nsegs, i) { physaddr = sg_dma_address(sgel); cnt = sg_dma_len(sgel); sgl->addr_hi = putPaddrHigh(physaddr); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 0fc9a242bc65..ad62fb3f3a54 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -3805,9 +3805,6 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, struct Scsi_Host *shost; int idx; uint32_t logit = LOG_FCP; -#ifdef CONFIG_SCSI_LPFC_DEBUG_FS - int cpu; -#endif /* Guard against abort handler being called at same time */ spin_lock(&lpfc_cmd->buf_lock); @@ -3826,11 +3823,8 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, phba->sli4_hba.hdwq[idx].scsi_cstat.io_cmpls++; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS - if (unlikely(phba->cpucheck_on & LPFC_CHECK_SCSI_IO)) { - cpu = raw_smp_processor_id(); - if (cpu < LPFC_CHECK_CPU_CNT && phba->sli4_hba.hdwq) - phba->sli4_hba.hdwq[idx].cpucheck_cmpl_io[cpu]++; - } + if (unlikely(phba->hdwqstat_on & LPFC_CHECK_SCSI_IO)) + this_cpu_inc(phba->sli4_hba.c_stat->cmpl_io); #endif shost = cmd->device->host; @@ -4031,6 +4025,14 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, lpfc_cmd->pCmd = NULL; spin_unlock(&lpfc_cmd->buf_lock); +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + if (lpfc_cmd->ts_cmd_start) { + lpfc_cmd->ts_isr_cmpl = pIocbIn->isr_timestamp; + lpfc_cmd->ts_data_io = ktime_get_ns(); + phba->ktime_last_cmd = lpfc_cmd->ts_data_io; + lpfc_io_ktime(phba, lpfc_cmd); + } +#endif /* The sdev is not guaranteed to be valid post scsi_done upcall. */ cmd->scsi_done(cmd); @@ -4504,7 +4506,10 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd) struct fc_rport *rport = starget_to_rport(scsi_target(cmnd->device)); int err, idx; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS - int cpu; + uint64_t start = 0L; + + if (phba->ktime_on) + start = ktime_get_ns(); #endif rdata = lpfc_rport_data_from_scsi_device(cmnd->device); @@ -4626,17 +4631,20 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd) lpfc_scsi_prep_cmnd(vport, lpfc_cmd, ndlp); #ifdef CONFIG_SCSI_LPFC_DEBUG_FS - if (unlikely(phba->cpucheck_on & LPFC_CHECK_SCSI_IO)) { - cpu = raw_smp_processor_id(); - if (cpu < LPFC_CHECK_CPU_CNT) { - struct lpfc_sli4_hdw_queue *hdwq = - &phba->sli4_hba.hdwq[lpfc_cmd->hdwq_no]; - hdwq->cpucheck_xmt_io[cpu]++; - } - } + if (unlikely(phba->hdwqstat_on & LPFC_CHECK_SCSI_IO)) + this_cpu_inc(phba->sli4_hba.c_stat->xmt_io); #endif err = lpfc_sli_issue_iocb(phba, LPFC_FCP_RING, &lpfc_cmd->cur_iocbq, SLI_IOCB_RET_IOCB); +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + if (start) { + lpfc_cmd->ts_cmd_start = start; + lpfc_cmd->ts_last_cmd = phba->ktime_last_cmd; + lpfc_cmd->ts_cmd_wqput = ktime_get_ns(); + } else { + lpfc_cmd->ts_cmd_start = 0; + } +#endif if (err) { lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP, "3376 FCP could not issue IOCB err %x" @@ -6023,31 +6031,6 @@ struct scsi_host_template lpfc_template_nvme = { .track_queue_depth = 0, }; -struct scsi_host_template lpfc_template_no_hr = { - .module = THIS_MODULE, - .name = LPFC_DRIVER_NAME, - .proc_name = LPFC_DRIVER_NAME, - .info = lpfc_info, - .queuecommand = lpfc_queuecommand, - .eh_timed_out = fc_eh_timed_out, - .eh_abort_handler = lpfc_abort_handler, - .eh_device_reset_handler = lpfc_device_reset_handler, - .eh_target_reset_handler = lpfc_target_reset_handler, - .eh_bus_reset_handler = lpfc_bus_reset_handler, - .slave_alloc = lpfc_slave_alloc, - .slave_configure = lpfc_slave_configure, - .slave_destroy = lpfc_slave_destroy, - .scan_finished = lpfc_scan_finished, - .this_id = -1, - .sg_tablesize = LPFC_DEFAULT_SG_SEG_CNT, - .cmd_per_lun = LPFC_CMD_PER_LUN, - .shost_attrs = lpfc_hba_attrs, - .max_sectors = 0xFFFFFFFF, - .vendor_id = LPFC_NL_VENDOR_ID, - .change_queue_depth = scsi_change_queue_depth, - .track_queue_depth = 1, -}; - struct scsi_host_template lpfc_template = { .module = THIS_MODULE, .name = LPFC_DRIVER_NAME, @@ -6073,26 +6056,3 @@ struct scsi_host_template lpfc_template = { .change_queue_depth = scsi_change_queue_depth, .track_queue_depth = 1, }; - -struct scsi_host_template lpfc_vport_template = { - .module = THIS_MODULE, - .name = LPFC_DRIVER_NAME, - .proc_name = LPFC_DRIVER_NAME, - .info = lpfc_info, - .queuecommand = lpfc_queuecommand, - .eh_timed_out = fc_eh_timed_out, - .eh_abort_handler = lpfc_abort_handler, - .eh_device_reset_handler = lpfc_device_reset_handler, - .eh_target_reset_handler = lpfc_target_reset_handler, - .slave_alloc = lpfc_slave_alloc, - .slave_configure = lpfc_slave_configure, - .slave_destroy = lpfc_slave_destroy, - .scan_finished = lpfc_scan_finished, - .this_id = -1, - .sg_tablesize = LPFC_DEFAULT_SG_SEG_CNT, - .cmd_per_lun = LPFC_CMD_PER_LUN, - .shost_attrs = lpfc_vport_attrs, - .max_sectors = 0xFFFF, - .change_queue_depth = scsi_change_queue_depth, - .track_queue_depth = 1, -}; diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 0b26b5c0527e..b6fb665e6ec4 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -230,25 +230,16 @@ lpfc_sli4_wq_put(struct lpfc_queue *q, union lpfc_wqe128 *wqe) * This routine will update the HBA index of a queue to reflect consumption of * Work Queue Entries by the HBA. When the HBA indicates that it has consumed * an entry the host calls this function to update the queue's internal - * pointers. This routine returns the number of entries that were consumed by - * the HBA. + * pointers. **/ -static uint32_t +static void lpfc_sli4_wq_release(struct lpfc_queue *q, uint32_t index) { - uint32_t released = 0; - /* sanity check on queue memory */ if (unlikely(!q)) - return 0; + return; - if (q->hba_index == index) - return 0; - do { - q->hba_index = ((q->hba_index + 1) % q->entry_count); - released++; - } while (q->hba_index != index); - return released; + q->hba_index = index; } /** @@ -2511,6 +2502,8 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) !pmb->u.mb.mbxStatus) { rpi = pmb->u.mb.un.varWords[0]; vpi = pmb->u.mb.un.varRegLogin.vpi; + if (phba->sli_rev == LPFC_SLI_REV4) + vpi -= phba->sli4_hba.max_cfg_param.vpi_base; lpfc_unreg_login(phba, vpi, rpi, pmb); pmb->vport = vport; pmb->mbox_cmpl = lpfc_sli_def_mbox_cmpl; @@ -4044,6 +4037,11 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba) struct lpfc_iocbq *piocb, *next_iocb; spin_lock_irq(&phba->hbalock); + if (phba->hba_flag & HBA_IOQ_FLUSH || + !phba->sli4_hba.hdwq) { + spin_unlock_irq(&phba->hbalock); + return; + } /* Indicate the I/O queues are flushed */ phba->hba_flag |= HBA_IOQ_FLUSH; spin_unlock_irq(&phba->hbalock); @@ -5034,23 +5032,6 @@ lpfc_sli_config_port(struct lpfc_hba *phba, int sli_mode) } else phba->max_vpi = 0; - phba->fips_level = 0; - phba->fips_spec_rev = 0; - if (pmb->u.mb.un.varCfgPort.gdss) { - phba->sli3_options |= LPFC_SLI3_DSS_ENABLED; - phba->fips_level = pmb->u.mb.un.varCfgPort.fips_level; - phba->fips_spec_rev = pmb->u.mb.un.varCfgPort.fips_rev; - lpfc_printf_log(phba, KERN_INFO, LOG_INIT, - "2850 Security Crypto Active. FIPS x%d " - "(Spec Rev: x%d)", - phba->fips_level, phba->fips_spec_rev); - } - if (pmb->u.mb.un.varCfgPort.sec_err) { - lpfc_printf_log(phba, KERN_ERR, LOG_INIT, - "2856 Config Port Security Crypto " - "Error: x%x ", - pmb->u.mb.un.varCfgPort.sec_err); - } if (pmb->u.mb.un.varCfgPort.gerbm) phba->sli3_options |= LPFC_SLI3_HBQ_ENABLED; if (pmb->u.mb.un.varCfgPort.gcrp) @@ -14442,12 +14423,10 @@ static inline void lpfc_sli4_add_to_poll_list(struct lpfc_queue *eq) { struct lpfc_hba *phba = eq->phba; - if (list_empty(&phba->poll_list)) { - timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0); - /* kickstart slowpath processing for this eq */ + /* kickstart slowpath processing if needed */ + if (list_empty(&phba->poll_list)) mod_timer(&phba->cpuhp_poll_timer, jiffies + msecs_to_jiffies(LPFC_POLL_HB)); - } list_add_rcu(&eq->_poll_list, &phba->poll_list); synchronize_rcu(); diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h index 7bcf922a8be2..93d976ea8c5d 100644 --- a/drivers/scsi/lpfc/lpfc_sli.h +++ b/drivers/scsi/lpfc/lpfc_sli.h @@ -446,6 +446,6 @@ struct lpfc_io_buf { uint64_t ts_last_cmd; uint64_t ts_cmd_wqput; uint64_t ts_isr_cmpl; - uint64_t ts_data_nvme; + uint64_t ts_data_io; #endif }; diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h index d963ca871383..8da7429e385a 100644 --- a/drivers/scsi/lpfc/lpfc_sli4.h +++ b/drivers/scsi/lpfc/lpfc_sli4.h @@ -697,13 +697,6 @@ struct lpfc_sli4_hdw_queue { struct lpfc_lock_stat lock_conflict; #endif -#ifdef CONFIG_SCSI_LPFC_DEBUG_FS -#define LPFC_CHECK_CPU_CNT 128 - uint32_t cpucheck_rcv_io[LPFC_CHECK_CPU_CNT]; - uint32_t cpucheck_xmt_io[LPFC_CHECK_CPU_CNT]; - uint32_t cpucheck_cmpl_io[LPFC_CHECK_CPU_CNT]; -#endif - /* Per HDWQ pool resources */ struct list_head sgl_list; struct list_head cmd_rsp_buf_list; @@ -740,6 +733,15 @@ struct lpfc_sli4_hdw_queue { #define lpfc_qp_spin_lock(lock, qp, lstat) spin_lock(lock) #endif +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS +struct lpfc_hdwq_stat { + u32 hdwq_no; + u32 rcv_io; + u32 xmt_io; + u32 cmpl_io; +}; +#endif + struct lpfc_sli4_hba { void __iomem *conf_regs_memmap_p; /* Kernel memory mapped address for * config space registers @@ -921,6 +923,9 @@ struct lpfc_sli4_hba { struct cpumask numa_mask; uint16_t curr_disp_cpu; struct lpfc_eq_intr_info __percpu *eq_info; +#ifdef CONFIG_SCSI_LPFC_DEBUG_FS + struct lpfc_hdwq_stat __percpu *c_stat; +#endif uint32_t conf_trunk; #define lpfc_conf_trunk_port0_WORD conf_trunk #define lpfc_conf_trunk_port0_SHIFT 0 diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index c4ab006e6ecc..ca40c47cfbe0 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "12.6.0.4" +#define LPFC_DRIVER_VERSION "12.8.0.0" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 778d5e6ce385..04a40afe60e3 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -9908,8 +9908,8 @@ static void scsih_remove(struct pci_dev *pdev) ioc->remove_host = 1; - mpt3sas_wait_for_commands_to_complete(ioc); - _scsih_flush_running_cmds(ioc); + if (!pci_device_is_present(pdev)) + _scsih_flush_running_cmds(ioc); _scsih_fw_event_cleanup_queue(ioc); @@ -9992,8 +9992,8 @@ scsih_shutdown(struct pci_dev *pdev) ioc->remove_host = 1; - mpt3sas_wait_for_commands_to_complete(ioc); - _scsih_flush_running_cmds(ioc); + if (!pci_device_is_present(pdev)) + _scsih_flush_running_cmds(ioc); _scsih_fw_event_cleanup_queue(ioc); diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 84e2a980dea0..4886d247df6f 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -610,7 +610,6 @@ static void qla_nvme_remoteport_delete(struct nvme_fc_remote_port *rport) } static struct nvme_fc_port_template qla_nvme_fc_transport = { - .module = THIS_MODULE, .localport_delete = qla_nvme_localport_delete, .remoteport_delete = qla_nvme_remoteport_delete, .create_queue = qla_nvme_alloc_queue, diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 0ec1b31c75a9..b2a803c51288 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2022,7 +2022,7 @@ static void __iscsi_unbind_session(struct work_struct *work) if (session->target_id == ISCSI_MAX_TARGET) { spin_unlock_irqrestore(&session->lock, flags); mutex_unlock(&ihost->mutex); - return; + goto unbind_session_exit; } target_id = session->target_id; @@ -2034,6 +2034,8 @@ static void __iscsi_unbind_session(struct work_struct *work) ida_simple_remove(&iscsi_sess_ida, target_id); scsi_remove_target(&session->dev); + +unbind_session_exit: iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION); ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n"); } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 1c270e6034d5..d2fe3fa470f9 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -550,10 +550,12 @@ out: static void sr_block_release(struct gendisk *disk, fmode_t mode) { struct scsi_cd *cd = scsi_cd(disk); + mutex_lock(&cd->lock); cdrom_release(&cd->cdi, mode); - scsi_cd_put(cd); mutex_unlock(&cd->lock); + + scsi_cd_put(cd); } static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index 40a66b31b31f..673c16596fb2 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -499,8 +499,15 @@ static int ufs_mtk_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) if (ufshcd_is_link_hibern8(hba)) { err = ufs_mtk_link_set_lpm(hba); - if (err) + if (err) { + /* + * Set link as off state enforcedly to trigger + * ufshcd_host_reset_and_restore() in ufshcd_suspend() + * for completed host reset. + */ + ufshcd_set_link_off(hba); return -EAGAIN; + } } if (!ufshcd_is_link_active(hba)) @@ -519,8 +526,10 @@ static int ufs_mtk_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op) if (ufshcd_is_link_hibern8(hba)) { err = ufs_mtk_link_set_hpm(hba); - if (err) + if (err) { + err = ufshcd_link_recovery(hba); return err; + } } return 0; diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index e04e8b8bdca6..698e8d20b4ba 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -172,19 +172,6 @@ enum { #define ufshcd_clear_eh_in_progress(h) \ ((h)->eh_flags &= ~UFSHCD_EH_IN_PROGRESS) -#define ufshcd_set_ufs_dev_active(h) \ - ((h)->curr_dev_pwr_mode = UFS_ACTIVE_PWR_MODE) -#define ufshcd_set_ufs_dev_sleep(h) \ - ((h)->curr_dev_pwr_mode = UFS_SLEEP_PWR_MODE) -#define ufshcd_set_ufs_dev_poweroff(h) \ - ((h)->curr_dev_pwr_mode = UFS_POWERDOWN_PWR_MODE) -#define ufshcd_is_ufs_dev_active(h) \ - ((h)->curr_dev_pwr_mode == UFS_ACTIVE_PWR_MODE) -#define ufshcd_is_ufs_dev_sleep(h) \ - ((h)->curr_dev_pwr_mode == UFS_SLEEP_PWR_MODE) -#define ufshcd_is_ufs_dev_poweroff(h) \ - ((h)->curr_dev_pwr_mode == UFS_POWERDOWN_PWR_MODE) - struct ufs_pm_lvl_states ufs_pm_lvl_states[] = { {UFS_ACTIVE_PWR_MODE, UIC_LINK_ACTIVE_STATE}, {UFS_ACTIVE_PWR_MODE, UIC_LINK_HIBERN8_STATE}, @@ -868,28 +855,29 @@ static bool ufshcd_is_unipro_pa_params_tuning_req(struct ufs_hba *hba) return false; } -static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up) +/** + * ufshcd_set_clk_freq - set UFS controller clock frequencies + * @hba: per adapter instance + * @scale_up: If True, set max possible frequency othewise set low frequency + * + * Returns 0 if successful + * Returns < 0 for any other errors + */ +static int ufshcd_set_clk_freq(struct ufs_hba *hba, bool scale_up) { int ret = 0; struct ufs_clk_info *clki; struct list_head *head = &hba->clk_list_head; - ktime_t start = ktime_get(); - bool clk_state_changed = false; if (list_empty(head)) goto out; - ret = ufshcd_vops_clk_scale_notify(hba, scale_up, PRE_CHANGE); - if (ret) - return ret; - list_for_each_entry(clki, head, list) { if (!IS_ERR_OR_NULL(clki->clk)) { if (scale_up && clki->max_freq) { if (clki->curr_freq == clki->max_freq) continue; - clk_state_changed = true; ret = clk_set_rate(clki->clk, clki->max_freq); if (ret) { dev_err(hba->dev, "%s: %s clk set rate(%dHz) failed, %d\n", @@ -908,7 +896,6 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up) if (clki->curr_freq == clki->min_freq) continue; - clk_state_changed = true; ret = clk_set_rate(clki->clk, clki->min_freq); if (ret) { dev_err(hba->dev, "%s: %s clk set rate(%dHz) failed, %d\n", @@ -927,11 +914,37 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up) clki->name, clk_get_rate(clki->clk)); } +out: + return ret; +} + +/** + * ufshcd_scale_clks - scale up or scale down UFS controller clocks + * @hba: per adapter instance + * @scale_up: True if scaling up and false if scaling down + * + * Returns 0 if successful + * Returns < 0 for any other errors + */ +static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up) +{ + int ret = 0; + ktime_t start = ktime_get(); + + ret = ufshcd_vops_clk_scale_notify(hba, scale_up, PRE_CHANGE); + if (ret) + goto out; + + ret = ufshcd_set_clk_freq(hba, scale_up); + if (ret) + goto out; + ret = ufshcd_vops_clk_scale_notify(hba, scale_up, POST_CHANGE); + if (ret) + ufshcd_set_clk_freq(hba, !scale_up); out: - if (clk_state_changed) - trace_ufshcd_profile_clk_scaling(dev_name(hba->dev), + trace_ufshcd_profile_clk_scaling(dev_name(hba->dev), (scale_up ? "up" : "down"), ktime_to_us(ktime_sub(ktime_get(), start)), ret); return ret; @@ -1065,8 +1078,7 @@ static int ufshcd_scale_gear(struct ufs_hba *hba, bool scale_up) } /* check if the power mode needs to be changed or not? */ - ret = ufshcd_change_power_mode(hba, &new_pwr_info); - + ret = ufshcd_config_pwr_mode(hba, &new_pwr_info); if (ret) dev_err(hba->dev, "%s: failed err %d, old gear: (tx %d rx %d), new gear: (tx %d rx %d)", __func__, ret, @@ -1119,35 +1131,32 @@ static int ufshcd_devfreq_scale(struct ufs_hba *hba, bool scale_up) ret = ufshcd_clock_scaling_prepare(hba); if (ret) - return ret; + goto out; /* scale down the gear before scaling down clocks */ if (!scale_up) { ret = ufshcd_scale_gear(hba, false); if (ret) - goto out; + goto out_unprepare; } ret = ufshcd_scale_clks(hba, scale_up); if (ret) { if (!scale_up) ufshcd_scale_gear(hba, true); - goto out; + goto out_unprepare; } /* scale up the gear after scaling up clocks */ if (scale_up) { ret = ufshcd_scale_gear(hba, true); - if (ret) { + if (ret) ufshcd_scale_clks(hba, false); - goto out; - } } - ret = ufshcd_vops_clk_scale_notify(hba, scale_up, POST_CHANGE); - -out: +out_unprepare: ufshcd_clock_scaling_unprepare(hba); +out: ufshcd_release(hba); return ret; } @@ -3785,7 +3794,7 @@ out: return ret; } -static int ufshcd_link_recovery(struct ufs_hba *hba) +int ufshcd_link_recovery(struct ufs_hba *hba) { int ret; unsigned long flags; @@ -3812,6 +3821,7 @@ static int ufshcd_link_recovery(struct ufs_hba *hba) return ret; } +EXPORT_SYMBOL_GPL(ufshcd_link_recovery); static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba) { @@ -4112,8 +4122,6 @@ int ufshcd_config_pwr_mode(struct ufs_hba *hba, memcpy(&final_params, desired_pwr_mode, sizeof(final_params)); ret = ufshcd_change_power_mode(hba, &final_params); - if (!ret) - ufshcd_print_pwr_info(hba); return ret; } @@ -6299,7 +6307,7 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba) spin_unlock_irqrestore(hba->host->host_lock, flags); /* scale up clocks to max frequency before full reinitialization */ - ufshcd_scale_clks(hba, true); + ufshcd_set_clk_freq(hba, true); err = ufshcd_hba_enable(hba); if (err) @@ -7127,6 +7135,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool async) __func__, ret); goto out; } + ufshcd_print_pwr_info(hba); } /* diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index dd1ee277069a..6ffc08ad85f6 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -130,6 +130,19 @@ enum uic_link_state { #define ufshcd_set_link_hibern8(hba) ((hba)->uic_link_state = \ UIC_LINK_HIBERN8_STATE) +#define ufshcd_set_ufs_dev_active(h) \ + ((h)->curr_dev_pwr_mode = UFS_ACTIVE_PWR_MODE) +#define ufshcd_set_ufs_dev_sleep(h) \ + ((h)->curr_dev_pwr_mode = UFS_SLEEP_PWR_MODE) +#define ufshcd_set_ufs_dev_poweroff(h) \ + ((h)->curr_dev_pwr_mode = UFS_POWERDOWN_PWR_MODE) +#define ufshcd_is_ufs_dev_active(h) \ + ((h)->curr_dev_pwr_mode == UFS_ACTIVE_PWR_MODE) +#define ufshcd_is_ufs_dev_sleep(h) \ + ((h)->curr_dev_pwr_mode == UFS_SLEEP_PWR_MODE) +#define ufshcd_is_ufs_dev_poweroff(h) \ + ((h)->curr_dev_pwr_mode == UFS_POWERDOWN_PWR_MODE) + /* * UFS Power management levels. * Each level is in increasing order of power savings. @@ -788,6 +801,7 @@ int ufshcd_alloc_host(struct device *, struct ufs_hba **); void ufshcd_dealloc_host(struct ufs_hba *); int ufshcd_hba_enable(struct ufs_hba *hba); int ufshcd_init(struct ufs_hba * , void __iomem * , unsigned int); +int ufshcd_link_recovery(struct ufs_hba *hba); int ufshcd_make_hba_operational(struct ufs_hba *hba); void ufshcd_remove(struct ufs_hba *); int ufshcd_uic_hibern8_exit(struct ufs_hba *hba); @@ -1083,6 +1097,7 @@ static inline void ufshcd_vops_device_reset(struct ufs_hba *hba) { if (hba->vops && hba->vops->device_reset) { hba->vops->device_reset(hba); + ufshcd_set_ufs_dev_active(hba); ufshcd_update_reg_hist(&hba->ufs_stats.dev_reset, 0); } } diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig index 1778f8c62861..425ab6f7e375 100644 --- a/drivers/soc/Kconfig +++ b/drivers/soc/Kconfig @@ -22,5 +22,6 @@ source "drivers/soc/ux500/Kconfig" source "drivers/soc/versatile/Kconfig" source "drivers/soc/xilinx/Kconfig" source "drivers/soc/zte/Kconfig" +source "drivers/soc/kendryte/Kconfig" endmenu diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile index a39f17cea376..36452bed86ef 100644 --- a/drivers/soc/Makefile +++ b/drivers/soc/Makefile @@ -28,3 +28,4 @@ obj-$(CONFIG_ARCH_U8500) += ux500/ obj-$(CONFIG_PLAT_VERSATILE) += versatile/ obj-y += xilinx/ obj-$(CONFIG_ARCH_ZX) += zte/ +obj-$(CONFIG_SOC_KENDRYTE) += kendryte/ diff --git a/drivers/soc/kendryte/Kconfig b/drivers/soc/kendryte/Kconfig new file mode 100644 index 000000000000..49785b1b0217 --- /dev/null +++ b/drivers/soc/kendryte/Kconfig @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 + +if SOC_KENDRYTE + +config K210_SYSCTL + bool "Kendryte K210 system controller" + default y + depends on RISCV + help + Enables controlling the K210 various clocks and to enable + general purpose use of the extra 2MB of SRAM normally + reserved for the AI engine. + +endif diff --git a/drivers/soc/kendryte/Makefile b/drivers/soc/kendryte/Makefile new file mode 100644 index 000000000000..002d9ce95c0d --- /dev/null +++ b/drivers/soc/kendryte/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_K210_SYSCTL) += k210-sysctl.o diff --git a/drivers/soc/kendryte/k210-sysctl.c b/drivers/soc/kendryte/k210-sysctl.c new file mode 100644 index 000000000000..4608fbca20e1 --- /dev/null +++ b/drivers/soc/kendryte/k210-sysctl.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2019 Christoph Hellwig. + * Copyright (c) 2019 Western Digital Corporation or its affiliates. + */ +#include <linux/types.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/clk-provider.h> +#include <linux/clkdev.h> +#include <linux/bitfield.h> +#include <asm/soc.h> + +#define K210_SYSCTL_CLK0_FREQ 26000000UL + +/* Registers base address */ +#define K210_SYSCTL_SYSCTL_BASE_ADDR 0x50440000ULL + +/* Registers */ +#define K210_SYSCTL_PLL0 0x08 +#define K210_SYSCTL_PLL1 0x0c +/* clkr: 4bits, clkf1: 6bits, clkod: 4bits, bwadj: 4bits */ +#define PLL_RESET (1 << 20) +#define PLL_PWR (1 << 21) +#define PLL_INTFB (1 << 22) +#define PLL_BYPASS (1 << 23) +#define PLL_TEST (1 << 24) +#define PLL_OUT_EN (1 << 25) +#define PLL_TEST_EN (1 << 26) +#define K210_SYSCTL_PLL_LOCK 0x18 +#define PLL0_LOCK1 (1 << 0) +#define PLL0_LOCK2 (1 << 1) +#define PLL0_SLIP_CLEAR (1 << 2) +#define PLL0_TEST_CLK_OUT (1 << 3) +#define PLL1_LOCK1 (1 << 8) +#define PLL1_LOCK2 (1 << 9) +#define PLL1_SLIP_CLEAR (1 << 10) +#define PLL1_TEST_CLK_OUT (1 << 11) +#define PLL2_LOCK1 (1 << 16) +#define PLL2_LOCK2 (1 << 16) +#define PLL2_SLIP_CLEAR (1 << 18) +#define PLL2_TEST_CLK_OUT (1 << 19) +#define K210_SYSCTL_CLKSEL0 0x20 +#define CLKSEL_ACLK (1 << 0) +#define K210_SYSCTL_CLKEN_CENT 0x28 +#define CLKEN_CPU (1 << 0) +#define CLKEN_SRAM0 (1 << 1) +#define CLKEN_SRAM1 (1 << 2) +#define CLKEN_APB0 (1 << 3) +#define CLKEN_APB1 (1 << 4) +#define CLKEN_APB2 (1 << 5) +#define K210_SYSCTL_CLKEN_PERI 0x2c +#define CLKEN_ROM (1 << 0) +#define CLKEN_DMA (1 << 1) +#define CLKEN_AI (1 << 2) +#define CLKEN_DVP (1 << 3) +#define CLKEN_FFT (1 << 4) +#define CLKEN_GPIO (1 << 5) +#define CLKEN_SPI0 (1 << 6) +#define CLKEN_SPI1 (1 << 7) +#define CLKEN_SPI2 (1 << 8) +#define CLKEN_SPI3 (1 << 9) +#define CLKEN_I2S0 (1 << 10) +#define CLKEN_I2S1 (1 << 11) +#define CLKEN_I2S2 (1 << 12) +#define CLKEN_I2C0 (1 << 13) +#define CLKEN_I2C1 (1 << 14) +#define CLKEN_I2C2 (1 << 15) +#define CLKEN_UART1 (1 << 16) +#define CLKEN_UART2 (1 << 17) +#define CLKEN_UART3 (1 << 18) +#define CLKEN_AES (1 << 19) +#define CLKEN_FPIO (1 << 20) +#define CLKEN_TIMER0 (1 << 21) +#define CLKEN_TIMER1 (1 << 22) +#define CLKEN_TIMER2 (1 << 23) +#define CLKEN_WDT0 (1 << 24) +#define CLKEN_WDT1 (1 << 25) +#define CLKEN_SHA (1 << 26) +#define CLKEN_OTP (1 << 27) +#define CLKEN_RTC (1 << 29) + +struct k210_sysctl { + void __iomem *regs; + struct clk_hw hw; +}; + +static void k210_set_bits(u32 val, void __iomem *reg) +{ + writel(readl(reg) | val, reg); +} + +static void k210_clear_bits(u32 val, void __iomem *reg) +{ + writel(readl(reg) & ~val, reg); +} + +static void k210_pll1_enable(void __iomem *regs) +{ + u32 val; + + val = readl(regs + K210_SYSCTL_PLL1); + val &= ~GENMASK(19, 0); /* clkr1 = 0 */ + val |= FIELD_PREP(GENMASK(9, 4), 0x3B); /* clkf1 = 59 */ + val |= FIELD_PREP(GENMASK(13, 10), 0x3); /* clkod1 = 3 */ + val |= FIELD_PREP(GENMASK(19, 14), 0x3B); /* bwadj1 = 59 */ + writel(val, regs + K210_SYSCTL_PLL1); + + k210_clear_bits(PLL_BYPASS, regs + K210_SYSCTL_PLL1); + k210_set_bits(PLL_PWR, regs + K210_SYSCTL_PLL1); + + /* + * Reset the pll. The magic NOPs come from the Kendryte reference SDK. + */ + k210_clear_bits(PLL_RESET, regs + K210_SYSCTL_PLL1); + k210_set_bits(PLL_RESET, regs + K210_SYSCTL_PLL1); + nop(); + nop(); + k210_clear_bits(PLL_RESET, regs + K210_SYSCTL_PLL1); + + for (;;) { + val = readl(regs + K210_SYSCTL_PLL_LOCK); + if (val & PLL1_LOCK2) + break; + writel(val | PLL1_SLIP_CLEAR, regs + K210_SYSCTL_PLL_LOCK); + } + + k210_set_bits(PLL_OUT_EN, regs + K210_SYSCTL_PLL1); +} + +static unsigned long k210_sysctl_clk_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct k210_sysctl *s = container_of(hw, struct k210_sysctl, hw); + u32 clksel0, pll0; + u64 pll0_freq, clkr0, clkf0, clkod0; + + /* + * If the clock selector is not set, use the base frequency. + * Otherwise, use PLL0 frequency with a frequency divisor. + */ + clksel0 = readl(s->regs + K210_SYSCTL_CLKSEL0); + if (!(clksel0 & CLKSEL_ACLK)) + return K210_SYSCTL_CLK0_FREQ; + + /* + * Get PLL0 frequency: + * freq = base frequency * clkf0 / (clkr0 * clkod0) + */ + pll0 = readl(s->regs + K210_SYSCTL_PLL0); + clkr0 = 1 + FIELD_GET(GENMASK(3, 0), pll0); + clkf0 = 1 + FIELD_GET(GENMASK(9, 4), pll0); + clkod0 = 1 + FIELD_GET(GENMASK(13, 10), pll0); + pll0_freq = clkf0 * K210_SYSCTL_CLK0_FREQ / (clkr0 * clkod0); + + /* Get the frequency divisor from the clock selector */ + return pll0_freq / (2ULL << FIELD_GET(0x00000006, clksel0)); +} + +static const struct clk_ops k210_sysctl_clk_ops = { + .recalc_rate = k210_sysctl_clk_recalc_rate, +}; + +static const struct clk_init_data k210_clk_init_data = { + .name = "k210-sysctl-pll1", + .ops = &k210_sysctl_clk_ops, +}; + +static int k210_sysctl_probe(struct platform_device *pdev) +{ + struct k210_sysctl *s; + int error; + + pr_info("Kendryte K210 SoC sysctl\n"); + + s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + s->regs = devm_ioremap_resource(&pdev->dev, + platform_get_resource(pdev, IORESOURCE_MEM, 0)); + if (IS_ERR(s->regs)) + return PTR_ERR(s->regs); + + s->hw.init = &k210_clk_init_data; + error = devm_clk_hw_register(&pdev->dev, &s->hw); + if (error) { + dev_err(&pdev->dev, "failed to register clk"); + return error; + } + + error = devm_of_clk_add_hw_provider(&pdev->dev, of_clk_hw_simple_get, + &s->hw); + if (error) { + dev_err(&pdev->dev, "adding clk provider failed\n"); + return error; + } + + return 0; +} + +static const struct of_device_id k210_sysctl_of_match[] = { + { .compatible = "kendryte,k210-sysctl", }, + {} +}; + +static struct platform_driver k210_sysctl_driver = { + .driver = { + .name = "k210-sysctl", + .of_match_table = k210_sysctl_of_match, + }, + .probe = k210_sysctl_probe, +}; + +static int __init k210_sysctl_init(void) +{ + return platform_driver_register(&k210_sysctl_driver); +} +core_initcall(k210_sysctl_init); + +/* + * This needs to be called very early during initialization, given that + * PLL1 needs to be enabled to be able to use all SRAM. + */ +static void __init k210_soc_early_init(const void *fdt) +{ + void __iomem *regs; + + regs = ioremap(K210_SYSCTL_SYSCTL_BASE_ADDR, 0x1000); + if (!regs) + panic("K210 sysctl ioremap"); + + /* Enable PLL1 to make the KPU SRAM useable */ + k210_pll1_enable(regs); + + k210_set_bits(PLL_OUT_EN, regs + K210_SYSCTL_PLL0); + + k210_set_bits(CLKEN_CPU | CLKEN_SRAM0 | CLKEN_SRAM1, + regs + K210_SYSCTL_CLKEN_CENT); + k210_set_bits(CLKEN_ROM | CLKEN_TIMER0 | CLKEN_RTC, + regs + K210_SYSCTL_CLKEN_PERI); + + k210_set_bits(CLKSEL_ACLK, regs + K210_SYSCTL_CLKSEL0); + + iounmap(regs); +} +SOC_EARLY_INIT_DECLARE(generic_k210, "kendryte,k210", k210_soc_early_init); diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c index cd181a64f737..8e0575fcb4c8 100644 --- a/drivers/staging/gasket/gasket_core.c +++ b/drivers/staging/gasket/gasket_core.c @@ -689,7 +689,7 @@ static bool gasket_mmap_has_permissions(struct gasket_dev *gasket_dev, /* Make sure that no wrong flags are set. */ requested_permissions = - (vma->vm_flags & (VM_WRITE | VM_READ | VM_EXEC)); + (vma->vm_flags & VM_ACCESS_FLAGS); if (requested_permissions & ~(bar_permissions)) { dev_dbg(gasket_dev->dev, "Attempting to map a region with requested permissions 0x%x, but region has permissions 0x%x.\n", diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index 425c1070de08..bd3ed6ce7571 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -134,7 +134,7 @@ static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op * Assigned designator */ desig_len = desc[7]; - if (desig_len != 16) { + if (desig_len != XCOPY_NAA_IEEE_REGEX_LEN) { pr_err("XCOPY 0xe4: invalid desig_len: %d\n", (int)desig_len); return -EINVAL; } @@ -315,11 +315,6 @@ static int target_xcopy_parse_segdesc_02(struct se_cmd *se_cmd, struct xcopy_op xop->nolb, (unsigned long long)xop->src_lba, (unsigned long long)xop->dst_lba); - if (dc != 0) { - xop->dbl = get_unaligned_be24(&desc[29]); - - pr_debug("XCOPY seg desc 0x02: DC=1 w/ dbl: %u\n", xop->dbl); - } return 0; } @@ -415,7 +410,8 @@ static void xcopy_pt_release_cmd(struct se_cmd *se_cmd) struct xcopy_pt_cmd *xpt_cmd = container_of(se_cmd, struct xcopy_pt_cmd, se_cmd); - kfree(xpt_cmd); + /* xpt_cmd is on the stack, nothing to free here */ + pr_debug("xpt_cmd done: %p\n", xpt_cmd); } static int xcopy_pt_check_stop_free(struct se_cmd *se_cmd) @@ -504,7 +500,6 @@ void target_xcopy_release_pt(void) * @cdb: SCSI CDB to be copied into @xpt_cmd. * @remote_port: If false, use the LUN through which the XCOPY command has * been received. If true, use @se_dev->xcopy_lun. - * @alloc_mem: Whether or not to allocate an SGL list. * * Set up a SCSI command (READ or WRITE) that will be used to execute an * XCOPY command. @@ -514,12 +509,9 @@ static int target_xcopy_setup_pt_cmd( struct xcopy_op *xop, struct se_device *se_dev, unsigned char *cdb, - bool remote_port, - bool alloc_mem) + bool remote_port) { struct se_cmd *cmd = &xpt_cmd->se_cmd; - sense_reason_t sense_rc; - int ret = 0, rc; /* * Setup LUN+port to honor reservations based upon xop->op_origin for @@ -535,46 +527,17 @@ static int target_xcopy_setup_pt_cmd( cmd->se_cmd_flags |= SCF_SE_LUN_CMD; cmd->tag = 0; - sense_rc = target_setup_cmd_from_cdb(cmd, cdb); - if (sense_rc) { - ret = -EINVAL; - goto out; - } + if (target_setup_cmd_from_cdb(cmd, cdb)) + return -EINVAL; - if (alloc_mem) { - rc = target_alloc_sgl(&cmd->t_data_sg, &cmd->t_data_nents, - cmd->data_length, false, false); - if (rc < 0) { - ret = rc; - goto out; - } - /* - * Set this bit so that transport_free_pages() allows the - * caller to release SGLs + physical memory allocated by - * transport_generic_get_mem().. - */ - cmd->se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC; - } else { - /* - * Here the previously allocated SGLs for the internal READ - * are mapped zero-copy to the internal WRITE. - */ - sense_rc = transport_generic_map_mem_to_cmd(cmd, - xop->xop_data_sg, xop->xop_data_nents, - NULL, 0); - if (sense_rc) { - ret = -EINVAL; - goto out; - } + if (transport_generic_map_mem_to_cmd(cmd, xop->xop_data_sg, + xop->xop_data_nents, NULL, 0)) + return -EINVAL; - pr_debug("Setup PASSTHROUGH_NOALLOC t_data_sg: %p t_data_nents:" - " %u\n", cmd->t_data_sg, cmd->t_data_nents); - } + pr_debug("Setup PASSTHROUGH_NOALLOC t_data_sg: %p t_data_nents:" + " %u\n", cmd->t_data_sg, cmd->t_data_nents); return 0; - -out: - return ret; } static int target_xcopy_issue_pt_cmd(struct xcopy_pt_cmd *xpt_cmd) @@ -604,20 +567,15 @@ static int target_xcopy_read_source( sector_t src_lba, u32 src_sectors) { - struct xcopy_pt_cmd *xpt_cmd; - struct se_cmd *se_cmd; + struct xcopy_pt_cmd xpt_cmd; + struct se_cmd *se_cmd = &xpt_cmd.se_cmd; u32 length = (src_sectors * src_dev->dev_attrib.block_size); int rc; unsigned char cdb[16]; bool remote_port = (xop->op_origin == XCOL_DEST_RECV_OP); - xpt_cmd = kzalloc(sizeof(struct xcopy_pt_cmd), GFP_KERNEL); - if (!xpt_cmd) { - pr_err("Unable to allocate xcopy_pt_cmd\n"); - return -ENOMEM; - } - init_completion(&xpt_cmd->xpt_passthrough_sem); - se_cmd = &xpt_cmd->se_cmd; + memset(&xpt_cmd, 0, sizeof(xpt_cmd)); + init_completion(&xpt_cmd.xpt_passthrough_sem); memset(&cdb[0], 0, 16); cdb[0] = READ_16; @@ -627,36 +585,24 @@ static int target_xcopy_read_source( (unsigned long long)src_lba, src_sectors, length); transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, &xcopy_pt_sess, length, - DMA_FROM_DEVICE, 0, &xpt_cmd->sense_buffer[0]); - xop->src_pt_cmd = xpt_cmd; + DMA_FROM_DEVICE, 0, &xpt_cmd.sense_buffer[0]); - rc = target_xcopy_setup_pt_cmd(xpt_cmd, xop, src_dev, &cdb[0], - remote_port, true); + rc = target_xcopy_setup_pt_cmd(&xpt_cmd, xop, src_dev, &cdb[0], + remote_port); if (rc < 0) { - ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status; - transport_generic_free_cmd(se_cmd, 0); - return rc; + ec_cmd->scsi_status = se_cmd->scsi_status; + goto out; } - xop->xop_data_sg = se_cmd->t_data_sg; - xop->xop_data_nents = se_cmd->t_data_nents; pr_debug("XCOPY-READ: Saved xop->xop_data_sg: %p, num: %u for READ" " memory\n", xop->xop_data_sg, xop->xop_data_nents); - rc = target_xcopy_issue_pt_cmd(xpt_cmd); - if (rc < 0) { - ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status; - transport_generic_free_cmd(se_cmd, 0); - return rc; - } - /* - * Clear off the allocated t_data_sg, that has been saved for - * zero-copy WRITE submission reuse in struct xcopy_op.. - */ - se_cmd->t_data_sg = NULL; - se_cmd->t_data_nents = 0; - - return 0; + rc = target_xcopy_issue_pt_cmd(&xpt_cmd); + if (rc < 0) + ec_cmd->scsi_status = se_cmd->scsi_status; +out: + transport_generic_free_cmd(se_cmd, 0); + return rc; } static int target_xcopy_write_destination( @@ -666,20 +612,15 @@ static int target_xcopy_write_destination( sector_t dst_lba, u32 dst_sectors) { - struct xcopy_pt_cmd *xpt_cmd; - struct se_cmd *se_cmd; + struct xcopy_pt_cmd xpt_cmd; + struct se_cmd *se_cmd = &xpt_cmd.se_cmd; u32 length = (dst_sectors * dst_dev->dev_attrib.block_size); int rc; unsigned char cdb[16]; bool remote_port = (xop->op_origin == XCOL_SOURCE_RECV_OP); - xpt_cmd = kzalloc(sizeof(struct xcopy_pt_cmd), GFP_KERNEL); - if (!xpt_cmd) { - pr_err("Unable to allocate xcopy_pt_cmd\n"); - return -ENOMEM; - } - init_completion(&xpt_cmd->xpt_passthrough_sem); - se_cmd = &xpt_cmd->se_cmd; + memset(&xpt_cmd, 0, sizeof(xpt_cmd)); + init_completion(&xpt_cmd.xpt_passthrough_sem); memset(&cdb[0], 0, 16); cdb[0] = WRITE_16; @@ -689,36 +630,21 @@ static int target_xcopy_write_destination( (unsigned long long)dst_lba, dst_sectors, length); transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, &xcopy_pt_sess, length, - DMA_TO_DEVICE, 0, &xpt_cmd->sense_buffer[0]); - xop->dst_pt_cmd = xpt_cmd; + DMA_TO_DEVICE, 0, &xpt_cmd.sense_buffer[0]); - rc = target_xcopy_setup_pt_cmd(xpt_cmd, xop, dst_dev, &cdb[0], - remote_port, false); + rc = target_xcopy_setup_pt_cmd(&xpt_cmd, xop, dst_dev, &cdb[0], + remote_port); if (rc < 0) { - struct se_cmd *src_cmd = &xop->src_pt_cmd->se_cmd; - ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status; - /* - * If the failure happened before the t_mem_list hand-off in - * target_xcopy_setup_pt_cmd(), Reset memory + clear flag so that - * core releases this memory on error during X-COPY WRITE I/O. - */ - src_cmd->se_cmd_flags &= ~SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC; - src_cmd->t_data_sg = xop->xop_data_sg; - src_cmd->t_data_nents = xop->xop_data_nents; - - transport_generic_free_cmd(se_cmd, 0); - return rc; - } - - rc = target_xcopy_issue_pt_cmd(xpt_cmd); - if (rc < 0) { - ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status; - se_cmd->se_cmd_flags &= ~SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC; - transport_generic_free_cmd(se_cmd, 0); - return rc; + ec_cmd->scsi_status = se_cmd->scsi_status; + goto out; } - return 0; + rc = target_xcopy_issue_pt_cmd(&xpt_cmd); + if (rc < 0) + ec_cmd->scsi_status = se_cmd->scsi_status; +out: + transport_generic_free_cmd(se_cmd, 0); + return rc; } static void target_xcopy_do_work(struct work_struct *work) @@ -729,7 +655,7 @@ static void target_xcopy_do_work(struct work_struct *work) sector_t src_lba, dst_lba, end_lba; unsigned int max_sectors; int rc = 0; - unsigned short nolb, cur_nolb, max_nolb, copied_nolb = 0; + unsigned short nolb, max_nolb, copied_nolb = 0; if (target_parse_xcopy_cmd(xop) != TCM_NO_SENSE) goto err_free; @@ -759,7 +685,23 @@ static void target_xcopy_do_work(struct work_struct *work) (unsigned long long)src_lba, (unsigned long long)dst_lba); while (src_lba < end_lba) { - cur_nolb = min(nolb, max_nolb); + unsigned short cur_nolb = min(nolb, max_nolb); + u32 cur_bytes = cur_nolb * src_dev->dev_attrib.block_size; + + if (cur_bytes != xop->xop_data_bytes) { + /* + * (Re)allocate a buffer large enough to hold the XCOPY + * I/O size, which can be reused each read / write loop. + */ + target_free_sgl(xop->xop_data_sg, xop->xop_data_nents); + rc = target_alloc_sgl(&xop->xop_data_sg, + &xop->xop_data_nents, + cur_bytes, + false, false); + if (rc < 0) + goto out; + xop->xop_data_bytes = cur_bytes; + } pr_debug("target_xcopy_do_work: Calling read src_dev: %p src_lba: %llu," " cur_nolb: %hu\n", src_dev, (unsigned long long)src_lba, cur_nolb); @@ -777,10 +719,8 @@ static void target_xcopy_do_work(struct work_struct *work) rc = target_xcopy_write_destination(ec_cmd, xop, dst_dev, dst_lba, cur_nolb); - if (rc < 0) { - transport_generic_free_cmd(&xop->src_pt_cmd->se_cmd, 0); + if (rc < 0) goto out; - } dst_lba += cur_nolb; pr_debug("target_xcopy_do_work: Incremented WRITE dst_lba to %llu\n", @@ -788,14 +728,10 @@ static void target_xcopy_do_work(struct work_struct *work) copied_nolb += cur_nolb; nolb -= cur_nolb; - - transport_generic_free_cmd(&xop->src_pt_cmd->se_cmd, 0); - xop->dst_pt_cmd->se_cmd.se_cmd_flags &= ~SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC; - - transport_generic_free_cmd(&xop->dst_pt_cmd->se_cmd, 0); } xcopy_pt_undepend_remotedev(xop); + target_free_sgl(xop->xop_data_sg, xop->xop_data_nents); kfree(xop); pr_debug("target_xcopy_do_work: Final src_lba: %llu, dst_lba: %llu\n", @@ -809,6 +745,7 @@ static void target_xcopy_do_work(struct work_struct *work) out: xcopy_pt_undepend_remotedev(xop); + target_free_sgl(xop->xop_data_sg, xop->xop_data_nents); err_free: kfree(xop); diff --git a/drivers/target/target_core_xcopy.h b/drivers/target/target_core_xcopy.h index 26ba4c3c9cff..c56a1bde9417 100644 --- a/drivers/target/target_core_xcopy.h +++ b/drivers/target/target_core_xcopy.h @@ -5,7 +5,7 @@ #define XCOPY_TARGET_DESC_LEN 32 #define XCOPY_SEGMENT_DESC_LEN 28 #define XCOPY_NAA_IEEE_REGEX_LEN 16 -#define XCOPY_MAX_SECTORS 1024 +#define XCOPY_MAX_SECTORS 4096 /* * SPC4r37 6.4.6.1 @@ -18,8 +18,6 @@ enum xcopy_origin_list { XCOL_DEST_RECV_OP = 0x02, }; -struct xcopy_pt_cmd; - struct xcopy_op { int op_origin; @@ -35,11 +33,8 @@ struct xcopy_op { unsigned short stdi; unsigned short dtdi; unsigned short nolb; - unsigned int dbl; - - struct xcopy_pt_cmd *src_pt_cmd; - struct xcopy_pt_cmd *dst_pt_cmd; + u32 xop_data_bytes; u32 xop_data_nents; struct scatterlist *xop_data_sg; struct work_struct xop_work; diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig new file mode 100644 index 000000000000..7db1460104b7 --- /dev/null +++ b/drivers/vdpa/Kconfig @@ -0,0 +1,37 @@ +# SPDX-License-Identifier: GPL-2.0-only +config VDPA + tristate + help + Enable this module to support vDPA device that uses a + datapath which complies with virtio specifications with + vendor specific control path. + +menuconfig VDPA_MENU + bool "VDPA drivers" + default n + +if VDPA_MENU + +config VDPA_SIM + tristate "vDPA device simulator" + depends on RUNTIME_TESTING_MENU + select VDPA + select VHOST_RING + default n + help + vDPA networking device simulator which loop TX traffic back + to RX. This device is used for testing, prototyping and + development of vDPA. + +config IFCVF + tristate "Intel IFC VF VDPA driver" + depends on PCI_MSI + select VDPA + default n + help + This kernel module can drive Intel IFC VF NIC to offload + virtio dataplane traffic to hardware. + To compile this driver as a module, choose M here: the module will + be called ifcvf. + +endif # VDPA_MENU diff --git a/drivers/vdpa/Makefile b/drivers/vdpa/Makefile new file mode 100644 index 000000000000..8bbb686ca7a2 --- /dev/null +++ b/drivers/vdpa/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_VDPA) += vdpa.o +obj-$(CONFIG_VDPA_SIM) += vdpa_sim/ +obj-$(CONFIG_IFCVF) += ifcvf/ diff --git a/drivers/vdpa/ifcvf/Makefile b/drivers/vdpa/ifcvf/Makefile new file mode 100644 index 000000000000..d709915995ab --- /dev/null +++ b/drivers/vdpa/ifcvf/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_IFCVF) += ifcvf.o +ifcvf-$(CONFIG_IFCVF) += ifcvf_main.o ifcvf_base.o diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c new file mode 100644 index 000000000000..b61b06ea26d3 --- /dev/null +++ b/drivers/vdpa/ifcvf/ifcvf_base.c @@ -0,0 +1,389 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Intel IFC VF NIC driver for virtio dataplane offloading + * + * Copyright (C) 2020 Intel Corporation. + * + * Author: Zhu Lingshan <lingshan.zhu@intel.com> + * + */ + +#include "ifcvf_base.h" + +static inline u8 ifc_ioread8(u8 __iomem *addr) +{ + return ioread8(addr); +} +static inline u16 ifc_ioread16 (__le16 __iomem *addr) +{ + return ioread16(addr); +} + +static inline u32 ifc_ioread32(__le32 __iomem *addr) +{ + return ioread32(addr); +} + +static inline void ifc_iowrite8(u8 value, u8 __iomem *addr) +{ + iowrite8(value, addr); +} + +static inline void ifc_iowrite16(u16 value, __le16 __iomem *addr) +{ + iowrite16(value, addr); +} + +static inline void ifc_iowrite32(u32 value, __le32 __iomem *addr) +{ + iowrite32(value, addr); +} + +static void ifc_iowrite64_twopart(u64 val, + __le32 __iomem *lo, __le32 __iomem *hi) +{ + ifc_iowrite32((u32)val, lo); + ifc_iowrite32(val >> 32, hi); +} + +struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw) +{ + return container_of(hw, struct ifcvf_adapter, vf); +} + +static void __iomem *get_cap_addr(struct ifcvf_hw *hw, + struct virtio_pci_cap *cap) +{ + struct ifcvf_adapter *ifcvf; + struct pci_dev *pdev; + u32 length, offset; + u8 bar; + + length = le32_to_cpu(cap->length); + offset = le32_to_cpu(cap->offset); + bar = cap->bar; + + ifcvf= vf_to_adapter(hw); + pdev = ifcvf->pdev; + + if (bar >= IFCVF_PCI_MAX_RESOURCE) { + IFCVF_DBG(pdev, + "Invalid bar number %u to get capabilities\n", bar); + return NULL; + } + + if (offset + length > pci_resource_len(pdev, bar)) { + IFCVF_DBG(pdev, + "offset(%u) + len(%u) overflows bar%u's capability\n", + offset, length, bar); + return NULL; + } + + return hw->base[bar] + offset; +} + +static int ifcvf_read_config_range(struct pci_dev *dev, + uint32_t *val, int size, int where) +{ + int ret, i; + + for (i = 0; i < size; i += 4) { + ret = pci_read_config_dword(dev, where + i, val + i / 4); + if (ret < 0) + return ret; + } + + return 0; +} + +int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev) +{ + struct virtio_pci_cap cap; + u16 notify_off; + int ret; + u8 pos; + u32 i; + + ret = pci_read_config_byte(pdev, PCI_CAPABILITY_LIST, &pos); + if (ret < 0) { + IFCVF_ERR(pdev, "Failed to read PCI capability list\n"); + return -EIO; + } + + while (pos) { + ret = ifcvf_read_config_range(pdev, (u32 *)&cap, + sizeof(cap), pos); + if (ret < 0) { + IFCVF_ERR(pdev, + "Failed to get PCI capability at %x\n", pos); + break; + } + + if (cap.cap_vndr != PCI_CAP_ID_VNDR) + goto next; + + switch (cap.cfg_type) { + case VIRTIO_PCI_CAP_COMMON_CFG: + hw->common_cfg = get_cap_addr(hw, &cap); + IFCVF_DBG(pdev, "hw->common_cfg = %p\n", + hw->common_cfg); + break; + case VIRTIO_PCI_CAP_NOTIFY_CFG: + pci_read_config_dword(pdev, pos + sizeof(cap), + &hw->notify_off_multiplier); + hw->notify_bar = cap.bar; + hw->notify_base = get_cap_addr(hw, &cap); + IFCVF_DBG(pdev, "hw->notify_base = %p\n", + hw->notify_base); + break; + case VIRTIO_PCI_CAP_ISR_CFG: + hw->isr = get_cap_addr(hw, &cap); + IFCVF_DBG(pdev, "hw->isr = %p\n", hw->isr); + break; + case VIRTIO_PCI_CAP_DEVICE_CFG: + hw->net_cfg = get_cap_addr(hw, &cap); + IFCVF_DBG(pdev, "hw->net_cfg = %p\n", hw->net_cfg); + break; + } + +next: + pos = cap.cap_next; + } + + if (hw->common_cfg == NULL || hw->notify_base == NULL || + hw->isr == NULL || hw->net_cfg == NULL) { + IFCVF_ERR(pdev, "Incomplete PCI capabilities\n"); + return -EIO; + } + + for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) { + ifc_iowrite16(i, &hw->common_cfg->queue_select); + notify_off = ifc_ioread16(&hw->common_cfg->queue_notify_off); + hw->vring[i].notify_addr = hw->notify_base + + notify_off * hw->notify_off_multiplier; + } + + hw->lm_cfg = hw->base[IFCVF_LM_BAR]; + + IFCVF_DBG(pdev, + "PCI capability mapping: common cfg: %p, notify base: %p\n, isr cfg: %p, device cfg: %p, multiplier: %u\n", + hw->common_cfg, hw->notify_base, hw->isr, + hw->net_cfg, hw->notify_off_multiplier); + + return 0; +} + +u8 ifcvf_get_status(struct ifcvf_hw *hw) +{ + return ifc_ioread8(&hw->common_cfg->device_status); +} + +void ifcvf_set_status(struct ifcvf_hw *hw, u8 status) +{ + ifc_iowrite8(status, &hw->common_cfg->device_status); +} + +void ifcvf_reset(struct ifcvf_hw *hw) +{ + ifcvf_set_status(hw, 0); + /* flush set_status, make sure VF is stopped, reset */ + ifcvf_get_status(hw); +} + +static void ifcvf_add_status(struct ifcvf_hw *hw, u8 status) +{ + if (status != 0) + status |= ifcvf_get_status(hw); + + ifcvf_set_status(hw, status); + ifcvf_get_status(hw); +} + +u64 ifcvf_get_features(struct ifcvf_hw *hw) +{ + struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg; + u32 features_lo, features_hi; + + ifc_iowrite32(0, &cfg->device_feature_select); + features_lo = ifc_ioread32(&cfg->device_feature); + + ifc_iowrite32(1, &cfg->device_feature_select); + features_hi = ifc_ioread32(&cfg->device_feature); + + return ((u64)features_hi << 32) | features_lo; +} + +void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset, + void *dst, int length) +{ + u8 old_gen, new_gen, *p; + int i; + + WARN_ON(offset + length > sizeof(struct virtio_net_config)); + do { + old_gen = ifc_ioread8(&hw->common_cfg->config_generation); + p = dst; + for (i = 0; i < length; i++) + *p++ = ifc_ioread8(hw->net_cfg + offset + i); + + new_gen = ifc_ioread8(&hw->common_cfg->config_generation); + } while (old_gen != new_gen); +} + +void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset, + const void *src, int length) +{ + const u8 *p; + int i; + + p = src; + WARN_ON(offset + length > sizeof(struct virtio_net_config)); + for (i = 0; i < length; i++) + ifc_iowrite8(*p++, hw->net_cfg + offset + i); +} + +static void ifcvf_set_features(struct ifcvf_hw *hw, u64 features) +{ + struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg; + + ifc_iowrite32(0, &cfg->guest_feature_select); + ifc_iowrite32((u32)features, &cfg->guest_feature); + + ifc_iowrite32(1, &cfg->guest_feature_select); + ifc_iowrite32(features >> 32, &cfg->guest_feature); +} + +static int ifcvf_config_features(struct ifcvf_hw *hw) +{ + struct ifcvf_adapter *ifcvf; + + ifcvf = vf_to_adapter(hw); + ifcvf_set_features(hw, hw->req_features); + ifcvf_add_status(hw, VIRTIO_CONFIG_S_FEATURES_OK); + + if (!(ifcvf_get_status(hw) & VIRTIO_CONFIG_S_FEATURES_OK)) { + IFCVF_ERR(ifcvf->pdev, "Failed to set FEATURES_OK status\n"); + return -EIO; + } + + return 0; +} + +u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid) +{ + struct ifcvf_lm_cfg __iomem *ifcvf_lm; + void __iomem *avail_idx_addr; + u16 last_avail_idx; + u32 q_pair_id; + + ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg; + q_pair_id = qid / (IFCVF_MAX_QUEUE_PAIRS * 2); + avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2]; + last_avail_idx = ifc_ioread16(avail_idx_addr); + + return last_avail_idx; +} + +int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num) +{ + struct ifcvf_lm_cfg __iomem *ifcvf_lm; + void __iomem *avail_idx_addr; + u32 q_pair_id; + + ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg; + q_pair_id = qid / (IFCVF_MAX_QUEUE_PAIRS * 2); + avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2]; + hw->vring[qid].last_avail_idx = num; + ifc_iowrite16(num, avail_idx_addr); + + return 0; +} + +static int ifcvf_hw_enable(struct ifcvf_hw *hw) +{ + struct ifcvf_lm_cfg __iomem *ifcvf_lm; + struct virtio_pci_common_cfg __iomem *cfg; + struct ifcvf_adapter *ifcvf; + u32 i; + + ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg; + ifcvf = vf_to_adapter(hw); + cfg = hw->common_cfg; + ifc_iowrite16(IFCVF_MSI_CONFIG_OFF, &cfg->msix_config); + + if (ifc_ioread16(&cfg->msix_config) == VIRTIO_MSI_NO_VECTOR) { + IFCVF_ERR(ifcvf->pdev, "No msix vector for device config\n"); + return -EINVAL; + } + + for (i = 0; i < hw->nr_vring; i++) { + if (!hw->vring[i].ready) + break; + + ifc_iowrite16(i, &cfg->queue_select); + ifc_iowrite64_twopart(hw->vring[i].desc, &cfg->queue_desc_lo, + &cfg->queue_desc_hi); + ifc_iowrite64_twopart(hw->vring[i].avail, &cfg->queue_avail_lo, + &cfg->queue_avail_hi); + ifc_iowrite64_twopart(hw->vring[i].used, &cfg->queue_used_lo, + &cfg->queue_used_hi); + ifc_iowrite16(hw->vring[i].size, &cfg->queue_size); + ifc_iowrite16(i + IFCVF_MSI_QUEUE_OFF, &cfg->queue_msix_vector); + + if (ifc_ioread16(&cfg->queue_msix_vector) == + VIRTIO_MSI_NO_VECTOR) { + IFCVF_ERR(ifcvf->pdev, + "No msix vector for queue %u\n", i); + return -EINVAL; + } + + ifcvf_set_vq_state(hw, i, hw->vring[i].last_avail_idx); + ifc_iowrite16(1, &cfg->queue_enable); + } + + return 0; +} + +static void ifcvf_hw_disable(struct ifcvf_hw *hw) +{ + struct virtio_pci_common_cfg __iomem *cfg; + u32 i; + + cfg = hw->common_cfg; + ifc_iowrite16(VIRTIO_MSI_NO_VECTOR, &cfg->msix_config); + + for (i = 0; i < hw->nr_vring; i++) { + ifc_iowrite16(i, &cfg->queue_select); + ifc_iowrite16(VIRTIO_MSI_NO_VECTOR, &cfg->queue_msix_vector); + } + + ifc_ioread16(&cfg->queue_msix_vector); +} + +int ifcvf_start_hw(struct ifcvf_hw *hw) +{ + ifcvf_reset(hw); + ifcvf_add_status(hw, VIRTIO_CONFIG_S_ACKNOWLEDGE); + ifcvf_add_status(hw, VIRTIO_CONFIG_S_DRIVER); + + if (ifcvf_config_features(hw) < 0) + return -EINVAL; + + if (ifcvf_hw_enable(hw) < 0) + return -EINVAL; + + ifcvf_add_status(hw, VIRTIO_CONFIG_S_DRIVER_OK); + + return 0; +} + +void ifcvf_stop_hw(struct ifcvf_hw *hw) +{ + ifcvf_hw_disable(hw); + ifcvf_reset(hw); +} + +void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid) +{ + ifc_iowrite16(qid, hw->vring[qid].notify_addr); +} diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h new file mode 100644 index 000000000000..e80307092351 --- /dev/null +++ b/drivers/vdpa/ifcvf/ifcvf_base.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Intel IFC VF NIC driver for virtio dataplane offloading + * + * Copyright (C) 2020 Intel Corporation. + * + * Author: Zhu Lingshan <lingshan.zhu@intel.com> + * + */ + +#ifndef _IFCVF_H_ +#define _IFCVF_H_ + +#include <linux/pci.h> +#include <linux/pci_regs.h> +#include <linux/vdpa.h> +#include <uapi/linux/virtio_net.h> +#include <uapi/linux/virtio_config.h> +#include <uapi/linux/virtio_pci.h> + +#define IFCVF_VENDOR_ID 0x1AF4 +#define IFCVF_DEVICE_ID 0x1041 +#define IFCVF_SUBSYS_VENDOR_ID 0x8086 +#define IFCVF_SUBSYS_DEVICE_ID 0x001A + +#define IFCVF_SUPPORTED_FEATURES \ + ((1ULL << VIRTIO_NET_F_MAC) | \ + (1ULL << VIRTIO_F_ANY_LAYOUT) | \ + (1ULL << VIRTIO_F_VERSION_1) | \ + (1ULL << VIRTIO_F_ORDER_PLATFORM) | \ + (1ULL << VIRTIO_F_IOMMU_PLATFORM) | \ + (1ULL << VIRTIO_NET_F_MRG_RXBUF)) + +/* Only one queue pair for now. */ +#define IFCVF_MAX_QUEUE_PAIRS 1 + +#define IFCVF_QUEUE_ALIGNMENT PAGE_SIZE +#define IFCVF_QUEUE_MAX 32768 +#define IFCVF_MSI_CONFIG_OFF 0 +#define IFCVF_MSI_QUEUE_OFF 1 +#define IFCVF_PCI_MAX_RESOURCE 6 + +#define IFCVF_LM_CFG_SIZE 0x40 +#define IFCVF_LM_RING_STATE_OFFSET 0x20 +#define IFCVF_LM_BAR 4 + +#define IFCVF_ERR(pdev, fmt, ...) dev_err(&pdev->dev, fmt, ##__VA_ARGS__) +#define IFCVF_DBG(pdev, fmt, ...) dev_dbg(&pdev->dev, fmt, ##__VA_ARGS__) +#define IFCVF_INFO(pdev, fmt, ...) dev_info(&pdev->dev, fmt, ##__VA_ARGS__) + +#define ifcvf_private_to_vf(adapter) \ + (&((struct ifcvf_adapter *)adapter)->vf) + +#define IFCVF_MAX_INTR (IFCVF_MAX_QUEUE_PAIRS * 2 + 1) + +struct vring_info { + u64 desc; + u64 avail; + u64 used; + u16 size; + u16 last_avail_idx; + bool ready; + void __iomem *notify_addr; + u32 irq; + struct vdpa_callback cb; + char msix_name[256]; +}; + +struct ifcvf_hw { + u8 __iomem *isr; + /* Live migration */ + u8 __iomem *lm_cfg; + u16 nr_vring; + /* Notification bar number */ + u8 notify_bar; + /* Notificaiton bar address */ + void __iomem *notify_base; + u32 notify_off_multiplier; + u64 req_features; + struct virtio_pci_common_cfg __iomem *common_cfg; + void __iomem *net_cfg; + struct vring_info vring[IFCVF_MAX_QUEUE_PAIRS * 2]; + void __iomem * const *base; +}; + +struct ifcvf_adapter { + struct vdpa_device vdpa; + struct pci_dev *pdev; + struct ifcvf_hw vf; +}; + +struct ifcvf_vring_lm_cfg { + u32 idx_addr[2]; + u8 reserved[IFCVF_LM_CFG_SIZE - 8]; +}; + +struct ifcvf_lm_cfg { + u8 reserved[IFCVF_LM_RING_STATE_OFFSET]; + struct ifcvf_vring_lm_cfg vring_lm_cfg[IFCVF_MAX_QUEUE_PAIRS]; +}; + +int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *dev); +int ifcvf_start_hw(struct ifcvf_hw *hw); +void ifcvf_stop_hw(struct ifcvf_hw *hw); +void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid); +void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset, + void *dst, int length); +void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset, + const void *src, int length); +u8 ifcvf_get_status(struct ifcvf_hw *hw); +void ifcvf_set_status(struct ifcvf_hw *hw, u8 status); +void io_write64_twopart(u64 val, u32 *lo, u32 *hi); +void ifcvf_reset(struct ifcvf_hw *hw); +u64 ifcvf_get_features(struct ifcvf_hw *hw); +u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid); +int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num); +struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw); +#endif /* _IFCVF_H_ */ diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c new file mode 100644 index 000000000000..8d54dc5b08d2 --- /dev/null +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -0,0 +1,435 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Intel IFC VF NIC driver for virtio dataplane offloading + * + * Copyright (C) 2020 Intel Corporation. + * + * Author: Zhu Lingshan <lingshan.zhu@intel.com> + * + */ + +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/sysfs.h> +#include "ifcvf_base.h" + +#define VERSION_STRING "0.1" +#define DRIVER_AUTHOR "Intel Corporation" +#define IFCVF_DRIVER_NAME "ifcvf" + +static irqreturn_t ifcvf_intr_handler(int irq, void *arg) +{ + struct vring_info *vring = arg; + + if (vring->cb.callback) + return vring->cb.callback(vring->cb.private); + + return IRQ_HANDLED; +} + +static int ifcvf_start_datapath(void *private) +{ + struct ifcvf_hw *vf = ifcvf_private_to_vf(private); + struct ifcvf_adapter *ifcvf; + u8 status; + int ret; + + ifcvf = vf_to_adapter(vf); + vf->nr_vring = IFCVF_MAX_QUEUE_PAIRS * 2; + ret = ifcvf_start_hw(vf); + if (ret < 0) { + status = ifcvf_get_status(vf); + status |= VIRTIO_CONFIG_S_FAILED; + ifcvf_set_status(vf, status); + } + + return ret; +} + +static int ifcvf_stop_datapath(void *private) +{ + struct ifcvf_hw *vf = ifcvf_private_to_vf(private); + int i; + + for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) + vf->vring[i].cb.callback = NULL; + + ifcvf_stop_hw(vf); + + return 0; +} + +static void ifcvf_reset_vring(struct ifcvf_adapter *adapter) +{ + struct ifcvf_hw *vf = ifcvf_private_to_vf(adapter); + int i; + + for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) { + vf->vring[i].last_avail_idx = 0; + vf->vring[i].desc = 0; + vf->vring[i].avail = 0; + vf->vring[i].used = 0; + vf->vring[i].ready = 0; + vf->vring[i].cb.callback = NULL; + vf->vring[i].cb.private = NULL; + } + + ifcvf_reset(vf); +} + +static struct ifcvf_adapter *vdpa_to_adapter(struct vdpa_device *vdpa_dev) +{ + return container_of(vdpa_dev, struct ifcvf_adapter, vdpa); +} + +static struct ifcvf_hw *vdpa_to_vf(struct vdpa_device *vdpa_dev) +{ + struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev); + + return &adapter->vf; +} + +static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + u64 features; + + features = ifcvf_get_features(vf) & IFCVF_SUPPORTED_FEATURES; + + return features; +} + +static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + vf->req_features = features; + + return 0; +} + +static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + return ifcvf_get_status(vf); +} + +static void ifcvf_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status) +{ + struct ifcvf_adapter *adapter; + struct ifcvf_hw *vf; + + vf = vdpa_to_vf(vdpa_dev); + adapter = dev_get_drvdata(vdpa_dev->dev.parent); + + if (status == 0) { + ifcvf_stop_datapath(adapter); + ifcvf_reset_vring(adapter); + return; + } + + if (status & VIRTIO_CONFIG_S_DRIVER_OK) { + if (ifcvf_start_datapath(adapter) < 0) + IFCVF_ERR(adapter->pdev, + "Failed to set ifcvf vdpa status %u\n", + status); + } + + ifcvf_set_status(vf, status); +} + +static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev) +{ + return IFCVF_QUEUE_MAX; +} + +static u64 ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + return ifcvf_get_vq_state(vf, qid); +} + +static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid, + u64 num) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + return ifcvf_set_vq_state(vf, qid, num); +} + +static void ifcvf_vdpa_set_vq_cb(struct vdpa_device *vdpa_dev, u16 qid, + struct vdpa_callback *cb) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + vf->vring[qid].cb = *cb; +} + +static void ifcvf_vdpa_set_vq_ready(struct vdpa_device *vdpa_dev, + u16 qid, bool ready) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + vf->vring[qid].ready = ready; +} + +static bool ifcvf_vdpa_get_vq_ready(struct vdpa_device *vdpa_dev, u16 qid) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + return vf->vring[qid].ready; +} + +static void ifcvf_vdpa_set_vq_num(struct vdpa_device *vdpa_dev, u16 qid, + u32 num) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + vf->vring[qid].size = num; +} + +static int ifcvf_vdpa_set_vq_address(struct vdpa_device *vdpa_dev, u16 qid, + u64 desc_area, u64 driver_area, + u64 device_area) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + vf->vring[qid].desc = desc_area; + vf->vring[qid].avail = driver_area; + vf->vring[qid].used = device_area; + + return 0; +} + +static void ifcvf_vdpa_kick_vq(struct vdpa_device *vdpa_dev, u16 qid) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + ifcvf_notify_queue(vf, qid); +} + +static u32 ifcvf_vdpa_get_generation(struct vdpa_device *vdpa_dev) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + return ioread8(&vf->common_cfg->config_generation); +} + +static u32 ifcvf_vdpa_get_device_id(struct vdpa_device *vdpa_dev) +{ + return VIRTIO_ID_NET; +} + +static u32 ifcvf_vdpa_get_vendor_id(struct vdpa_device *vdpa_dev) +{ + return IFCVF_SUBSYS_VENDOR_ID; +} + +static u16 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev) +{ + return IFCVF_QUEUE_ALIGNMENT; +} + +static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev, + unsigned int offset, + void *buf, unsigned int len) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + WARN_ON(offset + len > sizeof(struct virtio_net_config)); + ifcvf_read_net_config(vf, offset, buf, len); +} + +static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev, + unsigned int offset, const void *buf, + unsigned int len) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + WARN_ON(offset + len > sizeof(struct virtio_net_config)); + ifcvf_write_net_config(vf, offset, buf, len); +} + +static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev, + struct vdpa_callback *cb) +{ + /* We don't support config interrupt */ +} + +/* + * IFCVF currently does't have on-chip IOMMU, so not + * implemented set_map()/dma_map()/dma_unmap() + */ +static const struct vdpa_config_ops ifc_vdpa_ops = { + .get_features = ifcvf_vdpa_get_features, + .set_features = ifcvf_vdpa_set_features, + .get_status = ifcvf_vdpa_get_status, + .set_status = ifcvf_vdpa_set_status, + .get_vq_num_max = ifcvf_vdpa_get_vq_num_max, + .get_vq_state = ifcvf_vdpa_get_vq_state, + .set_vq_state = ifcvf_vdpa_set_vq_state, + .set_vq_cb = ifcvf_vdpa_set_vq_cb, + .set_vq_ready = ifcvf_vdpa_set_vq_ready, + .get_vq_ready = ifcvf_vdpa_get_vq_ready, + .set_vq_num = ifcvf_vdpa_set_vq_num, + .set_vq_address = ifcvf_vdpa_set_vq_address, + .kick_vq = ifcvf_vdpa_kick_vq, + .get_generation = ifcvf_vdpa_get_generation, + .get_device_id = ifcvf_vdpa_get_device_id, + .get_vendor_id = ifcvf_vdpa_get_vendor_id, + .get_vq_align = ifcvf_vdpa_get_vq_align, + .get_config = ifcvf_vdpa_get_config, + .set_config = ifcvf_vdpa_set_config, + .set_config_cb = ifcvf_vdpa_set_config_cb, +}; + +static int ifcvf_request_irq(struct ifcvf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ifcvf_hw *vf = &adapter->vf; + int vector, i, ret, irq; + + + for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) { + snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n", + pci_name(pdev), i); + vector = i + IFCVF_MSI_QUEUE_OFF; + irq = pci_irq_vector(pdev, vector); + ret = devm_request_irq(&pdev->dev, irq, + ifcvf_intr_handler, 0, + vf->vring[i].msix_name, + &vf->vring[i]); + if (ret) { + IFCVF_ERR(pdev, + "Failed to request irq for vq %d\n", i); + return ret; + } + vf->vring[i].irq = irq; + } + + return 0; +} + +static void ifcvf_free_irq_vectors(void *data) +{ + pci_free_irq_vectors(data); +} + +static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + struct ifcvf_adapter *adapter; + struct ifcvf_hw *vf; + int ret; + + ret = pcim_enable_device(pdev); + if (ret) { + IFCVF_ERR(pdev, "Failed to enable device\n"); + return ret; + } + + ret = pcim_iomap_regions(pdev, BIT(0) | BIT(2) | BIT(4), + IFCVF_DRIVER_NAME); + if (ret) { + IFCVF_ERR(pdev, "Failed to request MMIO region\n"); + return ret; + } + + ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + if (ret) { + IFCVF_ERR(pdev, "No usable DMA confiugration\n"); + return ret; + } + + ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + if (ret) { + IFCVF_ERR(pdev, + "No usable coherent DMA confiugration\n"); + return ret; + } + + ret = pci_alloc_irq_vectors(pdev, IFCVF_MAX_INTR, + IFCVF_MAX_INTR, PCI_IRQ_MSIX); + if (ret < 0) { + IFCVF_ERR(pdev, "Failed to alloc irq vectors\n"); + return ret; + } + + ret = devm_add_action_or_reset(dev, ifcvf_free_irq_vectors, pdev); + if (ret) { + IFCVF_ERR(pdev, + "Failed for adding devres for freeing irq vectors\n"); + return ret; + } + + adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, + dev, &ifc_vdpa_ops); + if (adapter == NULL) { + IFCVF_ERR(pdev, "Failed to allocate vDPA structure"); + return -ENOMEM; + } + + pci_set_master(pdev); + pci_set_drvdata(pdev, adapter); + + vf = &adapter->vf; + vf->base = pcim_iomap_table(pdev); + + adapter->pdev = pdev; + adapter->vdpa.dma_dev = &pdev->dev; + + ret = ifcvf_request_irq(adapter); + if (ret) { + IFCVF_ERR(pdev, "Failed to request MSI-X irq\n"); + goto err; + } + + ret = ifcvf_init_hw(vf, pdev); + if (ret) { + IFCVF_ERR(pdev, "Failed to init IFCVF hw\n"); + goto err; + } + + ret = vdpa_register_device(&adapter->vdpa); + if (ret) { + IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus"); + goto err; + } + + return 0; + +err: + put_device(&adapter->vdpa.dev); + return ret; +} + +static void ifcvf_remove(struct pci_dev *pdev) +{ + struct ifcvf_adapter *adapter = pci_get_drvdata(pdev); + + vdpa_unregister_device(&adapter->vdpa); +} + +static struct pci_device_id ifcvf_pci_ids[] = { + { PCI_DEVICE_SUB(IFCVF_VENDOR_ID, + IFCVF_DEVICE_ID, + IFCVF_SUBSYS_VENDOR_ID, + IFCVF_SUBSYS_DEVICE_ID) }, + { 0 }, +}; +MODULE_DEVICE_TABLE(pci, ifcvf_pci_ids); + +static struct pci_driver ifcvf_driver = { + .name = IFCVF_DRIVER_NAME, + .id_table = ifcvf_pci_ids, + .probe = ifcvf_probe, + .remove = ifcvf_remove, +}; + +module_pci_driver(ifcvf_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_VERSION(VERSION_STRING); diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c new file mode 100644 index 000000000000..e9ed6a2b635b --- /dev/null +++ b/drivers/vdpa/vdpa.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vDPA bus. + * + * Copyright (c) 2020, Red Hat. All rights reserved. + * Author: Jason Wang <jasowang@redhat.com> + * + */ + +#include <linux/module.h> +#include <linux/idr.h> +#include <linux/slab.h> +#include <linux/vdpa.h> + +static DEFINE_IDA(vdpa_index_ida); + +static int vdpa_dev_probe(struct device *d) +{ + struct vdpa_device *vdev = dev_to_vdpa(d); + struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver); + int ret = 0; + + if (drv && drv->probe) + ret = drv->probe(vdev); + + return ret; +} + +static int vdpa_dev_remove(struct device *d) +{ + struct vdpa_device *vdev = dev_to_vdpa(d); + struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver); + + if (drv && drv->remove) + drv->remove(vdev); + + return 0; +} + +static struct bus_type vdpa_bus = { + .name = "vdpa", + .probe = vdpa_dev_probe, + .remove = vdpa_dev_remove, +}; + +static void vdpa_release_dev(struct device *d) +{ + struct vdpa_device *vdev = dev_to_vdpa(d); + const struct vdpa_config_ops *ops = vdev->config; + + if (ops->free) + ops->free(vdev); + + ida_simple_remove(&vdpa_index_ida, vdev->index); + kfree(vdev); +} + +/** + * __vdpa_alloc_device - allocate and initilaize a vDPA device + * This allows driver to some prepartion after device is + * initialized but before registered. + * @parent: the parent device + * @config: the bus operations that is supported by this device + * @size: size of the parent structure that contains private data + * + * Drvier should use vdap_alloc_device() wrapper macro instead of + * using this directly. + * + * Returns an error when parent/config/dma_dev is not set or fail to get + * ida. + */ +struct vdpa_device *__vdpa_alloc_device(struct device *parent, + const struct vdpa_config_ops *config, + size_t size) +{ + struct vdpa_device *vdev; + int err = -EINVAL; + + if (!config) + goto err; + + if (!!config->dma_map != !!config->dma_unmap) + goto err; + + err = -ENOMEM; + vdev = kzalloc(size, GFP_KERNEL); + if (!vdev) + goto err; + + err = ida_simple_get(&vdpa_index_ida, 0, 0, GFP_KERNEL); + if (err < 0) + goto err_ida; + + vdev->dev.bus = &vdpa_bus; + vdev->dev.parent = parent; + vdev->dev.release = vdpa_release_dev; + vdev->index = err; + vdev->config = config; + + err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index); + if (err) + goto err_name; + + device_initialize(&vdev->dev); + + return vdev; + +err_name: + ida_simple_remove(&vdpa_index_ida, vdev->index); +err_ida: + kfree(vdev); +err: + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(__vdpa_alloc_device); + +/** + * vdpa_register_device - register a vDPA device + * Callers must have a succeed call of vdpa_init_device() before. + * @vdev: the vdpa device to be registered to vDPA bus + * + * Returns an error when fail to add to vDPA bus + */ +int vdpa_register_device(struct vdpa_device *vdev) +{ + return device_add(&vdev->dev); +} +EXPORT_SYMBOL_GPL(vdpa_register_device); + +/** + * vdpa_unregister_device - unregister a vDPA device + * @vdev: the vdpa device to be unregisted from vDPA bus + */ +void vdpa_unregister_device(struct vdpa_device *vdev) +{ + device_unregister(&vdev->dev); +} +EXPORT_SYMBOL_GPL(vdpa_unregister_device); + +/** + * __vdpa_register_driver - register a vDPA device driver + * @drv: the vdpa device driver to be registered + * @owner: module owner of the driver + * + * Returns an err when fail to do the registration + */ +int __vdpa_register_driver(struct vdpa_driver *drv, struct module *owner) +{ + drv->driver.bus = &vdpa_bus; + drv->driver.owner = owner; + + return driver_register(&drv->driver); +} +EXPORT_SYMBOL_GPL(__vdpa_register_driver); + +/** + * vdpa_unregister_driver - unregister a vDPA device driver + * @drv: the vdpa device driver to be unregistered + */ +void vdpa_unregister_driver(struct vdpa_driver *drv) +{ + driver_unregister(&drv->driver); +} +EXPORT_SYMBOL_GPL(vdpa_unregister_driver); + +static int vdpa_init(void) +{ + return bus_register(&vdpa_bus); +} + +static void __exit vdpa_exit(void) +{ + bus_unregister(&vdpa_bus); + ida_destroy(&vdpa_index_ida); +} +core_initcall(vdpa_init); +module_exit(vdpa_exit); + +MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/vdpa/vdpa_sim/Makefile b/drivers/vdpa/vdpa_sim/Makefile new file mode 100644 index 000000000000..b40278f65e04 --- /dev/null +++ b/drivers/vdpa/vdpa_sim/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_VDPA_SIM) += vdpa_sim.o diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c new file mode 100644 index 000000000000..6e8a0cf2fdeb --- /dev/null +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -0,0 +1,629 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VDPA networking device simulator. + * + * Copyright (c) 2020, Red Hat Inc. All rights reserved. + * Author: Jason Wang <jasowang@redhat.com> + * + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/fs.h> +#include <linux/poll.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/uuid.h> +#include <linux/iommu.h> +#include <linux/dma-mapping.h> +#include <linux/sysfs.h> +#include <linux/file.h> +#include <linux/etherdevice.h> +#include <linux/vringh.h> +#include <linux/vdpa.h> +#include <linux/vhost_iotlb.h> +#include <uapi/linux/virtio_config.h> +#include <uapi/linux/virtio_net.h> + +#define DRV_VERSION "0.1" +#define DRV_AUTHOR "Jason Wang <jasowang@redhat.com>" +#define DRV_DESC "vDPA Device Simulator" +#define DRV_LICENSE "GPL v2" + +struct vdpasim_virtqueue { + struct vringh vring; + struct vringh_kiov iov; + unsigned short head; + bool ready; + u64 desc_addr; + u64 device_addr; + u64 driver_addr; + u32 num; + void *private; + irqreturn_t (*cb)(void *data); +}; + +#define VDPASIM_QUEUE_ALIGN PAGE_SIZE +#define VDPASIM_QUEUE_MAX 256 +#define VDPASIM_DEVICE_ID 0x1 +#define VDPASIM_VENDOR_ID 0 +#define VDPASIM_VQ_NUM 0x2 +#define VDPASIM_NAME "vdpasim-netdev" + +static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) | + (1ULL << VIRTIO_F_VERSION_1) | + (1ULL << VIRTIO_F_IOMMU_PLATFORM); + +/* State of each vdpasim device */ +struct vdpasim { + struct vdpa_device vdpa; + struct vdpasim_virtqueue vqs[2]; + struct work_struct work; + /* spinlock to synchronize virtqueue state */ + spinlock_t lock; + struct virtio_net_config config; + struct vhost_iotlb *iommu; + void *buffer; + u32 status; + u32 generation; + u64 features; +}; + +static struct vdpasim *vdpasim_dev; + +static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa) +{ + return container_of(vdpa, struct vdpasim, vdpa); +} + +static struct vdpasim *dev_to_sim(struct device *dev) +{ + struct vdpa_device *vdpa = dev_to_vdpa(dev); + + return vdpa_to_sim(vdpa); +} + +static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) +{ + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + int ret; + + ret = vringh_init_iotlb(&vq->vring, vdpasim_features, + VDPASIM_QUEUE_MAX, false, + (struct vring_desc *)(uintptr_t)vq->desc_addr, + (struct vring_avail *) + (uintptr_t)vq->driver_addr, + (struct vring_used *) + (uintptr_t)vq->device_addr); +} + +static void vdpasim_vq_reset(struct vdpasim_virtqueue *vq) +{ + vq->ready = 0; + vq->desc_addr = 0; + vq->driver_addr = 0; + vq->device_addr = 0; + vq->cb = NULL; + vq->private = NULL; + vringh_init_iotlb(&vq->vring, vdpasim_features, VDPASIM_QUEUE_MAX, + false, NULL, NULL, NULL); +} + +static void vdpasim_reset(struct vdpasim *vdpasim) +{ + int i; + + for (i = 0; i < VDPASIM_VQ_NUM; i++) + vdpasim_vq_reset(&vdpasim->vqs[i]); + + vhost_iotlb_reset(vdpasim->iommu); + + vdpasim->features = 0; + vdpasim->status = 0; + ++vdpasim->generation; +} + +static void vdpasim_work(struct work_struct *work) +{ + struct vdpasim *vdpasim = container_of(work, struct + vdpasim, work); + struct vdpasim_virtqueue *txq = &vdpasim->vqs[1]; + struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0]; + size_t read, write, total_write; + int err; + int pkts = 0; + + spin_lock(&vdpasim->lock); + + if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto out; + + if (!txq->ready || !rxq->ready) + goto out; + + while (true) { + total_write = 0; + err = vringh_getdesc_iotlb(&txq->vring, &txq->iov, NULL, + &txq->head, GFP_ATOMIC); + if (err <= 0) + break; + + err = vringh_getdesc_iotlb(&rxq->vring, NULL, &rxq->iov, + &rxq->head, GFP_ATOMIC); + if (err <= 0) { + vringh_complete_iotlb(&txq->vring, txq->head, 0); + break; + } + + while (true) { + read = vringh_iov_pull_iotlb(&txq->vring, &txq->iov, + vdpasim->buffer, + PAGE_SIZE); + if (read <= 0) + break; + + write = vringh_iov_push_iotlb(&rxq->vring, &rxq->iov, + vdpasim->buffer, read); + if (write <= 0) + break; + + total_write += write; + } + + /* Make sure data is wrote before advancing index */ + smp_wmb(); + + vringh_complete_iotlb(&txq->vring, txq->head, 0); + vringh_complete_iotlb(&rxq->vring, rxq->head, total_write); + + /* Make sure used is visible before rasing the interrupt. */ + smp_wmb(); + + local_bh_disable(); + if (txq->cb) + txq->cb(txq->private); + if (rxq->cb) + rxq->cb(rxq->private); + local_bh_enable(); + + if (++pkts > 4) { + schedule_work(&vdpasim->work); + goto out; + } + } + +out: + spin_unlock(&vdpasim->lock); +} + +static int dir_to_perm(enum dma_data_direction dir) +{ + int perm = -EFAULT; + + switch (dir) { + case DMA_FROM_DEVICE: + perm = VHOST_MAP_WO; + break; + case DMA_TO_DEVICE: + perm = VHOST_MAP_RO; + break; + case DMA_BIDIRECTIONAL: + perm = VHOST_MAP_RW; + break; + default: + break; + } + + return perm; +} + +static dma_addr_t vdpasim_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + unsigned long attrs) +{ + struct vdpasim *vdpasim = dev_to_sim(dev); + struct vhost_iotlb *iommu = vdpasim->iommu; + u64 pa = (page_to_pfn(page) << PAGE_SHIFT) + offset; + int ret, perm = dir_to_perm(dir); + + if (perm < 0) + return DMA_MAPPING_ERROR; + + /* For simplicity, use identical mapping to avoid e.g iova + * allocator. + */ + ret = vhost_iotlb_add_range(iommu, pa, pa + size - 1, + pa, dir_to_perm(dir)); + if (ret) + return DMA_MAPPING_ERROR; + + return (dma_addr_t)(pa); +} + +static void vdpasim_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + struct vdpasim *vdpasim = dev_to_sim(dev); + struct vhost_iotlb *iommu = vdpasim->iommu; + + vhost_iotlb_del_range(iommu, (u64)dma_addr, + (u64)dma_addr + size - 1); +} + +static void *vdpasim_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_addr, gfp_t flag, + unsigned long attrs) +{ + struct vdpasim *vdpasim = dev_to_sim(dev); + struct vhost_iotlb *iommu = vdpasim->iommu; + void *addr = kmalloc(size, flag); + int ret; + + if (!addr) + *dma_addr = DMA_MAPPING_ERROR; + else { + u64 pa = virt_to_phys(addr); + + ret = vhost_iotlb_add_range(iommu, (u64)pa, + (u64)pa + size - 1, + pa, VHOST_MAP_RW); + if (ret) { + *dma_addr = DMA_MAPPING_ERROR; + kfree(addr); + addr = NULL; + } else + *dma_addr = (dma_addr_t)pa; + } + + return addr; +} + +static void vdpasim_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + unsigned long attrs) +{ + struct vdpasim *vdpasim = dev_to_sim(dev); + struct vhost_iotlb *iommu = vdpasim->iommu; + + vhost_iotlb_del_range(iommu, (u64)dma_addr, + (u64)dma_addr + size - 1); + kfree(phys_to_virt((uintptr_t)dma_addr)); +} + +static const struct dma_map_ops vdpasim_dma_ops = { + .map_page = vdpasim_map_page, + .unmap_page = vdpasim_unmap_page, + .alloc = vdpasim_alloc_coherent, + .free = vdpasim_free_coherent, +}; + +static const struct vdpa_config_ops vdpasim_net_config_ops; + +static struct vdpasim *vdpasim_create(void) +{ + struct virtio_net_config *config; + struct vdpasim *vdpasim; + struct device *dev; + int ret = -ENOMEM; + + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, + &vdpasim_net_config_ops); + if (!vdpasim) + goto err_alloc; + + INIT_WORK(&vdpasim->work, vdpasim_work); + spin_lock_init(&vdpasim->lock); + + dev = &vdpasim->vdpa.dev; + dev->coherent_dma_mask = DMA_BIT_MASK(64); + set_dma_ops(dev, &vdpasim_dma_ops); + + vdpasim->iommu = vhost_iotlb_alloc(2048, 0); + if (!vdpasim->iommu) + goto err_iommu; + + vdpasim->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!vdpasim->buffer) + goto err_iommu; + + config = &vdpasim->config; + config->mtu = 1500; + config->status = VIRTIO_NET_S_LINK_UP; + eth_random_addr(config->mac); + + vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu); + vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu); + + vdpasim->vdpa.dma_dev = dev; + ret = vdpa_register_device(&vdpasim->vdpa); + if (ret) + goto err_iommu; + + return vdpasim; + +err_iommu: + put_device(dev); +err_alloc: + return ERR_PTR(ret); +} + +static int vdpasim_set_vq_address(struct vdpa_device *vdpa, u16 idx, + u64 desc_area, u64 driver_area, + u64 device_area) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + vq->desc_addr = desc_area; + vq->driver_addr = driver_area; + vq->device_addr = device_area; + + return 0; +} + +static void vdpasim_set_vq_num(struct vdpa_device *vdpa, u16 idx, u32 num) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + vq->num = num; +} + +static void vdpasim_kick_vq(struct vdpa_device *vdpa, u16 idx) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + if (vq->ready) + schedule_work(&vdpasim->work); +} + +static void vdpasim_set_vq_cb(struct vdpa_device *vdpa, u16 idx, + struct vdpa_callback *cb) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + vq->cb = cb->callback; + vq->private = cb->private; +} + +static void vdpasim_set_vq_ready(struct vdpa_device *vdpa, u16 idx, bool ready) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + spin_lock(&vdpasim->lock); + vq->ready = ready; + if (vq->ready) + vdpasim_queue_ready(vdpasim, idx); + spin_unlock(&vdpasim->lock); +} + +static bool vdpasim_get_vq_ready(struct vdpa_device *vdpa, u16 idx) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + return vq->ready; +} + +static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, u64 state) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + struct vringh *vrh = &vq->vring; + + spin_lock(&vdpasim->lock); + vrh->last_avail_idx = state; + spin_unlock(&vdpasim->lock); + + return 0; +} + +static u64 vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + struct vringh *vrh = &vq->vring; + + return vrh->last_avail_idx; +} + +static u16 vdpasim_get_vq_align(struct vdpa_device *vdpa) +{ + return VDPASIM_QUEUE_ALIGN; +} + +static u64 vdpasim_get_features(struct vdpa_device *vdpa) +{ + return vdpasim_features; +} + +static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + /* DMA mapping must be done by driver */ + if (!(features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) + return -EINVAL; + + vdpasim->features = features & vdpasim_features; + + return 0; +} + +static void vdpasim_set_config_cb(struct vdpa_device *vdpa, + struct vdpa_callback *cb) +{ + /* We don't support config interrupt */ +} + +static u16 vdpasim_get_vq_num_max(struct vdpa_device *vdpa) +{ + return VDPASIM_QUEUE_MAX; +} + +static u32 vdpasim_get_device_id(struct vdpa_device *vdpa) +{ + return VDPASIM_DEVICE_ID; +} + +static u32 vdpasim_get_vendor_id(struct vdpa_device *vdpa) +{ + return VDPASIM_VENDOR_ID; +} + +static u8 vdpasim_get_status(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + u8 status; + + spin_lock(&vdpasim->lock); + status = vdpasim->status; + spin_unlock(&vdpasim->lock); + + return vdpasim->status; +} + +static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + spin_lock(&vdpasim->lock); + vdpasim->status = status; + if (status == 0) + vdpasim_reset(vdpasim); + spin_unlock(&vdpasim->lock); +} + +static void vdpasim_get_config(struct vdpa_device *vdpa, unsigned int offset, + void *buf, unsigned int len) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + if (offset + len < sizeof(struct virtio_net_config)) + memcpy(buf, &vdpasim->config + offset, len); +} + +static void vdpasim_set_config(struct vdpa_device *vdpa, unsigned int offset, + const void *buf, unsigned int len) +{ + /* No writable config supportted by vdpasim */ +} + +static u32 vdpasim_get_generation(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vdpasim->generation; +} + +static int vdpasim_set_map(struct vdpa_device *vdpa, + struct vhost_iotlb *iotlb) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vhost_iotlb_map *map; + u64 start = 0ULL, last = 0ULL - 1; + int ret; + + vhost_iotlb_reset(vdpasim->iommu); + + for (map = vhost_iotlb_itree_first(iotlb, start, last); map; + map = vhost_iotlb_itree_next(map, start, last)) { + ret = vhost_iotlb_add_range(vdpasim->iommu, map->start, + map->last, map->addr, map->perm); + if (ret) + goto err; + } + return 0; + +err: + vhost_iotlb_reset(vdpasim->iommu); + return ret; +} + +static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size, + u64 pa, u32 perm) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vhost_iotlb_add_range(vdpasim->iommu, iova, + iova + size - 1, pa, perm); +} + +static int vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + vhost_iotlb_del_range(vdpasim->iommu, iova, iova + size - 1); + + return 0; +} + +static void vdpasim_free(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + cancel_work_sync(&vdpasim->work); + kfree(vdpasim->buffer); + if (vdpasim->iommu) + vhost_iotlb_free(vdpasim->iommu); +} + +static const struct vdpa_config_ops vdpasim_net_config_ops = { + .set_vq_address = vdpasim_set_vq_address, + .set_vq_num = vdpasim_set_vq_num, + .kick_vq = vdpasim_kick_vq, + .set_vq_cb = vdpasim_set_vq_cb, + .set_vq_ready = vdpasim_set_vq_ready, + .get_vq_ready = vdpasim_get_vq_ready, + .set_vq_state = vdpasim_set_vq_state, + .get_vq_state = vdpasim_get_vq_state, + .get_vq_align = vdpasim_get_vq_align, + .get_features = vdpasim_get_features, + .set_features = vdpasim_set_features, + .set_config_cb = vdpasim_set_config_cb, + .get_vq_num_max = vdpasim_get_vq_num_max, + .get_device_id = vdpasim_get_device_id, + .get_vendor_id = vdpasim_get_vendor_id, + .get_status = vdpasim_get_status, + .set_status = vdpasim_set_status, + .get_config = vdpasim_get_config, + .set_config = vdpasim_set_config, + .get_generation = vdpasim_get_generation, + .set_map = vdpasim_set_map, + .dma_map = vdpasim_dma_map, + .dma_unmap = vdpasim_dma_unmap, + .free = vdpasim_free, +}; + +static int __init vdpasim_dev_init(void) +{ + vdpasim_dev = vdpasim_create(); + + if (!IS_ERR(vdpasim_dev)) + return 0; + + return PTR_ERR(vdpasim_dev); +} + +static void __exit vdpasim_dev_exit(void) +{ + struct vdpa_device *vdpa = &vdpasim_dev->vdpa; + + vdpa_unregister_device(vdpa); +} + +module_init(vdpasim_dev_init) +module_exit(vdpasim_dev_exit) + +MODULE_VERSION(DRV_VERSION); +MODULE_LICENSE(DRV_LICENSE); +MODULE_AUTHOR(DRV_AUTHOR); +MODULE_DESCRIPTION(DRV_DESC); diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig index 3d03ccbd1adc..362b832f5338 100644 --- a/drivers/vhost/Kconfig +++ b/drivers/vhost/Kconfig @@ -1,4 +1,29 @@ # SPDX-License-Identifier: GPL-2.0-only +config VHOST_IOTLB + tristate + help + Generic IOTLB implementation for vhost and vringh. + +config VHOST_RING + tristate + select VHOST_IOTLB + help + This option is selected by any driver which needs to access + the host side of a virtio ring. + +config VHOST + tristate + select VHOST_IOTLB + help + This option is selected by any driver which needs to access + the core of vhost. + +menuconfig VHOST_MENU + bool "VHOST drivers" + default y + +if VHOST_MENU + config VHOST_NET tristate "Host kernel accelerator for virtio net" depends on NET && EVENTFD && (TUN || !TUN) && (TAP || !TAP) @@ -23,8 +48,8 @@ config VHOST_SCSI config VHOST_VSOCK tristate "vhost virtio-vsock driver" depends on VSOCKETS && EVENTFD - select VIRTIO_VSOCKETS_COMMON select VHOST + select VIRTIO_VSOCKETS_COMMON default n ---help--- This kernel module can be loaded in the host kernel to provide AF_VSOCK @@ -34,11 +59,17 @@ config VHOST_VSOCK To compile this driver as a module, choose M here: the module will be called vhost_vsock. -config VHOST - tristate - ---help--- - This option is selected by any driver which needs to access - the core of vhost. +config VHOST_VDPA + tristate "Vhost driver for vDPA-based backend" + depends on EVENTFD + select VHOST + select VDPA + help + This kernel module can be loaded in host kernel to accelerate + guest virtio devices with the vDPA-based backends. + + To compile this driver as a module, choose M here: the module + will be called vhost_vdpa. config VHOST_CROSS_ENDIAN_LEGACY bool "Cross-endian support for vhost" @@ -54,3 +85,5 @@ config VHOST_CROSS_ENDIAN_LEGACY adds some overhead, it is disabled by default. If unsure, say "N". + +endif diff --git a/drivers/vhost/Kconfig.vringh b/drivers/vhost/Kconfig.vringh deleted file mode 100644 index c1fe36a9b8d4..000000000000 --- a/drivers/vhost/Kconfig.vringh +++ /dev/null @@ -1,6 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -config VHOST_RING - tristate - ---help--- - This option is selected by any driver which needs to access - the host side of a virtio ring. diff --git a/drivers/vhost/Makefile b/drivers/vhost/Makefile index 6c6df24f770c..f3e1897cce85 100644 --- a/drivers/vhost/Makefile +++ b/drivers/vhost/Makefile @@ -10,4 +10,10 @@ vhost_vsock-y := vsock.o obj-$(CONFIG_VHOST_RING) += vringh.o +obj-$(CONFIG_VHOST_VDPA) += vhost_vdpa.o +vhost_vdpa-y := vdpa.o + obj-$(CONFIG_VHOST) += vhost.o + +obj-$(CONFIG_VHOST_IOTLB) += vhost_iotlb.o +vhost_iotlb-y := iotlb.o diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c new file mode 100644 index 000000000000..1f0ca6e44410 --- /dev/null +++ b/drivers/vhost/iotlb.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2020 Red Hat, Inc. + * Author: Jason Wang <jasowang@redhat.com> + * + * IOTLB implementation for vhost. + */ +#include <linux/slab.h> +#include <linux/vhost_iotlb.h> +#include <linux/module.h> + +#define MOD_VERSION "0.1" +#define MOD_DESC "VHOST IOTLB" +#define MOD_AUTHOR "Jason Wang <jasowang@redhat.com>" +#define MOD_LICENSE "GPL v2" + +#define START(map) ((map)->start) +#define LAST(map) ((map)->last) + +INTERVAL_TREE_DEFINE(struct vhost_iotlb_map, + rb, __u64, __subtree_last, + START, LAST, static inline, vhost_iotlb_itree); + +/** + * vhost_iotlb_map_free - remove a map node and free it + * @iotlb: the IOTLB + * @map: the map that want to be remove and freed + */ +void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, + struct vhost_iotlb_map *map) +{ + vhost_iotlb_itree_remove(map, &iotlb->root); + list_del(&map->link); + kfree(map); + iotlb->nmaps--; +} +EXPORT_SYMBOL_GPL(vhost_iotlb_map_free); + +/** + * vhost_iotlb_add_range - add a new range to vhost IOTLB + * @iotlb: the IOTLB + * @start: start of the IOVA range + * @last: last of IOVA range + * @addr: the address that is mapped to @start + * @perm: access permission of this range + * + * Returns an error last is smaller than start or memory allocation + * fails + */ +int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, + u64 start, u64 last, + u64 addr, unsigned int perm) +{ + struct vhost_iotlb_map *map; + + if (last < start) + return -EFAULT; + + if (iotlb->limit && + iotlb->nmaps == iotlb->limit && + iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) { + map = list_first_entry(&iotlb->list, typeof(*map), link); + vhost_iotlb_map_free(iotlb, map); + } + + map = kmalloc(sizeof(*map), GFP_ATOMIC); + if (!map) + return -ENOMEM; + + map->start = start; + map->size = last - start + 1; + map->last = last; + map->addr = addr; + map->perm = perm; + + iotlb->nmaps++; + vhost_iotlb_itree_insert(map, &iotlb->root); + + INIT_LIST_HEAD(&map->link); + list_add_tail(&map->link, &iotlb->list); + + return 0; +} +EXPORT_SYMBOL_GPL(vhost_iotlb_add_range); + +/** + * vring_iotlb_del_range - delete overlapped ranges from vhost IOTLB + * @iotlb: the IOTLB + * @start: start of the IOVA range + * @last: last of IOVA range + */ +void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last) +{ + struct vhost_iotlb_map *map; + + while ((map = vhost_iotlb_itree_iter_first(&iotlb->root, + start, last))) + vhost_iotlb_map_free(iotlb, map); +} +EXPORT_SYMBOL_GPL(vhost_iotlb_del_range); + +/** + * vhost_iotlb_alloc - add a new vhost IOTLB + * @limit: maximum number of IOTLB entries + * @flags: VHOST_IOTLB_FLAG_XXX + * + * Returns an error is memory allocation fails + */ +struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags) +{ + struct vhost_iotlb *iotlb = kzalloc(sizeof(*iotlb), GFP_KERNEL); + + if (!iotlb) + return NULL; + + iotlb->root = RB_ROOT_CACHED; + iotlb->limit = limit; + iotlb->nmaps = 0; + iotlb->flags = flags; + INIT_LIST_HEAD(&iotlb->list); + + return iotlb; +} +EXPORT_SYMBOL_GPL(vhost_iotlb_alloc); + +/** + * vhost_iotlb_reset - reset vhost IOTLB (free all IOTLB entries) + * @iotlb: the IOTLB to be reset + */ +void vhost_iotlb_reset(struct vhost_iotlb *iotlb) +{ + vhost_iotlb_del_range(iotlb, 0ULL, 0ULL - 1); +} +EXPORT_SYMBOL_GPL(vhost_iotlb_reset); + +/** + * vhost_iotlb_free - reset and free vhost IOTLB + * @iotlb: the IOTLB to be freed + */ +void vhost_iotlb_free(struct vhost_iotlb *iotlb) +{ + if (iotlb) { + vhost_iotlb_reset(iotlb); + kfree(iotlb); + } +} +EXPORT_SYMBOL_GPL(vhost_iotlb_free); + +/** + * vhost_iotlb_itree_first - return the first overlapped range + * @iotlb: the IOTLB + * @start: start of IOVA range + * @end: end of IOVA range + */ +struct vhost_iotlb_map * +vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last) +{ + return vhost_iotlb_itree_iter_first(&iotlb->root, start, last); +} +EXPORT_SYMBOL_GPL(vhost_iotlb_itree_first); + +/** + * vhost_iotlb_itree_first - return the next overlapped range + * @iotlb: the IOTLB + * @start: start of IOVA range + * @end: end of IOVA range + */ +struct vhost_iotlb_map * +vhost_iotlb_itree_next(struct vhost_iotlb_map *map, u64 start, u64 last) +{ + return vhost_iotlb_itree_iter_next(map, start, last); +} +EXPORT_SYMBOL_GPL(vhost_iotlb_itree_next); + +MODULE_VERSION(MOD_VERSION); +MODULE_DESCRIPTION(MOD_DESC); +MODULE_AUTHOR(MOD_AUTHOR); +MODULE_LICENSE(MOD_LICENSE); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 18e205eeb9af..87469d67ede8 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1324,7 +1324,8 @@ static int vhost_net_open(struct inode *inode, struct file *f) } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, UIO_MAXIOV + VHOST_NET_BATCH, - VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT); + VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT, + NULL); vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev); vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev); @@ -1586,7 +1587,7 @@ static long vhost_net_reset_owner(struct vhost_net *n) struct socket *tx_sock = NULL; struct socket *rx_sock = NULL; long err; - struct vhost_umem *umem; + struct vhost_iotlb *umem; mutex_lock(&n->dev.mutex); err = vhost_dev_check_owner(&n->dev); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 0b949a14bce3..7653667a8cdc 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1628,7 +1628,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick; } vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV, - VHOST_SCSI_WEIGHT, 0); + VHOST_SCSI_WEIGHT, 0, NULL); vhost_scsi_init_inflight(vs, NULL); diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c new file mode 100644 index 000000000000..421f02a8530a --- /dev/null +++ b/drivers/vhost/vdpa.c @@ -0,0 +1,883 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018-2020 Intel Corporation. + * Copyright (C) 2020 Red Hat, Inc. + * + * Author: Tiwei Bie <tiwei.bie@intel.com> + * Jason Wang <jasowang@redhat.com> + * + * Thanks Michael S. Tsirkin for the valuable comments and + * suggestions. And thanks to Cunming Liang and Zhihong Wang for all + * their supports. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/cdev.h> +#include <linux/device.h> +#include <linux/iommu.h> +#include <linux/uuid.h> +#include <linux/vdpa.h> +#include <linux/nospec.h> +#include <linux/vhost.h> +#include <linux/virtio_net.h> + +#include "vhost.h" + +enum { + VHOST_VDPA_FEATURES = + (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) | + (1ULL << VIRTIO_F_ANY_LAYOUT) | + (1ULL << VIRTIO_F_VERSION_1) | + (1ULL << VIRTIO_F_IOMMU_PLATFORM) | + (1ULL << VIRTIO_F_RING_PACKED) | + (1ULL << VIRTIO_F_ORDER_PLATFORM) | + (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | + (1ULL << VIRTIO_RING_F_EVENT_IDX), + + VHOST_VDPA_NET_FEATURES = VHOST_VDPA_FEATURES | + (1ULL << VIRTIO_NET_F_CSUM) | + (1ULL << VIRTIO_NET_F_GUEST_CSUM) | + (1ULL << VIRTIO_NET_F_MTU) | + (1ULL << VIRTIO_NET_F_MAC) | + (1ULL << VIRTIO_NET_F_GUEST_TSO4) | + (1ULL << VIRTIO_NET_F_GUEST_TSO6) | + (1ULL << VIRTIO_NET_F_GUEST_ECN) | + (1ULL << VIRTIO_NET_F_GUEST_UFO) | + (1ULL << VIRTIO_NET_F_HOST_TSO4) | + (1ULL << VIRTIO_NET_F_HOST_TSO6) | + (1ULL << VIRTIO_NET_F_HOST_ECN) | + (1ULL << VIRTIO_NET_F_HOST_UFO) | + (1ULL << VIRTIO_NET_F_MRG_RXBUF) | + (1ULL << VIRTIO_NET_F_STATUS) | + (1ULL << VIRTIO_NET_F_SPEED_DUPLEX), +}; + +/* Currently, only network backend w/o multiqueue is supported. */ +#define VHOST_VDPA_VQ_MAX 2 + +#define VHOST_VDPA_DEV_MAX (1U << MINORBITS) + +struct vhost_vdpa { + struct vhost_dev vdev; + struct iommu_domain *domain; + struct vhost_virtqueue *vqs; + struct completion completion; + struct vdpa_device *vdpa; + struct device dev; + struct cdev cdev; + atomic_t opened; + int nvqs; + int virtio_id; + int minor; +}; + +static DEFINE_IDA(vhost_vdpa_ida); + +static dev_t vhost_vdpa_major; + +static const u64 vhost_vdpa_features[] = { + [VIRTIO_ID_NET] = VHOST_VDPA_NET_FEATURES, +}; + +static void handle_vq_kick(struct vhost_work *work) +{ + struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, + poll.work); + struct vhost_vdpa *v = container_of(vq->dev, struct vhost_vdpa, vdev); + const struct vdpa_config_ops *ops = v->vdpa->config; + + ops->kick_vq(v->vdpa, vq - v->vqs); +} + +static irqreturn_t vhost_vdpa_virtqueue_cb(void *private) +{ + struct vhost_virtqueue *vq = private; + struct eventfd_ctx *call_ctx = vq->call_ctx; + + if (call_ctx) + eventfd_signal(call_ctx, 1); + + return IRQ_HANDLED; +} + +static void vhost_vdpa_reset(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + ops->set_status(vdpa, 0); +} + +static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + u32 device_id; + + device_id = ops->get_device_id(vdpa); + + if (copy_to_user(argp, &device_id, sizeof(device_id))) + return -EFAULT; + + return 0; +} + +static long vhost_vdpa_get_status(struct vhost_vdpa *v, u8 __user *statusp) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + u8 status; + + status = ops->get_status(vdpa); + + if (copy_to_user(statusp, &status, sizeof(status))) + return -EFAULT; + + return 0; +} + +static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + u8 status; + + if (copy_from_user(&status, statusp, sizeof(status))) + return -EFAULT; + + /* + * Userspace shouldn't remove status bits unless reset the + * status to 0. + */ + if (status != 0 && (ops->get_status(vdpa) & ~status) != 0) + return -EINVAL; + + ops->set_status(vdpa, status); + + return 0; +} + +static int vhost_vdpa_config_validate(struct vhost_vdpa *v, + struct vhost_vdpa_config *c) +{ + long size = 0; + + switch (v->virtio_id) { + case VIRTIO_ID_NET: + size = sizeof(struct virtio_net_config); + break; + } + + if (c->len == 0) + return -EINVAL; + + if (c->len > size - c->off) + return -E2BIG; + + return 0; +} + +static long vhost_vdpa_get_config(struct vhost_vdpa *v, + struct vhost_vdpa_config __user *c) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + struct vhost_vdpa_config config; + unsigned long size = offsetof(struct vhost_vdpa_config, buf); + u8 *buf; + + if (copy_from_user(&config, c, size)) + return -EFAULT; + if (vhost_vdpa_config_validate(v, &config)) + return -EINVAL; + buf = kvzalloc(config.len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + ops->get_config(vdpa, config.off, buf, config.len); + + if (copy_to_user(c->buf, buf, config.len)) { + kvfree(buf); + return -EFAULT; + } + + kvfree(buf); + return 0; +} + +static long vhost_vdpa_set_config(struct vhost_vdpa *v, + struct vhost_vdpa_config __user *c) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + struct vhost_vdpa_config config; + unsigned long size = offsetof(struct vhost_vdpa_config, buf); + u8 *buf; + + if (copy_from_user(&config, c, size)) + return -EFAULT; + if (vhost_vdpa_config_validate(v, &config)) + return -EINVAL; + buf = kvzalloc(config.len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, c->buf, config.len)) { + kvfree(buf); + return -EFAULT; + } + + ops->set_config(vdpa, config.off, buf, config.len); + + kvfree(buf); + return 0; +} + +static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + u64 features; + + features = ops->get_features(vdpa); + features &= vhost_vdpa_features[v->virtio_id]; + + if (copy_to_user(featurep, &features, sizeof(features))) + return -EFAULT; + + return 0; +} + +static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + u64 features; + + /* + * It's not allowed to change the features after they have + * been negotiated. + */ + if (ops->get_status(vdpa) & VIRTIO_CONFIG_S_FEATURES_OK) + return -EBUSY; + + if (copy_from_user(&features, featurep, sizeof(features))) + return -EFAULT; + + if (features & ~vhost_vdpa_features[v->virtio_id]) + return -EINVAL; + + if (ops->set_features(vdpa, features)) + return -EINVAL; + + return 0; +} + +static long vhost_vdpa_get_vring_num(struct vhost_vdpa *v, u16 __user *argp) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + u16 num; + + num = ops->get_vq_num_max(vdpa); + + if (copy_to_user(argp, &num, sizeof(num))) + return -EFAULT; + + return 0; +} + +static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, + void __user *argp) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + struct vdpa_callback cb; + struct vhost_virtqueue *vq; + struct vhost_vring_state s; + u8 status; + u32 idx; + long r; + + r = get_user(idx, (u32 __user *)argp); + if (r < 0) + return r; + + if (idx >= v->nvqs) + return -ENOBUFS; + + idx = array_index_nospec(idx, v->nvqs); + vq = &v->vqs[idx]; + + status = ops->get_status(vdpa); + + if (cmd == VHOST_VDPA_SET_VRING_ENABLE) { + if (copy_from_user(&s, argp, sizeof(s))) + return -EFAULT; + ops->set_vq_ready(vdpa, idx, s.num); + return 0; + } + + if (cmd == VHOST_GET_VRING_BASE) + vq->last_avail_idx = ops->get_vq_state(v->vdpa, idx); + + r = vhost_vring_ioctl(&v->vdev, cmd, argp); + if (r) + return r; + + switch (cmd) { + case VHOST_SET_VRING_ADDR: + if (ops->set_vq_address(vdpa, idx, + (u64)(uintptr_t)vq->desc, + (u64)(uintptr_t)vq->avail, + (u64)(uintptr_t)vq->used)) + r = -EINVAL; + break; + + case VHOST_SET_VRING_BASE: + if (ops->set_vq_state(vdpa, idx, vq->last_avail_idx)) + r = -EINVAL; + break; + + case VHOST_SET_VRING_CALL: + if (vq->call_ctx) { + cb.callback = vhost_vdpa_virtqueue_cb; + cb.private = vq; + } else { + cb.callback = NULL; + cb.private = NULL; + } + ops->set_vq_cb(vdpa, idx, &cb); + break; + + case VHOST_SET_VRING_NUM: + ops->set_vq_num(vdpa, idx, vq->num); + break; + } + + return r; +} + +static long vhost_vdpa_unlocked_ioctl(struct file *filep, + unsigned int cmd, unsigned long arg) +{ + struct vhost_vdpa *v = filep->private_data; + struct vhost_dev *d = &v->vdev; + void __user *argp = (void __user *)arg; + long r; + + mutex_lock(&d->mutex); + + switch (cmd) { + case VHOST_VDPA_GET_DEVICE_ID: + r = vhost_vdpa_get_device_id(v, argp); + break; + case VHOST_VDPA_GET_STATUS: + r = vhost_vdpa_get_status(v, argp); + break; + case VHOST_VDPA_SET_STATUS: + r = vhost_vdpa_set_status(v, argp); + break; + case VHOST_VDPA_GET_CONFIG: + r = vhost_vdpa_get_config(v, argp); + break; + case VHOST_VDPA_SET_CONFIG: + r = vhost_vdpa_set_config(v, argp); + break; + case VHOST_GET_FEATURES: + r = vhost_vdpa_get_features(v, argp); + break; + case VHOST_SET_FEATURES: + r = vhost_vdpa_set_features(v, argp); + break; + case VHOST_VDPA_GET_VRING_NUM: + r = vhost_vdpa_get_vring_num(v, argp); + break; + case VHOST_SET_LOG_BASE: + case VHOST_SET_LOG_FD: + r = -ENOIOCTLCMD; + break; + default: + r = vhost_dev_ioctl(&v->vdev, cmd, argp); + if (r == -ENOIOCTLCMD) + r = vhost_vdpa_vring_ioctl(v, cmd, argp); + break; + } + + mutex_unlock(&d->mutex); + return r; +} + +static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last) +{ + struct vhost_dev *dev = &v->vdev; + struct vhost_iotlb *iotlb = dev->iotlb; + struct vhost_iotlb_map *map; + struct page *page; + unsigned long pfn, pinned; + + while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) { + pinned = map->size >> PAGE_SHIFT; + for (pfn = map->addr >> PAGE_SHIFT; + pinned > 0; pfn++, pinned--) { + page = pfn_to_page(pfn); + if (map->perm & VHOST_ACCESS_WO) + set_page_dirty_lock(page); + unpin_user_page(page); + } + atomic64_sub(map->size >> PAGE_SHIFT, &dev->mm->pinned_vm); + vhost_iotlb_map_free(iotlb, map); + } +} + +static void vhost_vdpa_iotlb_free(struct vhost_vdpa *v) +{ + struct vhost_dev *dev = &v->vdev; + + vhost_vdpa_iotlb_unmap(v, 0ULL, 0ULL - 1); + kfree(dev->iotlb); + dev->iotlb = NULL; +} + +static int perm_to_iommu_flags(u32 perm) +{ + int flags = 0; + + switch (perm) { + case VHOST_ACCESS_WO: + flags |= IOMMU_WRITE; + break; + case VHOST_ACCESS_RO: + flags |= IOMMU_READ; + break; + case VHOST_ACCESS_RW: + flags |= (IOMMU_WRITE | IOMMU_READ); + break; + default: + WARN(1, "invalidate vhost IOTLB permission\n"); + break; + } + + return flags | IOMMU_CACHE; +} + +static int vhost_vdpa_map(struct vhost_vdpa *v, + u64 iova, u64 size, u64 pa, u32 perm) +{ + struct vhost_dev *dev = &v->vdev; + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + int r = 0; + + r = vhost_iotlb_add_range(dev->iotlb, iova, iova + size - 1, + pa, perm); + if (r) + return r; + + if (ops->dma_map) + r = ops->dma_map(vdpa, iova, size, pa, perm); + else if (ops->set_map) + r = ops->set_map(vdpa, dev->iotlb); + else + r = iommu_map(v->domain, iova, pa, size, + perm_to_iommu_flags(perm)); + + return r; +} + +static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size) +{ + struct vhost_dev *dev = &v->vdev; + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + vhost_vdpa_iotlb_unmap(v, iova, iova + size - 1); + + if (ops->dma_map) + ops->dma_unmap(vdpa, iova, size); + else if (ops->set_map) + ops->set_map(vdpa, dev->iotlb); + else + iommu_unmap(v->domain, iova, size); +} + +static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, + struct vhost_iotlb_msg *msg) +{ + struct vhost_dev *dev = &v->vdev; + struct vhost_iotlb *iotlb = dev->iotlb; + struct page **page_list; + unsigned long list_size = PAGE_SIZE / sizeof(struct page *); + unsigned int gup_flags = FOLL_LONGTERM; + unsigned long npages, cur_base, map_pfn, last_pfn = 0; + unsigned long locked, lock_limit, pinned, i; + u64 iova = msg->iova; + int ret = 0; + + if (vhost_iotlb_itree_first(iotlb, msg->iova, + msg->iova + msg->size - 1)) + return -EEXIST; + + page_list = (struct page **) __get_free_page(GFP_KERNEL); + if (!page_list) + return -ENOMEM; + + if (msg->perm & VHOST_ACCESS_WO) + gup_flags |= FOLL_WRITE; + + npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT; + if (!npages) + return -EINVAL; + + down_read(&dev->mm->mmap_sem); + + locked = atomic64_add_return(npages, &dev->mm->pinned_vm); + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + if (locked > lock_limit) { + ret = -ENOMEM; + goto out; + } + + cur_base = msg->uaddr & PAGE_MASK; + iova &= PAGE_MASK; + + while (npages) { + pinned = min_t(unsigned long, npages, list_size); + ret = pin_user_pages(cur_base, pinned, + gup_flags, page_list, NULL); + if (ret != pinned) + goto out; + + if (!last_pfn) + map_pfn = page_to_pfn(page_list[0]); + + for (i = 0; i < ret; i++) { + unsigned long this_pfn = page_to_pfn(page_list[i]); + u64 csize; + + if (last_pfn && (this_pfn != last_pfn + 1)) { + /* Pin a contiguous chunk of memory */ + csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT; + if (vhost_vdpa_map(v, iova, csize, + map_pfn << PAGE_SHIFT, + msg->perm)) + goto out; + map_pfn = this_pfn; + iova += csize; + } + + last_pfn = this_pfn; + } + + cur_base += ret << PAGE_SHIFT; + npages -= ret; + } + + /* Pin the rest chunk */ + ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT, + map_pfn << PAGE_SHIFT, msg->perm); +out: + if (ret) { + vhost_vdpa_unmap(v, msg->iova, msg->size); + atomic64_sub(npages, &dev->mm->pinned_vm); + } + up_read(&dev->mm->mmap_sem); + free_page((unsigned long)page_list); + return ret; +} + +static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, + struct vhost_iotlb_msg *msg) +{ + struct vhost_vdpa *v = container_of(dev, struct vhost_vdpa, vdev); + int r = 0; + + r = vhost_dev_check_owner(dev); + if (r) + return r; + + switch (msg->type) { + case VHOST_IOTLB_UPDATE: + r = vhost_vdpa_process_iotlb_update(v, msg); + break; + case VHOST_IOTLB_INVALIDATE: + vhost_vdpa_unmap(v, msg->iova, msg->size); + break; + default: + r = -EINVAL; + break; + } + + return r; +} + +static ssize_t vhost_vdpa_chr_write_iter(struct kiocb *iocb, + struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct vhost_vdpa *v = file->private_data; + struct vhost_dev *dev = &v->vdev; + + return vhost_chr_write_iter(dev, from); +} + +static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + struct device *dma_dev = vdpa_get_dma_dev(vdpa); + struct bus_type *bus; + int ret; + + /* Device want to do DMA by itself */ + if (ops->set_map || ops->dma_map) + return 0; + + bus = dma_dev->bus; + if (!bus) + return -EFAULT; + + if (!iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY)) + return -ENOTSUPP; + + v->domain = iommu_domain_alloc(bus); + if (!v->domain) + return -EIO; + + ret = iommu_attach_device(v->domain, dma_dev); + if (ret) + goto err_attach; + + return 0; + +err_attach: + iommu_domain_free(v->domain); + return ret; +} + +static void vhost_vdpa_free_domain(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + struct device *dma_dev = vdpa_get_dma_dev(vdpa); + + if (v->domain) { + iommu_detach_device(v->domain, dma_dev); + iommu_domain_free(v->domain); + } + + v->domain = NULL; +} + +static int vhost_vdpa_open(struct inode *inode, struct file *filep) +{ + struct vhost_vdpa *v; + struct vhost_dev *dev; + struct vhost_virtqueue **vqs; + int nvqs, i, r, opened; + + v = container_of(inode->i_cdev, struct vhost_vdpa, cdev); + if (!v) + return -ENODEV; + + opened = atomic_cmpxchg(&v->opened, 0, 1); + if (opened) + return -EBUSY; + + nvqs = v->nvqs; + vhost_vdpa_reset(v); + + vqs = kmalloc_array(nvqs, sizeof(*vqs), GFP_KERNEL); + if (!vqs) { + r = -ENOMEM; + goto err; + } + + dev = &v->vdev; + for (i = 0; i < nvqs; i++) { + vqs[i] = &v->vqs[i]; + vqs[i]->handle_kick = handle_vq_kick; + } + vhost_dev_init(dev, vqs, nvqs, 0, 0, 0, + vhost_vdpa_process_iotlb_msg); + + dev->iotlb = vhost_iotlb_alloc(0, 0); + if (!dev->iotlb) { + r = -ENOMEM; + goto err_init_iotlb; + } + + r = vhost_vdpa_alloc_domain(v); + if (r) + goto err_init_iotlb; + + filep->private_data = v; + + return 0; + +err_init_iotlb: + vhost_dev_cleanup(&v->vdev); +err: + atomic_dec(&v->opened); + return r; +} + +static int vhost_vdpa_release(struct inode *inode, struct file *filep) +{ + struct vhost_vdpa *v = filep->private_data; + struct vhost_dev *d = &v->vdev; + + mutex_lock(&d->mutex); + filep->private_data = NULL; + vhost_vdpa_reset(v); + vhost_dev_stop(&v->vdev); + vhost_vdpa_iotlb_free(v); + vhost_vdpa_free_domain(v); + vhost_dev_cleanup(&v->vdev); + kfree(v->vdev.vqs); + mutex_unlock(&d->mutex); + + atomic_dec(&v->opened); + complete(&v->completion); + + return 0; +} + +static const struct file_operations vhost_vdpa_fops = { + .owner = THIS_MODULE, + .open = vhost_vdpa_open, + .release = vhost_vdpa_release, + .write_iter = vhost_vdpa_chr_write_iter, + .unlocked_ioctl = vhost_vdpa_unlocked_ioctl, + .compat_ioctl = compat_ptr_ioctl, +}; + +static void vhost_vdpa_release_dev(struct device *device) +{ + struct vhost_vdpa *v = + container_of(device, struct vhost_vdpa, dev); + + ida_simple_remove(&vhost_vdpa_ida, v->minor); + kfree(v->vqs); + kfree(v); +} + +static int vhost_vdpa_probe(struct vdpa_device *vdpa) +{ + const struct vdpa_config_ops *ops = vdpa->config; + struct vhost_vdpa *v; + int minor, nvqs = VHOST_VDPA_VQ_MAX; + int r; + + /* Currently, we only accept the network devices. */ + if (ops->get_device_id(vdpa) != VIRTIO_ID_NET) + return -ENOTSUPP; + + v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL); + if (!v) + return -ENOMEM; + + minor = ida_simple_get(&vhost_vdpa_ida, 0, + VHOST_VDPA_DEV_MAX, GFP_KERNEL); + if (minor < 0) { + kfree(v); + return minor; + } + + atomic_set(&v->opened, 0); + v->minor = minor; + v->vdpa = vdpa; + v->nvqs = nvqs; + v->virtio_id = ops->get_device_id(vdpa); + + device_initialize(&v->dev); + v->dev.release = vhost_vdpa_release_dev; + v->dev.parent = &vdpa->dev; + v->dev.devt = MKDEV(MAJOR(vhost_vdpa_major), minor); + v->vqs = kmalloc_array(nvqs, sizeof(struct vhost_virtqueue), + GFP_KERNEL); + if (!v->vqs) { + r = -ENOMEM; + goto err; + } + + r = dev_set_name(&v->dev, "vhost-vdpa-%u", minor); + if (r) + goto err; + + cdev_init(&v->cdev, &vhost_vdpa_fops); + v->cdev.owner = THIS_MODULE; + + r = cdev_device_add(&v->cdev, &v->dev); + if (r) + goto err; + + init_completion(&v->completion); + vdpa_set_drvdata(vdpa, v); + + return 0; + +err: + put_device(&v->dev); + return r; +} + +static void vhost_vdpa_remove(struct vdpa_device *vdpa) +{ + struct vhost_vdpa *v = vdpa_get_drvdata(vdpa); + int opened; + + cdev_device_del(&v->cdev, &v->dev); + + do { + opened = atomic_cmpxchg(&v->opened, 0, 1); + if (!opened) + break; + wait_for_completion(&v->completion); + } while (1); + + put_device(&v->dev); +} + +static struct vdpa_driver vhost_vdpa_driver = { + .driver = { + .name = "vhost_vdpa", + }, + .probe = vhost_vdpa_probe, + .remove = vhost_vdpa_remove, +}; + +static int __init vhost_vdpa_init(void) +{ + int r; + + r = alloc_chrdev_region(&vhost_vdpa_major, 0, VHOST_VDPA_DEV_MAX, + "vhost-vdpa"); + if (r) + goto err_alloc_chrdev; + + r = vdpa_register_driver(&vhost_vdpa_driver); + if (r) + goto err_vdpa_register_driver; + + return 0; + +err_vdpa_register_driver: + unregister_chrdev_region(vhost_vdpa_major, VHOST_VDPA_DEV_MAX); +err_alloc_chrdev: + return r; +} +module_init(vhost_vdpa_init); + +static void __exit vhost_vdpa_exit(void) +{ + vdpa_unregister_driver(&vhost_vdpa_driver); + unregister_chrdev_region(vhost_vdpa_major, VHOST_VDPA_DEV_MAX); +} +module_exit(vhost_vdpa_exit); + +MODULE_VERSION("0.0.1"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Intel Corporation"); +MODULE_DESCRIPTION("vDPA-based vhost backend for virtio"); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index f44340b41494..d450e16c5c25 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -50,10 +50,6 @@ enum { #define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num]) #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num]) -INTERVAL_TREE_DEFINE(struct vhost_umem_node, - rb, __u64, __subtree_last, - START, LAST, static inline, vhost_umem_interval_tree); - #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY static void vhost_disable_cross_endian(struct vhost_virtqueue *vq) { @@ -457,7 +453,9 @@ static size_t vhost_get_desc_size(struct vhost_virtqueue *vq, void vhost_dev_init(struct vhost_dev *dev, struct vhost_virtqueue **vqs, int nvqs, - int iov_limit, int weight, int byte_weight) + int iov_limit, int weight, int byte_weight, + int (*msg_handler)(struct vhost_dev *dev, + struct vhost_iotlb_msg *msg)) { struct vhost_virtqueue *vq; int i; @@ -473,6 +471,7 @@ void vhost_dev_init(struct vhost_dev *dev, dev->iov_limit = iov_limit; dev->weight = weight; dev->byte_weight = byte_weight; + dev->msg_handler = msg_handler; init_llist_head(&dev->work_list); init_waitqueue_head(&dev->wait); INIT_LIST_HEAD(&dev->read_list); @@ -581,21 +580,25 @@ err_mm: } EXPORT_SYMBOL_GPL(vhost_dev_set_owner); -struct vhost_umem *vhost_dev_reset_owner_prepare(void) +static struct vhost_iotlb *iotlb_alloc(void) +{ + return vhost_iotlb_alloc(max_iotlb_entries, + VHOST_IOTLB_FLAG_RETIRE); +} + +struct vhost_iotlb *vhost_dev_reset_owner_prepare(void) { - return kvzalloc(sizeof(struct vhost_umem), GFP_KERNEL); + return iotlb_alloc(); } EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare); /* Caller should have device mutex */ -void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_umem *umem) +void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_iotlb *umem) { int i; vhost_dev_cleanup(dev); - /* Restore memory to default empty mapping. */ - INIT_LIST_HEAD(&umem->umem_list); dev->umem = umem; /* We don't need VQ locks below since vhost_dev_cleanup makes sure * VQs aren't running. @@ -618,28 +621,6 @@ void vhost_dev_stop(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_dev_stop); -static void vhost_umem_free(struct vhost_umem *umem, - struct vhost_umem_node *node) -{ - vhost_umem_interval_tree_remove(node, &umem->umem_tree); - list_del(&node->link); - kfree(node); - umem->numem--; -} - -static void vhost_umem_clean(struct vhost_umem *umem) -{ - struct vhost_umem_node *node, *tmp; - - if (!umem) - return; - - list_for_each_entry_safe(node, tmp, &umem->umem_list, link) - vhost_umem_free(umem, node); - - kvfree(umem); -} - static void vhost_clear_msg(struct vhost_dev *dev) { struct vhost_msg_node *node, *n; @@ -677,9 +658,9 @@ void vhost_dev_cleanup(struct vhost_dev *dev) eventfd_ctx_put(dev->log_ctx); dev->log_ctx = NULL; /* No one will access memory at this point */ - vhost_umem_clean(dev->umem); + vhost_iotlb_free(dev->umem); dev->umem = NULL; - vhost_umem_clean(dev->iotlb); + vhost_iotlb_free(dev->iotlb); dev->iotlb = NULL; vhost_clear_msg(dev); wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM); @@ -715,27 +696,26 @@ static bool vhost_overflow(u64 uaddr, u64 size) } /* Caller should have vq mutex and device mutex. */ -static bool vq_memory_access_ok(void __user *log_base, struct vhost_umem *umem, +static bool vq_memory_access_ok(void __user *log_base, struct vhost_iotlb *umem, int log_all) { - struct vhost_umem_node *node; + struct vhost_iotlb_map *map; if (!umem) return false; - list_for_each_entry(node, &umem->umem_list, link) { - unsigned long a = node->userspace_addr; + list_for_each_entry(map, &umem->list, link) { + unsigned long a = map->addr; - if (vhost_overflow(node->userspace_addr, node->size)) + if (vhost_overflow(map->addr, map->size)) return false; - if (!access_ok((void __user *)a, - node->size)) + if (!access_ok((void __user *)a, map->size)) return false; else if (log_all && !log_access_ok(log_base, - node->start, - node->size)) + map->start, + map->size)) return false; } return true; @@ -745,17 +725,17 @@ static inline void __user *vhost_vq_meta_fetch(struct vhost_virtqueue *vq, u64 addr, unsigned int size, int type) { - const struct vhost_umem_node *node = vq->meta_iotlb[type]; + const struct vhost_iotlb_map *map = vq->meta_iotlb[type]; - if (!node) + if (!map) return NULL; - return (void *)(uintptr_t)(node->userspace_addr + addr - node->start); + return (void *)(uintptr_t)(map->addr + addr - map->start); } /* Can we switch to this memory table? */ /* Caller should have device mutex but not vq mutex */ -static bool memory_access_ok(struct vhost_dev *d, struct vhost_umem *umem, +static bool memory_access_ok(struct vhost_dev *d, struct vhost_iotlb *umem, int log_all) { int i; @@ -1020,47 +1000,6 @@ static inline int vhost_get_desc(struct vhost_virtqueue *vq, return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc)); } -static int vhost_new_umem_range(struct vhost_umem *umem, - u64 start, u64 size, u64 end, - u64 userspace_addr, int perm) -{ - struct vhost_umem_node *tmp, *node; - - if (!size) - return -EFAULT; - - node = kmalloc(sizeof(*node), GFP_ATOMIC); - if (!node) - return -ENOMEM; - - if (umem->numem == max_iotlb_entries) { - tmp = list_first_entry(&umem->umem_list, typeof(*tmp), link); - vhost_umem_free(umem, tmp); - } - - node->start = start; - node->size = size; - node->last = end; - node->userspace_addr = userspace_addr; - node->perm = perm; - INIT_LIST_HEAD(&node->link); - list_add_tail(&node->link, &umem->umem_list); - vhost_umem_interval_tree_insert(node, &umem->umem_tree); - umem->numem++; - - return 0; -} - -static void vhost_del_umem_range(struct vhost_umem *umem, - u64 start, u64 end) -{ - struct vhost_umem_node *node; - - while ((node = vhost_umem_interval_tree_iter_first(&umem->umem_tree, - start, end))) - vhost_umem_free(umem, node); -} - static void vhost_iotlb_notify_vq(struct vhost_dev *d, struct vhost_iotlb_msg *msg) { @@ -1117,9 +1056,9 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, break; } vhost_vq_meta_reset(dev); - if (vhost_new_umem_range(dev->iotlb, msg->iova, msg->size, - msg->iova + msg->size - 1, - msg->uaddr, msg->perm)) { + if (vhost_iotlb_add_range(dev->iotlb, msg->iova, + msg->iova + msg->size - 1, + msg->uaddr, msg->perm)) { ret = -ENOMEM; break; } @@ -1131,8 +1070,8 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, break; } vhost_vq_meta_reset(dev); - vhost_del_umem_range(dev->iotlb, msg->iova, - msg->iova + msg->size - 1); + vhost_iotlb_del_range(dev->iotlb, msg->iova, + msg->iova + msg->size - 1); break; default: ret = -EINVAL; @@ -1178,7 +1117,12 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, ret = -EINVAL; goto done; } - if (vhost_process_iotlb_msg(dev, &msg)) { + + if (dev->msg_handler) + ret = dev->msg_handler(dev, &msg); + else + ret = vhost_process_iotlb_msg(dev, &msg); + if (ret) { ret = -EFAULT; goto done; } @@ -1311,44 +1255,42 @@ static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, } static void vhost_vq_meta_update(struct vhost_virtqueue *vq, - const struct vhost_umem_node *node, + const struct vhost_iotlb_map *map, int type) { int access = (type == VHOST_ADDR_USED) ? VHOST_ACCESS_WO : VHOST_ACCESS_RO; - if (likely(node->perm & access)) - vq->meta_iotlb[type] = node; + if (likely(map->perm & access)) + vq->meta_iotlb[type] = map; } static bool iotlb_access_ok(struct vhost_virtqueue *vq, int access, u64 addr, u64 len, int type) { - const struct vhost_umem_node *node; - struct vhost_umem *umem = vq->iotlb; + const struct vhost_iotlb_map *map; + struct vhost_iotlb *umem = vq->iotlb; u64 s = 0, size, orig_addr = addr, last = addr + len - 1; if (vhost_vq_meta_fetch(vq, addr, len, type)) return true; while (len > s) { - node = vhost_umem_interval_tree_iter_first(&umem->umem_tree, - addr, - last); - if (node == NULL || node->start > addr) { + map = vhost_iotlb_itree_first(umem, addr, last); + if (map == NULL || map->start > addr) { vhost_iotlb_miss(vq, addr, access); return false; - } else if (!(node->perm & access)) { + } else if (!(map->perm & access)) { /* Report the possible access violation by * request another translation from userspace. */ return false; } - size = node->size - addr + node->start; + size = map->size - addr + map->start; if (orig_addr == addr && size >= len) - vhost_vq_meta_update(vq, node, type); + vhost_vq_meta_update(vq, map, type); s += size; addr += size; @@ -1364,12 +1306,12 @@ int vq_meta_prefetch(struct vhost_virtqueue *vq) if (!vq->iotlb) return 1; - return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc, + return iotlb_access_ok(vq, VHOST_MAP_RO, (u64)(uintptr_t)vq->desc, vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) && - iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail, + iotlb_access_ok(vq, VHOST_MAP_RO, (u64)(uintptr_t)vq->avail, vhost_get_avail_size(vq, num), VHOST_ADDR_AVAIL) && - iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used, + iotlb_access_ok(vq, VHOST_MAP_WO, (u64)(uintptr_t)vq->used, vhost_get_used_size(vq, num), VHOST_ADDR_USED); } EXPORT_SYMBOL_GPL(vq_meta_prefetch); @@ -1408,25 +1350,11 @@ bool vhost_vq_access_ok(struct vhost_virtqueue *vq) } EXPORT_SYMBOL_GPL(vhost_vq_access_ok); -static struct vhost_umem *vhost_umem_alloc(void) -{ - struct vhost_umem *umem = kvzalloc(sizeof(*umem), GFP_KERNEL); - - if (!umem) - return NULL; - - umem->umem_tree = RB_ROOT_CACHED; - umem->numem = 0; - INIT_LIST_HEAD(&umem->umem_list); - - return umem; -} - static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) { struct vhost_memory mem, *newmem; struct vhost_memory_region *region; - struct vhost_umem *newumem, *oldumem; + struct vhost_iotlb *newumem, *oldumem; unsigned long size = offsetof(struct vhost_memory, regions); int i; @@ -1448,7 +1376,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) return -EFAULT; } - newumem = vhost_umem_alloc(); + newumem = iotlb_alloc(); if (!newumem) { kvfree(newmem); return -ENOMEM; @@ -1457,13 +1385,12 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) for (region = newmem->regions; region < newmem->regions + mem.nregions; region++) { - if (vhost_new_umem_range(newumem, - region->guest_phys_addr, - region->memory_size, - region->guest_phys_addr + - region->memory_size - 1, - region->userspace_addr, - VHOST_ACCESS_RW)) + if (vhost_iotlb_add_range(newumem, + region->guest_phys_addr, + region->guest_phys_addr + + region->memory_size - 1, + region->userspace_addr, + VHOST_MAP_RW)) goto err; } @@ -1481,11 +1408,11 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) } kvfree(newmem); - vhost_umem_clean(oldumem); + vhost_iotlb_free(oldumem); return 0; err: - vhost_umem_clean(newumem); + vhost_iotlb_free(newumem); kvfree(newmem); return -EFAULT; } @@ -1726,10 +1653,10 @@ EXPORT_SYMBOL_GPL(vhost_vring_ioctl); int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled) { - struct vhost_umem *niotlb, *oiotlb; + struct vhost_iotlb *niotlb, *oiotlb; int i; - niotlb = vhost_umem_alloc(); + niotlb = iotlb_alloc(); if (!niotlb) return -ENOMEM; @@ -1745,7 +1672,7 @@ int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled) mutex_unlock(&vq->mutex); } - vhost_umem_clean(oiotlb); + vhost_iotlb_free(oiotlb); return 0; } @@ -1875,8 +1802,8 @@ static int log_write(void __user *log_base, static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len) { - struct vhost_umem *umem = vq->umem; - struct vhost_umem_node *u; + struct vhost_iotlb *umem = vq->umem; + struct vhost_iotlb_map *u; u64 start, end, l, min; int r; bool hit = false; @@ -1886,16 +1813,15 @@ static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len) /* More than one GPAs can be mapped into a single HVA. So * iterate all possible umems here to be safe. */ - list_for_each_entry(u, &umem->umem_list, link) { - if (u->userspace_addr > hva - 1 + len || - u->userspace_addr - 1 + u->size < hva) + list_for_each_entry(u, &umem->list, link) { + if (u->addr > hva - 1 + len || + u->addr - 1 + u->size < hva) continue; - start = max(u->userspace_addr, hva); - end = min(u->userspace_addr - 1 + u->size, - hva - 1 + len); + start = max(u->addr, hva); + end = min(u->addr - 1 + u->size, hva - 1 + len); l = end - start + 1; r = log_write(vq->log_base, - u->start + start - u->userspace_addr, + u->start + start - u->addr, l); if (r < 0) return r; @@ -2046,9 +1972,9 @@ EXPORT_SYMBOL_GPL(vhost_vq_init_access); static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, struct iovec iov[], int iov_size, int access) { - const struct vhost_umem_node *node; + const struct vhost_iotlb_map *map; struct vhost_dev *dev = vq->dev; - struct vhost_umem *umem = dev->iotlb ? dev->iotlb : dev->umem; + struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem; struct iovec *_iov; u64 s = 0; int ret = 0; @@ -2060,25 +1986,24 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, break; } - node = vhost_umem_interval_tree_iter_first(&umem->umem_tree, - addr, addr + len - 1); - if (node == NULL || node->start > addr) { + map = vhost_iotlb_itree_first(umem, addr, addr + len - 1); + if (map == NULL || map->start > addr) { if (umem != dev->iotlb) { ret = -EFAULT; break; } ret = -EAGAIN; break; - } else if (!(node->perm & access)) { + } else if (!(map->perm & access)) { ret = -EPERM; break; } _iov = iov + ret; - size = node->size - addr + node->start; + size = map->size - addr + map->start; _iov->iov_len = min((u64)len - s, size); _iov->iov_base = (void __user *)(unsigned long) - (node->userspace_addr + addr - node->start); + (map->addr + addr - map->start); s += size; addr += size; ++ret; diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index a123fd70847e..181382185bbc 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -12,6 +12,7 @@ #include <linux/virtio_config.h> #include <linux/virtio_ring.h> #include <linux/atomic.h> +#include <linux/vhost_iotlb.h> struct vhost_work; typedef void (*vhost_work_fn_t)(struct vhost_work *work); @@ -52,27 +53,6 @@ struct vhost_log { u64 len; }; -#define START(node) ((node)->start) -#define LAST(node) ((node)->last) - -struct vhost_umem_node { - struct rb_node rb; - struct list_head link; - __u64 start; - __u64 last; - __u64 size; - __u64 userspace_addr; - __u32 perm; - __u32 flags_padding; - __u64 __subtree_last; -}; - -struct vhost_umem { - struct rb_root_cached umem_tree; - struct list_head umem_list; - int numem; -}; - enum vhost_uaddr_type { VHOST_ADDR_DESC = 0, VHOST_ADDR_AVAIL = 1, @@ -90,7 +70,7 @@ struct vhost_virtqueue { struct vring_desc __user *desc; struct vring_avail __user *avail; struct vring_used __user *used; - const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS]; + const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS]; struct file *kick; struct eventfd_ctx *call_ctx; struct eventfd_ctx *error_ctx; @@ -128,8 +108,8 @@ struct vhost_virtqueue { struct iovec *indirect; struct vring_used_elem *heads; /* Protected by virtqueue mutex. */ - struct vhost_umem *umem; - struct vhost_umem *iotlb; + struct vhost_iotlb *umem; + struct vhost_iotlb *iotlb; void *private_data; u64 acked_features; u64 acked_backend_features; @@ -164,8 +144,8 @@ struct vhost_dev { struct eventfd_ctx *log_ctx; struct llist_head work_list; struct task_struct *worker; - struct vhost_umem *umem; - struct vhost_umem *iotlb; + struct vhost_iotlb *umem; + struct vhost_iotlb *iotlb; spinlock_t iotlb_lock; struct list_head read_list; struct list_head pending_list; @@ -174,16 +154,20 @@ struct vhost_dev { int weight; int byte_weight; u64 kcov_handle; + int (*msg_handler)(struct vhost_dev *dev, + struct vhost_iotlb_msg *msg); }; bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len); void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, - int nvqs, int iov_limit, int weight, int byte_weight); + int nvqs, int iov_limit, int weight, int byte_weight, + int (*msg_handler)(struct vhost_dev *dev, + struct vhost_iotlb_msg *msg)); long vhost_dev_set_owner(struct vhost_dev *dev); bool vhost_dev_has_owner(struct vhost_dev *dev); long vhost_dev_check_owner(struct vhost_dev *); -struct vhost_umem *vhost_dev_reset_owner_prepare(void); -void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_umem *); +struct vhost_iotlb *vhost_dev_reset_owner_prepare(void); +void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_iotlb *iotlb); void vhost_dev_cleanup(struct vhost_dev *); void vhost_dev_stop(struct vhost_dev *); long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp); @@ -229,6 +213,9 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, struct iov_iter *from); int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled); +void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, + struct vhost_iotlb_map *map); + #define vq_err(vq, fmt, ...) do { \ pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \ if ((vq)->error_ctx) \ diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index a0a2d74967ef..ee0491f579ac 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -13,6 +13,9 @@ #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/bvec.h> +#include <linux/highmem.h> +#include <linux/vhost_iotlb.h> #include <uapi/linux/virtio_config.h> static __printf(1,2) __cold void vringh_bad(const char *fmt, ...) @@ -71,9 +74,11 @@ static inline int __vringh_get_head(const struct vringh *vrh, } /* Copy some bytes to/from the iovec. Returns num copied. */ -static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov, +static inline ssize_t vringh_iov_xfer(struct vringh *vrh, + struct vringh_kiov *iov, void *ptr, size_t len, - int (*xfer)(void *addr, void *ptr, + int (*xfer)(const struct vringh *vrh, + void *addr, void *ptr, size_t len)) { int err, done = 0; @@ -82,7 +87,7 @@ static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov, size_t partlen; partlen = min(iov->iov[iov->i].iov_len, len); - err = xfer(iov->iov[iov->i].iov_base, ptr, partlen); + err = xfer(vrh, iov->iov[iov->i].iov_base, ptr, partlen); if (err) return err; done += partlen; @@ -96,6 +101,7 @@ static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov, /* Fix up old iov element then increment. */ iov->iov[iov->i].iov_len = iov->consumed; iov->iov[iov->i].iov_base -= iov->consumed; + iov->consumed = 0; iov->i++; @@ -227,7 +233,8 @@ static int slow_copy(struct vringh *vrh, void *dst, const void *src, u64 addr, struct vringh_range *r), struct vringh_range *range, - int (*copy)(void *dst, const void *src, size_t len)) + int (*copy)(const struct vringh *vrh, + void *dst, const void *src, size_t len)) { size_t part, len = sizeof(struct vring_desc); @@ -241,7 +248,7 @@ static int slow_copy(struct vringh *vrh, void *dst, const void *src, if (!rcheck(vrh, addr, &part, range, getrange)) return -EINVAL; - err = copy(dst, src, part); + err = copy(vrh, dst, src, part); if (err) return err; @@ -262,7 +269,8 @@ __vringh_iov(struct vringh *vrh, u16 i, struct vringh_range *)), bool (*getrange)(struct vringh *, u64, struct vringh_range *), gfp_t gfp, - int (*copy)(void *dst, const void *src, size_t len)) + int (*copy)(const struct vringh *vrh, + void *dst, const void *src, size_t len)) { int err, count = 0, up_next, desc_max; struct vring_desc desc, *descs; @@ -291,7 +299,7 @@ __vringh_iov(struct vringh *vrh, u16 i, err = slow_copy(vrh, &desc, &descs[i], rcheck, getrange, &slowrange, copy); else - err = copy(&desc, &descs[i], sizeof(desc)); + err = copy(vrh, &desc, &descs[i], sizeof(desc)); if (unlikely(err)) goto fail; @@ -404,7 +412,8 @@ static inline int __vringh_complete(struct vringh *vrh, unsigned int num_used, int (*putu16)(const struct vringh *vrh, __virtio16 *p, u16 val), - int (*putused)(struct vring_used_elem *dst, + int (*putused)(const struct vringh *vrh, + struct vring_used_elem *dst, const struct vring_used_elem *src, unsigned num)) { @@ -420,12 +429,12 @@ static inline int __vringh_complete(struct vringh *vrh, /* Compiler knows num_used == 1 sometimes, hence extra check */ if (num_used > 1 && unlikely(off + num_used >= vrh->vring.num)) { u16 part = vrh->vring.num - off; - err = putused(&used_ring->ring[off], used, part); + err = putused(vrh, &used_ring->ring[off], used, part); if (!err) - err = putused(&used_ring->ring[0], used + part, + err = putused(vrh, &used_ring->ring[0], used + part, num_used - part); } else - err = putused(&used_ring->ring[off], used, num_used); + err = putused(vrh, &used_ring->ring[off], used, num_used); if (err) { vringh_bad("Failed to write %u used entries %u at %p", @@ -564,13 +573,15 @@ static inline int putu16_user(const struct vringh *vrh, __virtio16 *p, u16 val) return put_user(v, (__force __virtio16 __user *)p); } -static inline int copydesc_user(void *dst, const void *src, size_t len) +static inline int copydesc_user(const struct vringh *vrh, + void *dst, const void *src, size_t len) { return copy_from_user(dst, (__force void __user *)src, len) ? -EFAULT : 0; } -static inline int putused_user(struct vring_used_elem *dst, +static inline int putused_user(const struct vringh *vrh, + struct vring_used_elem *dst, const struct vring_used_elem *src, unsigned int num) { @@ -578,13 +589,15 @@ static inline int putused_user(struct vring_used_elem *dst, sizeof(*dst) * num) ? -EFAULT : 0; } -static inline int xfer_from_user(void *src, void *dst, size_t len) +static inline int xfer_from_user(const struct vringh *vrh, void *src, + void *dst, size_t len) { return copy_from_user(dst, (__force void __user *)src, len) ? -EFAULT : 0; } -static inline int xfer_to_user(void *dst, void *src, size_t len) +static inline int xfer_to_user(const struct vringh *vrh, + void *dst, void *src, size_t len) { return copy_to_user((__force void __user *)dst, src, len) ? -EFAULT : 0; @@ -706,7 +719,7 @@ EXPORT_SYMBOL(vringh_getdesc_user); */ ssize_t vringh_iov_pull_user(struct vringh_iov *riov, void *dst, size_t len) { - return vringh_iov_xfer((struct vringh_kiov *)riov, + return vringh_iov_xfer(NULL, (struct vringh_kiov *)riov, dst, len, xfer_from_user); } EXPORT_SYMBOL(vringh_iov_pull_user); @@ -722,7 +735,7 @@ EXPORT_SYMBOL(vringh_iov_pull_user); ssize_t vringh_iov_push_user(struct vringh_iov *wiov, const void *src, size_t len) { - return vringh_iov_xfer((struct vringh_kiov *)wiov, + return vringh_iov_xfer(NULL, (struct vringh_kiov *)wiov, (void *)src, len, xfer_to_user); } EXPORT_SYMBOL(vringh_iov_push_user); @@ -832,13 +845,15 @@ static inline int putu16_kern(const struct vringh *vrh, __virtio16 *p, u16 val) return 0; } -static inline int copydesc_kern(void *dst, const void *src, size_t len) +static inline int copydesc_kern(const struct vringh *vrh, + void *dst, const void *src, size_t len) { memcpy(dst, src, len); return 0; } -static inline int putused_kern(struct vring_used_elem *dst, +static inline int putused_kern(const struct vringh *vrh, + struct vring_used_elem *dst, const struct vring_used_elem *src, unsigned int num) { @@ -846,13 +861,15 @@ static inline int putused_kern(struct vring_used_elem *dst, return 0; } -static inline int xfer_kern(void *src, void *dst, size_t len) +static inline int xfer_kern(const struct vringh *vrh, void *src, + void *dst, size_t len) { memcpy(dst, src, len); return 0; } -static inline int kern_xfer(void *dst, void *src, size_t len) +static inline int kern_xfer(const struct vringh *vrh, void *dst, + void *src, size_t len) { memcpy(dst, src, len); return 0; @@ -949,7 +966,7 @@ EXPORT_SYMBOL(vringh_getdesc_kern); */ ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len) { - return vringh_iov_xfer(riov, dst, len, xfer_kern); + return vringh_iov_xfer(NULL, riov, dst, len, xfer_kern); } EXPORT_SYMBOL(vringh_iov_pull_kern); @@ -964,7 +981,7 @@ EXPORT_SYMBOL(vringh_iov_pull_kern); ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov, const void *src, size_t len) { - return vringh_iov_xfer(wiov, (void *)src, len, kern_xfer); + return vringh_iov_xfer(NULL, wiov, (void *)src, len, kern_xfer); } EXPORT_SYMBOL(vringh_iov_push_kern); @@ -1042,4 +1059,362 @@ int vringh_need_notify_kern(struct vringh *vrh) } EXPORT_SYMBOL(vringh_need_notify_kern); +static int iotlb_translate(const struct vringh *vrh, + u64 addr, u64 len, struct bio_vec iov[], + int iov_size, u32 perm) +{ + struct vhost_iotlb_map *map; + struct vhost_iotlb *iotlb = vrh->iotlb; + int ret = 0; + u64 s = 0; + + while (len > s) { + u64 size, pa, pfn; + + if (unlikely(ret >= iov_size)) { + ret = -ENOBUFS; + break; + } + + map = vhost_iotlb_itree_first(iotlb, addr, + addr + len - 1); + if (!map || map->start > addr) { + ret = -EINVAL; + break; + } else if (!(map->perm & perm)) { + ret = -EPERM; + break; + } + + size = map->size - addr + map->start; + pa = map->addr + addr - map->start; + pfn = pa >> PAGE_SHIFT; + iov[ret].bv_page = pfn_to_page(pfn); + iov[ret].bv_len = min(len - s, size); + iov[ret].bv_offset = pa & (PAGE_SIZE - 1); + s += size; + addr += size; + ++ret; + } + + return ret; +} + +static inline int copy_from_iotlb(const struct vringh *vrh, void *dst, + void *src, size_t len) +{ + struct iov_iter iter; + struct bio_vec iov[16]; + int ret; + + ret = iotlb_translate(vrh, (u64)(uintptr_t)src, + len, iov, 16, VHOST_MAP_RO); + if (ret < 0) + return ret; + + iov_iter_bvec(&iter, READ, iov, ret, len); + + ret = copy_from_iter(dst, len, &iter); + + return ret; +} + +static inline int copy_to_iotlb(const struct vringh *vrh, void *dst, + void *src, size_t len) +{ + struct iov_iter iter; + struct bio_vec iov[16]; + int ret; + + ret = iotlb_translate(vrh, (u64)(uintptr_t)dst, + len, iov, 16, VHOST_MAP_WO); + if (ret < 0) + return ret; + + iov_iter_bvec(&iter, WRITE, iov, ret, len); + + return copy_to_iter(src, len, &iter); +} + +static inline int getu16_iotlb(const struct vringh *vrh, + u16 *val, const __virtio16 *p) +{ + struct bio_vec iov; + void *kaddr, *from; + int ret; + + /* Atomic read is needed for getu16 */ + ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), + &iov, 1, VHOST_MAP_RO); + if (ret < 0) + return ret; + + kaddr = kmap_atomic(iov.bv_page); + from = kaddr + iov.bv_offset; + *val = vringh16_to_cpu(vrh, READ_ONCE(*(__virtio16 *)from)); + kunmap_atomic(kaddr); + + return 0; +} + +static inline int putu16_iotlb(const struct vringh *vrh, + __virtio16 *p, u16 val) +{ + struct bio_vec iov; + void *kaddr, *to; + int ret; + + /* Atomic write is needed for putu16 */ + ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), + &iov, 1, VHOST_MAP_WO); + if (ret < 0) + return ret; + + kaddr = kmap_atomic(iov.bv_page); + to = kaddr + iov.bv_offset; + WRITE_ONCE(*(__virtio16 *)to, cpu_to_vringh16(vrh, val)); + kunmap_atomic(kaddr); + + return 0; +} + +static inline int copydesc_iotlb(const struct vringh *vrh, + void *dst, const void *src, size_t len) +{ + int ret; + + ret = copy_from_iotlb(vrh, dst, (void *)src, len); + if (ret != len) + return -EFAULT; + + return 0; +} + +static inline int xfer_from_iotlb(const struct vringh *vrh, void *src, + void *dst, size_t len) +{ + int ret; + + ret = copy_from_iotlb(vrh, dst, src, len); + if (ret != len) + return -EFAULT; + + return 0; +} + +static inline int xfer_to_iotlb(const struct vringh *vrh, + void *dst, void *src, size_t len) +{ + int ret; + + ret = copy_to_iotlb(vrh, dst, src, len); + if (ret != len) + return -EFAULT; + + return 0; +} + +static inline int putused_iotlb(const struct vringh *vrh, + struct vring_used_elem *dst, + const struct vring_used_elem *src, + unsigned int num) +{ + int size = num * sizeof(*dst); + int ret; + + ret = copy_to_iotlb(vrh, dst, (void *)src, num * sizeof(*dst)); + if (ret != size) + return -EFAULT; + + return 0; +} + +/** + * vringh_init_iotlb - initialize a vringh for a ring with IOTLB. + * @vrh: the vringh to initialize. + * @features: the feature bits for this ring. + * @num: the number of elements. + * @weak_barriers: true if we only need memory barriers, not I/O. + * @desc: the userpace descriptor pointer. + * @avail: the userpace avail pointer. + * @used: the userpace used pointer. + * + * Returns an error if num is invalid. + */ +int vringh_init_iotlb(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used) +{ + return vringh_init_kern(vrh, features, num, weak_barriers, + desc, avail, used); +} +EXPORT_SYMBOL(vringh_init_iotlb); + +/** + * vringh_set_iotlb - initialize a vringh for a ring with IOTLB. + * @vrh: the vring + * @iotlb: iotlb associated with this vring + */ +void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb) +{ + vrh->iotlb = iotlb; +} +EXPORT_SYMBOL(vringh_set_iotlb); + +/** + * vringh_getdesc_iotlb - get next available descriptor from ring with + * IOTLB. + * @vrh: the kernelspace vring. + * @riov: where to put the readable descriptors (or NULL) + * @wiov: where to put the writable descriptors (or NULL) + * @head: head index we received, for passing to vringh_complete_iotlb(). + * @gfp: flags for allocating larger riov/wiov. + * + * Returns 0 if there was no descriptor, 1 if there was, or -errno. + * + * Note that on error return, you can tell the difference between an + * invalid ring and a single invalid descriptor: in the former case, + * *head will be vrh->vring.num. You may be able to ignore an invalid + * descriptor, but there's not much you can do with an invalid ring. + * + * Note that you may need to clean up riov and wiov, even on error! + */ +int vringh_getdesc_iotlb(struct vringh *vrh, + struct vringh_kiov *riov, + struct vringh_kiov *wiov, + u16 *head, + gfp_t gfp) +{ + int err; + + err = __vringh_get_head(vrh, getu16_iotlb, &vrh->last_avail_idx); + if (err < 0) + return err; + + /* Empty... */ + if (err == vrh->vring.num) + return 0; + + *head = err; + err = __vringh_iov(vrh, *head, riov, wiov, no_range_check, NULL, + gfp, copydesc_iotlb); + if (err) + return err; + + return 1; +} +EXPORT_SYMBOL(vringh_getdesc_iotlb); + +/** + * vringh_iov_pull_iotlb - copy bytes from vring_iov. + * @vrh: the vring. + * @riov: the riov as passed to vringh_getdesc_iotlb() (updated as we consume) + * @dst: the place to copy. + * @len: the maximum length to copy. + * + * Returns the bytes copied <= len or a negative errno. + */ +ssize_t vringh_iov_pull_iotlb(struct vringh *vrh, + struct vringh_kiov *riov, + void *dst, size_t len) +{ + return vringh_iov_xfer(vrh, riov, dst, len, xfer_from_iotlb); +} +EXPORT_SYMBOL(vringh_iov_pull_iotlb); + +/** + * vringh_iov_push_iotlb - copy bytes into vring_iov. + * @vrh: the vring. + * @wiov: the wiov as passed to vringh_getdesc_iotlb() (updated as we consume) + * @dst: the place to copy. + * @len: the maximum length to copy. + * + * Returns the bytes copied <= len or a negative errno. + */ +ssize_t vringh_iov_push_iotlb(struct vringh *vrh, + struct vringh_kiov *wiov, + const void *src, size_t len) +{ + return vringh_iov_xfer(vrh, wiov, (void *)src, len, xfer_to_iotlb); +} +EXPORT_SYMBOL(vringh_iov_push_iotlb); + +/** + * vringh_abandon_iotlb - we've decided not to handle the descriptor(s). + * @vrh: the vring. + * @num: the number of descriptors to put back (ie. num + * vringh_get_iotlb() to undo). + * + * The next vringh_get_iotlb() will return the old descriptor(s) again. + */ +void vringh_abandon_iotlb(struct vringh *vrh, unsigned int num) +{ + /* We only update vring_avail_event(vr) when we want to be notified, + * so we haven't changed that yet. + */ + vrh->last_avail_idx -= num; +} +EXPORT_SYMBOL(vringh_abandon_iotlb); + +/** + * vringh_complete_iotlb - we've finished with descriptor, publish it. + * @vrh: the vring. + * @head: the head as filled in by vringh_getdesc_iotlb. + * @len: the length of data we have written. + * + * You should check vringh_need_notify_iotlb() after one or more calls + * to this function. + */ +int vringh_complete_iotlb(struct vringh *vrh, u16 head, u32 len) +{ + struct vring_used_elem used; + + used.id = cpu_to_vringh32(vrh, head); + used.len = cpu_to_vringh32(vrh, len); + + return __vringh_complete(vrh, &used, 1, putu16_iotlb, putused_iotlb); +} +EXPORT_SYMBOL(vringh_complete_iotlb); + +/** + * vringh_notify_enable_iotlb - we want to know if something changes. + * @vrh: the vring. + * + * This always enables notifications, but returns false if there are + * now more buffers available in the vring. + */ +bool vringh_notify_enable_iotlb(struct vringh *vrh) +{ + return __vringh_notify_enable(vrh, getu16_iotlb, putu16_iotlb); +} +EXPORT_SYMBOL(vringh_notify_enable_iotlb); + +/** + * vringh_notify_disable_iotlb - don't tell us if something changes. + * @vrh: the vring. + * + * This is our normal running state: we disable and then only enable when + * we're going to sleep. + */ +void vringh_notify_disable_iotlb(struct vringh *vrh) +{ + __vringh_notify_disable(vrh, putu16_iotlb); +} +EXPORT_SYMBOL(vringh_notify_disable_iotlb); + +/** + * vringh_need_notify_iotlb - must we tell the other side about used buffers? + * @vrh: the vring we've called vringh_complete_iotlb() on. + * + * Returns -errno or 0 if we don't need to tell the other side, 1 if we do. + */ +int vringh_need_notify_iotlb(struct vringh *vrh) +{ + return __vringh_need_notify(vrh, getu16_iotlb); +} +EXPORT_SYMBOL(vringh_need_notify_iotlb); + + MODULE_LICENSE("GPL"); diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index c2d7d57e98cf..97669484a3f6 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -621,7 +621,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV, VHOST_VSOCK_PKT_WEIGHT, - VHOST_VSOCK_WEIGHT); + VHOST_VSOCK_WEIGHT, NULL); file->private_data = vsock; spin_lock_init(&vsock->send_pkt_list_lock); diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 4b2dd8259ff5..2bbf94b15bba 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -43,6 +43,19 @@ config VIRTIO_PCI_LEGACY If unsure, say Y. +config VIRTIO_VDPA + tristate "vDPA driver for virtio devices" + select VDPA + select VIRTIO + help + This driver provides support for virtio based paravirtual + device driver over vDPA bus. For this to be useful, you need + an appropriate vDPA device implementation that operates on a + physical device to allow the datapath of virtio to be + offloaded to hardware. + + If unsure, say M. + config VIRTIO_PMEM tristate "Support for virtio pmem driver" depends on VIRTIO diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index 3a2b5c5dcf46..29a1386ecc03 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -6,3 +6,4 @@ virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o +obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c new file mode 100644 index 000000000000..c30eb55030be --- /dev/null +++ b/drivers/virtio/virtio_vdpa.c @@ -0,0 +1,396 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VIRTIO based driver for vDPA device + * + * Copyright (c) 2020, Red Hat. All rights reserved. + * Author: Jason Wang <jasowang@redhat.com> + * + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/uuid.h> +#include <linux/virtio.h> +#include <linux/vdpa.h> +#include <linux/virtio_config.h> +#include <linux/virtio_ring.h> + +#define MOD_VERSION "0.1" +#define MOD_AUTHOR "Jason Wang <jasowang@redhat.com>" +#define MOD_DESC "vDPA bus driver for virtio devices" +#define MOD_LICENSE "GPL v2" + +struct virtio_vdpa_device { + struct virtio_device vdev; + struct vdpa_device *vdpa; + u64 features; + + /* The lock to protect virtqueue list */ + spinlock_t lock; + /* List of virtio_vdpa_vq_info */ + struct list_head virtqueues; +}; + +struct virtio_vdpa_vq_info { + /* the actual virtqueue */ + struct virtqueue *vq; + + /* the list node for the virtqueues list */ + struct list_head node; +}; + +static inline struct virtio_vdpa_device * +to_virtio_vdpa_device(struct virtio_device *dev) +{ + return container_of(dev, struct virtio_vdpa_device, vdev); +} + +static struct vdpa_device *vd_get_vdpa(struct virtio_device *vdev) +{ + return to_virtio_vdpa_device(vdev)->vdpa; +} + +static void virtio_vdpa_get(struct virtio_device *vdev, unsigned offset, + void *buf, unsigned len) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + ops->get_config(vdpa, offset, buf, len); +} + +static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset, + const void *buf, unsigned len) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + ops->set_config(vdpa, offset, buf, len); +} + +static u32 virtio_vdpa_generation(struct virtio_device *vdev) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + if (ops->get_generation) + return ops->get_generation(vdpa); + + return 0; +} + +static u8 virtio_vdpa_get_status(struct virtio_device *vdev) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->get_status(vdpa); +} + +static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->set_status(vdpa, status); +} + +static void virtio_vdpa_reset(struct virtio_device *vdev) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->set_status(vdpa, 0); +} + +static bool virtio_vdpa_notify(struct virtqueue *vq) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vq->vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + ops->kick_vq(vdpa, vq->index); + + return true; +} + +static irqreturn_t virtio_vdpa_config_cb(void *private) +{ + struct virtio_vdpa_device *vd_dev = private; + + virtio_config_changed(&vd_dev->vdev); + + return IRQ_HANDLED; +} + +static irqreturn_t virtio_vdpa_virtqueue_cb(void *private) +{ + struct virtio_vdpa_vq_info *info = private; + + return vring_interrupt(0, info->vq); +} + +static struct virtqueue * +virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, + void (*callback)(struct virtqueue *vq), + const char *name, bool ctx) +{ + struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev); + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + struct virtio_vdpa_vq_info *info; + struct vdpa_callback cb; + struct virtqueue *vq; + u64 desc_addr, driver_addr, device_addr; + unsigned long flags; + u32 align, num; + int err; + + if (!name) + return NULL; + + /* Queue shouldn't already be set up. */ + if (ops->get_vq_ready(vdpa, index)) + return ERR_PTR(-ENOENT); + + /* Allocate and fill out our active queue description */ + info = kmalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return ERR_PTR(-ENOMEM); + + num = ops->get_vq_num_max(vdpa); + if (num == 0) { + err = -ENOENT; + goto error_new_virtqueue; + } + + /* Create the vring */ + align = ops->get_vq_align(vdpa); + vq = vring_create_virtqueue(index, num, align, vdev, + true, true, ctx, + virtio_vdpa_notify, callback, name); + if (!vq) { + err = -ENOMEM; + goto error_new_virtqueue; + } + + /* Setup virtqueue callback */ + cb.callback = virtio_vdpa_virtqueue_cb; + cb.private = info; + ops->set_vq_cb(vdpa, index, &cb); + ops->set_vq_num(vdpa, index, virtqueue_get_vring_size(vq)); + + desc_addr = virtqueue_get_desc_addr(vq); + driver_addr = virtqueue_get_avail_addr(vq); + device_addr = virtqueue_get_used_addr(vq); + + if (ops->set_vq_address(vdpa, index, + desc_addr, driver_addr, + device_addr)) { + err = -EINVAL; + goto err_vq; + } + + ops->set_vq_ready(vdpa, index, 1); + + vq->priv = info; + info->vq = vq; + + spin_lock_irqsave(&vd_dev->lock, flags); + list_add(&info->node, &vd_dev->virtqueues); + spin_unlock_irqrestore(&vd_dev->lock, flags); + + return vq; + +err_vq: + vring_del_virtqueue(vq); +error_new_virtqueue: + ops->set_vq_ready(vdpa, index, 0); + /* VDPA driver should make sure vq is stopeed here */ + WARN_ON(ops->get_vq_ready(vdpa, index)); + kfree(info); + return ERR_PTR(err); +} + +static void virtio_vdpa_del_vq(struct virtqueue *vq) +{ + struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vq->vdev); + struct vdpa_device *vdpa = vd_dev->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + struct virtio_vdpa_vq_info *info = vq->priv; + unsigned int index = vq->index; + unsigned long flags; + + spin_lock_irqsave(&vd_dev->lock, flags); + list_del(&info->node); + spin_unlock_irqrestore(&vd_dev->lock, flags); + + /* Select and deactivate the queue */ + ops->set_vq_ready(vdpa, index, 0); + WARN_ON(ops->get_vq_ready(vdpa, index)); + + vring_del_virtqueue(vq); + + kfree(info); +} + +static void virtio_vdpa_del_vqs(struct virtio_device *vdev) +{ + struct virtqueue *vq, *n; + + list_for_each_entry_safe(vq, n, &vdev->vqs, list) + virtio_vdpa_del_vq(vq); +} + +static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned nvqs, + struct virtqueue *vqs[], + vq_callback_t *callbacks[], + const char * const names[], + const bool *ctx, + struct irq_affinity *desc) +{ + struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev); + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + struct vdpa_callback cb; + int i, err, queue_idx = 0; + + for (i = 0; i < nvqs; ++i) { + if (!names[i]) { + vqs[i] = NULL; + continue; + } + + vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++, + callbacks[i], names[i], ctx ? + ctx[i] : false); + if (IS_ERR(vqs[i])) { + err = PTR_ERR(vqs[i]); + goto err_setup_vq; + } + } + + cb.callback = virtio_vdpa_config_cb; + cb.private = vd_dev; + ops->set_config_cb(vdpa, &cb); + + return 0; + +err_setup_vq: + virtio_vdpa_del_vqs(vdev); + return err; +} + +static u64 virtio_vdpa_get_features(struct virtio_device *vdev) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->get_features(vdpa); +} + +static int virtio_vdpa_finalize_features(struct virtio_device *vdev) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + /* Give virtio_ring a chance to accept features. */ + vring_transport_features(vdev); + + return ops->set_features(vdpa, vdev->features); +} + +static const char *virtio_vdpa_bus_name(struct virtio_device *vdev) +{ + struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev); + struct vdpa_device *vdpa = vd_dev->vdpa; + + return dev_name(&vdpa->dev); +} + +static const struct virtio_config_ops virtio_vdpa_config_ops = { + .get = virtio_vdpa_get, + .set = virtio_vdpa_set, + .generation = virtio_vdpa_generation, + .get_status = virtio_vdpa_get_status, + .set_status = virtio_vdpa_set_status, + .reset = virtio_vdpa_reset, + .find_vqs = virtio_vdpa_find_vqs, + .del_vqs = virtio_vdpa_del_vqs, + .get_features = virtio_vdpa_get_features, + .finalize_features = virtio_vdpa_finalize_features, + .bus_name = virtio_vdpa_bus_name, +}; + +static void virtio_vdpa_release_dev(struct device *_d) +{ + struct virtio_device *vdev = + container_of(_d, struct virtio_device, dev); + struct virtio_vdpa_device *vd_dev = + container_of(vdev, struct virtio_vdpa_device, vdev); + + kfree(vd_dev); +} + +static int virtio_vdpa_probe(struct vdpa_device *vdpa) +{ + const struct vdpa_config_ops *ops = vdpa->config; + struct virtio_vdpa_device *vd_dev, *reg_dev = NULL; + int ret = -EINVAL; + + vd_dev = kzalloc(sizeof(*vd_dev), GFP_KERNEL); + if (!vd_dev) + return -ENOMEM; + + vd_dev->vdev.dev.parent = vdpa_get_dma_dev(vdpa); + vd_dev->vdev.dev.release = virtio_vdpa_release_dev; + vd_dev->vdev.config = &virtio_vdpa_config_ops; + vd_dev->vdpa = vdpa; + INIT_LIST_HEAD(&vd_dev->virtqueues); + spin_lock_init(&vd_dev->lock); + + vd_dev->vdev.id.device = ops->get_device_id(vdpa); + if (vd_dev->vdev.id.device == 0) + goto err; + + vd_dev->vdev.id.vendor = ops->get_vendor_id(vdpa); + ret = register_virtio_device(&vd_dev->vdev); + reg_dev = vd_dev; + if (ret) + goto err; + + vdpa_set_drvdata(vdpa, vd_dev); + + return 0; + +err: + if (reg_dev) + put_device(&vd_dev->vdev.dev); + else + kfree(vd_dev); + return ret; +} + +static void virtio_vdpa_remove(struct vdpa_device *vdpa) +{ + struct virtio_vdpa_device *vd_dev = vdpa_get_drvdata(vdpa); + + unregister_virtio_device(&vd_dev->vdev); +} + +static struct vdpa_driver virtio_vdpa_driver = { + .driver = { + .name = "virtio_vdpa", + }, + .probe = virtio_vdpa_probe, + .remove = virtio_vdpa_remove, +}; + +module_vdpa_driver(virtio_vdpa_driver); + +MODULE_VERSION(MOD_VERSION); +MODULE_LICENSE(MOD_LICENSE); +MODULE_AUTHOR(MOD_AUTHOR); +MODULE_DESCRIPTION(MOD_DESC); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 9ea2b43d4b01..0663c604bd64 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -584,6 +584,14 @@ config DAVINCI_WATCHDOG NOTE: once enabled, this timer cannot be disabled. Say N if you are unsure. +config K3_RTI_WATCHDOG + tristate "Texas Instruments K3 RTI watchdog" + depends on ARCH_K3 || COMPILE_TEST + select WATCHDOG_CORE + help + Say Y here if you want to include support for the K3 watchdog + timer (RTI module) available in the K3 generation of processors. + config ORION_WATCHDOG tristate "Orion watchdog" depends on ARCH_ORION5X || ARCH_DOVE || MACH_DOVE || ARCH_MVEBU || (COMPILE_TEST && !ARCH_EBSA110) diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index 2ee352bf3372..6de2e4ceef19 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_EP93XX_WATCHDOG) += ep93xx_wdt.o obj-$(CONFIG_PNX4008_WATCHDOG) += pnx4008_wdt.o obj-$(CONFIG_IOP_WATCHDOG) += iop_wdt.o obj-$(CONFIG_DAVINCI_WATCHDOG) += davinci_wdt.o +obj-$(CONFIG_K3_RTI_WATCHDOG) += rti_wdt.o obj-$(CONFIG_ORION_WATCHDOG) += orion_wdt.o obj-$(CONFIG_SUNXI_WATCHDOG) += sunxi_wdt.o obj-$(CONFIG_RN5T618_WATCHDOG) += rn5t618_wdt.o diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c index f8d58bf0bf66..1fe472f56cb3 100644 --- a/drivers/watchdog/imx2_wdt.c +++ b/drivers/watchdog/imx2_wdt.c @@ -244,6 +244,11 @@ static const struct regmap_config imx2_wdt_regmap_config = { .max_register = 0x8, }; +static void imx2_wdt_action(void *data) +{ + clk_disable_unprepare(data); +} + static int __init imx2_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -292,6 +297,10 @@ static int __init imx2_wdt_probe(struct platform_device *pdev) if (ret) return ret; + ret = devm_add_action_or_reset(dev, imx2_wdt_action, wdev->clk); + if (ret) + return ret; + regmap_read(wdev->regmap, IMX2_WDT_WRSR, &val); wdog->bootstatus = val & IMX2_WDT_WRSR_TOUT ? WDIOF_CARDRESET : 0; @@ -315,32 +324,7 @@ static int __init imx2_wdt_probe(struct platform_device *pdev) */ regmap_write(wdev->regmap, IMX2_WDT_WMCR, 0); - ret = watchdog_register_device(wdog); - if (ret) - goto disable_clk; - - dev_info(dev, "timeout %d sec (nowayout=%d)\n", - wdog->timeout, nowayout); - - return 0; - -disable_clk: - clk_disable_unprepare(wdev->clk); - return ret; -} - -static int __exit imx2_wdt_remove(struct platform_device *pdev) -{ - struct watchdog_device *wdog = platform_get_drvdata(pdev); - struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog); - - watchdog_unregister_device(wdog); - - if (imx2_wdt_is_running(wdev)) { - imx2_wdt_ping(wdog); - dev_crit(&pdev->dev, "Device removed: Expect reboot!\n"); - } - return 0; + return devm_watchdog_register_device(dev, wdog); } static void imx2_wdt_shutdown(struct platform_device *pdev) @@ -417,7 +401,6 @@ static const struct of_device_id imx2_wdt_dt_ids[] = { MODULE_DEVICE_TABLE(of, imx2_wdt_dt_ids); static struct platform_driver imx2_wdt_driver = { - .remove = __exit_p(imx2_wdt_remove), .shutdown = imx2_wdt_shutdown, .driver = { .name = DRIVER_NAME, diff --git a/drivers/watchdog/imx7ulp_wdt.c b/drivers/watchdog/imx7ulp_wdt.c index 11b9e7c6b7f5..7993c8c41b3a 100644 --- a/drivers/watchdog/imx7ulp_wdt.c +++ b/drivers/watchdog/imx7ulp_wdt.c @@ -4,7 +4,6 @@ */ #include <linux/clk.h> -#include <linux/init.h> #include <linux/io.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/watchdog/imx_sc_wdt.c b/drivers/watchdog/imx_sc_wdt.c index 8ed89f032ebf..60a32469f7de 100644 --- a/drivers/watchdog/imx_sc_wdt.c +++ b/drivers/watchdog/imx_sc_wdt.c @@ -6,13 +6,11 @@ #include <linux/arm-smccc.h> #include <linux/firmware/imx/sci.h> #include <linux/io.h> -#include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/of.h> #include <linux/platform_device.h> -#include <linux/reboot.h> #include <linux/watchdog.h> #define DEFAULT_TIMEOUT 60 diff --git a/drivers/watchdog/npcm_wdt.c b/drivers/watchdog/npcm_wdt.c index 9c773c3d6d5d..765577f11c8d 100644 --- a/drivers/watchdog/npcm_wdt.c +++ b/drivers/watchdog/npcm_wdt.c @@ -103,30 +103,29 @@ static int npcm_wdt_stop(struct watchdog_device *wdd) return 0; } - static int npcm_wdt_set_timeout(struct watchdog_device *wdd, unsigned int timeout) { if (timeout < 2) wdd->timeout = 1; else if (timeout < 3) - wdd->timeout = 2; + wdd->timeout = 2; else if (timeout < 6) - wdd->timeout = 5; + wdd->timeout = 5; else if (timeout < 11) - wdd->timeout = 10; + wdd->timeout = 10; else if (timeout < 22) - wdd->timeout = 21; + wdd->timeout = 21; else if (timeout < 44) - wdd->timeout = 43; + wdd->timeout = 43; else if (timeout < 87) - wdd->timeout = 86; + wdd->timeout = 86; else if (timeout < 173) - wdd->timeout = 172; + wdd->timeout = 172; else if (timeout < 688) - wdd->timeout = 687; + wdd->timeout = 687; else - wdd->timeout = 2750; + wdd->timeout = 2750; if (watchdog_active(wdd)) npcm_wdt_start(wdd); diff --git a/drivers/watchdog/orion_wdt.c b/drivers/watchdog/orion_wdt.c index 8e6dfe76f9c9..4ddb4ea2e4a3 100644 --- a/drivers/watchdog/orion_wdt.c +++ b/drivers/watchdog/orion_wdt.c @@ -52,7 +52,7 @@ #define WDT_A370_RATIO (1 << WDT_A370_RATIO_SHIFT) static bool nowayout = WATCHDOG_NOWAYOUT; -static int heartbeat = -1; /* module parameter (seconds) */ +static int heartbeat; /* module parameter (seconds) */ struct orion_watchdog; diff --git a/drivers/watchdog/pm8916_wdt.c b/drivers/watchdog/pm8916_wdt.c index 1213179f863c..0937b8d33104 100644 --- a/drivers/watchdog/pm8916_wdt.c +++ b/drivers/watchdog/pm8916_wdt.c @@ -192,6 +192,7 @@ static int pm8916_wdt_probe(struct platform_device *pdev) wdt->wdev.timeout = PM8916_WDT_DEFAULT_TIMEOUT; wdt->wdev.pretimeout = 0; watchdog_set_drvdata(&wdt->wdev, wdt); + platform_set_drvdata(pdev, wdt); watchdog_init_timeout(&wdt->wdev, 0, dev); pm8916_wdt_configure_timers(&wdt->wdev); @@ -199,6 +200,29 @@ static int pm8916_wdt_probe(struct platform_device *pdev) return devm_watchdog_register_device(dev, &wdt->wdev); } +static int __maybe_unused pm8916_wdt_suspend(struct device *dev) +{ + struct pm8916_wdt *wdt = dev_get_drvdata(dev); + + if (watchdog_active(&wdt->wdev)) + return pm8916_wdt_stop(&wdt->wdev); + + return 0; +} + +static int __maybe_unused pm8916_wdt_resume(struct device *dev) +{ + struct pm8916_wdt *wdt = dev_get_drvdata(dev); + + if (watchdog_active(&wdt->wdev)) + return pm8916_wdt_start(&wdt->wdev); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(pm8916_wdt_pm_ops, pm8916_wdt_suspend, + pm8916_wdt_resume); + static const struct of_device_id pm8916_wdt_id_table[] = { { .compatible = "qcom,pm8916-wdt" }, { } @@ -210,6 +234,7 @@ static struct platform_driver pm8916_wdt_driver = { .driver = { .name = "pm8916-wdt", .of_match_table = of_match_ptr(pm8916_wdt_id_table), + .pm = &pm8916_wdt_pm_ops, }, }; module_platform_driver(pm8916_wdt_driver); diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c index eb47fe5ed280..ab7465d186fd 100644 --- a/drivers/watchdog/qcom-wdt.c +++ b/drivers/watchdog/qcom-wdt.c @@ -40,6 +40,11 @@ static const u32 reg_offset_data_kpss[] = { [WDT_BITE_TIME] = 0x14, }; +struct qcom_wdt_match_data { + const u32 *offset; + bool pretimeout; +}; + struct qcom_wdt { struct watchdog_device wdd; unsigned long rate; @@ -179,19 +184,29 @@ static void qcom_clk_disable_unprepare(void *data) clk_disable_unprepare(data); } +static const struct qcom_wdt_match_data match_data_apcs_tmr = { + .offset = reg_offset_data_apcs_tmr, + .pretimeout = false, +}; + +static const struct qcom_wdt_match_data match_data_kpss = { + .offset = reg_offset_data_kpss, + .pretimeout = true, +}; + static int qcom_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct qcom_wdt *wdt; struct resource *res; struct device_node *np = dev->of_node; - const u32 *regs; + const struct qcom_wdt_match_data *data; u32 percpu_offset; int irq, ret; struct clk *clk; - regs = of_device_get_match_data(dev); - if (!regs) { + data = of_device_get_match_data(dev); + if (!data) { dev_err(dev, "Unsupported QCOM WDT module\n"); return -ENODEV; } @@ -247,9 +262,8 @@ static int qcom_wdt_probe(struct platform_device *pdev) /* check if there is pretimeout support */ irq = platform_get_irq_optional(pdev, 0); - if (irq > 0) { - ret = devm_request_irq(dev, irq, qcom_wdt_isr, - IRQF_TRIGGER_RISING, + if (data->pretimeout && irq > 0) { + ret = devm_request_irq(dev, irq, qcom_wdt_isr, 0, "wdt_bark", &wdt->wdd); if (ret) return ret; @@ -267,7 +281,7 @@ static int qcom_wdt_probe(struct platform_device *pdev) wdt->wdd.min_timeout = 1; wdt->wdd.max_timeout = 0x10000000U / wdt->rate; wdt->wdd.parent = dev; - wdt->layout = regs; + wdt->layout = data->offset; if (readl(wdt_addr(wdt, WDT_STS)) & 1) wdt->wdd.bootstatus = WDIOF_CARDRESET; @@ -311,9 +325,9 @@ static int __maybe_unused qcom_wdt_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(qcom_wdt_pm_ops, qcom_wdt_suspend, qcom_wdt_resume); static const struct of_device_id qcom_wdt_of_table[] = { - { .compatible = "qcom,kpss-timer", .data = reg_offset_data_apcs_tmr }, - { .compatible = "qcom,scss-timer", .data = reg_offset_data_apcs_tmr }, - { .compatible = "qcom,kpss-wdt", .data = reg_offset_data_kpss }, + { .compatible = "qcom,kpss-timer", .data = &match_data_apcs_tmr }, + { .compatible = "qcom,scss-timer", .data = &match_data_apcs_tmr }, + { .compatible = "qcom,kpss-wdt", .data = &match_data_kpss }, { }, }; MODULE_DEVICE_TABLE(of, qcom_wdt_of_table); diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c new file mode 100644 index 000000000000..d456dd72d99a --- /dev/null +++ b/drivers/watchdog/rti_wdt.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Watchdog driver for the K3 RTI module + * + * (c) Copyright 2019-2020 Texas Instruments Inc. + * All rights reserved. + */ + +#include <linux/clk.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/types.h> +#include <linux/watchdog.h> + +#define DEFAULT_HEARTBEAT 60 + +/* Max heartbeat is calculated at 32kHz source clock */ +#define MAX_HEARTBEAT 1000 + +/* Timer register set definition */ +#define RTIDWDCTRL 0x90 +#define RTIDWDPRLD 0x94 +#define RTIWDSTATUS 0x98 +#define RTIWDKEY 0x9c +#define RTIDWDCNTR 0xa0 +#define RTIWWDRXCTRL 0xa4 +#define RTIWWDSIZECTRL 0xa8 + +#define RTIWWDRX_NMI 0xa + +#define RTIWWDSIZE_50P 0x50 + +#define WDENABLE_KEY 0xa98559da + +#define WDKEY_SEQ0 0xe51a +#define WDKEY_SEQ1 0xa35c + +#define WDT_PRELOAD_SHIFT 13 + +#define WDT_PRELOAD_MAX 0xfff + +#define DWDST BIT(1) + +static int heartbeat; + +/* + * struct to hold data for each WDT device + * @base - base io address of WD device + * @freq - source clock frequency of WDT + * @wdd - hold watchdog device as is in WDT core + */ +struct rti_wdt_device { + void __iomem *base; + unsigned long freq; + struct watchdog_device wdd; +}; + +static int rti_wdt_start(struct watchdog_device *wdd) +{ + u32 timer_margin; + struct rti_wdt_device *wdt = watchdog_get_drvdata(wdd); + + /* set timeout period */ + timer_margin = (u64)wdd->timeout * wdt->freq; + timer_margin >>= WDT_PRELOAD_SHIFT; + if (timer_margin > WDT_PRELOAD_MAX) + timer_margin = WDT_PRELOAD_MAX; + writel_relaxed(timer_margin, wdt->base + RTIDWDPRLD); + + /* + * RTI only supports a windowed mode, where the watchdog can only + * be petted during the open window; not too early or not too late. + * The HW configuration options only allow for the open window size + * to be 50% or less than that; we obviouly want to configure the open + * window as large as possible so we select the 50% option. To avoid + * any glitches, we accommodate 5% safety margin also, so we setup + * the min_hw_hearbeat at 55% of the timeout period. + */ + wdd->min_hw_heartbeat_ms = 11 * wdd->timeout * 1000 / 20; + + /* Generate NMI when wdt expires */ + writel_relaxed(RTIWWDRX_NMI, wdt->base + RTIWWDRXCTRL); + + /* Open window size 50%; this is the largest window size available */ + writel_relaxed(RTIWWDSIZE_50P, wdt->base + RTIWWDSIZECTRL); + + readl_relaxed(wdt->base + RTIWWDSIZECTRL); + + /* enable watchdog */ + writel_relaxed(WDENABLE_KEY, wdt->base + RTIDWDCTRL); + return 0; +} + +static int rti_wdt_ping(struct watchdog_device *wdd) +{ + struct rti_wdt_device *wdt = watchdog_get_drvdata(wdd); + + /* put watchdog in service state */ + writel_relaxed(WDKEY_SEQ0, wdt->base + RTIWDKEY); + /* put watchdog in active state */ + writel_relaxed(WDKEY_SEQ1, wdt->base + RTIWDKEY); + + return 0; +} + +static unsigned int rti_wdt_get_timeleft(struct watchdog_device *wdd) +{ + u64 timer_counter; + u32 val; + struct rti_wdt_device *wdt = watchdog_get_drvdata(wdd); + + /* if timeout has occurred then return 0 */ + val = readl_relaxed(wdt->base + RTIWDSTATUS); + if (val & DWDST) + return 0; + + timer_counter = readl_relaxed(wdt->base + RTIDWDCNTR); + + do_div(timer_counter, wdt->freq); + + return timer_counter; +} + +static const struct watchdog_info rti_wdt_info = { + .options = WDIOF_KEEPALIVEPING, + .identity = "K3 RTI Watchdog", +}; + +static const struct watchdog_ops rti_wdt_ops = { + .owner = THIS_MODULE, + .start = rti_wdt_start, + .ping = rti_wdt_ping, + .get_timeleft = rti_wdt_get_timeleft, +}; + +static int rti_wdt_probe(struct platform_device *pdev) +{ + int ret = 0; + struct device *dev = &pdev->dev; + struct resource *wdt_mem; + struct watchdog_device *wdd; + struct rti_wdt_device *wdt; + struct clk *clk; + + wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL); + if (!wdt) + return -ENOMEM; + + clk = clk_get(dev, NULL); + if (IS_ERR(clk)) { + if (PTR_ERR(clk) != -EPROBE_DEFER) + dev_err(dev, "failed to get clock\n"); + return PTR_ERR(clk); + } + + wdt->freq = clk_get_rate(clk); + + clk_put(clk); + + if (!wdt->freq) { + dev_err(dev, "Failed to get fck rate.\n"); + return -EINVAL; + } + + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret) { + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, "runtime pm failed\n"); + return ret; + } + + platform_set_drvdata(pdev, wdt); + + wdd = &wdt->wdd; + wdd->info = &rti_wdt_info; + wdd->ops = &rti_wdt_ops; + wdd->min_timeout = 1; + wdd->max_hw_heartbeat_ms = (WDT_PRELOAD_MAX << WDT_PRELOAD_SHIFT) / + wdt->freq * 1000; + wdd->timeout = DEFAULT_HEARTBEAT; + wdd->parent = dev; + + watchdog_init_timeout(wdd, heartbeat, dev); + + watchdog_set_drvdata(wdd, wdt); + watchdog_set_nowayout(wdd, 1); + watchdog_set_restart_priority(wdd, 128); + + wdt_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + wdt->base = devm_ioremap_resource(dev, wdt_mem); + if (IS_ERR(wdt->base)) { + ret = PTR_ERR(wdt->base); + goto err_iomap; + } + + ret = watchdog_register_device(wdd); + if (ret) { + dev_err(dev, "cannot register watchdog device\n"); + goto err_iomap; + } + + return 0; + +err_iomap: + pm_runtime_put_sync(&pdev->dev); + + return ret; +} + +static int rti_wdt_remove(struct platform_device *pdev) +{ + struct rti_wdt_device *wdt = platform_get_drvdata(pdev); + + watchdog_unregister_device(&wdt->wdd); + pm_runtime_put(&pdev->dev); + + return 0; +} + +static const struct of_device_id rti_wdt_of_match[] = { + { .compatible = "ti,j7-rti-wdt", }, + {}, +}; +MODULE_DEVICE_TABLE(of, rti_wdt_of_match); + +static struct platform_driver rti_wdt_driver = { + .driver = { + .name = "rti-wdt", + .of_match_table = rti_wdt_of_match, + }, + .probe = rti_wdt_probe, + .remove = rti_wdt_remove, +}; + +module_platform_driver(rti_wdt_driver); + +MODULE_AUTHOR("Tero Kristo <t-kristo@ti.com>"); +MODULE_DESCRIPTION("K3 RTI Watchdog Driver"); + +module_param(heartbeat, int, 0); +MODULE_PARM_DESC(heartbeat, + "Watchdog heartbeat period in seconds from 1 to " + __MODULE_STRING(MAX_HEARTBEAT) ", default " + __MODULE_STRING(DEFAULT_HEARTBEAT)); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:rti-wdt"); diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c index 861daf4f37b2..423844757812 100644 --- a/drivers/watchdog/watchdog_core.c +++ b/drivers/watchdog/watchdog_core.c @@ -39,6 +39,10 @@ static DEFINE_IDA(watchdog_ida); +static int stop_on_reboot = -1; +module_param(stop_on_reboot, int, 0444); +MODULE_PARM_DESC(stop_on_reboot, "Stop watchdogs on reboot (0=keep watching, 1=stop)"); + /* * Deferred Registration infrastructure. * @@ -254,6 +258,14 @@ static int __watchdog_register_device(struct watchdog_device *wdd) } } + /* Module parameter to force watchdog policy on reboot. */ + if (stop_on_reboot != -1) { + if (stop_on_reboot) + set_bit(WDOG_STOP_ON_REBOOT, &wdd->status); + else + clear_bit(WDOG_STOP_ON_REBOOT, &wdd->status); + } + if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status)) { wdd->reboot_nb.notifier_call = watchdog_reboot_notifier; diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index 8b5c742f24e8..7e4cd34a8c20 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -282,6 +282,7 @@ static int watchdog_start(struct watchdog_device *wdd) if (err == 0) { set_bit(WDOG_ACTIVE, &wdd->status); wd_data->last_keepalive = started_at; + wd_data->last_hw_keepalive = started_at; watchdog_update_worker(wdd); } diff --git a/drivers/watchdog/wm831x_wdt.c b/drivers/watchdog/wm831x_wdt.c index 030ce240620d..d96ad8f38bd2 100644 --- a/drivers/watchdog/wm831x_wdt.c +++ b/drivers/watchdog/wm831x_wdt.c @@ -13,7 +13,6 @@ #include <linux/platform_device.h> #include <linux/watchdog.h> #include <linux/uaccess.h> -#include <linux/gpio.h> #include <linux/mfd/wm831x/core.h> #include <linux/mfd/wm831x/pdata.h> @@ -29,7 +28,6 @@ struct wm831x_wdt_drvdata { struct watchdog_device wdt; struct wm831x *wm831x; struct mutex lock; - int update_gpio; int update_state; }; @@ -103,14 +101,6 @@ static int wm831x_wdt_ping(struct watchdog_device *wdt_dev) mutex_lock(&driver_data->lock); - if (driver_data->update_gpio) { - gpio_set_value_cansleep(driver_data->update_gpio, - driver_data->update_state); - driver_data->update_state = !driver_data->update_state; - ret = 0; - goto out; - } - reg = wm831x_reg_read(wm831x, WM831X_WATCHDOG); if (!(reg & WM831X_WDOG_RST_SRC)) { @@ -239,23 +229,6 @@ static int wm831x_wdt_probe(struct platform_device *pdev) reg |= pdata->secondary << WM831X_WDOG_SECACT_SHIFT; reg |= pdata->software << WM831X_WDOG_RST_SRC_SHIFT; - if (pdata->update_gpio) { - ret = devm_gpio_request_one(dev, pdata->update_gpio, - GPIOF_OUT_INIT_LOW, - "Watchdog update"); - if (ret < 0) { - dev_err(wm831x->dev, - "Failed to request update GPIO: %d\n", - ret); - return ret; - } - - driver_data->update_gpio = pdata->update_gpio; - - /* Make sure the watchdog takes hardware updates */ - reg |= WM831X_WDOG_RST_SRC; - } - ret = wm831x_reg_unlock(wm831x); if (ret == 0) { ret = wm831x_reg_write(wm831x, WM831X_WATCHDOG, reg); diff --git a/drivers/watchdog/ziirave_wdt.c b/drivers/watchdog/ziirave_wdt.c index 4a363a8b2d20..cab86a08456b 100644 --- a/drivers/watchdog/ziirave_wdt.c +++ b/drivers/watchdog/ziirave_wdt.c @@ -422,7 +422,7 @@ static int ziirave_firm_upload(struct watchdog_device *wdd, static const struct watchdog_info ziirave_wdt_info = { .options = WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING, - .identity = "Zodiac RAVE Watchdog", + .identity = "RAVE Switch Watchdog", }; static const struct watchdog_ops ziirave_wdt_ops = { diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c index 8edef51c92e5..64df919a2111 100644 --- a/drivers/xen/events/events_2l.c +++ b/drivers/xen/events/events_2l.c @@ -53,37 +53,37 @@ static void evtchn_2l_bind_to_cpu(struct irq_info *info, unsigned cpu) set_bit(info->evtchn, BM(per_cpu(cpu_evtchn_mask, cpu))); } -static void evtchn_2l_clear_pending(unsigned port) +static void evtchn_2l_clear_pending(evtchn_port_t port) { struct shared_info *s = HYPERVISOR_shared_info; sync_clear_bit(port, BM(&s->evtchn_pending[0])); } -static void evtchn_2l_set_pending(unsigned port) +static void evtchn_2l_set_pending(evtchn_port_t port) { struct shared_info *s = HYPERVISOR_shared_info; sync_set_bit(port, BM(&s->evtchn_pending[0])); } -static bool evtchn_2l_is_pending(unsigned port) +static bool evtchn_2l_is_pending(evtchn_port_t port) { struct shared_info *s = HYPERVISOR_shared_info; return sync_test_bit(port, BM(&s->evtchn_pending[0])); } -static bool evtchn_2l_test_and_set_mask(unsigned port) +static bool evtchn_2l_test_and_set_mask(evtchn_port_t port) { struct shared_info *s = HYPERVISOR_shared_info; return sync_test_and_set_bit(port, BM(&s->evtchn_mask[0])); } -static void evtchn_2l_mask(unsigned port) +static void evtchn_2l_mask(evtchn_port_t port) { struct shared_info *s = HYPERVISOR_shared_info; sync_set_bit(port, BM(&s->evtchn_mask[0])); } -static void evtchn_2l_unmask(unsigned port) +static void evtchn_2l_unmask(evtchn_port_t port) { struct shared_info *s = HYPERVISOR_shared_info; unsigned int cpu = get_cpu(); @@ -173,7 +173,7 @@ static void evtchn_2l_handle_events(unsigned cpu) /* Timer interrupt has highest priority. */ irq = irq_from_virq(cpu, VIRQ_TIMER); if (irq != -1) { - unsigned int evtchn = evtchn_from_irq(irq); + evtchn_port_t evtchn = evtchn_from_irq(irq); word_idx = evtchn / BITS_PER_LONG; bit_idx = evtchn % BITS_PER_LONG; if (active_evtchns(cpu, s, word_idx) & (1ULL << bit_idx)) @@ -228,7 +228,7 @@ static void evtchn_2l_handle_events(unsigned cpu) do { xen_ulong_t bits; - int port; + evtchn_port_t port; bits = MASK_LSBS(pending_bits, bit_idx); diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 499eff7d3f65..3a791c8485d0 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -116,7 +116,7 @@ static void clear_evtchn_to_irq_all(void) } } -static int set_evtchn_to_irq(unsigned evtchn, unsigned irq) +static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) { unsigned row; unsigned col; @@ -143,7 +143,7 @@ static int set_evtchn_to_irq(unsigned evtchn, unsigned irq) return 0; } -int get_evtchn_to_irq(unsigned evtchn) +int get_evtchn_to_irq(evtchn_port_t evtchn) { if (evtchn >= xen_evtchn_max_channels()) return -1; @@ -162,7 +162,7 @@ struct irq_info *info_for_irq(unsigned irq) static int xen_irq_info_common_setup(struct irq_info *info, unsigned irq, enum xen_irq_type type, - unsigned evtchn, + evtchn_port_t evtchn, unsigned short cpu) { int ret; @@ -184,7 +184,7 @@ static int xen_irq_info_common_setup(struct irq_info *info, } static int xen_irq_info_evtchn_setup(unsigned irq, - unsigned evtchn) + evtchn_port_t evtchn) { struct irq_info *info = info_for_irq(irq); @@ -193,7 +193,7 @@ static int xen_irq_info_evtchn_setup(unsigned irq, static int xen_irq_info_ipi_setup(unsigned cpu, unsigned irq, - unsigned evtchn, + evtchn_port_t evtchn, enum ipi_vector ipi) { struct irq_info *info = info_for_irq(irq); @@ -207,7 +207,7 @@ static int xen_irq_info_ipi_setup(unsigned cpu, static int xen_irq_info_virq_setup(unsigned cpu, unsigned irq, - unsigned evtchn, + evtchn_port_t evtchn, unsigned virq) { struct irq_info *info = info_for_irq(irq); @@ -220,7 +220,7 @@ static int xen_irq_info_virq_setup(unsigned cpu, } static int xen_irq_info_pirq_setup(unsigned irq, - unsigned evtchn, + evtchn_port_t evtchn, unsigned pirq, unsigned gsi, uint16_t domid, @@ -245,7 +245,7 @@ static void xen_irq_info_cleanup(struct irq_info *info) /* * Accessors for packed IRQ information. */ -unsigned int evtchn_from_irq(unsigned irq) +evtchn_port_t evtchn_from_irq(unsigned irq) { if (WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq)) return 0; @@ -253,7 +253,7 @@ unsigned int evtchn_from_irq(unsigned irq) return info_for_irq(irq)->evtchn; } -unsigned irq_from_evtchn(unsigned int evtchn) +unsigned int irq_from_evtchn(evtchn_port_t evtchn) { return get_evtchn_to_irq(evtchn); } @@ -304,7 +304,7 @@ unsigned cpu_from_irq(unsigned irq) return info_for_irq(irq)->cpu; } -unsigned int cpu_from_evtchn(unsigned int evtchn) +unsigned int cpu_from_evtchn(evtchn_port_t evtchn) { int irq = get_evtchn_to_irq(evtchn); unsigned ret = 0; @@ -330,9 +330,9 @@ static bool pirq_needs_eoi_flag(unsigned irq) return info->u.pirq.flags & PIRQ_NEEDS_EOI; } -static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu) +static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu) { - int irq = get_evtchn_to_irq(chn); + int irq = get_evtchn_to_irq(evtchn); struct irq_info *info = info_for_irq(irq); BUG_ON(irq == -1); @@ -354,7 +354,7 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu) */ void notify_remote_via_irq(int irq) { - int evtchn = evtchn_from_irq(irq); + evtchn_port_t evtchn = evtchn_from_irq(irq); if (VALID_EVTCHN(evtchn)) notify_remote_via_evtchn(evtchn); @@ -445,7 +445,7 @@ static void xen_free_irq(unsigned irq) irq_free_desc(irq); } -static void xen_evtchn_close(unsigned int port) +static void xen_evtchn_close(evtchn_port_t port) { struct evtchn_close close; @@ -472,7 +472,7 @@ static void pirq_query_unmask(int irq) static void eoi_pirq(struct irq_data *data) { - int evtchn = evtchn_from_irq(data->irq); + evtchn_port_t evtchn = evtchn_from_irq(data->irq); struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) }; int rc = 0; @@ -508,7 +508,7 @@ static unsigned int __startup_pirq(unsigned int irq) { struct evtchn_bind_pirq bind_pirq; struct irq_info *info = info_for_irq(irq); - int evtchn = evtchn_from_irq(irq); + evtchn_port_t evtchn = evtchn_from_irq(irq); int rc; BUG_ON(info->type != IRQT_PIRQ); @@ -561,7 +561,7 @@ static void shutdown_pirq(struct irq_data *data) { unsigned int irq = data->irq; struct irq_info *info = info_for_irq(irq); - unsigned evtchn = evtchn_from_irq(irq); + evtchn_port_t evtchn = evtchn_from_irq(irq); BUG_ON(info->type != IRQT_PIRQ); @@ -601,7 +601,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi); static void __unbind_from_irq(unsigned int irq) { - int evtchn = evtchn_from_irq(irq); + evtchn_port_t evtchn = evtchn_from_irq(irq); struct irq_info *info = irq_get_handler_data(irq); if (info->refcnt > 0) { @@ -827,7 +827,7 @@ int xen_pirq_from_irq(unsigned irq) } EXPORT_SYMBOL_GPL(xen_pirq_from_irq); -int bind_evtchn_to_irq(unsigned int evtchn) +int bind_evtchn_to_irq(evtchn_port_t evtchn) { int irq; int ret; @@ -870,8 +870,8 @@ EXPORT_SYMBOL_GPL(bind_evtchn_to_irq); static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) { struct evtchn_bind_ipi bind_ipi; - int evtchn, irq; - int ret; + evtchn_port_t evtchn; + int ret, irq; mutex_lock(&irq_mapping_update_lock); @@ -909,7 +909,7 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) } int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, - unsigned int remote_port) + evtchn_port_t remote_port) { struct evtchn_bind_interdomain bind_interdomain; int err; @@ -924,10 +924,11 @@ int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, } EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq); -static int find_virq(unsigned int virq, unsigned int cpu) +static int find_virq(unsigned int virq, unsigned int cpu, evtchn_port_t *evtchn) { struct evtchn_status status; - int port, rc = -ENOENT; + evtchn_port_t port; + int rc = -ENOENT; memset(&status, 0, sizeof(status)); for (port = 0; port < xen_evtchn_max_channels(); port++) { @@ -939,7 +940,7 @@ static int find_virq(unsigned int virq, unsigned int cpu) if (status.status != EVTCHNSTAT_virq) continue; if (status.u.virq == virq && status.vcpu == xen_vcpu_nr(cpu)) { - rc = port; + *evtchn = port; break; } } @@ -962,7 +963,8 @@ EXPORT_SYMBOL_GPL(xen_evtchn_nr_channels); int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu) { struct evtchn_bind_virq bind_virq; - int evtchn, irq, ret; + evtchn_port_t evtchn = 0; + int irq, ret; mutex_lock(&irq_mapping_update_lock); @@ -988,9 +990,8 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu) evtchn = bind_virq.port; else { if (ret == -EEXIST) - ret = find_virq(virq, cpu); + ret = find_virq(virq, cpu, &evtchn); BUG_ON(ret < 0); - evtchn = ret; } ret = xen_irq_info_virq_setup(cpu, irq, evtchn, virq); @@ -1019,7 +1020,7 @@ static void unbind_from_irq(unsigned int irq) mutex_unlock(&irq_mapping_update_lock); } -int bind_evtchn_to_irqhandler(unsigned int evtchn, +int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id) @@ -1040,7 +1041,7 @@ int bind_evtchn_to_irqhandler(unsigned int evtchn, EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler); int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, - unsigned int remote_port, + evtchn_port_t remote_port, irq_handler_t handler, unsigned long irqflags, const char *devname, @@ -1132,7 +1133,7 @@ int xen_set_irq_priority(unsigned irq, unsigned priority) } EXPORT_SYMBOL_GPL(xen_set_irq_priority); -int evtchn_make_refcounted(unsigned int evtchn) +int evtchn_make_refcounted(evtchn_port_t evtchn) { int irq = get_evtchn_to_irq(evtchn); struct irq_info *info; @@ -1153,7 +1154,7 @@ int evtchn_make_refcounted(unsigned int evtchn) } EXPORT_SYMBOL_GPL(evtchn_make_refcounted); -int evtchn_get(unsigned int evtchn) +int evtchn_get(evtchn_port_t evtchn) { int irq; struct irq_info *info; @@ -1186,7 +1187,7 @@ int evtchn_get(unsigned int evtchn) } EXPORT_SYMBOL_GPL(evtchn_get); -void evtchn_put(unsigned int evtchn) +void evtchn_put(evtchn_port_t evtchn) { int irq = get_evtchn_to_irq(evtchn); if (WARN_ON(irq == -1)) @@ -1252,7 +1253,7 @@ void xen_hvm_evtchn_do_upcall(void) EXPORT_SYMBOL_GPL(xen_hvm_evtchn_do_upcall); /* Rebind a new event channel to an existing irq. */ -void rebind_evtchn_irq(int evtchn, int irq) +void rebind_evtchn_irq(evtchn_port_t evtchn, int irq) { struct irq_info *info = info_for_irq(irq); @@ -1284,7 +1285,7 @@ void rebind_evtchn_irq(int evtchn, int irq) } /* Rebind an evtchn so that it gets delivered to a specific cpu */ -static int xen_rebind_evtchn_to_cpu(int evtchn, unsigned int tcpu) +static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu) { struct evtchn_bind_vcpu bind_vcpu; int masked; @@ -1342,7 +1343,7 @@ EXPORT_SYMBOL_GPL(xen_set_affinity_evtchn); static void enable_dynirq(struct irq_data *data) { - int evtchn = evtchn_from_irq(data->irq); + evtchn_port_t evtchn = evtchn_from_irq(data->irq); if (VALID_EVTCHN(evtchn)) unmask_evtchn(evtchn); @@ -1350,7 +1351,7 @@ static void enable_dynirq(struct irq_data *data) static void disable_dynirq(struct irq_data *data) { - int evtchn = evtchn_from_irq(data->irq); + evtchn_port_t evtchn = evtchn_from_irq(data->irq); if (VALID_EVTCHN(evtchn)) mask_evtchn(evtchn); @@ -1358,7 +1359,7 @@ static void disable_dynirq(struct irq_data *data) static void ack_dynirq(struct irq_data *data) { - int evtchn = evtchn_from_irq(data->irq); + evtchn_port_t evtchn = evtchn_from_irq(data->irq); if (!VALID_EVTCHN(evtchn)) return; @@ -1385,7 +1386,7 @@ static void mask_ack_dynirq(struct irq_data *data) static int retrigger_dynirq(struct irq_data *data) { - unsigned int evtchn = evtchn_from_irq(data->irq); + evtchn_port_t evtchn = evtchn_from_irq(data->irq); int masked; if (!VALID_EVTCHN(evtchn)) @@ -1440,7 +1441,8 @@ static void restore_pirqs(void) static void restore_cpu_virqs(unsigned int cpu) { struct evtchn_bind_virq bind_virq; - int virq, irq, evtchn; + evtchn_port_t evtchn; + int virq, irq; for (virq = 0; virq < NR_VIRQS; virq++) { if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1) @@ -1465,7 +1467,8 @@ static void restore_cpu_virqs(unsigned int cpu) static void restore_cpu_ipis(unsigned int cpu) { struct evtchn_bind_ipi bind_ipi; - int ipi, irq, evtchn; + evtchn_port_t evtchn; + int ipi, irq; for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) { if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1) @@ -1489,7 +1492,7 @@ static void restore_cpu_ipis(unsigned int cpu) /* Clear an irq's pending state, in preparation for polling on it */ void xen_clear_irq_pending(int irq) { - int evtchn = evtchn_from_irq(irq); + evtchn_port_t evtchn = evtchn_from_irq(irq); if (VALID_EVTCHN(evtchn)) clear_evtchn(evtchn); @@ -1497,7 +1500,7 @@ void xen_clear_irq_pending(int irq) EXPORT_SYMBOL(xen_clear_irq_pending); void xen_set_irq_pending(int irq) { - int evtchn = evtchn_from_irq(irq); + evtchn_port_t evtchn = evtchn_from_irq(irq); if (VALID_EVTCHN(evtchn)) set_evtchn(evtchn); @@ -1505,7 +1508,7 @@ void xen_set_irq_pending(int irq) bool xen_test_irq_pending(int irq) { - int evtchn = evtchn_from_irq(irq); + evtchn_port_t evtchn = evtchn_from_irq(irq); bool ret = false; if (VALID_EVTCHN(evtchn)) @@ -1667,7 +1670,7 @@ module_param(fifo_events, bool, 0); void __init xen_init_IRQ(void) { int ret = -EINVAL; - unsigned int evtchn; + evtchn_port_t evtchn; if (fifo_events) ret = xen_evtchn_fifo_init(); diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 76b318e88382..c60ee0450173 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -82,7 +82,7 @@ static unsigned event_array_pages __read_mostly; #endif -static inline event_word_t *event_word_from_port(unsigned port) +static inline event_word_t *event_word_from_port(evtchn_port_t port) { unsigned i = port / EVENT_WORDS_PER_PAGE; @@ -140,7 +140,7 @@ static void init_array_page(event_word_t *array_page) static int evtchn_fifo_setup(struct irq_info *info) { - unsigned port = info->evtchn; + evtchn_port_t port = info->evtchn; unsigned new_array_pages; int ret; @@ -191,37 +191,37 @@ static void evtchn_fifo_bind_to_cpu(struct irq_info *info, unsigned cpu) /* no-op */ } -static void evtchn_fifo_clear_pending(unsigned port) +static void evtchn_fifo_clear_pending(evtchn_port_t port) { event_word_t *word = event_word_from_port(port); sync_clear_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word)); } -static void evtchn_fifo_set_pending(unsigned port) +static void evtchn_fifo_set_pending(evtchn_port_t port) { event_word_t *word = event_word_from_port(port); sync_set_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word)); } -static bool evtchn_fifo_is_pending(unsigned port) +static bool evtchn_fifo_is_pending(evtchn_port_t port) { event_word_t *word = event_word_from_port(port); return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word)); } -static bool evtchn_fifo_test_and_set_mask(unsigned port) +static bool evtchn_fifo_test_and_set_mask(evtchn_port_t port) { event_word_t *word = event_word_from_port(port); return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); } -static void evtchn_fifo_mask(unsigned port) +static void evtchn_fifo_mask(evtchn_port_t port) { event_word_t *word = event_word_from_port(port); sync_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); } -static bool evtchn_fifo_is_masked(unsigned port) +static bool evtchn_fifo_is_masked(evtchn_port_t port) { event_word_t *word = event_word_from_port(port); return sync_test_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); @@ -242,7 +242,7 @@ static void clear_masked(volatile event_word_t *word) } while (w != old); } -static void evtchn_fifo_unmask(unsigned port) +static void evtchn_fifo_unmask(evtchn_port_t port) { event_word_t *word = event_word_from_port(port); @@ -270,7 +270,7 @@ static uint32_t clear_linked(volatile event_word_t *word) return w & EVTCHN_FIFO_LINK_MASK; } -static void handle_irq_for_port(unsigned port) +static void handle_irq_for_port(evtchn_port_t port) { int irq; @@ -286,7 +286,7 @@ static void consume_one_event(unsigned cpu, { struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); uint32_t head; - unsigned port; + evtchn_port_t port; event_word_t *word; head = q->head[priority]; diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h index 82938cff6c7a..10684feb094e 100644 --- a/drivers/xen/events/events_internal.h +++ b/drivers/xen/events/events_internal.h @@ -33,7 +33,7 @@ struct irq_info { int refcnt; enum xen_irq_type type; /* type */ unsigned irq; - unsigned int evtchn; /* event channel */ + evtchn_port_t evtchn; /* event channel */ unsigned short cpu; /* cpu bound */ union { @@ -60,12 +60,12 @@ struct evtchn_ops { int (*setup)(struct irq_info *info); void (*bind_to_cpu)(struct irq_info *info, unsigned cpu); - void (*clear_pending)(unsigned port); - void (*set_pending)(unsigned port); - bool (*is_pending)(unsigned port); - bool (*test_and_set_mask)(unsigned port); - void (*mask)(unsigned port); - void (*unmask)(unsigned port); + void (*clear_pending)(evtchn_port_t port); + void (*set_pending)(evtchn_port_t port); + bool (*is_pending)(evtchn_port_t port); + bool (*test_and_set_mask)(evtchn_port_t port); + void (*mask)(evtchn_port_t port); + void (*unmask)(evtchn_port_t port); void (*handle_events)(unsigned cpu); void (*resume)(void); @@ -74,11 +74,11 @@ struct evtchn_ops { extern const struct evtchn_ops *evtchn_ops; extern int **evtchn_to_irq; -int get_evtchn_to_irq(unsigned int evtchn); +int get_evtchn_to_irq(evtchn_port_t evtchn); struct irq_info *info_for_irq(unsigned irq); unsigned cpu_from_irq(unsigned irq); -unsigned cpu_from_evtchn(unsigned int evtchn); +unsigned int cpu_from_evtchn(evtchn_port_t evtchn); static inline unsigned xen_evtchn_max_channels(void) { @@ -102,32 +102,32 @@ static inline void xen_evtchn_port_bind_to_cpu(struct irq_info *info, evtchn_ops->bind_to_cpu(info, cpu); } -static inline void clear_evtchn(unsigned port) +static inline void clear_evtchn(evtchn_port_t port) { evtchn_ops->clear_pending(port); } -static inline void set_evtchn(unsigned port) +static inline void set_evtchn(evtchn_port_t port) { evtchn_ops->set_pending(port); } -static inline bool test_evtchn(unsigned port) +static inline bool test_evtchn(evtchn_port_t port) { return evtchn_ops->is_pending(port); } -static inline bool test_and_set_mask(unsigned port) +static inline bool test_and_set_mask(evtchn_port_t port) { return evtchn_ops->test_and_set_mask(port); } -static inline void mask_evtchn(unsigned port) +static inline void mask_evtchn(evtchn_port_t port) { return evtchn_ops->mask(port); } -static inline void unmask_evtchn(unsigned port) +static inline void unmask_evtchn(evtchn_port_t port) { return evtchn_ops->unmask(port); } diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 052b55a14ebc..6e0b1dd5573c 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -83,7 +83,7 @@ struct per_user_data { struct user_evtchn { struct rb_node node; struct per_user_data *user; - unsigned port; + evtchn_port_t port; bool enabled; }; @@ -138,7 +138,8 @@ static void del_evtchn(struct per_user_data *u, struct user_evtchn *evtchn) kfree(evtchn); } -static struct user_evtchn *find_evtchn(struct per_user_data *u, unsigned port) +static struct user_evtchn *find_evtchn(struct per_user_data *u, + evtchn_port_t port) { struct rb_node *node = u->evtchns.rb_node; @@ -163,7 +164,7 @@ static irqreturn_t evtchn_interrupt(int irq, void *data) struct per_user_data *u = evtchn->user; WARN(!evtchn->enabled, - "Interrupt for port %d, but apparently not enabled; per-user %p\n", + "Interrupt for port %u, but apparently not enabled; per-user %p\n", evtchn->port, u); disable_irq_nosync(irq); @@ -286,7 +287,7 @@ static ssize_t evtchn_write(struct file *file, const char __user *buf, mutex_lock(&u->bind_mutex); for (i = 0; i < (count/sizeof(evtchn_port_t)); i++) { - unsigned port = kbuf[i]; + evtchn_port_t port = kbuf[i]; struct user_evtchn *evtchn; evtchn = find_evtchn(u, port); @@ -361,7 +362,7 @@ static int evtchn_resize_ring(struct per_user_data *u) return 0; } -static int evtchn_bind_to_user(struct per_user_data *u, int port) +static int evtchn_bind_to_user(struct per_user_data *u, evtchn_port_t port) { struct user_evtchn *evtchn; struct evtchn_close close; @@ -423,7 +424,7 @@ static void evtchn_unbind_from_user(struct per_user_data *u, static DEFINE_PER_CPU(int, bind_last_selected_cpu); -static void evtchn_bind_interdom_next_vcpu(int evtchn) +static void evtchn_bind_interdom_next_vcpu(evtchn_port_t evtchn) { unsigned int selected_cpu, irq; struct irq_desc *desc; diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h index 9a3960ecff6c..20d7d059dadb 100644 --- a/drivers/xen/gntdev-common.h +++ b/drivers/xen/gntdev-common.h @@ -15,6 +15,7 @@ #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/types.h> +#include <xen/interface/event_channel.h> struct gntdev_dmabuf_priv; @@ -38,7 +39,7 @@ struct gntdev_unmap_notify { int flags; /* Address relative to the start of the gntdev_grant_map. */ int addr; - int event; + evtchn_port_t event; }; struct gntdev_grant_map { diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 0258415ca0b2..50651e566564 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -652,7 +652,7 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u) struct gntdev_grant_map *map; int rc; int out_flags; - unsigned int out_event; + evtchn_port_t out_event; if (copy_from_user(&op, u, sizeof(op))) return -EFAULT; diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index c57c71b7d53d..cf4ce3e9358d 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -300,7 +300,7 @@ static struct sock_mapping *pvcalls_new_active_socket( struct pvcalls_fedata *fedata, uint64_t id, grant_ref_t ref, - uint32_t evtchn, + evtchn_port_t evtchn, struct socket *sock) { int ret; @@ -905,7 +905,8 @@ static irqreturn_t pvcalls_back_conn_event(int irq, void *sock_map) static int backend_connect(struct xenbus_device *dev) { - int err, evtchn; + int err; + evtchn_port_t evtchn; grant_ref_t ring_ref; struct pvcalls_fedata *fedata = NULL; diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 57592a6b5c9e..b43b5595e988 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -368,12 +368,12 @@ out: return -ENOMEM; } -static int create_active(struct sock_mapping *map, int *evtchn) +static int create_active(struct sock_mapping *map, evtchn_port_t *evtchn) { void *bytes; int ret = -ENOMEM, irq = -1, i; - *evtchn = -1; + *evtchn = 0; init_waitqueue_head(&map->active.inflight_conn_req); bytes = map->active.data.in; @@ -404,7 +404,7 @@ static int create_active(struct sock_mapping *map, int *evtchn) return 0; out_error: - if (*evtchn >= 0) + if (*evtchn > 0) xenbus_free_evtchn(pvcalls_front_dev, *evtchn); return ret; } @@ -415,7 +415,8 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, struct pvcalls_bedata *bedata; struct sock_mapping *map = NULL; struct xen_pvcalls_request *req; - int notify, req_id, ret, evtchn; + int notify, req_id, ret; + evtchn_port_t evtchn; if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM) return -EOPNOTSUPP; @@ -765,7 +766,8 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) struct sock_mapping *map; struct sock_mapping *map2 = NULL; struct xen_pvcalls_request *req; - int notify, req_id, ret, evtchn, nonblock; + int notify, req_id, ret, nonblock; + evtchn_port_t evtchn; map = pvcalls_enter_sock(sock); if (IS_ERR(map)) @@ -1125,7 +1127,8 @@ static int pvcalls_front_remove(struct xenbus_device *dev) static int pvcalls_front_probe(struct xenbus_device *dev, const struct xenbus_device_id *id) { - int ret = -ENOMEM, evtchn, i; + int ret = -ENOMEM, i; + evtchn_port_t evtchn; unsigned int max_page_order, function_calls, len; char *versions; grant_ref_t gref_head = 0; diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index 833b2d2c4318..f2115587855f 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -105,13 +105,13 @@ static void free_pdev(struct xen_pcibk_device *pdev) } static int xen_pcibk_do_attach(struct xen_pcibk_device *pdev, int gnt_ref, - int remote_evtchn) + evtchn_port_t remote_evtchn) { int err = 0; void *vaddr; dev_dbg(&pdev->xdev->dev, - "Attaching to frontend resources - gnt_ref=%d evtchn=%d\n", + "Attaching to frontend resources - gnt_ref=%d evtchn=%u\n", gnt_ref, remote_evtchn); err = xenbus_map_ring_valloc(pdev->xdev, &gnt_ref, 1, &vaddr); @@ -142,7 +142,8 @@ out: static int xen_pcibk_attach(struct xen_pcibk_device *pdev) { int err = 0; - int gnt_ref, remote_evtchn; + int gnt_ref; + evtchn_port_t remote_evtchn; char *magic = NULL; diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index ba0942e481bc..75c0a2e9a6db 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -854,7 +854,8 @@ unmap_page: static int scsiback_map(struct vscsibk_info *info) { struct xenbus_device *dev = info->dev; - unsigned int ring_ref, evtchn; + unsigned int ring_ref; + evtchn_port_t evtchn; int err; err = xenbus_gather(XBT_NIL, dev->otherend, diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 31eb822ac313..385843256865 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -391,7 +391,7 @@ EXPORT_SYMBOL_GPL(xenbus_grant_ring); * error, the device will switch to XenbusStateClosing, and the error will be * saved in the store. */ -int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port) +int xenbus_alloc_evtchn(struct xenbus_device *dev, evtchn_port_t *port) { struct evtchn_alloc_unbound alloc_unbound; int err; @@ -414,7 +414,7 @@ EXPORT_SYMBOL_GPL(xenbus_alloc_evtchn); /** * Free an existing event channel. Returns 0 on success or -errno on error. */ -int xenbus_free_evtchn(struct xenbus_device *dev, int port) +int xenbus_free_evtchn(struct xenbus_device *dev, evtchn_port_t port) { struct evtchn_close close; int err; @@ -423,7 +423,7 @@ int xenbus_free_evtchn(struct xenbus_device *dev, int port) err = HYPERVISOR_event_channel_op(EVTCHNOP_close, &close); if (err) - xenbus_dev_error(dev, err, "freeing event channel %d", port); + xenbus_dev_error(dev, err, "freeing event channel %u", port); return err; } |