diff options
Diffstat (limited to 'drivers/s390/crypto/vfio_ap_ops.c')
| -rw-r--r-- | drivers/s390/crypto/vfio_ap_ops.c | 1069 |
1 files changed, 831 insertions, 238 deletions
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 9c01957e56b3..48da32ad0493 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -30,10 +30,13 @@ #define AP_QUEUE_UNASSIGNED "unassigned" #define AP_QUEUE_IN_USE "in use" -static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable); +#define AP_RESET_INTERVAL 20 /* Reset sleep interval (20ms) */ + +static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev); +static int vfio_ap_mdev_reset_qlist(struct list_head *qlist); static struct vfio_ap_queue *vfio_ap_find_queue(int apqn); static const struct vfio_device_ops vfio_ap_matrix_dev_ops; -static int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q, unsigned int retry); +static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q); /** * get_update_locks_for_kvm: Acquire the locks required to dynamically update a @@ -298,7 +301,7 @@ static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q) */ static struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q) { - struct ap_qirq_ctrl aqic_gisa = {}; + union ap_qirq_ctrl aqic_gisa = { .value = 0 }; struct ap_queue_status status; int retries = 5; @@ -349,13 +352,48 @@ static int vfio_ap_validate_nib(struct kvm_vcpu *vcpu, dma_addr_t *nib) { *nib = vcpu->run->s.regs.gprs[2]; - if (kvm_is_error_hva(gfn_to_hva(vcpu->kvm, *nib >> PAGE_SHIFT))) + if (!*nib) + return -EINVAL; + if (!kvm_s390_is_gpa_in_memslot(vcpu->kvm, *nib)) return -EINVAL; return 0; } /** + * ensure_nib_shared() - Ensure the address of the NIB is secure and shared + * @addr: the physical (absolute) address of the NIB + * + * This function checks whether the NIB page, which has been pinned with + * vfio_pin_pages(), is a shared page belonging to a secure guest. + * + * It will call uv_pin_shared() on it; if the page was already pinned shared + * (i.e. if the NIB belongs to a secure guest and is shared), then 0 + * (success) is returned. If the NIB was not shared, vfio_pin_pages() had + * exported it and now it does not belong to the secure guest anymore. In + * that case, an error is returned. + * + * Context: the NIB (at physical address @addr) has to be pinned with + * vfio_pin_pages() before calling this function. + * + * Return: 0 in case of success, otherwise an error < 0. + */ +static int ensure_nib_shared(unsigned long addr) +{ + /* + * The nib has to be located in shared storage since guest and + * host access it. vfio_pin_pages() will do a pin shared and + * if that fails (possibly because it's not a shared page) it + * calls export. We try to do a second pin shared here so that + * the UV gives us an error code if we try to pin a non-shared + * page. + * + * If the page is already pinned shared the UV will return a success. + */ + return uv_pin_shared(addr); +} + +/** * vfio_ap_irq_enable - Enable Interruption for a APQN * * @q: the vfio_ap_queue holding AQIC parameters @@ -367,8 +405,8 @@ static int vfio_ap_validate_nib(struct kvm_vcpu *vcpu, dma_addr_t *nib) * Register the guest ISC to GIB interface and retrieve the * host ISC to issue the host side PQAP/AQIC * - * Response.status may be set to AP_RESPONSE_INVALID_ADDRESS in case the - * vfio_pin_pages failed. + * status.response_code may be set to AP_RESPONSE_INVALID_ADDRESS in case the + * vfio_pin_pages or kvm_s390_gisc_register failed. * * Otherwise return the ap_queue_status returned by the ap_aqic(), * all retry handling will be done by the guest. @@ -379,7 +417,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, int isc, struct kvm_vcpu *vcpu) { - struct ap_qirq_ctrl aqic_gisa = {}; + union ap_qirq_ctrl aqic_gisa = { .value = 0 }; struct ap_queue_status status = {}; struct kvm_s390_gisa *gisa; struct page *h_page; @@ -398,6 +436,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, return status; } + /* The pin will probably be successful even if the NIB was not shared */ ret = vfio_pin_pages(&q->matrix_mdev->vdev, nib, 1, IOMMU_READ | IOMMU_WRITE, &h_page); switch (ret) { @@ -418,12 +457,21 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, h_nib = page_to_phys(h_page) | (nib & ~PAGE_MASK); aqic_gisa.gisc = isc; + /* NIB in non-shared storage is a rc 6 for PV guests */ + if (kvm_s390_pv_cpu_is_protected(vcpu) && + ensure_nib_shared(h_nib & PAGE_MASK)) { + vfio_unpin_pages(&q->matrix_mdev->vdev, nib, 1); + status.response_code = AP_RESPONSE_INVALID_ADDRESS; + return status; + } + nisc = kvm_s390_gisc_register(kvm, isc); if (nisc < 0) { VFIO_AP_DBF_WARN("%s: gisc registration failed: nisc=%d, isc=%d, apqn=%#04x\n", __func__, nisc, isc, q->apqn); - status.response_code = AP_RESPONSE_INVALID_GISA; + vfio_unpin_pages(&q->matrix_mdev->vdev, nib, 1); + status.response_code = AP_RESPONSE_INVALID_ADDRESS; return status; } @@ -440,9 +488,12 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, q->saved_isc = isc; break; case AP_RESPONSE_OTHERWISE_CHANGED: - /* We could not modify IRQ setings: clear new configuration */ + /* We could not modify IRQ settings: clear new configuration */ + ret = kvm_s390_gisc_unregister(kvm, isc); + if (ret) + VFIO_AP_DBF_WARN("%s: kvm_s390_gisc_unregister: rc=%d isc=%d, apqn=%#04x\n", + __func__, ret, isc, q->apqn); vfio_unpin_pages(&q->matrix_mdev->vdev, nib, 1); - kvm_s390_gisc_unregister(kvm, isc); break; default: pr_warn("%s: apqn %04x: response: %02x\n", __func__, q->apqn, @@ -519,7 +570,7 @@ static void vfio_ap_le_guid_to_be_uuid(guid_t *guid, unsigned long *uuid) * Response.status may be set to following Response Code: * - AP_RESPONSE_Q_NOT_AVAIL: if the queue is not available * - AP_RESPONSE_DECONFIGURED: if the queue is not configured - * - AP_RESPONSE_NORMAL (0) : in case of successs + * - AP_RESPONSE_NORMAL (0) : in case of success * Check vfio_ap_setirq() and vfio_ap_clrirq() for other possible RC. * We take the matrix_dev lock to ensure serialization on queues and * mediated device access. @@ -594,18 +645,27 @@ out_unlock: static void vfio_ap_matrix_init(struct ap_config_info *info, struct ap_matrix *matrix) { - matrix->apm_max = info->apxa ? info->Na : 63; - matrix->aqm_max = info->apxa ? info->Nd : 15; - matrix->adm_max = info->apxa ? info->Nd : 15; + matrix->apm_max = info->apxa ? info->na : 63; + matrix->aqm_max = info->apxa ? info->nd : 15; + matrix->adm_max = info->apxa ? info->nd : 15; +} + +static void signal_guest_ap_cfg_changed(struct ap_matrix_mdev *matrix_mdev) +{ + if (matrix_mdev->cfg_chg_trigger) + eventfd_signal(matrix_mdev->cfg_chg_trigger); } static void vfio_ap_mdev_update_guest_apcb(struct ap_matrix_mdev *matrix_mdev) { - if (matrix_mdev->kvm) + if (matrix_mdev->kvm) { kvm_arch_crypto_set_masks(matrix_mdev->kvm, matrix_mdev->shadow_apcb.apm, matrix_mdev->shadow_apcb.aqm, matrix_mdev->shadow_apcb.adm); + + signal_guest_ap_cfg_changed(matrix_mdev); + } } static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev) @@ -620,6 +680,21 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev) AP_DOMAINS); } +static bool _queue_passable(struct vfio_ap_queue *q) +{ + if (!q) + return false; + + switch (q->reset_status.response_code) { + case AP_RESPONSE_NORMAL: + case AP_RESPONSE_DECONFIGURED: + case AP_RESPONSE_CHECKSTOPPED: + return true; + default: + return false; + } +} + /* * vfio_ap_mdev_filter_matrix - filter the APQNs assigned to the matrix mdev * to ensure no queue devices are passed through to @@ -627,26 +702,32 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev) * device driver. * * @matrix_mdev: the matrix mdev whose matrix is to be filtered. + * @apm_filtered: a 256-bit bitmap for storing the APIDs filtered from the + * guest's AP configuration that are still in the host's AP + * configuration. * * Note: If an APQN referencing a queue device that is not bound to the vfio_ap * driver, its APID will be filtered from the guest's APCB. The matrix * structure precludes filtering an individual APQN, so its APID will be - * filtered. + * filtered. Consequently, all queues associated with the adapter that + * are in the host's AP configuration must be reset. If queues are + * subsequently made available again to the guest, they should re-appear + * in a reset state * * Return: a boolean value indicating whether the KVM guest's APCB was changed * by the filtering or not. */ -static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm, - struct ap_matrix_mdev *matrix_mdev) +static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev, + unsigned long *apm_filtered) { unsigned long apid, apqi, apqn; DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES); DECLARE_BITMAP(prev_shadow_aqm, AP_DOMAINS); - struct vfio_ap_queue *q; bitmap_copy(prev_shadow_apm, matrix_mdev->shadow_apcb.apm, AP_DEVICES); bitmap_copy(prev_shadow_aqm, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS); vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->shadow_apcb); + bitmap_clear(apm_filtered, 0, AP_DEVICES); /* * Copy the adapters, domains and control domains to the shadow_apcb @@ -658,8 +739,9 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm, bitmap_and(matrix_mdev->shadow_apcb.aqm, matrix_mdev->matrix.aqm, (unsigned long *)matrix_dev->info.aqm, AP_DOMAINS); - for_each_set_bit_inv(apid, apm, AP_DEVICES) { - for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) { + for_each_set_bit_inv(apid, matrix_mdev->shadow_apcb.apm, AP_DEVICES) { + for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm, + AP_DOMAINS) { /* * If the APQN is not bound to the vfio_ap device * driver, then we can't assign it to the guest's @@ -669,10 +751,17 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm, * hardware device. */ apqn = AP_MKQID(apid, apqi); - q = vfio_ap_mdev_get_queue(matrix_mdev, apqn); - if (!q || q->reset_rc) { - clear_bit_inv(apid, - matrix_mdev->shadow_apcb.apm); + if (!_queue_passable(vfio_ap_mdev_get_queue(matrix_mdev, apqn))) { + clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm); + + /* + * If the adapter was previously plugged into + * the guest, let's let the caller know that + * the APID was filtered. + */ + if (test_bit_inv(apid, prev_shadow_apm)) + set_bit_inv(apid, apm_filtered); + break; } } @@ -711,6 +800,8 @@ static int vfio_ap_mdev_probe(struct mdev_device *mdev) ret = vfio_register_emulated_iommu_dev(&matrix_mdev->vdev); if (ret) goto err_put_vdev; + matrix_mdev->req_trigger = NULL; + matrix_mdev->cfg_chg_trigger = NULL; dev_set_drvdata(&mdev->dev, matrix_mdev); mutex_lock(&matrix_dev->mdevs_lock); list_add(&matrix_mdev->node, &matrix_dev->mdev_list); @@ -725,10 +816,11 @@ err_put_vdev: static void vfio_ap_mdev_link_queue(struct ap_matrix_mdev *matrix_mdev, struct vfio_ap_queue *q) { - if (q) { - q->matrix_mdev = matrix_mdev; - hash_add(matrix_mdev->qtable.queues, &q->mdev_qnode, q->apqn); - } + if (!q || vfio_ap_mdev_get_queue(matrix_mdev, q->apqn)) + return; + + q->matrix_mdev = matrix_mdev; + hash_add(matrix_mdev->qtable.queues, &q->mdev_qnode, q->apqn); } static void vfio_ap_mdev_link_apqn(struct ap_matrix_mdev *matrix_mdev, int apqn) @@ -773,7 +865,7 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev) mutex_lock(&matrix_dev->guests_lock); mutex_lock(&matrix_dev->mdevs_lock); - vfio_ap_mdev_reset_queues(&matrix_mdev->qtable); + vfio_ap_mdev_reset_queues(matrix_mdev); vfio_ap_mdev_unlink_fr_queues(matrix_mdev); list_del(&matrix_mdev->node); mutex_unlock(&matrix_dev->mdevs_lock); @@ -781,48 +873,66 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev) vfio_put_device(&matrix_mdev->vdev); } -#define MDEV_SHARING_ERR "Userspace may not re-assign queue %02lx.%04lx " \ - "already assigned to %s" +#define MDEV_SHARING_ERR "Userspace may not assign queue %02lx.%04lx to mdev: already assigned to %s" -static void vfio_ap_mdev_log_sharing_err(struct ap_matrix_mdev *matrix_mdev, - unsigned long *apm, - unsigned long *aqm) +#define MDEV_IN_USE_ERR "Can not reserve queue %02lx.%04lx for host driver: in use by mdev" + +static void vfio_ap_mdev_log_sharing_err(struct ap_matrix_mdev *assignee, + struct ap_matrix_mdev *assigned_to, + unsigned long *apm, unsigned long *aqm) +{ + unsigned long apid, apqi; + + for_each_set_bit_inv(apid, apm, AP_DEVICES) { + for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) { + dev_warn(mdev_dev(assignee->mdev), MDEV_SHARING_ERR, + apid, apqi, dev_name(mdev_dev(assigned_to->mdev))); + } + } +} + +static void vfio_ap_mdev_log_in_use_err(struct ap_matrix_mdev *assignee, + unsigned long *apm, unsigned long *aqm) { unsigned long apid, apqi; - const struct device *dev = mdev_dev(matrix_mdev->mdev); - const char *mdev_name = dev_name(dev); - for_each_set_bit_inv(apid, apm, AP_DEVICES) + for_each_set_bit_inv(apid, apm, AP_DEVICES) { for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) - dev_warn(dev, MDEV_SHARING_ERR, apid, apqi, mdev_name); + dev_warn(mdev_dev(assignee->mdev), MDEV_IN_USE_ERR, apid, apqi); + } } /** * vfio_ap_mdev_verify_no_sharing - verify APQNs are not shared by matrix mdevs * + * @assignee: the matrix mdev to which @mdev_apm and @mdev_aqm are being + * assigned; or, NULL if this function was called by the AP bus + * driver in_use callback to verify none of the APQNs being reserved + * for the host device driver are in use by a vfio_ap mediated device * @mdev_apm: mask indicating the APIDs of the APQNs to be verified * @mdev_aqm: mask indicating the APQIs of the APQNs to be verified * - * Verifies that each APQN derived from the Cartesian product of a bitmap of - * AP adapter IDs and AP queue indexes is not configured for any matrix - * mediated device. AP queue sharing is not allowed. + * Verifies that each APQN derived from the Cartesian product of APIDs + * represented by the bits set in @mdev_apm and the APQIs of the bits set in + * @mdev_aqm is not assigned to a mediated device other than the mdev to which + * the APQN is being assigned (@assignee). AP queue sharing is not allowed. * * Return: 0 if the APQNs are not shared; otherwise return -EADDRINUSE. */ -static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm, +static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *assignee, + unsigned long *mdev_apm, unsigned long *mdev_aqm) { - struct ap_matrix_mdev *matrix_mdev; + struct ap_matrix_mdev *assigned_to; DECLARE_BITMAP(apm, AP_DEVICES); DECLARE_BITMAP(aqm, AP_DOMAINS); - list_for_each_entry(matrix_mdev, &matrix_dev->mdev_list, node) { + list_for_each_entry(assigned_to, &matrix_dev->mdev_list, node) { /* - * If the input apm and aqm are fields of the matrix_mdev - * object, then move on to the next matrix_mdev. + * If the mdev to which the mdev_apm and mdev_aqm is being + * assigned is the same as the mdev being verified */ - if (mdev_apm == matrix_mdev->matrix.apm && - mdev_aqm == matrix_mdev->matrix.aqm) + if (assignee == assigned_to) continue; memset(apm, 0, sizeof(apm)); @@ -832,15 +942,16 @@ static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm, * We work on full longs, as we can only exclude the leftover * bits in non-inverse order. The leftover is all zeros. */ - if (!bitmap_and(apm, mdev_apm, matrix_mdev->matrix.apm, - AP_DEVICES)) + if (!bitmap_and(apm, mdev_apm, assigned_to->matrix.apm, AP_DEVICES)) continue; - if (!bitmap_and(aqm, mdev_aqm, matrix_mdev->matrix.aqm, - AP_DOMAINS)) + if (!bitmap_and(aqm, mdev_aqm, assigned_to->matrix.aqm, AP_DOMAINS)) continue; - vfio_ap_mdev_log_sharing_err(matrix_mdev, apm, aqm); + if (assignee) + vfio_ap_mdev_log_sharing_err(assignee, assigned_to, apm, aqm); + else + vfio_ap_mdev_log_in_use_err(assigned_to, apm, aqm); return -EADDRINUSE; } @@ -857,7 +968,7 @@ static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm, * * Return: One of the following values: * o the error returned from the ap_apqn_in_matrix_owned_by_def_drv() function, - * most likely -EBUSY indicating the ap_perms_mutex lock is already held. + * most likely -EBUSY indicating the ap_attr_mutex lock is already held. * o EADDRNOTAVAIL if an APQN assigned to @matrix_mdev is reserved for the * zcrypt default driver. * o EADDRINUSE if an APQN assigned to @matrix_mdev is assigned to another mdev @@ -869,7 +980,8 @@ static int vfio_ap_mdev_validate_masks(struct ap_matrix_mdev *matrix_mdev) matrix_mdev->matrix.aqm)) return -EADDRNOTAVAIL; - return vfio_ap_mdev_verify_no_sharing(matrix_mdev->matrix.apm, + return vfio_ap_mdev_verify_no_sharing(matrix_mdev, + matrix_mdev->matrix.apm, matrix_mdev->matrix.aqm); } @@ -883,6 +995,47 @@ static void vfio_ap_mdev_link_adapter(struct ap_matrix_mdev *matrix_mdev, AP_MKQID(apid, apqi)); } +static void collect_queues_to_reset(struct ap_matrix_mdev *matrix_mdev, + unsigned long apid, + struct list_head *qlist) +{ + struct vfio_ap_queue *q; + unsigned long apqi; + + for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS) { + q = vfio_ap_mdev_get_queue(matrix_mdev, AP_MKQID(apid, apqi)); + if (q) + list_add_tail(&q->reset_qnode, qlist); + } +} + +static void reset_queues_for_apid(struct ap_matrix_mdev *matrix_mdev, + unsigned long apid) +{ + struct list_head qlist; + + INIT_LIST_HEAD(&qlist); + collect_queues_to_reset(matrix_mdev, apid, &qlist); + vfio_ap_mdev_reset_qlist(&qlist); +} + +static int reset_queues_for_apids(struct ap_matrix_mdev *matrix_mdev, + unsigned long *apm_reset) +{ + struct list_head qlist; + unsigned long apid; + + if (bitmap_empty(apm_reset, AP_DEVICES)) + return 0; + + INIT_LIST_HEAD(&qlist); + + for_each_set_bit_inv(apid, apm_reset, AP_DEVICES) + collect_queues_to_reset(matrix_mdev, apid, &qlist); + + return vfio_ap_mdev_reset_qlist(&qlist); +} + /** * assign_adapter_store - parses the APID from @buf and sets the * corresponding bit in the mediated matrix device's APM @@ -923,10 +1076,10 @@ static ssize_t assign_adapter_store(struct device *dev, { int ret; unsigned long apid; - DECLARE_BITMAP(apm_delta, AP_DEVICES); + DECLARE_BITMAP(apm_filtered, AP_DEVICES); struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev); - mutex_lock(&ap_perms_mutex); + mutex_lock(&ap_attr_mutex); get_update_locks_for_mdev(matrix_mdev); ret = kstrtoul(buf, 0, &apid); @@ -952,17 +1105,16 @@ static ssize_t assign_adapter_store(struct device *dev, } vfio_ap_mdev_link_adapter(matrix_mdev, apid); - memset(apm_delta, 0, sizeof(apm_delta)); - set_bit_inv(apid, apm_delta); - if (vfio_ap_mdev_filter_matrix(apm_delta, - matrix_mdev->matrix.aqm, matrix_mdev)) + if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) { vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apids(matrix_mdev, apm_filtered); + } ret = count; done: release_update_locks_for_mdev(matrix_mdev); - mutex_unlock(&ap_perms_mutex); + mutex_unlock(&ap_attr_mutex); return ret; } @@ -988,11 +1140,12 @@ static struct vfio_ap_queue * adapter was assigned. * @matrix_mdev: the matrix mediated device to which the adapter was assigned. * @apid: the APID of the unassigned adapter. - * @qtable: table for storing queues associated with unassigned adapter. + * @qlist: list for storing queues associated with unassigned adapter that + * need to be reset. */ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev, unsigned long apid, - struct ap_queue_table *qtable) + struct list_head *qlist) { unsigned long apqi; struct vfio_ap_queue *q; @@ -1000,38 +1153,53 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev, for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, AP_DOMAINS) { q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi); - if (q && qtable) { + if (q && qlist) { if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) && test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) - hash_add(qtable->queues, &q->mdev_qnode, - q->apqn); + list_add_tail(&q->reset_qnode, qlist); } } } -static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev, - unsigned long apid) +static void vfio_ap_mdev_hot_unplug_adapters(struct ap_matrix_mdev *matrix_mdev, + unsigned long *apids) { - int loop_cursor; - struct vfio_ap_queue *q; - struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL); + struct vfio_ap_queue *q, *tmpq; + struct list_head qlist; + unsigned long apid; + bool apcb_update = false; - hash_init(qtable->queues); - vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, qtable); + INIT_LIST_HEAD(&qlist); - if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm)) { - clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm); - vfio_ap_mdev_update_guest_apcb(matrix_mdev); + for_each_set_bit_inv(apid, apids, AP_DEVICES) { + vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, &qlist); + + if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm)) { + clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm); + apcb_update = true; + } } - vfio_ap_mdev_reset_queues(qtable); + /* Only update apcb if needed to avoid impacting guest */ + if (apcb_update) + vfio_ap_mdev_update_guest_apcb(matrix_mdev); - hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) { + vfio_ap_mdev_reset_qlist(&qlist); + + list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) { vfio_ap_unlink_mdev_fr_queue(q); - hash_del(&q->mdev_qnode); + list_del(&q->reset_qnode); } +} + +static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev, + unsigned long apid) +{ + DECLARE_BITMAP(apids, AP_DEVICES); - kfree(qtable); + bitmap_zero(apids, AP_DEVICES); + set_bit_inv(apid, apids); + vfio_ap_mdev_hot_unplug_adapters(matrix_mdev, apids); } /** @@ -1132,10 +1300,10 @@ static ssize_t assign_domain_store(struct device *dev, { int ret; unsigned long apqi; - DECLARE_BITMAP(aqm_delta, AP_DOMAINS); + DECLARE_BITMAP(apm_filtered, AP_DEVICES); struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev); - mutex_lock(&ap_perms_mutex); + mutex_lock(&ap_attr_mutex); get_update_locks_for_mdev(matrix_mdev); ret = kstrtoul(buf, 0, &apqi); @@ -1161,17 +1329,16 @@ static ssize_t assign_domain_store(struct device *dev, } vfio_ap_mdev_link_domain(matrix_mdev, apqi); - memset(aqm_delta, 0, sizeof(aqm_delta)); - set_bit_inv(apqi, aqm_delta); - if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm, aqm_delta, - matrix_mdev)) + if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) { vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apids(matrix_mdev, apm_filtered); + } ret = count; done: release_update_locks_for_mdev(matrix_mdev); - mutex_unlock(&ap_perms_mutex); + mutex_unlock(&ap_attr_mutex); return ret; } @@ -1179,7 +1346,7 @@ static DEVICE_ATTR_WO(assign_domain); static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev, unsigned long apqi, - struct ap_queue_table *qtable) + struct list_head *qlist) { unsigned long apid; struct vfio_ap_queue *q; @@ -1187,38 +1354,53 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev, for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, AP_DEVICES) { q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi); - if (q && qtable) { + if (q && qlist) { if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) && test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) - hash_add(qtable->queues, &q->mdev_qnode, - q->apqn); + list_add_tail(&q->reset_qnode, qlist); } } } -static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev, - unsigned long apqi) +static void vfio_ap_mdev_hot_unplug_domains(struct ap_matrix_mdev *matrix_mdev, + unsigned long *apqis) { - int loop_cursor; - struct vfio_ap_queue *q; - struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL); + struct vfio_ap_queue *q, *tmpq; + struct list_head qlist; + unsigned long apqi; + bool apcb_update = false; - hash_init(qtable->queues); - vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, qtable); + INIT_LIST_HEAD(&qlist); - if (test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) { - clear_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm); - vfio_ap_mdev_update_guest_apcb(matrix_mdev); + for_each_set_bit_inv(apqi, apqis, AP_DOMAINS) { + vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, &qlist); + + if (test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) { + clear_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm); + apcb_update = true; + } } - vfio_ap_mdev_reset_queues(qtable); + /* Only update apcb if needed to avoid impacting guest */ + if (apcb_update) + vfio_ap_mdev_update_guest_apcb(matrix_mdev); + + vfio_ap_mdev_reset_qlist(&qlist); - hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) { + list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) { vfio_ap_unlink_mdev_fr_queue(q); - hash_del(&q->mdev_qnode); + list_del(&q->reset_qnode); } +} - kfree(qtable); +static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev, + unsigned long apqi) +{ + DECLARE_BITMAP(apqis, AP_DOMAINS); + + bitmap_zero(apqis, AP_DEVICES); + set_bit_inv(apqi, apqis); + vfio_ap_mdev_hot_unplug_domains(matrix_mdev, apqis); } /** @@ -1381,18 +1563,13 @@ static ssize_t control_domains_show(struct device *dev, char *buf) { unsigned long id; - int nchars = 0; - int n; - char *bufpos = buf; struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev); unsigned long max_domid = matrix_mdev->matrix.adm_max; + int nchars = 0; mutex_lock(&matrix_dev->mdevs_lock); - for_each_set_bit_inv(id, matrix_mdev->matrix.adm, max_domid + 1) { - n = sprintf(bufpos, "%04lx\n", id); - bufpos += n; - nchars += n; - } + for_each_set_bit_inv(id, matrix_mdev->matrix.adm, max_domid + 1) + nchars += sysfs_emit_at(buf, nchars, "%04lx\n", id); mutex_unlock(&matrix_dev->mdevs_lock); return nchars; @@ -1401,7 +1578,6 @@ static DEVICE_ATTR_RO(control_domains); static ssize_t vfio_ap_mdev_matrix_show(struct ap_matrix *matrix, char *buf) { - char *bufpos = buf; unsigned long apid; unsigned long apqi; unsigned long apid1; @@ -1409,33 +1585,21 @@ static ssize_t vfio_ap_mdev_matrix_show(struct ap_matrix *matrix, char *buf) unsigned long napm_bits = matrix->apm_max + 1; unsigned long naqm_bits = matrix->aqm_max + 1; int nchars = 0; - int n; apid1 = find_first_bit_inv(matrix->apm, napm_bits); apqi1 = find_first_bit_inv(matrix->aqm, naqm_bits); if ((apid1 < napm_bits) && (apqi1 < naqm_bits)) { for_each_set_bit_inv(apid, matrix->apm, napm_bits) { - for_each_set_bit_inv(apqi, matrix->aqm, - naqm_bits) { - n = sprintf(bufpos, "%02lx.%04lx\n", apid, - apqi); - bufpos += n; - nchars += n; - } + for_each_set_bit_inv(apqi, matrix->aqm, naqm_bits) + nchars += sysfs_emit_at(buf, nchars, "%02lx.%04lx\n", apid, apqi); } } else if (apid1 < napm_bits) { - for_each_set_bit_inv(apid, matrix->apm, napm_bits) { - n = sprintf(bufpos, "%02lx.\n", apid); - bufpos += n; - nchars += n; - } + for_each_set_bit_inv(apid, matrix->apm, napm_bits) + nchars += sysfs_emit_at(buf, nchars, "%02lx.\n", apid); } else if (apqi1 < naqm_bits) { - for_each_set_bit_inv(apqi, matrix->aqm, naqm_bits) { - n = sprintf(bufpos, ".%04lx\n", apqi); - bufpos += n; - nchars += n; - } + for_each_set_bit_inv(apqi, matrix->aqm, naqm_bits) + nchars += sysfs_emit_at(buf, nchars, ".%04lx\n", apqi); } return nchars; @@ -1469,6 +1633,158 @@ static ssize_t guest_matrix_show(struct device *dev, } static DEVICE_ATTR_RO(guest_matrix); +static ssize_t write_ap_bitmap(unsigned long *bitmap, char *buf, int offset, char sep) +{ + return sysfs_emit_at(buf, offset, "0x%016lx%016lx%016lx%016lx%c", + bitmap[0], bitmap[1], bitmap[2], bitmap[3], sep); +} + +static ssize_t ap_config_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev); + int idx = 0; + + idx += write_ap_bitmap(matrix_mdev->matrix.apm, buf, idx, ','); + idx += write_ap_bitmap(matrix_mdev->matrix.aqm, buf, idx, ','); + idx += write_ap_bitmap(matrix_mdev->matrix.adm, buf, idx, '\n'); + + return idx; +} + +/* Number of characters needed for a complete hex mask representing the bits in .. */ +#define AP_DEVICES_STRLEN (AP_DEVICES / 4 + 3) +#define AP_DOMAINS_STRLEN (AP_DOMAINS / 4 + 3) +#define AP_CONFIG_STRLEN (AP_DEVICES_STRLEN + 2 * AP_DOMAINS_STRLEN) + +static int parse_bitmap(char **strbufptr, unsigned long *bitmap, int nbits) +{ + char *curmask; + + curmask = strsep(strbufptr, ",\n"); + if (!curmask) + return -EINVAL; + + bitmap_clear(bitmap, 0, nbits); + return ap_hex2bitmap(curmask, bitmap, nbits); +} + +static int ap_matrix_overflow_check(struct ap_matrix_mdev *matrix_mdev) +{ + unsigned long bit; + + for_each_set_bit_inv(bit, matrix_mdev->matrix.apm, AP_DEVICES) { + if (bit > matrix_mdev->matrix.apm_max) + return -ENODEV; + } + + for_each_set_bit_inv(bit, matrix_mdev->matrix.aqm, AP_DOMAINS) { + if (bit > matrix_mdev->matrix.aqm_max) + return -ENODEV; + } + + for_each_set_bit_inv(bit, matrix_mdev->matrix.adm, AP_DOMAINS) { + if (bit > matrix_mdev->matrix.adm_max) + return -ENODEV; + } + + return 0; +} + +static void ap_matrix_copy(struct ap_matrix *dst, struct ap_matrix *src) +{ + /* This check works around false positive gcc -Wstringop-overread */ + if (!src) + return; + + bitmap_copy(dst->apm, src->apm, AP_DEVICES); + bitmap_copy(dst->aqm, src->aqm, AP_DOMAINS); + bitmap_copy(dst->adm, src->adm, AP_DOMAINS); +} + +static ssize_t ap_config_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev); + struct ap_matrix m_new, m_old, m_added, m_removed; + DECLARE_BITMAP(apm_filtered, AP_DEVICES); + unsigned long newbit; + char *newbuf, *rest; + int rc = count; + bool do_update; + + newbuf = kstrndup(buf, AP_CONFIG_STRLEN, GFP_KERNEL); + if (!newbuf) + return -ENOMEM; + rest = newbuf; + + mutex_lock(&ap_attr_mutex); + get_update_locks_for_mdev(matrix_mdev); + + /* Save old state */ + ap_matrix_copy(&m_old, &matrix_mdev->matrix); + if (parse_bitmap(&rest, m_new.apm, AP_DEVICES) || + parse_bitmap(&rest, m_new.aqm, AP_DOMAINS) || + parse_bitmap(&rest, m_new.adm, AP_DOMAINS)) { + rc = -EINVAL; + goto out; + } + + bitmap_andnot(m_removed.apm, m_old.apm, m_new.apm, AP_DEVICES); + bitmap_andnot(m_removed.aqm, m_old.aqm, m_new.aqm, AP_DOMAINS); + bitmap_andnot(m_added.apm, m_new.apm, m_old.apm, AP_DEVICES); + bitmap_andnot(m_added.aqm, m_new.aqm, m_old.aqm, AP_DOMAINS); + + /* Need new bitmaps in matrix_mdev for validation */ + ap_matrix_copy(&matrix_mdev->matrix, &m_new); + + /* Ensure new state is valid, else undo new state */ + rc = vfio_ap_mdev_validate_masks(matrix_mdev); + if (rc) { + ap_matrix_copy(&matrix_mdev->matrix, &m_old); + goto out; + } + rc = ap_matrix_overflow_check(matrix_mdev); + if (rc) { + ap_matrix_copy(&matrix_mdev->matrix, &m_old); + goto out; + } + rc = count; + + /* Need old bitmaps in matrix_mdev for unplug/unlink */ + ap_matrix_copy(&matrix_mdev->matrix, &m_old); + + /* Unlink removed adapters/domains */ + vfio_ap_mdev_hot_unplug_adapters(matrix_mdev, m_removed.apm); + vfio_ap_mdev_hot_unplug_domains(matrix_mdev, m_removed.aqm); + + /* Need new bitmaps in matrix_mdev for linking new adapters/domains */ + ap_matrix_copy(&matrix_mdev->matrix, &m_new); + + /* Link newly added adapters */ + for_each_set_bit_inv(newbit, m_added.apm, AP_DEVICES) + vfio_ap_mdev_link_adapter(matrix_mdev, newbit); + + for_each_set_bit_inv(newbit, m_added.aqm, AP_DOMAINS) + vfio_ap_mdev_link_domain(matrix_mdev, newbit); + + /* filter resources not bound to vfio-ap */ + do_update = vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered); + do_update |= vfio_ap_mdev_filter_cdoms(matrix_mdev); + + /* Apply changes to shadow apbc if things changed */ + if (do_update) { + vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apids(matrix_mdev, apm_filtered); + } +out: + release_update_locks_for_mdev(matrix_mdev); + mutex_unlock(&ap_attr_mutex); + kfree(newbuf); + return rc; +} +static DEVICE_ATTR_RW(ap_config); + static struct attribute *vfio_ap_mdev_attrs[] = { &dev_attr_assign_adapter.attr, &dev_attr_unassign_adapter.attr, @@ -1476,6 +1792,7 @@ static struct attribute *vfio_ap_mdev_attrs[] = { &dev_attr_unassign_domain.attr, &dev_attr_assign_control_domain.attr, &dev_attr_unassign_control_domain.attr, + &dev_attr_ap_config.attr, &dev_attr_control_domains.attr, &dev_attr_matrix.attr, &dev_attr_guest_matrix.attr, @@ -1573,7 +1890,7 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) get_update_locks_for_kvm(kvm); kvm_arch_crypto_clear_masks(kvm); - vfio_ap_mdev_reset_queues(&matrix_mdev->qtable); + vfio_ap_mdev_reset_queues(matrix_mdev); kvm_put_kvm(kvm); matrix_mdev->kvm = NULL; @@ -1598,80 +1915,139 @@ static struct vfio_ap_queue *vfio_ap_find_queue(int apqn) return q; } -static int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q, - unsigned int retry) +static int apq_status_check(int apqn, struct ap_queue_status *status) +{ + switch (status->response_code) { + case AP_RESPONSE_NORMAL: + case AP_RESPONSE_DECONFIGURED: + case AP_RESPONSE_CHECKSTOPPED: + return 0; + case AP_RESPONSE_RESET_IN_PROGRESS: + case AP_RESPONSE_BUSY: + return -EBUSY; + case AP_RESPONSE_ASSOC_SECRET_NOT_UNIQUE: + case AP_RESPONSE_ASSOC_FAILED: + /* + * These asynchronous response codes indicate a PQAP(AAPQ) + * instruction to associate a secret with the guest failed. All + * subsequent AP instructions will end with the asynchronous + * response code until the AP queue is reset; so, let's return + * a value indicating a reset needs to be performed again. + */ + return -EAGAIN; + default: + WARN(true, + "failed to verify reset of queue %02x.%04x: TAPQ rc=%u\n", + AP_QID_CARD(apqn), AP_QID_QUEUE(apqn), + status->response_code); + return -EIO; + } +} + +#define WAIT_MSG "Waited %dms for reset of queue %02x.%04x (%u, %u, %u)" + +static void apq_reset_check(struct work_struct *reset_work) +{ + int ret = -EBUSY, elapsed = 0; + struct ap_queue_status status; + struct vfio_ap_queue *q; + + q = container_of(reset_work, struct vfio_ap_queue, reset_work); + memcpy(&status, &q->reset_status, sizeof(status)); + while (true) { + msleep(AP_RESET_INTERVAL); + elapsed += AP_RESET_INTERVAL; + status = ap_tapq(q->apqn, NULL); + ret = apq_status_check(q->apqn, &status); + if (ret == -EIO) + return; + if (ret == -EBUSY) { + pr_notice_ratelimited(WAIT_MSG, elapsed, + AP_QID_CARD(q->apqn), + AP_QID_QUEUE(q->apqn), + status.response_code, + status.queue_empty, + status.irq_enabled); + } else { + if (q->reset_status.response_code == AP_RESPONSE_RESET_IN_PROGRESS || + q->reset_status.response_code == AP_RESPONSE_BUSY || + q->reset_status.response_code == AP_RESPONSE_STATE_CHANGE_IN_PROGRESS || + ret == -EAGAIN) { + status = ap_zapq(q->apqn, 0); + memcpy(&q->reset_status, &status, sizeof(status)); + continue; + } + if (q->saved_isc != VFIO_AP_ISC_INVALID) + vfio_ap_free_aqic_resources(q); + break; + } + } +} + +static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q) { struct ap_queue_status status; - int ret; - int retry2 = 2; if (!q) - return 0; -retry_zapq: - status = ap_zapq(q->apqn); - q->reset_rc = status.response_code; + return; + status = ap_zapq(q->apqn, 0); + memcpy(&q->reset_status, &status, sizeof(status)); switch (status.response_code) { case AP_RESPONSE_NORMAL: - ret = 0; - break; case AP_RESPONSE_RESET_IN_PROGRESS: - if (retry--) { - msleep(20); - goto retry_zapq; - } - ret = -EBUSY; + case AP_RESPONSE_BUSY: + case AP_RESPONSE_STATE_CHANGE_IN_PROGRESS: + /* + * Let's verify whether the ZAPQ completed successfully on a work queue. + */ + queue_work(system_long_wq, &q->reset_work); break; - case AP_RESPONSE_Q_NOT_AVAIL: case AP_RESPONSE_DECONFIGURED: case AP_RESPONSE_CHECKSTOPPED: - WARN_ONCE(status.irq_enabled, - "PQAP/ZAPQ for %02x.%04x failed with rc=%u while IRQ enabled", - AP_QID_CARD(q->apqn), AP_QID_QUEUE(q->apqn), - status.response_code); - ret = -EBUSY; - goto free_resources; + vfio_ap_free_aqic_resources(q); + break; default: - /* things are really broken, give up */ WARN(true, "PQAP/ZAPQ for %02x.%04x failed with invalid rc=%u\n", AP_QID_CARD(q->apqn), AP_QID_QUEUE(q->apqn), status.response_code); - return -EIO; } +} - /* wait for the reset to take effect */ - while (retry2--) { - if (status.queue_empty && !status.irq_enabled) - break; - msleep(20); - status = ap_tapq(q->apqn, NULL); - } - WARN_ONCE(retry2 <= 0, "unable to verify reset of queue %02x.%04x", - AP_QID_CARD(q->apqn), AP_QID_QUEUE(q->apqn)); +static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev) +{ + int ret = 0, loop_cursor; + struct vfio_ap_queue *q; -free_resources: - vfio_ap_free_aqic_resources(q); + hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode) + vfio_ap_mdev_reset_queue(q); + + hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode) { + flush_work(&q->reset_work); + + if (q->reset_status.response_code) + ret = -EIO; + } return ret; } -static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable) +static int vfio_ap_mdev_reset_qlist(struct list_head *qlist) { - int ret, loop_cursor, rc = 0; + int ret = 0; struct vfio_ap_queue *q; - hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) { - ret = vfio_ap_mdev_reset_queue(q, 1); - /* - * Regardless whether a queue turns out to be busy, or - * is not operational, we need to continue resetting - * the remaining queues. - */ - if (ret) - rc = ret; + list_for_each_entry(q, qlist, reset_qnode) + vfio_ap_mdev_reset_queue(q); + + list_for_each_entry(q, qlist, reset_qnode) { + flush_work(&q->reset_work); + + if (q->reset_status.response_code) + ret = -EIO; } - return rc; + return ret; } static int vfio_ap_mdev_open_device(struct vfio_device *vdev) @@ -1693,6 +2069,35 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev) vfio_ap_mdev_unset_kvm(matrix_mdev); } +static void vfio_ap_mdev_request(struct vfio_device *vdev, unsigned int count) +{ + struct device *dev = vdev->dev; + struct ap_matrix_mdev *matrix_mdev; + + matrix_mdev = container_of(vdev, struct ap_matrix_mdev, vdev); + + get_update_locks_for_mdev(matrix_mdev); + + if (matrix_mdev->kvm) { + kvm_arch_crypto_clear_masks(matrix_mdev->kvm); + signal_guest_ap_cfg_changed(matrix_mdev); + } + + if (matrix_mdev->req_trigger) { + if (!(count % 10)) + dev_notice_ratelimited(dev, + "Relaying device request to user (#%u)\n", + count); + + eventfd_signal(matrix_mdev->req_trigger); + } else if (count == 0) { + dev_notice(dev, + "No device request registered, blocked until released by user\n"); + } + + release_update_locks_for_mdev(matrix_mdev); +} + static int vfio_ap_mdev_get_device_info(unsigned long arg) { unsigned long minsz; @@ -1708,11 +2113,154 @@ static int vfio_ap_mdev_get_device_info(unsigned long arg) info.flags = VFIO_DEVICE_FLAGS_AP | VFIO_DEVICE_FLAGS_RESET; info.num_regions = 0; - info.num_irqs = 0; + info.num_irqs = VFIO_AP_NUM_IRQS; + + return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; +} + +static ssize_t vfio_ap_get_irq_info(unsigned long arg) +{ + unsigned long minsz; + struct vfio_irq_info info; + + minsz = offsetofend(struct vfio_irq_info, count); + + if (copy_from_user(&info, (void __user *)arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz || info.index >= VFIO_AP_NUM_IRQS) + return -EINVAL; + + switch (info.index) { + case VFIO_AP_REQ_IRQ_INDEX: + info.count = 1; + info.flags = VFIO_IRQ_INFO_EVENTFD; + break; + case VFIO_AP_CFG_CHG_IRQ_INDEX: + info.count = 1; + info.flags = VFIO_IRQ_INFO_EVENTFD; + break; + default: + return -EINVAL; + } return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; } +static int vfio_ap_irq_set_init(struct vfio_irq_set *irq_set, unsigned long arg) +{ + int ret; + size_t data_size; + unsigned long minsz; + + minsz = offsetofend(struct vfio_irq_set, count); + + if (copy_from_user(irq_set, (void __user *)arg, minsz)) + return -EFAULT; + + ret = vfio_set_irqs_validate_and_prepare(irq_set, 1, VFIO_AP_NUM_IRQS, + &data_size); + if (ret) + return ret; + + if (!(irq_set->flags & VFIO_IRQ_SET_ACTION_TRIGGER)) + return -EINVAL; + + return 0; +} + +static int vfio_ap_set_request_irq(struct ap_matrix_mdev *matrix_mdev, + unsigned long arg) +{ + s32 fd; + void __user *data; + unsigned long minsz; + struct eventfd_ctx *req_trigger; + + minsz = offsetofend(struct vfio_irq_set, count); + data = (void __user *)(arg + minsz); + + if (get_user(fd, (s32 __user *)data)) + return -EFAULT; + + if (fd == -1) { + if (matrix_mdev->req_trigger) + eventfd_ctx_put(matrix_mdev->req_trigger); + matrix_mdev->req_trigger = NULL; + } else if (fd >= 0) { + req_trigger = eventfd_ctx_fdget(fd); + if (IS_ERR(req_trigger)) + return PTR_ERR(req_trigger); + + if (matrix_mdev->req_trigger) + eventfd_ctx_put(matrix_mdev->req_trigger); + + matrix_mdev->req_trigger = req_trigger; + } else { + return -EINVAL; + } + + return 0; +} + +static int vfio_ap_set_cfg_change_irq(struct ap_matrix_mdev *matrix_mdev, unsigned long arg) +{ + s32 fd; + void __user *data; + unsigned long minsz; + struct eventfd_ctx *cfg_chg_trigger; + + minsz = offsetofend(struct vfio_irq_set, count); + data = (void __user *)(arg + minsz); + + if (get_user(fd, (s32 __user *)data)) + return -EFAULT; + + if (fd == -1) { + if (matrix_mdev->cfg_chg_trigger) + eventfd_ctx_put(matrix_mdev->cfg_chg_trigger); + matrix_mdev->cfg_chg_trigger = NULL; + } else if (fd >= 0) { + cfg_chg_trigger = eventfd_ctx_fdget(fd); + if (IS_ERR(cfg_chg_trigger)) + return PTR_ERR(cfg_chg_trigger); + + if (matrix_mdev->cfg_chg_trigger) + eventfd_ctx_put(matrix_mdev->cfg_chg_trigger); + + matrix_mdev->cfg_chg_trigger = cfg_chg_trigger; + } else { + return -EINVAL; + } + + return 0; +} + +static int vfio_ap_set_irqs(struct ap_matrix_mdev *matrix_mdev, + unsigned long arg) +{ + int ret; + struct vfio_irq_set irq_set; + + ret = vfio_ap_irq_set_init(&irq_set, arg); + if (ret) + return ret; + + switch (irq_set.flags & VFIO_IRQ_SET_DATA_TYPE_MASK) { + case VFIO_IRQ_SET_DATA_EVENTFD: + switch (irq_set.index) { + case VFIO_AP_REQ_IRQ_INDEX: + return vfio_ap_set_request_irq(matrix_mdev, arg); + case VFIO_AP_CFG_CHG_IRQ_INDEX: + return vfio_ap_set_cfg_change_irq(matrix_mdev, arg); + default: + return -EINVAL; + } + default: + return -EINVAL; + } +} + static ssize_t vfio_ap_mdev_ioctl(struct vfio_device *vdev, unsigned int cmd, unsigned long arg) { @@ -1726,7 +2274,13 @@ static ssize_t vfio_ap_mdev_ioctl(struct vfio_device *vdev, ret = vfio_ap_mdev_get_device_info(arg); break; case VFIO_DEVICE_RESET: - ret = vfio_ap_mdev_reset_queues(&matrix_mdev->qtable); + ret = vfio_ap_mdev_reset_queues(matrix_mdev); + break; + case VFIO_DEVICE_GET_IRQ_INFO: + ret = vfio_ap_get_irq_info(arg); + break; + case VFIO_DEVICE_SET_IRQS: + ret = vfio_ap_set_irqs(matrix_mdev, arg); break; default: ret = -EOPNOTSUPP; @@ -1758,6 +2312,7 @@ static ssize_t status_show(struct device *dev, { ssize_t nchars = 0; struct vfio_ap_queue *q; + unsigned long apid, apqi; struct ap_matrix_mdev *matrix_mdev; struct ap_device *apdev = to_ap_dev(dev); @@ -1765,16 +2320,26 @@ static ssize_t status_show(struct device *dev, q = dev_get_drvdata(&apdev->device); matrix_mdev = vfio_ap_mdev_for_queue(q); + /* If the queue is assigned to the matrix mediated device, then + * determine whether it is passed through to a guest; otherwise, + * indicate that it is unassigned. + */ if (matrix_mdev) { - if (matrix_mdev->kvm) - nchars = scnprintf(buf, PAGE_SIZE, "%s\n", - AP_QUEUE_IN_USE); + apid = AP_QID_CARD(q->apqn); + apqi = AP_QID_QUEUE(q->apqn); + /* + * If the queue is passed through to the guest, then indicate + * that it is in use; otherwise, indicate that it is + * merely assigned to a matrix mediated device. + */ + if (matrix_mdev->kvm && + test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) && + test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) + nchars = sysfs_emit(buf, "%s\n", AP_QUEUE_IN_USE); else - nchars = scnprintf(buf, PAGE_SIZE, "%s\n", - AP_QUEUE_ASSIGNED); + nchars = sysfs_emit(buf, "%s\n", AP_QUEUE_ASSIGNED); } else { - nchars = scnprintf(buf, PAGE_SIZE, "%s\n", - AP_QUEUE_UNASSIGNED); + nchars = sysfs_emit(buf, "%s\n", AP_QUEUE_UNASSIGNED); } mutex_unlock(&matrix_dev->mdevs_lock); @@ -1802,6 +2367,8 @@ static const struct vfio_device_ops vfio_ap_matrix_dev_ops = { .bind_iommufd = vfio_iommufd_emulated_bind, .unbind_iommufd = vfio_iommufd_emulated_unbind, .attach_ioas = vfio_iommufd_emulated_attach_ioas, + .detach_ioas = vfio_iommufd_emulated_detach_ioas, + .request = vfio_ap_mdev_request }; static struct mdev_driver vfio_ap_matrix_driver = { @@ -1827,10 +2394,10 @@ int vfio_ap_mdev_register(void) matrix_dev->mdev_type.sysfs_name = VFIO_AP_MDEV_TYPE_HWVIRT; matrix_dev->mdev_type.pretty_name = VFIO_AP_MDEV_NAME_HWVIRT; - matrix_dev->mdev_types[0] = &matrix_dev->mdev_type; + matrix_dev->mdev_types = &matrix_dev->mdev_type; ret = mdev_register_parent(&matrix_dev->parent, &matrix_dev->device, &vfio_ap_matrix_driver, - matrix_dev->mdev_types, 1); + &matrix_dev->mdev_types, 1); if (ret) goto err_driver; return 0; @@ -1850,6 +2417,7 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev) { int ret; struct vfio_ap_queue *q; + DECLARE_BITMAP(apm_filtered, AP_DEVICES); struct ap_matrix_mdev *matrix_mdev; ret = sysfs_create_group(&apdev->device.kobj, &vfio_queue_attr_group); @@ -1857,25 +2425,46 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev) return ret; q = kzalloc(sizeof(*q), GFP_KERNEL); - if (!q) - return -ENOMEM; + if (!q) { + ret = -ENOMEM; + goto err_remove_group; + } q->apqn = to_ap_queue(&apdev->device)->qid; q->saved_isc = VFIO_AP_ISC_INVALID; + memset(&q->reset_status, 0, sizeof(q->reset_status)); + INIT_WORK(&q->reset_work, apq_reset_check); matrix_mdev = get_update_locks_by_apqn(q->apqn); if (matrix_mdev) { vfio_ap_mdev_link_queue(matrix_mdev, q); - if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm, - matrix_mdev->matrix.aqm, - matrix_mdev)) + /* + * If we're in the process of handling the adding of adapters or + * domains to the host's AP configuration, then let the + * vfio_ap device driver's on_scan_complete callback filter the + * matrix and update the guest's AP configuration after all of + * the new queue devices are probed. + */ + if (!bitmap_empty(matrix_mdev->apm_add, AP_DEVICES) || + !bitmap_empty(matrix_mdev->aqm_add, AP_DOMAINS)) + goto done; + + if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) { vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apids(matrix_mdev, apm_filtered); + } } + +done: dev_set_drvdata(&apdev->device, q); release_update_locks_for_mdev(matrix_mdev); - return 0; + return ret; + +err_remove_group: + sysfs_remove_group(&apdev->device.kobj, &vfio_queue_attr_group); + return ret; } void vfio_ap_mdev_remove_queue(struct ap_device *apdev) @@ -1888,25 +2477,40 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev) q = dev_get_drvdata(&apdev->device); get_update_locks_for_queue(q); matrix_mdev = q->matrix_mdev; + apid = AP_QID_CARD(q->apqn); + apqi = AP_QID_QUEUE(q->apqn); if (matrix_mdev) { - vfio_ap_unlink_queue_fr_mdev(q); - - apid = AP_QID_CARD(q->apqn); - apqi = AP_QID_QUEUE(q->apqn); - - /* - * If the queue is assigned to the guest's APCB, then remove - * the adapter's APID from the APCB and hot it into the guest. - */ + /* If the queue is assigned to the guest's AP configuration */ if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) && test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) { + /* + * Since the queues are defined via a matrix of adapters + * and domains, it is not possible to hot unplug a + * single queue; so, let's unplug the adapter. + */ clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm); vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apid(matrix_mdev, apid); + goto done; } } - vfio_ap_mdev_reset_queue(q, 1); + /* + * If the queue is not in the host's AP configuration, then resetting + * it will fail with response code 01, (APQN not valid); so, let's make + * sure it is in the host's config. + */ + if (test_bit_inv(apid, (unsigned long *)matrix_dev->info.apm) && + test_bit_inv(apqi, (unsigned long *)matrix_dev->info.aqm)) { + vfio_ap_mdev_reset_queue(q); + flush_work(&q->reset_work); + } + +done: + if (matrix_mdev) + vfio_ap_unlink_queue_fr_mdev(q); + dev_set_drvdata(&apdev->device, NULL); kfree(q); release_update_locks_for_mdev(matrix_mdev); @@ -1932,7 +2536,7 @@ int vfio_ap_mdev_resource_in_use(unsigned long *apm, unsigned long *aqm) mutex_lock(&matrix_dev->guests_lock); mutex_lock(&matrix_dev->mdevs_lock); - ret = vfio_ap_mdev_verify_no_sharing(apm, aqm); + ret = vfio_ap_mdev_verify_no_sharing(NULL, apm, aqm); mutex_unlock(&matrix_dev->mdevs_lock); mutex_unlock(&matrix_dev->guests_lock); @@ -2067,8 +2671,8 @@ static void vfio_ap_filter_apid_by_qtype(unsigned long *apm, unsigned long *aqm) { bool apid_cleared; struct ap_queue_status status; - unsigned long apid, apqi, info; - int qtype, qtype_mask = 0xff000000; + unsigned long apid, apqi; + struct ap_tapq_hwinfo info; for_each_set_bit_inv(apid, apm, AP_DEVICES) { apid_cleared = false; @@ -2085,15 +2689,13 @@ static void vfio_ap_filter_apid_by_qtype(unsigned long *apm, unsigned long *aqm) case AP_RESPONSE_DECONFIGURED: case AP_RESPONSE_CHECKSTOPPED: case AP_RESPONSE_BUSY: - qtype = info & qtype_mask; - /* * The vfio_ap device driver only * supports CEX4 and newer adapters, so * remove the APID if the adapter is * older than a CEX4. */ - if (qtype < AP_DEVICE_TYPE_CEX4) { + if (info.at < AP_DEVICE_TYPE_CEX4) { clear_bit_inv(apid, apm); apid_cleared = true; } @@ -2216,39 +2818,30 @@ void vfio_ap_on_cfg_changed(struct ap_config_info *cur_cfg_info, static void vfio_ap_mdev_hot_plug_cfg(struct ap_matrix_mdev *matrix_mdev) { - bool do_hotplug = false; - int filter_domains = 0; - int filter_adapters = 0; - DECLARE_BITMAP(apm, AP_DEVICES); - DECLARE_BITMAP(aqm, AP_DOMAINS); + DECLARE_BITMAP(apm_filtered, AP_DEVICES); + bool filter_domains, filter_adapters, filter_cdoms, do_hotplug = false; mutex_lock(&matrix_mdev->kvm->lock); mutex_lock(&matrix_dev->mdevs_lock); - filter_adapters = bitmap_and(apm, matrix_mdev->matrix.apm, - matrix_mdev->apm_add, AP_DEVICES); - filter_domains = bitmap_and(aqm, matrix_mdev->matrix.aqm, - matrix_mdev->aqm_add, AP_DOMAINS); - - if (filter_adapters && filter_domains) - do_hotplug |= vfio_ap_mdev_filter_matrix(apm, aqm, matrix_mdev); - else if (filter_adapters) - do_hotplug |= - vfio_ap_mdev_filter_matrix(apm, - matrix_mdev->shadow_apcb.aqm, - matrix_mdev); - else - do_hotplug |= - vfio_ap_mdev_filter_matrix(matrix_mdev->shadow_apcb.apm, - aqm, matrix_mdev); + filter_adapters = bitmap_intersects(matrix_mdev->matrix.apm, + matrix_mdev->apm_add, AP_DEVICES); + filter_domains = bitmap_intersects(matrix_mdev->matrix.aqm, + matrix_mdev->aqm_add, AP_DOMAINS); + filter_cdoms = bitmap_intersects(matrix_mdev->matrix.adm, + matrix_mdev->adm_add, AP_DOMAINS); - if (bitmap_intersects(matrix_mdev->matrix.adm, matrix_mdev->adm_add, - AP_DOMAINS)) + if (filter_adapters || filter_domains) + do_hotplug = vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered); + + if (filter_cdoms) do_hotplug |= vfio_ap_mdev_filter_cdoms(matrix_mdev); if (do_hotplug) vfio_ap_mdev_update_guest_apcb(matrix_mdev); + reset_queues_for_apids(matrix_mdev, apm_filtered); + mutex_unlock(&matrix_dev->mdevs_lock); mutex_unlock(&matrix_mdev->kvm->lock); } |