From ce4b4657ff18925c315855aa290e93c5fa652d96 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 19 Jul 2022 21:02:48 -0300 Subject: vfio: Replace the DMA unmapping notifier with a callback Instead of having drivers register the notifier with explicit code just have them provide a dma_unmap callback op in their driver ops and rely on the core code to wire it up. Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Kevin Tian Reviewed-by: Tony Krowiak Reviewed-by: Eric Farman Reviewed-by: Zhenyu Wang Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1-v4-681e038e30fd+78-vfio_unmap_notif_jgg@nvidia.com Signed-off-by: Alex Williamson --- drivers/s390/crypto/vfio_ap_ops.c | 53 ++++++----------------------------- drivers/s390/crypto/vfio_ap_private.h | 3 -- 2 files changed, 8 insertions(+), 48 deletions(-) (limited to 'drivers/s390/crypto') diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index a7d2a95796d3..bb1a1677c5c2 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -1226,34 +1226,14 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, return 0; } -/** - * vfio_ap_mdev_iommu_notifier - IOMMU notifier callback - * - * @nb: The notifier block - * @action: Action to be taken - * @data: data associated with the request - * - * For an UNMAP request, unpin the guest IOVA (the NIB guest address we - * pinned before). Other requests are ignored. - * - * Return: for an UNMAP request, NOFITY_OK; otherwise NOTIFY_DONE. - */ -static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb, - unsigned long action, void *data) +static void vfio_ap_mdev_dma_unmap(struct vfio_device *vdev, u64 iova, + u64 length) { - struct ap_matrix_mdev *matrix_mdev; - - matrix_mdev = container_of(nb, struct ap_matrix_mdev, iommu_notifier); - - if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) { - struct vfio_iommu_type1_dma_unmap *unmap = data; - unsigned long g_pfn = unmap->iova >> PAGE_SHIFT; - - vfio_unpin_pages(&matrix_mdev->vdev, &g_pfn, 1); - return NOTIFY_OK; - } + struct ap_matrix_mdev *matrix_mdev = + container_of(vdev, struct ap_matrix_mdev, vdev); + unsigned long g_pfn = iova >> PAGE_SHIFT; - return NOTIFY_DONE; + vfio_unpin_pages(&matrix_mdev->vdev, &g_pfn, 1); } /** @@ -1380,27 +1360,11 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) { struct ap_matrix_mdev *matrix_mdev = container_of(vdev, struct ap_matrix_mdev, vdev); - unsigned long events; - int ret; if (!vdev->kvm) return -EINVAL; - ret = vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm); - if (ret) - return ret; - - matrix_mdev->iommu_notifier.notifier_call = vfio_ap_mdev_iommu_notifier; - events = VFIO_IOMMU_NOTIFY_DMA_UNMAP; - ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY, &events, - &matrix_mdev->iommu_notifier); - if (ret) - goto err_kvm; - return 0; - -err_kvm: - vfio_ap_mdev_unset_kvm(matrix_mdev); - return ret; + return vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm); } static void vfio_ap_mdev_close_device(struct vfio_device *vdev) @@ -1408,8 +1372,6 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev) struct ap_matrix_mdev *matrix_mdev = container_of(vdev, struct ap_matrix_mdev, vdev); - vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, - &matrix_mdev->iommu_notifier); vfio_ap_mdev_unset_kvm(matrix_mdev); } @@ -1461,6 +1423,7 @@ static const struct vfio_device_ops vfio_ap_matrix_dev_ops = { .open_device = vfio_ap_mdev_open_device, .close_device = vfio_ap_mdev_close_device, .ioctl = vfio_ap_mdev_ioctl, + .dma_unmap = vfio_ap_mdev_dma_unmap, }; static struct mdev_driver vfio_ap_matrix_driver = { diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h index a26efd804d0d..abb59d59f81b 100644 --- a/drivers/s390/crypto/vfio_ap_private.h +++ b/drivers/s390/crypto/vfio_ap_private.h @@ -81,8 +81,6 @@ struct ap_matrix { * @node: allows the ap_matrix_mdev struct to be added to a list * @matrix: the adapters, usage domains and control domains assigned to the * mediated matrix device. - * @iommu_notifier: notifier block used for specifying callback function for - * handling the VFIO_IOMMU_NOTIFY_DMA_UNMAP even * @kvm: the struct holding guest's state * @pqap_hook: the function pointer to the interception handler for the * PQAP(AQIC) instruction. @@ -92,7 +90,6 @@ struct ap_matrix_mdev { struct vfio_device vdev; struct list_head node; struct ap_matrix matrix; - struct notifier_block iommu_notifier; struct kvm *kvm; crypto_hook pqap_hook; struct mdev_device *mdev; -- cgit v1.2.3-59-g8ed1b From 10e19d492a326afe7f016a8735ccdfd7c65fc979 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 22 Jul 2022 19:02:49 -0700 Subject: vfio/ap: Pass in physical address of ind to ap_aqic() The ap_aqic() is called by vfio_ap_irq_enable() where it passes in a virt value that's casted from a physical address "h_nib". Inside the ap_aqic(), it does virt_to_phys() again. Since ap_aqic() needs a physical address, let's just pass in a pa of ind directly. So change the "ind" to "pa_ind". Reviewed-by: Harald Freudenberger Reviewed-by: Jason Gunthorpe Tested-by: Eric Farman Signed-off-by: Nicolin Chen Link: https://lore.kernel.org/r/20220723020256.30081-4-nicolinc@nvidia.com Signed-off-by: Alex Williamson --- arch/s390/include/asm/ap.h | 6 +++--- drivers/s390/crypto/ap_queue.c | 2 +- drivers/s390/crypto/vfio_ap_ops.c | 7 ++++--- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'drivers/s390/crypto') diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index b515cfa62bd9..f508f5025e38 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -227,13 +227,13 @@ struct ap_qirq_ctrl { * ap_aqic(): Control interruption for a specific AP. * @qid: The AP queue number * @qirqctrl: struct ap_qirq_ctrl (64 bit value) - * @ind: The notification indicator byte + * @pa_ind: Physical address of the notification indicator byte * * Returns AP queue status. */ static inline struct ap_queue_status ap_aqic(ap_qid_t qid, struct ap_qirq_ctrl qirqctrl, - void *ind) + phys_addr_t pa_ind) { unsigned long reg0 = qid | (3UL << 24); /* fc 3UL is AQIC */ union { @@ -241,7 +241,7 @@ static inline struct ap_queue_status ap_aqic(ap_qid_t qid, struct ap_qirq_ctrl qirqctrl; struct ap_queue_status status; } reg1; - unsigned long reg2 = virt_to_phys(ind); + unsigned long reg2 = pa_ind; reg1.qirqctrl = qirqctrl; diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index c48b0db824e3..a32457b4cbb8 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -34,7 +34,7 @@ static int ap_queue_enable_irq(struct ap_queue *aq, void *ind) qirqctrl.ir = 1; qirqctrl.isc = AP_ISC; - status = ap_aqic(aq->qid, qirqctrl, ind); + status = ap_aqic(aq->qid, qirqctrl, virt_to_phys(ind)); switch (status.response_code) { case AP_RESPONSE_NORMAL: case AP_RESPONSE_OTHERWISE_CHANGED: diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index bb1a1677c5c2..5781059d3ed2 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -154,7 +154,7 @@ static struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q) int retries = 5; do { - status = ap_aqic(q->apqn, aqic_gisa, NULL); + status = ap_aqic(q->apqn, aqic_gisa, 0); switch (status.response_code) { case AP_RESPONSE_OTHERWISE_CHANGED: case AP_RESPONSE_NORMAL: @@ -245,7 +245,8 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, struct kvm_s390_gisa *gisa; int nisc; struct kvm *kvm; - unsigned long h_nib, g_pfn, h_pfn; + unsigned long g_pfn, h_pfn; + phys_addr_t h_nib; int ret; /* Verify that the notification indicator byte address is valid */ @@ -290,7 +291,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, aqic_gisa.ir = 1; aqic_gisa.gisa = (uint64_t)gisa >> 4; - status = ap_aqic(q->apqn, aqic_gisa, (void *)h_nib); + status = ap_aqic(q->apqn, aqic_gisa, h_nib); switch (status.response_code) { case AP_RESPONSE_NORMAL: /* See if we did clear older IRQ configuration */ -- cgit v1.2.3-59-g8ed1b From 44abdd1646e1fbfb781972c0bffc90b4eb3e87b3 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 22 Jul 2022 19:02:51 -0700 Subject: vfio: Pass in starting IOVA to vfio_pin/unpin_pages API The vfio_pin/unpin_pages() so far accepted arrays of PFNs of user IOVA. Among all three callers, there was only one caller possibly passing in a non-contiguous PFN list, which is now ensured to have contiguous PFN inputs too. Pass in the starting address with "iova" alone to simplify things, so callers no longer need to maintain a PFN list or to pin/unpin one page at a time. This also allows VFIO to use more efficient implementations of pin/unpin_pages. For now, also update vfio_iommu_type1 to fit this new parameter too, while keeping its input intact (being user_iova) since we don't want to spend too much effort swapping its parameters and local variables at that level. Reviewed-by: Christoph Hellwig Reviewed-by: Kirti Wankhede Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Tony Krowiak Acked-by: Eric Farman Tested-by: Terrence Xu Tested-by: Eric Farman Signed-off-by: Nicolin Chen Link: https://lore.kernel.org/r/20220723020256.30081-6-nicolinc@nvidia.com Signed-off-by: Alex Williamson --- Documentation/driver-api/vfio-mediated-device.rst | 4 ++-- drivers/gpu/drm/i915/gvt/kvmgt.c | 18 +++++---------- drivers/s390/cio/vfio_ccw_cp.c | 4 ++-- drivers/s390/crypto/vfio_ap_ops.c | 9 ++++---- drivers/vfio/vfio.c | 27 ++++++++++------------- drivers/vfio/vfio.h | 4 ++-- drivers/vfio/vfio_iommu_type1.c | 15 ++++++------- include/linux/vfio.h | 5 ++--- 8 files changed, 37 insertions(+), 49 deletions(-) (limited to 'drivers/s390/crypto') diff --git a/Documentation/driver-api/vfio-mediated-device.rst b/Documentation/driver-api/vfio-mediated-device.rst index b0fdf76b339a..ea32a0f13ddb 100644 --- a/Documentation/driver-api/vfio-mediated-device.rst +++ b/Documentation/driver-api/vfio-mediated-device.rst @@ -262,10 +262,10 @@ Translation APIs for Mediated Devices The following APIs are provided for translating user pfn to host pfn in a VFIO driver:: - int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, + int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, int npage, int prot, unsigned long *phys_pfn); - void vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn, + void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage); These functions call back into the back-end IOMMU module by using the pin_pages diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 2fee5695515a..8be75c282611 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -231,14 +231,8 @@ static void intel_gvt_cleanup_vgpu_type_groups(struct intel_gvt *gvt) static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size) { - int total_pages = DIV_ROUND_UP(size, PAGE_SIZE); - int npage; - - for (npage = 0; npage < total_pages; npage++) { - unsigned long cur_gfn = gfn + npage; - - vfio_unpin_pages(&vgpu->vfio_device, &cur_gfn, 1); - } + vfio_unpin_pages(&vgpu->vfio_device, gfn << PAGE_SHIFT, + DIV_ROUND_UP(size, PAGE_SIZE)); } /* Pin a normal or compound guest page for dma. */ @@ -255,14 +249,14 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, * on stack to hold pfns. */ for (npage = 0; npage < total_pages; npage++) { - unsigned long cur_gfn = gfn + npage; + dma_addr_t cur_iova = (gfn + npage) << PAGE_SHIFT; unsigned long pfn; - ret = vfio_pin_pages(&vgpu->vfio_device, &cur_gfn, 1, + ret = vfio_pin_pages(&vgpu->vfio_device, cur_iova, 1, IOMMU_READ | IOMMU_WRITE, &pfn); if (ret != 1) { - gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx, ret %d\n", - cur_gfn, ret); + gvt_vgpu_err("vfio_pin_pages failed for iova %pad, ret %d\n", + &cur_iova, ret); goto err; } diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 3b94863ad24e..a739262f988d 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -114,7 +114,7 @@ static void pfn_array_unpin(struct pfn_array *pa, continue; } - vfio_unpin_pages(vdev, first, npage); + vfio_unpin_pages(vdev, *first << PAGE_SHIFT, npage); unpinned += npage; npage = 1; } @@ -146,7 +146,7 @@ static int pfn_array_pin(struct pfn_array *pa, struct vfio_device *vdev) continue; } - ret = vfio_pin_pages(vdev, first, npage, + ret = vfio_pin_pages(vdev, *first << PAGE_SHIFT, npage, IOMMU_READ | IOMMU_WRITE, &pa->pa_pfn[pinned]); if (ret < 0) { diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 5781059d3ed2..70f484668ca0 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -124,7 +124,7 @@ static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q) q->saved_isc = VFIO_AP_ISC_INVALID; } if (q->saved_pfn && !WARN_ON(!q->matrix_mdev)) { - vfio_unpin_pages(&q->matrix_mdev->vdev, &q->saved_pfn, 1); + vfio_unpin_pages(&q->matrix_mdev->vdev, q->saved_pfn << PAGE_SHIFT, 1); q->saved_pfn = 0; } } @@ -258,7 +258,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, return status; } - ret = vfio_pin_pages(&q->matrix_mdev->vdev, &g_pfn, 1, + ret = vfio_pin_pages(&q->matrix_mdev->vdev, g_pfn << PAGE_SHIFT, 1, IOMMU_READ | IOMMU_WRITE, &h_pfn); switch (ret) { case 1: @@ -301,7 +301,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, break; case AP_RESPONSE_OTHERWISE_CHANGED: /* We could not modify IRQ setings: clear new configuration */ - vfio_unpin_pages(&q->matrix_mdev->vdev, &g_pfn, 1); + vfio_unpin_pages(&q->matrix_mdev->vdev, g_pfn << PAGE_SHIFT, 1); kvm_s390_gisc_unregister(kvm, isc); break; default: @@ -1232,9 +1232,8 @@ static void vfio_ap_mdev_dma_unmap(struct vfio_device *vdev, u64 iova, { struct ap_matrix_mdev *matrix_mdev = container_of(vdev, struct ap_matrix_mdev, vdev); - unsigned long g_pfn = iova >> PAGE_SHIFT; - vfio_unpin_pages(&matrix_mdev->vdev, &g_pfn, 1); + vfio_unpin_pages(&matrix_mdev->vdev, iova, 1); } /** diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 92b10aafae28..ffd1a492eea9 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1934,17 +1934,17 @@ int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs, EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare); /* - * Pin a set of guest PFNs and return their associated host PFNs for local + * Pin contiguous user pages and return their associated host pages for local * domain only. * @device [in] : device - * @user_pfn [in]: array of user/guest PFNs to be pinned. - * @npage [in] : count of elements in user_pfn array. This count should not - * be greater VFIO_PIN_PAGES_MAX_ENTRIES. + * @iova [in] : starting IOVA of user pages to be pinned. + * @npage [in] : count of pages to be pinned. This count should not + * be greater than VFIO_PIN_PAGES_MAX_ENTRIES. * @prot [in] : protection flags * @phys_pfn[out]: array of host PFNs * Return error or number of pages pinned. */ -int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, +int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, int npage, int prot, unsigned long *phys_pfn) { struct vfio_container *container; @@ -1952,8 +1952,7 @@ int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, struct vfio_iommu_driver *driver; int ret; - if (!user_pfn || !phys_pfn || !npage || - !vfio_assert_device_open(device)) + if (!phys_pfn || !npage || !vfio_assert_device_open(device)) return -EINVAL; if (npage > VFIO_PIN_PAGES_MAX_ENTRIES) @@ -1967,7 +1966,7 @@ int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, driver = container->iommu_driver; if (likely(driver && driver->ops->pin_pages)) ret = driver->ops->pin_pages(container->iommu_data, - group->iommu_group, user_pfn, + group->iommu_group, iova, npage, prot, phys_pfn); else ret = -ENOTTY; @@ -1977,15 +1976,13 @@ int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, EXPORT_SYMBOL(vfio_pin_pages); /* - * Unpin set of host PFNs for local domain only. + * Unpin contiguous host pages for local domain only. * @device [in] : device - * @user_pfn [in]: array of user/guest PFNs to be unpinned. Number of user/guest - * PFNs should not be greater than VFIO_PIN_PAGES_MAX_ENTRIES. - * @npage [in] : count of elements in user_pfn array. This count should not + * @iova [in] : starting address of user pages to be unpinned. + * @npage [in] : count of pages to be unpinned. This count should not * be greater than VFIO_PIN_PAGES_MAX_ENTRIES. */ -void vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn, - int npage) +void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage) { struct vfio_container *container; struct vfio_iommu_driver *driver; @@ -2000,7 +1997,7 @@ void vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn, container = device->group->container; driver = container->iommu_driver; - driver->ops->unpin_pages(container->iommu_data, user_pfn, npage); + driver->ops->unpin_pages(container->iommu_data, iova, npage); } EXPORT_SYMBOL(vfio_unpin_pages); diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index 6a8424b407c7..e9767e13f00f 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -50,11 +50,11 @@ struct vfio_iommu_driver_ops { struct iommu_group *group); int (*pin_pages)(void *iommu_data, struct iommu_group *group, - unsigned long *user_pfn, + dma_addr_t user_iova, int npage, int prot, unsigned long *phys_pfn); void (*unpin_pages)(void *iommu_data, - unsigned long *user_pfn, int npage); + dma_addr_t user_iova, int npage); void (*register_device)(void *iommu_data, struct vfio_device *vdev); void (*unregister_device)(void *iommu_data, diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index e49fbe9968ef..e629e059118c 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -829,7 +829,7 @@ static int vfio_unpin_page_external(struct vfio_dma *dma, dma_addr_t iova, static int vfio_iommu_type1_pin_pages(void *iommu_data, struct iommu_group *iommu_group, - unsigned long *user_pfn, + dma_addr_t user_iova, int npage, int prot, unsigned long *phys_pfn) { @@ -841,7 +841,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, bool do_accounting; dma_addr_t iova; - if (!iommu || !user_pfn || !phys_pfn) + if (!iommu || !phys_pfn) return -EINVAL; /* Supported for v2 version only */ @@ -857,7 +857,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, again: if (iommu->vaddr_invalid_count) { for (i = 0; i < npage; i++) { - iova = user_pfn[i] << PAGE_SHIFT; + iova = user_iova + PAGE_SIZE * i; ret = vfio_find_dma_valid(iommu, iova, PAGE_SIZE, &dma); if (ret < 0) goto pin_done; @@ -882,7 +882,7 @@ again: for (i = 0; i < npage; i++) { struct vfio_pfn *vpfn; - iova = user_pfn[i] << PAGE_SHIFT; + iova = user_iova + PAGE_SIZE * i; dma = vfio_find_dma(iommu, iova, PAGE_SIZE); if (!dma) { ret = -EINVAL; @@ -939,7 +939,7 @@ pin_unwind: for (j = 0; j < i; j++) { dma_addr_t iova; - iova = user_pfn[j] << PAGE_SHIFT; + iova = user_iova + PAGE_SIZE * j; dma = vfio_find_dma(iommu, iova, PAGE_SIZE); vfio_unpin_page_external(dma, iova, do_accounting); phys_pfn[j] = 0; @@ -950,7 +950,7 @@ pin_done: } static void vfio_iommu_type1_unpin_pages(void *iommu_data, - unsigned long *user_pfn, int npage) + dma_addr_t user_iova, int npage) { struct vfio_iommu *iommu = iommu_data; bool do_accounting; @@ -964,10 +964,9 @@ static void vfio_iommu_type1_unpin_pages(void *iommu_data, do_accounting = list_empty(&iommu->domain_list); for (i = 0; i < npage; i++) { + dma_addr_t iova = user_iova + PAGE_SIZE * i; struct vfio_dma *dma; - dma_addr_t iova; - iova = user_pfn[i] << PAGE_SHIFT; dma = vfio_find_dma(iommu, iova, PAGE_SIZE); if (!dma) break; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 9f7d74c24925..9e3b6abcf890 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -161,10 +161,9 @@ bool vfio_file_has_dev(struct file *file, struct vfio_device *device); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) -int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, +int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, int npage, int prot, unsigned long *phys_pfn); -void vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn, - int npage); +void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage); int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, void *data, size_t len, bool write); -- cgit v1.2.3-59-g8ed1b From 3fad3a26139d5a41bc6b20df47ff067f5db2fe75 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 22 Jul 2022 19:02:52 -0700 Subject: vfio/ap: Change saved_pfn to saved_iova The vfio_ap_ops code maintains both nib address and its PFN, which is redundant, merely because vfio_pin/unpin_pages API wanted pfn. Since vfio_pin/unpin_pages() now accept "iova", change "saved_pfn" to "saved_iova" and remove pfn in the vfio_ap_validate_nib(). Reviewed-by: Jason Gunthorpe Reviewed-by: Tony Krowiak Tested-by: Eric Farman Signed-off-by: Nicolin Chen Link: https://lore.kernel.org/r/20220723020256.30081-7-nicolinc@nvidia.com Signed-off-by: Alex Williamson --- drivers/s390/crypto/vfio_ap_ops.c | 42 ++++++++++++++--------------------- drivers/s390/crypto/vfio_ap_private.h | 4 ++-- 2 files changed, 19 insertions(+), 27 deletions(-) (limited to 'drivers/s390/crypto') diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 70f484668ca0..d7c38c82f694 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -112,7 +112,7 @@ static void vfio_ap_wait_for_irqclear(int apqn) * * Unregisters the ISC in the GIB when the saved ISC not invalid. * Unpins the guest's page holding the NIB when it exists. - * Resets the saved_pfn and saved_isc to invalid values. + * Resets the saved_iova and saved_isc to invalid values. */ static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q) { @@ -123,9 +123,9 @@ static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q) kvm_s390_gisc_unregister(q->matrix_mdev->kvm, q->saved_isc); q->saved_isc = VFIO_AP_ISC_INVALID; } - if (q->saved_pfn && !WARN_ON(!q->matrix_mdev)) { - vfio_unpin_pages(&q->matrix_mdev->vdev, q->saved_pfn << PAGE_SHIFT, 1); - q->saved_pfn = 0; + if (q->saved_iova && !WARN_ON(!q->matrix_mdev)) { + vfio_unpin_pages(&q->matrix_mdev->vdev, q->saved_iova, 1); + q->saved_iova = 0; } } @@ -189,27 +189,19 @@ end_free: * * @vcpu: the object representing the vcpu executing the PQAP(AQIC) instruction. * @nib: the location for storing the nib address. - * @g_pfn: the location for storing the page frame number of the page containing - * the nib. * * When the PQAP(AQIC) instruction is executed, general register 2 contains the * address of the notification indicator byte (nib) used for IRQ notification. - * This function parses the nib from gr2 and calculates the page frame - * number for the guest of the page containing the nib. The values are - * stored in @nib and @g_pfn respectively. - * - * The g_pfn of the nib is then validated to ensure the nib address is valid. + * This function parses and validates the nib from gr2. * * Return: returns zero if the nib address is a valid; otherwise, returns * -EINVAL. */ -static int vfio_ap_validate_nib(struct kvm_vcpu *vcpu, unsigned long *nib, - unsigned long *g_pfn) +static int vfio_ap_validate_nib(struct kvm_vcpu *vcpu, dma_addr_t *nib) { *nib = vcpu->run->s.regs.gprs[2]; - *g_pfn = *nib >> PAGE_SHIFT; - if (kvm_is_error_hva(gfn_to_hva(vcpu->kvm, *g_pfn))) + if (kvm_is_error_hva(gfn_to_hva(vcpu->kvm, *nib >> PAGE_SHIFT))) return -EINVAL; return 0; @@ -239,34 +231,34 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, int isc, struct kvm_vcpu *vcpu) { - unsigned long nib; struct ap_qirq_ctrl aqic_gisa = {}; struct ap_queue_status status = {}; struct kvm_s390_gisa *gisa; int nisc; struct kvm *kvm; - unsigned long g_pfn, h_pfn; + unsigned long h_pfn; phys_addr_t h_nib; + dma_addr_t nib; int ret; /* Verify that the notification indicator byte address is valid */ - if (vfio_ap_validate_nib(vcpu, &nib, &g_pfn)) { - VFIO_AP_DBF_WARN("%s: invalid NIB address: nib=%#lx, g_pfn=%#lx, apqn=%#04x\n", - __func__, nib, g_pfn, q->apqn); + if (vfio_ap_validate_nib(vcpu, &nib)) { + VFIO_AP_DBF_WARN("%s: invalid NIB address: nib=%pad, apqn=%#04x\n", + __func__, &nib, q->apqn); status.response_code = AP_RESPONSE_INVALID_ADDRESS; return status; } - ret = vfio_pin_pages(&q->matrix_mdev->vdev, g_pfn << PAGE_SHIFT, 1, + ret = vfio_pin_pages(&q->matrix_mdev->vdev, nib, 1, IOMMU_READ | IOMMU_WRITE, &h_pfn); switch (ret) { case 1: break; default: VFIO_AP_DBF_WARN("%s: vfio_pin_pages failed: rc=%d," - "nib=%#lx, g_pfn=%#lx, apqn=%#04x\n", - __func__, ret, nib, g_pfn, q->apqn); + "nib=%pad, apqn=%#04x\n", + __func__, ret, &nib, q->apqn); status.response_code = AP_RESPONSE_INVALID_ADDRESS; return status; @@ -296,12 +288,12 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, case AP_RESPONSE_NORMAL: /* See if we did clear older IRQ configuration */ vfio_ap_free_aqic_resources(q); - q->saved_pfn = g_pfn; + q->saved_iova = nib; q->saved_isc = isc; break; case AP_RESPONSE_OTHERWISE_CHANGED: /* We could not modify IRQ setings: clear new configuration */ - vfio_unpin_pages(&q->matrix_mdev->vdev, g_pfn << PAGE_SHIFT, 1); + vfio_unpin_pages(&q->matrix_mdev->vdev, nib, 1); kvm_s390_gisc_unregister(kvm, isc); break; default: diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h index abb59d59f81b..d912487175d3 100644 --- a/drivers/s390/crypto/vfio_ap_private.h +++ b/drivers/s390/crypto/vfio_ap_private.h @@ -99,13 +99,13 @@ struct ap_matrix_mdev { * struct vfio_ap_queue - contains the data associated with a queue bound to the * vfio_ap device driver * @matrix_mdev: the matrix mediated device - * @saved_pfn: the guest PFN pinned for the guest + * @saved_iova: the notification indicator byte (nib) address * @apqn: the APQN of the AP queue device * @saved_isc: the guest ISC registered with the GIB interface */ struct vfio_ap_queue { struct ap_matrix_mdev *matrix_mdev; - unsigned long saved_pfn; + dma_addr_t saved_iova; int apqn; #define VFIO_AP_ISC_INVALID 0xff unsigned char saved_isc; -- cgit v1.2.3-59-g8ed1b From 34a255e67615995f729254307a0581c143e03752 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 22 Jul 2022 19:02:56 -0700 Subject: vfio: Replace phys_pfn with pages for vfio_pin_pages() Most of the callers of vfio_pin_pages() want "struct page *" and the low-level mm code to pin pages returns a list of "struct page *" too. So there's no gain in converting "struct page *" to PFN in between. Replace the output parameter "phys_pfn" list with a "pages" list, to simplify callers. This also allows us to replace the vfio_iommu_type1 implementation with a more efficient one. And drop the pfn_valid check in the gvt code, as there is no need to do such a check at a page-backed struct page pointer. For now, also update vfio_iommu_type1 to fit this new parameter too. Reviewed-by: Christoph Hellwig Reviewed-by: Kirti Wankhede Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Acked-by: Eric Farman Tested-by: Terrence Xu Tested-by: Eric Farman Signed-off-by: Nicolin Chen Link: https://lore.kernel.org/r/20220723020256.30081-11-nicolinc@nvidia.com Signed-off-by: Alex Williamson --- Documentation/driver-api/vfio-mediated-device.rst | 2 +- drivers/gpu/drm/i915/gvt/kvmgt.c | 19 ++++++------------- drivers/s390/cio/vfio_ccw_cp.c | 19 +++++++++---------- drivers/s390/crypto/vfio_ap_ops.c | 6 +++--- drivers/vfio/vfio.c | 8 ++++---- drivers/vfio/vfio.h | 2 +- drivers/vfio/vfio_iommu_type1.c | 19 +++++++++++-------- include/linux/vfio.h | 2 +- 8 files changed, 36 insertions(+), 41 deletions(-) (limited to 'drivers/s390/crypto') diff --git a/Documentation/driver-api/vfio-mediated-device.rst b/Documentation/driver-api/vfio-mediated-device.rst index ea32a0f13ddb..ba5fefcdae1a 100644 --- a/Documentation/driver-api/vfio-mediated-device.rst +++ b/Documentation/driver-api/vfio-mediated-device.rst @@ -263,7 +263,7 @@ The following APIs are provided for translating user pfn to host pfn in a VFIO driver:: int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, - int npage, int prot, unsigned long *phys_pfn); + int npage, int prot, struct page **pages); void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 8be75c282611..e3cd58946477 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -240,7 +240,7 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size, struct page **page) { int total_pages = DIV_ROUND_UP(size, PAGE_SIZE); - unsigned long base_pfn = 0; + struct page *base_page = NULL; int npage; int ret; @@ -250,26 +250,19 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, */ for (npage = 0; npage < total_pages; npage++) { dma_addr_t cur_iova = (gfn + npage) << PAGE_SHIFT; - unsigned long pfn; + struct page *cur_page; ret = vfio_pin_pages(&vgpu->vfio_device, cur_iova, 1, - IOMMU_READ | IOMMU_WRITE, &pfn); + IOMMU_READ | IOMMU_WRITE, &cur_page); if (ret != 1) { gvt_vgpu_err("vfio_pin_pages failed for iova %pad, ret %d\n", &cur_iova, ret); goto err; } - if (!pfn_valid(pfn)) { - gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn); - npage++; - ret = -EFAULT; - goto err; - } - if (npage == 0) - base_pfn = pfn; - else if (base_pfn + npage != pfn) { + base_page = cur_page; + else if (base_page + npage != cur_page) { gvt_vgpu_err("The pages are not continuous\n"); ret = -EINVAL; npage++; @@ -277,7 +270,7 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, } } - *page = pfn_to_page(base_pfn); + *page = base_page; return 0; err: gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE); diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index cd4ec4f6d6ff..8963f452f963 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -22,8 +22,8 @@ struct page_array { /* Array that stores pages need to pin. */ dma_addr_t *pa_iova; - /* Array that receives PFNs of the pages pinned. */ - unsigned long *pa_pfn; + /* Array that receives the pinned pages. */ + struct page **pa_page; /* Number of pages pinned from @pa_iova. */ int pa_nr; }; @@ -68,19 +68,19 @@ static int page_array_alloc(struct page_array *pa, u64 iova, unsigned int len) return -EINVAL; pa->pa_iova = kcalloc(pa->pa_nr, - sizeof(*pa->pa_iova) + sizeof(*pa->pa_pfn), + sizeof(*pa->pa_iova) + sizeof(*pa->pa_page), GFP_KERNEL); if (unlikely(!pa->pa_iova)) { pa->pa_nr = 0; return -ENOMEM; } - pa->pa_pfn = (unsigned long *)&pa->pa_iova[pa->pa_nr]; + pa->pa_page = (struct page **)&pa->pa_iova[pa->pa_nr]; pa->pa_iova[0] = iova; - pa->pa_pfn[0] = -1ULL; + pa->pa_page[0] = NULL; for (i = 1; i < pa->pa_nr; i++) { pa->pa_iova[i] = pa->pa_iova[i - 1] + PAGE_SIZE; - pa->pa_pfn[i] = -1ULL; + pa->pa_page[i] = NULL; } return 0; @@ -144,7 +144,7 @@ static int page_array_pin(struct page_array *pa, struct vfio_device *vdev) ret = vfio_pin_pages(vdev, *first, npage, IOMMU_READ | IOMMU_WRITE, - &pa->pa_pfn[pinned]); + &pa->pa_page[pinned]); if (ret < 0) { goto err_out; } else if (ret > 0 && ret != npage) { @@ -195,7 +195,7 @@ static inline void page_array_idal_create_words(struct page_array *pa, */ for (i = 0; i < pa->pa_nr; i++) - idaws[i] = pa->pa_pfn[i] << PAGE_SHIFT; + idaws[i] = page_to_phys(pa->pa_page[i]); /* Adjust the first IDAW, since it may not start on a page boundary */ idaws[0] += pa->pa_iova[0] & (PAGE_SIZE - 1); @@ -246,8 +246,7 @@ static long copy_from_iova(struct vfio_device *vdev, void *to, u64 iova, l = n; for (i = 0; i < pa.pa_nr; i++) { - struct page *page = pfn_to_page(pa.pa_pfn[i]); - void *from = kmap_local_page(page); + void *from = kmap_local_page(pa.pa_page[i]); m = PAGE_SIZE; if (i == 0) { diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index d7c38c82f694..75cd92c291e3 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -234,9 +234,9 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, struct ap_qirq_ctrl aqic_gisa = {}; struct ap_queue_status status = {}; struct kvm_s390_gisa *gisa; + struct page *h_page; int nisc; struct kvm *kvm; - unsigned long h_pfn; phys_addr_t h_nib; dma_addr_t nib; int ret; @@ -251,7 +251,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, } ret = vfio_pin_pages(&q->matrix_mdev->vdev, nib, 1, - IOMMU_READ | IOMMU_WRITE, &h_pfn); + IOMMU_READ | IOMMU_WRITE, &h_page); switch (ret) { case 1: break; @@ -267,7 +267,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, kvm = q->matrix_mdev->kvm; gisa = kvm->arch.gisa_int.origin; - h_nib = (h_pfn << PAGE_SHIFT) | (nib & ~PAGE_MASK); + h_nib = page_to_phys(h_page) | (nib & ~PAGE_MASK); aqic_gisa.gisc = isc; nisc = kvm_s390_gisc_register(kvm, isc); diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 606a20b605ba..8e23ca59ceed 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1941,18 +1941,18 @@ EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare); * @npage [in] : count of pages to be pinned. This count should not * be greater than VFIO_PIN_PAGES_MAX_ENTRIES. * @prot [in] : protection flags - * @phys_pfn[out]: array of host PFNs + * @pages[out] : array of host pages * Return error or number of pages pinned. */ int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, - int npage, int prot, unsigned long *phys_pfn) + int npage, int prot, struct page **pages) { struct vfio_container *container; struct vfio_group *group = device->group; struct vfio_iommu_driver *driver; int ret; - if (!phys_pfn || !npage || !vfio_assert_device_open(device)) + if (!pages || !npage || !vfio_assert_device_open(device)) return -EINVAL; if (npage > VFIO_PIN_PAGES_MAX_ENTRIES) @@ -1967,7 +1967,7 @@ int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, if (likely(driver && driver->ops->pin_pages)) ret = driver->ops->pin_pages(container->iommu_data, group->iommu_group, iova, - npage, prot, phys_pfn); + npage, prot, pages); else ret = -ENOTTY; diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index e9767e13f00f..503bea6c843d 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -52,7 +52,7 @@ struct vfio_iommu_driver_ops { struct iommu_group *group, dma_addr_t user_iova, int npage, int prot, - unsigned long *phys_pfn); + struct page **pages); void (*unpin_pages)(void *iommu_data, dma_addr_t user_iova, int npage); void (*register_device)(void *iommu_data, diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index e629e059118c..db516c90a977 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -831,7 +831,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, struct iommu_group *iommu_group, dma_addr_t user_iova, int npage, int prot, - unsigned long *phys_pfn) + struct page **pages) { struct vfio_iommu *iommu = iommu_data; struct vfio_iommu_group *group; @@ -841,7 +841,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, bool do_accounting; dma_addr_t iova; - if (!iommu || !phys_pfn) + if (!iommu || !pages) return -EINVAL; /* Supported for v2 version only */ @@ -880,6 +880,7 @@ again: do_accounting = list_empty(&iommu->domain_list); for (i = 0; i < npage; i++) { + unsigned long phys_pfn; struct vfio_pfn *vpfn; iova = user_iova + PAGE_SIZE * i; @@ -896,23 +897,25 @@ again: vpfn = vfio_iova_get_vfio_pfn(dma, iova); if (vpfn) { - phys_pfn[i] = vpfn->pfn; + pages[i] = pfn_to_page(vpfn->pfn); continue; } remote_vaddr = dma->vaddr + (iova - dma->iova); - ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn[i], + ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn, do_accounting); if (ret) goto pin_unwind; - ret = vfio_add_to_pfn_list(dma, iova, phys_pfn[i]); + ret = vfio_add_to_pfn_list(dma, iova, phys_pfn); if (ret) { - if (put_pfn(phys_pfn[i], dma->prot) && do_accounting) + if (put_pfn(phys_pfn, dma->prot) && do_accounting) vfio_lock_acct(dma, -1, true); goto pin_unwind; } + pages[i] = pfn_to_page(phys_pfn); + if (iommu->dirty_page_tracking) { unsigned long pgshift = __ffs(iommu->pgsize_bitmap); @@ -935,14 +938,14 @@ again: goto pin_done; pin_unwind: - phys_pfn[i] = 0; + pages[i] = NULL; for (j = 0; j < i; j++) { dma_addr_t iova; iova = user_iova + PAGE_SIZE * j; dma = vfio_find_dma(iommu, iova, PAGE_SIZE); vfio_unpin_page_external(dma, iova, do_accounting); - phys_pfn[j] = 0; + pages[j] = NULL; } pin_done: mutex_unlock(&iommu->lock); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index acefd663e63b..e05ddc6fe6a5 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -162,7 +162,7 @@ bool vfio_file_has_dev(struct file *file, struct vfio_device *device); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, - int npage, int prot, unsigned long *phys_pfn); + int npage, int prot, struct page **pages); void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage); int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova, void *data, size_t len, bool write); -- cgit v1.2.3-59-g8ed1b