diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gvt')
-rw-r--r-- | drivers/gpu/drm/i915/gvt/gtt.c | 102 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gvt/gtt.h | 1 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gvt/gvt.h | 3 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gvt/kvmgt.c | 120 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gvt/page_track.c | 10 |
5 files changed, 63 insertions, 173 deletions
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 4ec85308379a..094fca9b0e73 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -49,22 +49,6 @@ static bool enable_out_of_sync = false; static int preallocated_oos_pages = 8192; -static bool intel_gvt_is_valid_gfn(struct intel_vgpu *vgpu, unsigned long gfn) -{ - struct kvm *kvm = vgpu->vfio_device.kvm; - int idx; - bool ret; - - if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) - return false; - - idx = srcu_read_lock(&kvm->srcu); - ret = kvm_is_visible_gfn(kvm, gfn); - srcu_read_unlock(&kvm->srcu, idx); - - return ret; -} - /* * validate a gm address and related range size, * translate it to host gm address @@ -1161,31 +1145,6 @@ static inline void ppgtt_generate_shadow_entry(struct intel_gvt_gtt_entry *se, ops->set_pfn(se, s->shadow_page.mfn); } -/* - * Check if can do 2M page - * @vgpu: target vgpu - * @entry: target pfn's gtt entry - * - * Return 1 if 2MB huge gtt shadowing is possible, 0 if miscondition, - * negative if found err. - */ -static int is_2MB_gtt_possible(struct intel_vgpu *vgpu, - struct intel_gvt_gtt_entry *entry) -{ - const struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops; - kvm_pfn_t pfn; - - if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M)) - return 0; - - if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) - return -EINVAL; - pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry)); - if (is_error_noslot_pfn(pfn)) - return -EINVAL; - return PageTransHuge(pfn_to_page(pfn)); -} - static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, struct intel_vgpu_ppgtt_spt *spt, unsigned long index, struct intel_gvt_gtt_entry *se) @@ -1279,7 +1238,7 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu, { const struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops; struct intel_gvt_gtt_entry se = *ge; - unsigned long gfn, page_size = PAGE_SIZE; + unsigned long gfn; dma_addr_t dma_addr; int ret; @@ -1291,6 +1250,9 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu, switch (ge->type) { case GTT_TYPE_PPGTT_PTE_4K_ENTRY: gvt_vdbg_mm("shadow 4K gtt entry\n"); + ret = intel_gvt_dma_map_guest_page(vgpu, gfn, PAGE_SIZE, &dma_addr); + if (ret) + return -ENXIO; break; case GTT_TYPE_PPGTT_PTE_64K_ENTRY: gvt_vdbg_mm("shadow 64K gtt entry\n"); @@ -1302,25 +1264,20 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu, return split_64KB_gtt_entry(vgpu, spt, index, &se); case GTT_TYPE_PPGTT_PTE_2M_ENTRY: gvt_vdbg_mm("shadow 2M gtt entry\n"); - ret = is_2MB_gtt_possible(vgpu, ge); - if (ret == 0) + if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M) || + intel_gvt_dma_map_guest_page(vgpu, gfn, + I915_GTT_PAGE_SIZE_2M, &dma_addr)) return split_2MB_gtt_entry(vgpu, spt, index, &se); - else if (ret < 0) - return ret; - page_size = I915_GTT_PAGE_SIZE_2M; break; case GTT_TYPE_PPGTT_PTE_1G_ENTRY: gvt_vgpu_err("GVT doesn't support 1GB entry\n"); return -EINVAL; default: GEM_BUG_ON(1); + return -EINVAL; } - /* direct shadow */ - ret = intel_gvt_dma_map_guest_page(vgpu, gfn, page_size, &dma_addr); - if (ret) - return -ENXIO; - + /* Successfully shadowed a 4K or 2M page (without splitting). */ pte_ops->set_pfn(&se, dma_addr >> PAGE_SHIFT); ppgtt_set_shadow_entry(spt, &se, index); return 0; @@ -1329,11 +1286,9 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu, static int ppgtt_populate_spt(struct intel_vgpu_ppgtt_spt *spt) { struct intel_vgpu *vgpu = spt->vgpu; - struct intel_gvt *gvt = vgpu->gvt; - const struct intel_gvt_gtt_pte_ops *ops = gvt->gtt.pte_ops; struct intel_vgpu_ppgtt_spt *s; struct intel_gvt_gtt_entry se, ge; - unsigned long gfn, i; + unsigned long i; int ret; trace_spt_change(spt->vgpu->id, "born", spt, @@ -1350,13 +1305,6 @@ static int ppgtt_populate_spt(struct intel_vgpu_ppgtt_spt *spt) ppgtt_generate_shadow_entry(&se, s, &ge); ppgtt_set_shadow_entry(spt, &se, i); } else { - gfn = ops->get_pfn(&ge); - if (!intel_gvt_is_valid_gfn(vgpu, gfn)) { - ops->set_pfn(&se, gvt->gtt.scratch_mfn); - ppgtt_set_shadow_entry(spt, &se, i); - continue; - } - ret = ppgtt_populate_shadow_entry(vgpu, spt, i, &ge); if (ret) goto fail; @@ -1845,6 +1793,9 @@ static int shadow_ppgtt_mm(struct intel_vgpu_mm *mm) if (mm->ppgtt_mm.shadowed) return 0; + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) + return -EINVAL; + mm->ppgtt_mm.shadowed = true; for (index = 0; index < ARRAY_SIZE(mm->ppgtt_mm.guest_pdps); index++) { @@ -2331,14 +2282,6 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, m.val64 = e.val64; m.type = e.type; - /* one PTE update may be issued in multiple writes and the - * first write may not construct a valid gfn - */ - if (!intel_gvt_is_valid_gfn(vgpu, gfn)) { - ops->set_pfn(&m, gvt->gtt.scratch_mfn); - goto out; - } - ret = intel_gvt_dma_map_guest_page(vgpu, gfn, PAGE_SIZE, &dma_addr); if (ret) { @@ -2355,7 +2298,6 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, ops->clear_present(&m); } -out: ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); ggtt_get_host_entry(ggtt_mm, &e, g_gtt_index); @@ -2876,24 +2818,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old) } /** - * intel_vgpu_reset_gtt - reset the all GTT related status - * @vgpu: a vGPU - * - * This function is called from vfio core to reset reset all - * GTT related status, including GGTT, PPGTT, scratch page. - * - */ -void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu) -{ - /* Shadow pages are only created when there is no page - * table tracking data, so remove page tracking data after - * removing the shadow pages. - */ - intel_vgpu_destroy_all_ppgtt_mm(vgpu); - intel_vgpu_reset_ggtt(vgpu, true); -} - -/** * intel_gvt_restore_ggtt - restore all vGPU's ggtt entries * @gvt: intel gvt device * diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index a3b0f59ec8bd..4cb183e06e95 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -224,7 +224,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old); void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu); int intel_gvt_init_gtt(struct intel_gvt *gvt); -void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu); void intel_gvt_clean_gtt(struct intel_gvt *gvt); struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu, diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 2d65800d8e93..53a0a42a50db 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -34,10 +34,11 @@ #define _GVT_H_ #include <uapi/linux/pci_regs.h> -#include <linux/kvm_host.h> #include <linux/vfio.h> #include <linux/mdev.h> +#include <asm/kvm_page_track.h> + #include "i915_drv.h" #include "intel_gvt.h" diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 9cd9e9da60dd..42ce20e72db7 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -106,12 +106,10 @@ struct gvt_dma { #define vfio_dev_to_vgpu(vfio_dev) \ container_of((vfio_dev), struct intel_vgpu, vfio_device) -static void kvmgt_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *val, int len, - struct kvm_page_track_notifier_node *node); -static void kvmgt_page_track_flush_slot(struct kvm *kvm, - struct kvm_memory_slot *slot, - struct kvm_page_track_notifier_node *node); +static void kvmgt_page_track_write(gpa_t gpa, const u8 *val, int len, + struct kvm_page_track_notifier_node *node); +static void kvmgt_page_track_remove_region(gfn_t gfn, unsigned long nr_pages, + struct kvm_page_track_notifier_node *node); static ssize_t intel_vgpu_show_description(struct mdev_type *mtype, char *buf) { @@ -161,8 +159,7 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, if (npage == 0) base_page = cur_page; - else if (base_page + npage != cur_page) { - gvt_vgpu_err("The pages are not continuous\n"); + else if (page_to_pfn(base_page) + npage != page_to_pfn(cur_page)) { ret = -EINVAL; npage++; goto err; @@ -172,7 +169,8 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, *page = base_page; return 0; err: - gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE); + if (npage) + gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE); return ret; } @@ -352,6 +350,8 @@ __kvmgt_protect_table_find(struct intel_vgpu *info, gfn_t gfn) { struct kvmgt_pgfn *p, *res = NULL; + lockdep_assert_held(&info->vgpu_lock); + hash_for_each_possible(info->ptable, p, hnode, gfn) { if (gfn == p->gfn) { res = p; @@ -654,21 +654,19 @@ out: static int intel_vgpu_open_device(struct vfio_device *vfio_dev) { struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); - - if (!vgpu->vfio_device.kvm || - vgpu->vfio_device.kvm->mm != current->mm) { - gvt_vgpu_err("KVM is required to use Intel vGPU\n"); - return -ESRCH; - } + int ret; if (__kvmgt_vgpu_exist(vgpu)) return -EEXIST; vgpu->track_node.track_write = kvmgt_page_track_write; - vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot; - kvm_get_kvm(vgpu->vfio_device.kvm); - kvm_page_track_register_notifier(vgpu->vfio_device.kvm, - &vgpu->track_node); + vgpu->track_node.track_remove_region = kvmgt_page_track_remove_region; + ret = kvm_page_track_register_notifier(vgpu->vfio_device.kvm, + &vgpu->track_node); + if (ret) { + gvt_vgpu_err("KVM is required to use Intel vGPU\n"); + return ret; + } set_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status); @@ -703,7 +701,6 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev) kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm, &vgpu->track_node); - kvm_put_kvm(vgpu->vfio_device.kvm); kvmgt_protect_table_destroy(vgpu); gvt_cache_destroy(vgpu); @@ -1547,95 +1544,70 @@ static struct mdev_driver intel_vgpu_mdev_driver = { int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn) { - struct kvm *kvm = info->vfio_device.kvm; - struct kvm_memory_slot *slot; - int idx; + int r; if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status)) return -ESRCH; - idx = srcu_read_lock(&kvm->srcu); - slot = gfn_to_memslot(kvm, gfn); - if (!slot) { - srcu_read_unlock(&kvm->srcu, idx); - return -EINVAL; - } - - write_lock(&kvm->mmu_lock); - if (kvmgt_gfn_is_write_protected(info, gfn)) - goto out; + return 0; - kvm_slot_page_track_add_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE); - kvmgt_protect_table_add(info, gfn); + r = kvm_write_track_add_gfn(info->vfio_device.kvm, gfn); + if (r) + return r; -out: - write_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); + kvmgt_protect_table_add(info, gfn); return 0; } int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn) { - struct kvm *kvm = info->vfio_device.kvm; - struct kvm_memory_slot *slot; - int idx; + int r; if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status)) return -ESRCH; - idx = srcu_read_lock(&kvm->srcu); - slot = gfn_to_memslot(kvm, gfn); - if (!slot) { - srcu_read_unlock(&kvm->srcu, idx); - return -EINVAL; - } - - write_lock(&kvm->mmu_lock); - if (!kvmgt_gfn_is_write_protected(info, gfn)) - goto out; + return 0; - kvm_slot_page_track_remove_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE); - kvmgt_protect_table_del(info, gfn); + r = kvm_write_track_remove_gfn(info->vfio_device.kvm, gfn); + if (r) + return r; -out: - write_unlock(&kvm->mmu_lock); - srcu_read_unlock(&kvm->srcu, idx); + kvmgt_protect_table_del(info, gfn); return 0; } -static void kvmgt_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *val, int len, - struct kvm_page_track_notifier_node *node) +static void kvmgt_page_track_write(gpa_t gpa, const u8 *val, int len, + struct kvm_page_track_notifier_node *node) { struct intel_vgpu *info = container_of(node, struct intel_vgpu, track_node); - if (kvmgt_gfn_is_write_protected(info, gpa_to_gfn(gpa))) + mutex_lock(&info->vgpu_lock); + + if (kvmgt_gfn_is_write_protected(info, gpa >> PAGE_SHIFT)) intel_vgpu_page_track_handler(info, gpa, (void *)val, len); + + mutex_unlock(&info->vgpu_lock); } -static void kvmgt_page_track_flush_slot(struct kvm *kvm, - struct kvm_memory_slot *slot, - struct kvm_page_track_notifier_node *node) +static void kvmgt_page_track_remove_region(gfn_t gfn, unsigned long nr_pages, + struct kvm_page_track_notifier_node *node) { - int i; - gfn_t gfn; + unsigned long i; struct intel_vgpu *info = container_of(node, struct intel_vgpu, track_node); - write_lock(&kvm->mmu_lock); - for (i = 0; i < slot->npages; i++) { - gfn = slot->base_gfn + i; - if (kvmgt_gfn_is_write_protected(info, gfn)) { - kvm_slot_page_track_remove_page(kvm, slot, gfn, - KVM_PAGE_TRACK_WRITE); - kvmgt_protect_table_del(info, gfn); - } + mutex_lock(&info->vgpu_lock); + + for (i = 0; i < nr_pages; i++) { + if (kvmgt_gfn_is_write_protected(info, gfn + i)) + kvmgt_protect_table_del(info, gfn + i); } - write_unlock(&kvm->mmu_lock); + + mutex_unlock(&info->vgpu_lock); } void intel_vgpu_detach_regions(struct intel_vgpu *vgpu) diff --git a/drivers/gpu/drm/i915/gvt/page_track.c b/drivers/gpu/drm/i915/gvt/page_track.c index df34e73cba41..60a65435556d 100644 --- a/drivers/gpu/drm/i915/gvt/page_track.c +++ b/drivers/gpu/drm/i915/gvt/page_track.c @@ -162,13 +162,9 @@ int intel_vgpu_page_track_handler(struct intel_vgpu *vgpu, u64 gpa, struct intel_vgpu_page_track *page_track; int ret = 0; - mutex_lock(&vgpu->vgpu_lock); - page_track = intel_vgpu_find_page_track(vgpu, gpa >> PAGE_SHIFT); - if (!page_track) { - ret = -ENXIO; - goto out; - } + if (!page_track) + return -ENXIO; if (unlikely(vgpu->failsafe)) { /* Remove write protection to prevent furture traps. */ @@ -179,7 +175,5 @@ int intel_vgpu_page_track_handler(struct intel_vgpu *vgpu, u64 gpa, gvt_err("guest page write error, gpa %llx\n", gpa); } -out: - mutex_unlock(&vgpu->vgpu_lock); return ret; } |