#define GTT_SPTE_FLAG_MASK GENMASK_ULL(62, 52)
#define GTT_SPTE_FLAG_64K_SPLITED BIT(52) /* splited 64K gtt entry */
+#define GTT_64K_PTE_STRIDE 16
+
static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
{
unsigned long pfn;
radix_tree_delete(&spt->vgpu->gtt.spt_tree, spt->shadow_page.mfn);
- if (spt->guest_page.oos_page)
- detach_oos_page(spt->vgpu, spt->guest_page.oos_page);
+ if (spt->guest_page.gfn) {
+ if (spt->guest_page.oos_page)
+ detach_oos_page(spt->vgpu, spt->guest_page.oos_page);
- intel_vgpu_unregister_page_track(spt->vgpu, spt->guest_page.gfn);
+ intel_vgpu_unregister_page_track(spt->vgpu, spt->guest_page.gfn);
+ }
list_del_init(&spt->post_shadow_list);
free_spt(spt);
static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt);
+/* Allocate shadow page table without guest page. */
static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt(
- struct intel_vgpu *vgpu, int type, unsigned long gfn,
- bool guest_pde_ips)
+ struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type)
{
struct device *kdev = &vgpu->gvt->dev_priv->drm.pdev->dev;
struct intel_vgpu_ppgtt_spt *spt = NULL;
spt->shadow_page.vaddr = page_address(spt->shadow_page.page);
spt->shadow_page.mfn = daddr >> I915_GTT_PAGE_SHIFT;
- /*
- * Init guest_page.
- */
- spt->guest_page.type = type;
- spt->guest_page.gfn = gfn;
- spt->guest_page.pde_ips = guest_pde_ips;
-
- ret = intel_vgpu_register_page_track(vgpu, spt->guest_page.gfn,
- ppgtt_write_protection_handler, spt);
- if (ret)
- goto err_unmap_dma;
-
ret = radix_tree_insert(&vgpu->gtt.spt_tree, spt->shadow_page.mfn, spt);
if (ret)
- goto err_unreg_page_track;
+ goto err_unmap_dma;
- trace_spt_alloc(vgpu->id, spt, type, spt->shadow_page.mfn, gfn);
return spt;
-err_unreg_page_track:
- intel_vgpu_unregister_page_track(vgpu, spt->guest_page.gfn);
err_unmap_dma:
dma_unmap_page(kdev, daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
err_free_spt:
return ERR_PTR(ret);
}
+/* Allocate shadow page table associated with specific gfn. */
+static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt_gfn(
+ struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type,
+ unsigned long gfn, bool guest_pde_ips)
+{
+ struct intel_vgpu_ppgtt_spt *spt;
+ int ret;
+
+ spt = ppgtt_alloc_spt(vgpu, type);
+ if (IS_ERR(spt))
+ return spt;
+
+ /*
+ * Init guest_page.
+ */
+ ret = intel_vgpu_register_page_track(vgpu, gfn,
+ ppgtt_write_protection_handler, spt);
+ if (ret) {
+ ppgtt_free_spt(spt);
+ return ERR_PTR(ret);
+ }
+
+ spt->guest_page.type = type;
+ spt->guest_page.gfn = gfn;
+ spt->guest_page.pde_ips = guest_pde_ips;
+
+ trace_spt_alloc(vgpu->id, spt, type, spt->shadow_page.mfn, gfn);
+
+ return spt;
+}
+
#define pt_entry_size_shift(spt) \
((spt)->vgpu->gvt->device_info.gtt_entry_size_shift)
(I915_GTT_PAGE_SIZE >> pt_entry_size_shift(spt))
#define for_each_present_guest_entry(spt, e, i) \
- for (i = 0; i < pt_entries(spt); i++) \
+ for (i = 0; i < pt_entries(spt); \
+ i += spt->guest_page.pde_ips ? GTT_64K_PTE_STRIDE : 1) \
if (!ppgtt_get_guest_entry(spt, e, i) && \
spt->vgpu->gvt->gtt.pte_ops->test_present(e))
#define for_each_present_shadow_entry(spt, e, i) \
- for (i = 0; i < pt_entries(spt); i++) \
+ for (i = 0; i < pt_entries(spt); \
+ i += spt->shadow_page.pde_ips ? GTT_64K_PTE_STRIDE : 1) \
if (!ppgtt_get_shadow_entry(spt, e, i) && \
spt->vgpu->gvt->gtt.pte_ops->test_present(e))
-static void ppgtt_get_spt(struct intel_vgpu_ppgtt_spt *spt)
+#define for_each_shadow_entry(spt, e, i) \
+ for (i = 0; i < pt_entries(spt); \
+ i += (spt->shadow_page.pde_ips ? GTT_64K_PTE_STRIDE : 1)) \
+ if (!ppgtt_get_shadow_entry(spt, e, i))
+
+static inline void ppgtt_get_spt(struct intel_vgpu_ppgtt_spt *spt)
{
int v = atomic_read(&spt->refcount);
trace_spt_refcount(spt->vgpu->id, "inc", spt, v, (v + 1));
-
atomic_inc(&spt->refcount);
}
+static inline int ppgtt_put_spt(struct intel_vgpu_ppgtt_spt *spt)
+{
+ int v = atomic_read(&spt->refcount);
+
+ trace_spt_refcount(spt->vgpu->id, "dec", spt, v, (v - 1));
+ return atomic_dec_return(&spt->refcount);
+}
+
static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt);
static int ppgtt_invalidate_spt_by_shadow_entry(struct intel_vgpu *vgpu,
pfn = ops->get_pfn(entry);
type = spt->shadow_page.type;
- if (pfn == vgpu->gtt.scratch_pt[type].page_mfn)
+ /* Uninitialized spte or unshadowed spte. */
+ if (!pfn || pfn == vgpu->gtt.scratch_pt[type].page_mfn)
return;
intel_gvt_hypervisor_dma_unmap_guest_page(vgpu, pfn << PAGE_SHIFT);
struct intel_gvt_gtt_entry e;
unsigned long index;
int ret;
- int v = atomic_read(&spt->refcount);
trace_spt_change(spt->vgpu->id, "die", spt,
spt->guest_page.gfn, spt->shadow_page.type);
- trace_spt_refcount(spt->vgpu->id, "dec", spt, v, (v - 1));
-
- if (atomic_dec_return(&spt->refcount) > 0)
+ if (ppgtt_put_spt(spt) > 0)
return 0;
for_each_present_shadow_entry(spt, &e, index) {
ppgtt_invalidate_pte(spt, &e);
break;
case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+ /* We don't setup 64K shadow entry so far. */
+ WARN(1, "suspicious 64K gtt entry\n");
+ continue;
case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+ gvt_vdbg_mm("invalidate 2M entry\n");
+ continue;
case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
- WARN(1, "GVT doesn't support 64K/2M/1GB page\n");
+ WARN(1, "GVT doesn't support 1GB page\n");
continue;
case GTT_TYPE_PPGTT_PML4_ENTRY:
case GTT_TYPE_PPGTT_PDP_ENTRY:
GEM_BUG_ON(!gtt_type_is_pt(get_next_pt_type(we->type)));
+ if (we->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+ ips = vgpu_ips_enabled(vgpu) && ops->test_ips(we);
+
spt = intel_vgpu_find_spt_by_gfn(vgpu, ops->get_pfn(we));
- if (spt)
+ if (spt) {
ppgtt_get_spt(spt);
- else {
- int type = get_next_pt_type(we->type);
- if (we->type == GTT_TYPE_PPGTT_PDE_ENTRY)
- ips = vgpu_ips_enabled(vgpu) && ops->test_ips(we);
+ if (ips != spt->guest_page.pde_ips) {
+ spt->guest_page.pde_ips = ips;
- spt = ppgtt_alloc_spt(vgpu, type, ops->get_pfn(we), ips);
+ gvt_dbg_mm("reshadow PDE since ips changed\n");
+ clear_page(spt->shadow_page.vaddr);
+ ret = ppgtt_populate_spt(spt);
+ if (ret) {
+ ppgtt_put_spt(spt);
+ goto err;
+ }
+ }
+ } else {
+ int type = get_next_pt_type(we->type);
+
+ spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
if (IS_ERR(spt)) {
ret = PTR_ERR(spt);
- goto fail;
+ goto err;
}
ret = intel_vgpu_enable_page_track(vgpu, spt->guest_page.gfn);
if (ret)
- goto fail;
+ goto err_free_spt;
ret = ppgtt_populate_spt(spt);
if (ret)
- goto fail;
+ goto err_free_spt;
trace_spt_change(vgpu->id, "new", spt, spt->guest_page.gfn,
spt->shadow_page.type);
}
return spt;
-fail:
+
+err_free_spt:
+ ppgtt_free_spt(spt);
+err:
gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
spt, we->val64, we->type);
return ERR_PTR(ret);
se->type = ge->type;
se->val64 = ge->val64;
+ /* Because we always split 64KB pages, so clear IPS in shadow PDE. */
+ if (se->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+ ops->clear_ips(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 possilbe, 0 if miscondition,
+ * negtive if found err.
+ */
+static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
+ struct intel_gvt_gtt_entry *entry)
+{
+ struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+ unsigned long pfn;
+
+ if (!HAS_PAGE_SIZES(vgpu->gvt->dev_priv, I915_GTT_PAGE_SIZE_2M))
+ return 0;
+
+ pfn = intel_gvt_hypervisor_gfn_to_mfn(vgpu, ops->get_pfn(entry));
+ if (pfn == INTEL_GVT_INVALID_ADDR)
+ 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)
+{
+ struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+ struct intel_vgpu_ppgtt_spt *sub_spt;
+ struct intel_gvt_gtt_entry sub_se;
+ unsigned long start_gfn;
+ dma_addr_t dma_addr;
+ unsigned long sub_index;
+ int ret;
+
+ gvt_dbg_mm("Split 2M gtt entry, index %lu\n", index);
+
+ start_gfn = ops->get_pfn(se);
+
+ sub_spt = ppgtt_alloc_spt(vgpu, GTT_TYPE_PPGTT_PTE_PT);
+ if (IS_ERR(sub_spt))
+ return PTR_ERR(sub_spt);
+
+ for_each_shadow_entry(sub_spt, &sub_se, sub_index) {
+ ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
+ start_gfn + sub_index, PAGE_SIZE, &dma_addr);
+ if (ret) {
+ ppgtt_invalidate_spt(spt);
+ return ret;
+ }
+ sub_se.val64 = se->val64;
+
+ /* Copy the PAT field from PDE. */
+ sub_se.val64 &= ~_PAGE_PAT;
+ sub_se.val64 |= (se->val64 & _PAGE_PAT_LARGE) >> 5;
+
+ ops->set_pfn(&sub_se, dma_addr >> PAGE_SHIFT);
+ ppgtt_set_shadow_entry(sub_spt, &sub_se, sub_index);
+ }
+
+ /* Clear dirty field. */
+ se->val64 &= ~_PAGE_DIRTY;
+
+ ops->clear_pse(se);
+ ops->clear_ips(se);
+ ops->set_pfn(se, sub_spt->shadow_page.mfn);
+ ppgtt_set_shadow_entry(spt, se, index);
+ return 0;
+}
+
+static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
+ struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
+ struct intel_gvt_gtt_entry *se)
+{
+ struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+ struct intel_gvt_gtt_entry entry = *se;
+ unsigned long start_gfn;
+ dma_addr_t dma_addr;
+ int i, ret;
+
+ gvt_vdbg_mm("Split 64K gtt entry, index %lu\n", index);
+
+ GEM_BUG_ON(index % GTT_64K_PTE_STRIDE);
+
+ start_gfn = ops->get_pfn(se);
+
+ entry.type = GTT_TYPE_PPGTT_PTE_4K_ENTRY;
+ ops->set_64k_splited(&entry);
+
+ for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+ ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
+ start_gfn + i, PAGE_SIZE, &dma_addr);
+ if (ret)
+ return ret;
+
+ ops->set_pfn(&entry, dma_addr >> PAGE_SHIFT);
+ ppgtt_set_shadow_entry(spt, &entry, index + i);
+ }
+ return 0;
+}
+
static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
struct intel_gvt_gtt_entry *ge)
{
struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
struct intel_gvt_gtt_entry se = *ge;
- unsigned long gfn;
+ unsigned long gfn, page_size = PAGE_SIZE;
dma_addr_t dma_addr;
int ret;
gvt_vdbg_mm("shadow 4K gtt entry\n");
break;
case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+ gvt_vdbg_mm("shadow 64K gtt entry\n");
+ /*
+ * The layout of 64K page is special, the page size is
+ * controlled by uper PDE. To be simple, we always split
+ * 64K page to smaller 4K pages in shadow PT.
+ */
+ 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)
+ 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 64K/2M/1GB entry\n");
+ gvt_vgpu_err("GVT doesn't support 1GB entry\n");
return -EINVAL;
default:
GEM_BUG_ON(1);
};
/* direct shadow */
- ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, &dma_addr);
+ ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, page_size,
+ &dma_addr);
if (ret)
return -ENXIO;
ret = ppgtt_invalidate_spt(s);
if (ret)
goto fail;
- } else
+ } else {
+ /* We don't setup 64K shadow entry so far. */
+ WARN(se->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY,
+ "suspicious 64K entry\n");
ppgtt_invalidate_pte(spt, se);
+ }
return 0;
fail:
struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
struct intel_gvt_gtt_entry old_se;
int new_present;
- int ret;
+ int i, ret;
new_present = ops->test_present(we);
goto fail;
if (!new_present) {
- ops->set_pfn(&old_se, vgpu->gtt.scratch_pt[type].page_mfn);
- ppgtt_set_shadow_entry(spt, &old_se, index);
+ /* For 64KB splited entries, we need clear them all. */
+ if (ops->test_64k_splited(&old_se) &&
+ !(index % GTT_64K_PTE_STRIDE)) {
+ gvt_vdbg_mm("remove splited 64K shadow entries\n");
+ for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+ ops->clear_64k_splited(&old_se);
+ ops->set_pfn(&old_se,
+ vgpu->gtt.scratch_pt[type].page_mfn);
+ ppgtt_set_shadow_entry(spt, &old_se, index + i);
+ }
+ } else if (old_se.type == GTT_TYPE_PPGTT_PTE_2M_ENTRY ||
+ old_se.type == GTT_TYPE_PPGTT_PTE_1G_ENTRY) {
+ ops->clear_pse(&old_se);
+ ops->set_pfn(&old_se,
+ vgpu->gtt.scratch_pt[type].page_mfn);
+ ppgtt_set_shadow_entry(spt, &old_se, index);
+ } else {
+ ops->set_pfn(&old_se,
+ vgpu->gtt.scratch_pt[type].page_mfn);
+ ppgtt_set_shadow_entry(spt, &old_se, index);
+ }
}
return 0;
ppgtt_get_guest_entry(spt, &we, index);
+ /*
+ * For page table which has 64K gtt entry, only PTE#0, PTE#16,
+ * PTE#32, ... PTE#496 are used. Unused PTEs update should be
+ * ignored.
+ */
+ if (we.type == GTT_TYPE_PPGTT_PTE_64K_ENTRY &&
+ (index % GTT_64K_PTE_STRIDE)) {
+ gvt_vdbg_mm("Ignore write to unused PTE entry, index %lu\n",
+ index);
+ return 0;
+ }
+
if (bytes == info->gtt_entry_size) {
ret = ppgtt_handle_guest_write_page_table(spt, &we, index);
if (ret)
mm->type = INTEL_GVT_MM_GGTT;
nr_entries = gvt_ggtt_gm_sz(vgpu->gvt) >> I915_GTT_PAGE_SHIFT;
- mm->ggtt_mm.virtual_ggtt = vzalloc(nr_entries *
- vgpu->gvt->device_info.gtt_entry_size);
+ mm->ggtt_mm.virtual_ggtt =
+ vzalloc(array_size(nr_entries,
+ vgpu->gvt->device_info.gtt_entry_size));
if (!mm->ggtt_mm.virtual_ggtt) {
vgpu_free_mm(mm);
return ERR_PTR(-ENOMEM);
/**
* intel_vgpu_pin_mm - increase the pin count of a vGPU mm object
- * @vgpu: a vGPU
+ * @mm: target vgpu mm
*
* This function is called when user wants to use a vGPU mm object. If this
* mm object hasn't been shadowed yet, the shadow will be populated at this
}
ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn,
- &dma_addr);
+ PAGE_SIZE, &dma_addr);
if (ret) {
gvt_vgpu_err("fail to populate guest ggtt entry\n");
/* guest driver may read/write the entry when partial
/**
* intel_vgpu_find_ppgtt_mm - find a PPGTT mm object
* @vgpu: a vGPU
- * @page_table_level: PPGTT page table level
- * @root_entry: PPGTT page table root pointers
+ * @pdps: pdp root array
*
* This function is used to find a PPGTT mm object from mm object pool
*
git.samba.org / sfrench / cifs-2.6.git / blobdiff