diff options
| author | Dave Airlie | 2018-07-20 12:29:23 +1000 |
|---|---|---|
| committer | Dave Airlie | 2018-07-20 12:29:24 +1000 |
| commit | ef8e0ff97ae8168ffe1558a5726a8b348c8228a3 (patch) | |
| tree | afb391fb68d6d9fdaec7a2093d7b06ca8e671f0d | |
| parent | 294f96ae8aa53415272045649e3e7a1749cc0575 (diff) | |
| parent | ef821e3f14e868779505bf08f96afb4eade53652 (diff) | |
Merge tag 'drm-intel-next-2018-07-19' of git://anongit.freedesktop.org/drm/drm-intel into drm-next
On GEM side:
- GuC related fixes (Chris, Michal)
- GTT read-only pages support (Jon, Chris)
- More selftests fixes (Chris)
- More GPU reset improvements (Chris)
- Flush caches after GGTT writes (Chris)
- Handle recursive shrinker for vma->last_active allocation (Chris)
- Other execlists fixes (Chris)
On Display side:
- GLK HDMI fix (Clint)
- Rework and cleanup around HPD pin (Ville)
- Preparation work for Display Stream Compression support coming on ICL (Anusha)
- Nuke LVDS lid notification (Ville)
- Assume eDP is always connected (Ville)
- Kill intel panel detection (Ville)
Signed-off-by: Dave Airlie <airlied@redhat.com>
# gpg: Signature made Fri 20 Jul 2018 01:51:45 AM AEST
# gpg: using RSA key FA625F640EEB13CA
# gpg: Good signature from "Rodrigo Vivi <rodrigo.vivi@intel.com>"
# gpg: aka "Rodrigo Vivi <rodrigo.vivi@gmail.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 6D20 7068 EEDD 6509 1C2C E2A3 FA62 5F64 0EEB 13CA
# Conflicts:
# drivers/gpu/drm/i915/intel_lrc.c
Link: https://patchwork.freedesktop.org/patch/msgid/20180719171257.GA12199@intel.com
60 files changed, 2158 insertions, 1009 deletions
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index da5d8ac60062..50d5848bf22e 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -338,6 +338,18 @@ static resource_size_t __init gen3_stolen_base(int num, int slot, int func, return bsm & INTEL_BSM_MASK; } +static resource_size_t __init gen11_stolen_base(int num, int slot, int func, + resource_size_t stolen_size) +{ + u64 bsm; + + bsm = read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW0); + bsm &= INTEL_BSM_MASK; + bsm |= (u64)read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW1) << 32; + + return bsm; +} + static resource_size_t __init i830_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; @@ -498,6 +510,11 @@ static const struct intel_early_ops chv_early_ops __initconst = { .stolen_size = chv_stolen_size, }; +static const struct intel_early_ops gen11_early_ops __initconst = { + .stolen_base = gen11_stolen_base, + .stolen_size = gen9_stolen_size, +}; + static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_I830_IDS(&i830_early_ops), INTEL_I845G_IDS(&i845_early_ops), @@ -529,6 +546,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_CFL_IDS(&gen9_early_ops), INTEL_GLK_IDS(&gen9_early_ops), INTEL_CNL_IDS(&gen9_early_ops), + INTEL_ICL_11_IDS(&gen11_early_ops), }; struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 4a16d7b26c89..bf90625df3c5 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1036,6 +1036,15 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) return -EACCES; } + if (node->readonly) { + if (vma->vm_flags & VM_WRITE) { + drm_gem_object_put_unlocked(obj); + return -EINVAL; + } + + vma->vm_flags &= ~VM_MAYWRITE; + } + ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT, vma); diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 642e216e0a5b..39980dfbbebd 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -216,16 +216,22 @@ static struct gtt_type_table_entry gtt_type_table[] = { GTT_TYPE_PPGTT_PDE_PT, GTT_TYPE_PPGTT_PTE_PT, GTT_TYPE_PPGTT_PTE_2M_ENTRY), + /* We take IPS bit as 'PSE' for PTE level. */ GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_PT, GTT_TYPE_PPGTT_PTE_4K_ENTRY, GTT_TYPE_PPGTT_PTE_PT, GTT_TYPE_INVALID, - GTT_TYPE_INVALID), + GTT_TYPE_PPGTT_PTE_64K_ENTRY), GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_4K_ENTRY, GTT_TYPE_PPGTT_PTE_4K_ENTRY, GTT_TYPE_PPGTT_PTE_PT, GTT_TYPE_INVALID, - GTT_TYPE_INVALID), + GTT_TYPE_PPGTT_PTE_64K_ENTRY), + GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_64K_ENTRY, + GTT_TYPE_PPGTT_PTE_4K_ENTRY, + GTT_TYPE_PPGTT_PTE_PT, + GTT_TYPE_INVALID, + GTT_TYPE_PPGTT_PTE_64K_ENTRY), GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_2M_ENTRY, GTT_TYPE_PPGTT_PDE_ENTRY, GTT_TYPE_PPGTT_PDE_PT, @@ -339,8 +345,14 @@ static inline int gtt_set_entry64(void *pt, #define ADDR_1G_MASK GENMASK_ULL(GTT_HAW - 1, 30) #define ADDR_2M_MASK GENMASK_ULL(GTT_HAW - 1, 21) +#define ADDR_64K_MASK GENMASK_ULL(GTT_HAW - 1, 16) #define ADDR_4K_MASK GENMASK_ULL(GTT_HAW - 1, 12) +#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; @@ -349,6 +361,8 @@ static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e) pfn = (e->val64 & ADDR_1G_MASK) >> PAGE_SHIFT; else if (e->type == GTT_TYPE_PPGTT_PTE_2M_ENTRY) pfn = (e->val64 & ADDR_2M_MASK) >> PAGE_SHIFT; + else if (e->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY) + pfn = (e->val64 & ADDR_64K_MASK) >> PAGE_SHIFT; else pfn = (e->val64 & ADDR_4K_MASK) >> PAGE_SHIFT; return pfn; @@ -362,6 +376,9 @@ static void gen8_gtt_set_pfn(struct intel_gvt_gtt_entry *e, unsigned long pfn) } else if (e->type == GTT_TYPE_PPGTT_PTE_2M_ENTRY) { e->val64 &= ~ADDR_2M_MASK; pfn &= (ADDR_2M_MASK >> PAGE_SHIFT); + } else if (e->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY) { + e->val64 &= ~ADDR_64K_MASK; + pfn &= (ADDR_64K_MASK >> PAGE_SHIFT); } else { e->val64 &= ~ADDR_4K_MASK; pfn &= (ADDR_4K_MASK >> PAGE_SHIFT); @@ -372,16 +389,41 @@ static void gen8_gtt_set_pfn(struct intel_gvt_gtt_entry *e, unsigned long pfn) static bool gen8_gtt_test_pse(struct intel_gvt_gtt_entry *e) { - /* Entry doesn't have PSE bit. */ - if (get_pse_type(e->type) == GTT_TYPE_INVALID) - return false; + return !!(e->val64 & _PAGE_PSE); +} - e->type = get_entry_type(e->type); - if (!(e->val64 & _PAGE_PSE)) +static void gen8_gtt_clear_pse(struct intel_gvt_gtt_entry *e) +{ + if (gen8_gtt_test_pse(e)) { + switch (e->type) { + case GTT_TYPE_PPGTT_PTE_2M_ENTRY: + e->val64 &= ~_PAGE_PSE; + e->type = GTT_TYPE_PPGTT_PDE_ENTRY; + break; + case GTT_TYPE_PPGTT_PTE_1G_ENTRY: + e->type = GTT_TYPE_PPGTT_PDP_ENTRY; + e->val64 &= ~_PAGE_PSE; + break; + default: + WARN_ON(1); + } + } +} + +static bool gen8_gtt_test_ips(struct intel_gvt_gtt_entry *e) +{ + if (GEM_WARN_ON(e->type != GTT_TYPE_PPGTT_PDE_ENTRY)) return false; - e->type = get_pse_type(e->type); - return true; + return !!(e->val64 & GEN8_PDE_IPS_64K); +} + +static void gen8_gtt_clear_ips(struct intel_gvt_gtt_entry *e) +{ + if (GEM_WARN_ON(e->type != GTT_TYPE_PPGTT_PDE_ENTRY)) + return; + + e->val64 &= ~GEN8_PDE_IPS_64K; } static bool gen8_gtt_test_present(struct intel_gvt_gtt_entry *e) @@ -408,6 +450,21 @@ static void gtt_entry_set_present(struct intel_gvt_gtt_entry *e) e->val64 |= _PAGE_PRESENT; } +static bool gen8_gtt_test_64k_splited(struct intel_gvt_gtt_entry *e) +{ + return !!(e->val64 & GTT_SPTE_FLAG_64K_SPLITED); +} + +static void gen8_gtt_set_64k_splited(struct intel_gvt_gtt_entry *e) +{ + e->val64 |= GTT_SPTE_FLAG_64K_SPLITED; +} + +static void gen8_gtt_clear_64k_splited(struct intel_gvt_gtt_entry *e) +{ + e->val64 &= ~GTT_SPTE_FLAG_64K_SPLITED; +} + /* * Per-platform GMA routines. */ @@ -440,6 +497,12 @@ static struct intel_gvt_gtt_pte_ops gen8_gtt_pte_ops = { .set_present = gtt_entry_set_present, .test_present = gen8_gtt_test_present, .test_pse = gen8_gtt_test_pse, + .clear_pse = gen8_gtt_clear_pse, + .clear_ips = gen8_gtt_clear_ips, + .test_ips = gen8_gtt_test_ips, + .clear_64k_splited = gen8_gtt_clear_64k_splited, + .set_64k_splited = gen8_gtt_set_64k_splited, + .test_64k_splited = gen8_gtt_test_64k_splited, .get_pfn = gen8_gtt_get_pfn, .set_pfn = gen8_gtt_set_pfn, }; @@ -453,6 +516,27 @@ static struct intel_gvt_gtt_gma_ops gen8_gtt_gma_ops = { .gma_to_pml4_index = gen8_gma_to_pml4_index, }; +/* Update entry type per pse and ips bit. */ +static void update_entry_type_for_real(struct intel_gvt_gtt_pte_ops *pte_ops, + struct intel_gvt_gtt_entry *entry, bool ips) +{ + switch (entry->type) { + case GTT_TYPE_PPGTT_PDE_ENTRY: + case GTT_TYPE_PPGTT_PDP_ENTRY: + if (pte_ops->test_pse(entry)) + entry->type = get_pse_type(entry->type); + break; + case GTT_TYPE_PPGTT_PTE_4K_ENTRY: + if (ips) + entry->type = get_pse_type(entry->type); + break; + default: + GEM_BUG_ON(!gtt_type_is_entry(entry->type)); + } + + GEM_BUG_ON(entry->type == GTT_TYPE_INVALID); +} + /* * MM helpers. */ @@ -468,8 +552,7 @@ static void _ppgtt_get_root_entry(struct intel_vgpu_mm *mm, pte_ops->get_entry(guest ? mm->ppgtt_mm.guest_pdps : mm->ppgtt_mm.shadow_pdps, entry, index, false, 0, mm->vgpu); - - pte_ops->test_pse(entry); + update_entry_type_for_real(pte_ops, entry, false); } static inline void ppgtt_get_guest_root_entry(struct intel_vgpu_mm *mm, @@ -574,7 +657,8 @@ static inline int ppgtt_spt_get_entry( if (ret) return ret; - ops->test_pse(e); + update_entry_type_for_real(ops, e, guest ? + spt->guest_page.pde_ips : false); gvt_vdbg_mm("read ppgtt entry, spt type %d, entry type %d, index %lu, value %llx\n", type, e->type, index, e->val64); @@ -653,10 +737,12 @@ static void ppgtt_free_spt(struct intel_vgpu_ppgtt_spt *spt) 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); @@ -717,8 +803,9 @@ static inline struct intel_vgpu_ppgtt_spt *intel_vgpu_find_spt_by_mfn( 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) + 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; @@ -753,26 +840,12 @@ retry: 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; - - 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: @@ -780,6 +853,37 @@ 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) @@ -787,24 +891,38 @@ err_free_spt: (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, @@ -843,7 +961,8 @@ static inline void ppgtt_invalidate_pte(struct intel_vgpu_ppgtt_spt *spt, 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); @@ -855,14 +974,11 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt) 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) { @@ -871,9 +987,15 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt) gvt_vdbg_mm("invalidate 4K entry\n"); 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 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: @@ -899,6 +1021,22 @@ fail: return ret; } +static bool vgpu_ips_enabled(struct intel_vgpu *vgpu) +{ + struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; + + if (INTEL_GEN(dev_priv) == 9 || INTEL_GEN(dev_priv) == 10) { + u32 ips = vgpu_vreg_t(vgpu, GEN8_GAMW_ECO_DEV_RW_IA) & + GAMW_ECO_ENABLE_64K_IPS_FIELD; + + return ips == GAMW_ECO_ENABLE_64K_IPS_FIELD; + } else if (INTEL_GEN(dev_priv) >= 11) { + /* 64K paging only controlled by IPS bit in PTE now. */ + return true; + } else + return false; +} + static int ppgtt_populate_spt(struct intel_vgpu_ppgtt_spt *spt); static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry( @@ -906,35 +1044,54 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry( { struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops; struct intel_vgpu_ppgtt_spt *spt = NULL; + bool ips = false; int ret; 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 { + + if (ips != spt->guest_page.pde_ips) { + spt->guest_page.pde_ips = 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(vgpu, type, ops->get_pfn(we)); + 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); @@ -948,16 +1105,118 @@ static inline void ppgtt_generate_shadow_entry(struct intel_gvt_gtt_entry *se, 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); } +/** + * 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; @@ -970,16 +1229,33 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu, case GTT_TYPE_PPGTT_PTE_4K_ENTRY: 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 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; @@ -1062,8 +1338,12 @@ static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_ppgtt_spt *spt, 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: @@ -1286,7 +1566,7 @@ static int ppgtt_handle_guest_write_page_table( 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); @@ -1308,8 +1588,27 @@ static int ppgtt_handle_guest_write_page_table( 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; @@ -1391,7 +1690,17 @@ static int ppgtt_handle_guest_write_page_table_bytes( ppgtt_get_guest_entry(spt, &we, index); - ops->test_pse(&we); + /* + * 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); @@ -1881,7 +2190,7 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, } 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 diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 3792f2b7f4ff..b7bf68cc8418 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -63,6 +63,12 @@ struct intel_gvt_gtt_pte_ops { void (*clear_present)(struct intel_gvt_gtt_entry *e); void (*set_present)(struct intel_gvt_gtt_entry *e); bool (*test_pse)(struct intel_gvt_gtt_entry *e); + void (*clear_pse)(struct intel_gvt_gtt_entry *e); + bool (*test_ips)(struct intel_gvt_gtt_entry *e); + void (*clear_ips)(struct intel_gvt_gtt_entry *e); + bool (*test_64k_splited)(struct intel_gvt_gtt_entry *e); + void (*clear_64k_splited)(struct intel_gvt_gtt_entry *e); + void (*set_64k_splited)(struct intel_gvt_gtt_entry *e); void (*set_pfn)(struct intel_gvt_gtt_entry *e, unsigned long pfn); unsigned long (*get_pfn)(struct intel_gvt_gtt_entry *e); }; @@ -95,6 +101,7 @@ typedef enum { GTT_TYPE_GGTT_PTE, GTT_TYPE_PPGTT_PTE_4K_ENTRY, + GTT_TYPE_PPGTT_PTE_64K_ENTRY, GTT_TYPE_PPGTT_PTE_2M_ENTRY, GTT_TYPE_PPGTT_PTE_1G_ENTRY, @@ -220,6 +227,7 @@ struct intel_vgpu_ppgtt_spt { struct { intel_gvt_gtt_type_t type; + bool pde_ips; /* for 64KB PTEs */ void *vaddr; struct page *page; unsigned long mfn; @@ -227,6 +235,7 @@ struct intel_vgpu_ppgtt_spt { struct { intel_gvt_gtt_type_t type; + bool pde_ips; /* for 64KB PTEs */ unsigned long gfn; unsigned long write_cnt; struct intel_vgpu_oos_page *oos_page; diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c index 4e65266e7b95..712f9d14e720 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.c +++ b/drivers/gpu/drm/i915/gvt/gvt.c @@ -468,3 +468,7 @@ out_clean_idr: kfree(gvt); return ret; } + +#if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT) +MODULE_SOFTDEP("pre: kvmgt"); +#endif diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index e39492aaff6c..6b50f850dc28 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -210,6 +210,31 @@ static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu, return 0; } +static int gamw_echo_dev_rw_ia_write(struct intel_vgpu *vgpu, + unsigned int offset, void *p_data, unsigned int bytes) +{ + u32 ips = (*(u32 *)p_data) & GAMW_ECO_ENABLE_64K_IPS_FIELD; + + if (INTEL_GEN(vgpu->gvt->dev_priv) <= 10) { + if (ips == GAMW_ECO_ENABLE_64K_IPS_FIELD) + gvt_dbg_core("vgpu%d: ips enabled\n", vgpu->id); + else if (!ips) + gvt_dbg_core("vgpu%d: ips disabled\n", vgpu->id); + else { + /* All engines must be enabled together for vGPU, + * since we don't know which engine the ppgtt will + * bind to when shadowing. + */ + gvt_vgpu_err("Unsupported IPS setting %x, cannot enable 64K gtt.\n", + ips); + return -EINVAL; + } + } + + write_vreg(vgpu, offset, p_data, bytes); + return 0; +} + static int fence_mmio_read(struct intel_vgpu *vgpu, unsigned int off, void *p_data, unsigned int bytes) { @@ -1564,6 +1589,13 @@ static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu, return 0; } +static int bxt_edp_psr_imr_iir_write(struct intel_vgpu *vgpu, + unsigned int offset, void *p_data, unsigned int bytes) +{ + vgpu_vreg(vgpu, offset) = 0; + return 0; +} + static int mmio_read_from_hw(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { @@ -1774,7 +1806,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_RING_DFH(RING_HWSTAM, D_ALL, F_CMD_ACCESS, NULL, NULL); - MMIO_GM_RDR(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL); + MMIO_DH(GEN8_GAMW_ECO_DEV_RW_IA, D_BDW_PLUS, NULL, + gamw_echo_dev_rw_ia_write); + MMIO_GM_RDR(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL); MMIO_GM_RDR(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL); MMIO_GM_RDR(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL); @@ -3160,6 +3194,9 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt) MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT); MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT); + MMIO_DH(EDP_PSR_IMR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); + MMIO_DH(EDP_PSR_IIR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); + MMIO_D(RC6_CTX_BASE, D_BXT); MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT); diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h index f6dd9f717888..5af11cf1b482 100644 --- a/drivers/gpu/drm/i915/gvt/hypercall.h +++ b/drivers/gpu/drm/i915/gvt/hypercall.h @@ -53,7 +53,7 @@ struct intel_gvt_mpt { unsigned long (*gfn_to_mfn)(unsigned long handle, unsigned long gfn); int (*dma_map_guest_page)(unsigned long handle, unsigned long gfn, - dma_addr_t *dma_addr); + unsigned long size, dma_addr_t *dma_addr); void (*dma_unmap_guest_page)(unsigned long handle, dma_addr_t dma_addr); int (*map_gfn_to_mfn)(unsigned long handle, unsigned long gfn, diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index df4e4a07db3d..718ab307a500 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -94,6 +94,7 @@ struct gvt_dma { struct rb_node dma_addr_node; gfn_t gfn; dma_addr_t dma_addr; + unsigned long size; struct kref ref; }; @@ -106,22 +107,83 @@ static int kvmgt_guest_init(struct mdev_device *mdev); static void intel_vgpu_release_work(struct work_struct *work); static bool kvmgt_guest_exit(struct kvmgt_guest_info *info); +static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, + unsigned long size) +{ + int total_pages; + int npage; + int ret; + + total_pages = roundup(size, PAGE_SIZE) / PAGE_SIZE; + + for (npage = 0; npage < total_pages; npage++) { + unsigned long cur_gfn = gfn + npage; + + ret = vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &cur_gfn, 1); + WARN_ON(ret != 1); + } +} + +/* Pin a normal or compound guest page for dma. */ +static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, + unsigned long size, struct page **page) +{ + unsigned long base_pfn = 0; + int total_pages; + int npage; + int ret; + + total_pages = roundup(size, PAGE_SIZE) / PAGE_SIZE; + /* + * We pin the pages one-by-one to avoid allocating a big arrary + * on stack to hold pfns. + */ + for (npage = 0; npage < total_pages; npage++) { + unsigned long cur_gfn = gfn + npage; + unsigned long pfn; + + ret = vfio_pin_pages(mdev_dev(vgpu->vdev.mdev), &cur_gfn, 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); + 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) { + gvt_vgpu_err("The pages are not continuous\n"); + ret = -EINVAL; + npage++; + goto err; + } + } + + *page = pfn_to_page(base_pfn); + return 0; +err: + gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE); + return ret; +} + static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn, - dma_addr_t *dma_addr) + dma_addr_t *dma_addr, unsigned long size) { struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev; - struct page *page; - unsigned long pfn; + struct page *page = NULL; int ret; - /* Pin the page first. */ - ret = vfio_pin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1, - IOMMU_READ | IOMMU_WRITE, &pfn); - if (ret != 1) { - gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx: %d\n", - gfn, ret); - return -EINVAL; - } + ret = gvt_pin_guest_page(vgpu, gfn, size, &page); + if (ret) + return ret; if (!pfn_valid(pfn)) { gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn); @@ -130,27 +192,24 @@ static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn, } /* Setup DMA mapping. */ - page = pfn_to_page(pfn); - *dma_addr = dma_map_page(dev, page, 0, PAGE_SIZE, - PCI_DMA_BIDIRECTIONAL); - if (dma_mapping_error(dev, *dma_addr)) { - gvt_vgpu_err("DMA mapping failed for gfn 0x%lx\n", gfn); - vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1); - return -ENOMEM; + *dma_addr = dma_map_page(dev, page, 0, size, PCI_DMA_BIDIRECTIONAL); + ret = dma_mapping_error(dev, *dma_addr); + if (ret) { + gvt_vgpu_err("DMA mapping failed for pfn 0x%lx, ret %d\n", + page_to_pfn(page), ret); + gvt_unpin_guest_page(vgpu, gfn, size); } - return 0; + return ret; } static void gvt_dma_unmap_page(struct intel_vgpu *vgpu, unsigned long gfn, - dma_addr_t dma_addr) + dma_addr_t dma_addr, unsigned long size) { struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev; - int ret; - dma_unmap_page(dev, dma_addr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - ret = vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1); - WARN_ON(ret != 1); + dma_unmap_page(dev, dma_addr, size, PCI_DMA_BIDIRECTIONAL); + gvt_unpin_guest_page(vgpu, gfn, size); } static struct gvt_dma *__gvt_cache_find_dma_addr(struct intel_vgpu *vgpu, @@ -191,7 +250,7 @@ static struct gvt_dma *__gvt_cache_find_gfn(struct intel_vgpu *vgpu, gfn_t gfn) } static int __gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn, - dma_addr_t dma_addr) + dma_addr_t dma_addr, unsigned long size) { struct gvt_dma *new, *itr; struct rb_node **link, *parent = NULL; @@ -203,6 +262,7 @@ static int __gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn, new->vgpu = vgpu; new->gfn = gfn; new->dma_addr = dma_addr; + new->size = size; kref_init(&new->ref); /* gfn_cache maps gfn to struct gvt_dma. */ @@ -260,7 +320,7 @@ static void gvt_cache_destroy(struct intel_vgpu *vgpu) break; } dma = rb_entry(node, struct gvt_dma, gfn_node); - gvt_dma_unmap_page(vgpu, dma->gfn, dma->dma_addr); + gvt_dma_unmap_page(vgpu, dma->gfn, dma->dma_addr, dma->size); __gvt_cache_remove_entry(vgpu, dma); mutex_unlock(&vgpu->vdev.cache_lock); } @@ -515,7 +575,8 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb, if (!entry) continue; - gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr); + gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr, + entry->size); __gvt_cache_remove_entry(vgpu, entry); } mutex_unlock(&vgpu->vdev.cache_lock); @@ -1648,7 +1709,7 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn) } int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn, - dma_addr_t *dma_addr) + unsigned long size, dma_addr_t *dma_addr) { struct kvmgt_guest_info *info; struct intel_vgpu *vgpu; @@ -1665,11 +1726,11 @@ int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn, entry = __gvt_cache_find_gfn(info->vgpu, gfn); if (!entry) { - ret = gvt_dma_map_page(vgpu, gfn, dma_addr); + ret = gvt_dma_map_page(vgpu, gfn, dma_addr, size); if (ret) goto err_unlock; - ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr); + ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr, size); if (ret) goto err_unmap; } else { @@ -1681,7 +1742,7 @@ int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn, return 0; err_unmap: - gvt_dma_unmap_page(vgpu, gfn, *dma_addr); + gvt_dma_unmap_page(vgpu, gfn, *dma_addr, size); err_unlock: mutex_unlock(&info->vgpu->vdev.cache_lock); return ret; @@ -1691,7 +1752,8 @@ static void __gvt_dma_release(struct kref *ref) { struct gvt_dma *entry = container_of(ref, typeof(*entry), ref); - gvt_dma_unmap_page(entry->vgpu, entry->gfn, entry->dma_addr); + gvt_dma_unmap_page(entry->vgpu, entry->gfn, entry->dma_addr, + entry->size); __gvt_cache_remove_entry(entry->vgpu, entry); } diff --git a/drivers/gpu/drm/i915/gvt/mpt.h b/drivers/gpu/drm/i915/gvt/mpt.h index 32ffcd566cdd..67f19992b226 100644 --- a/drivers/gpu/drm/i915/gvt/mpt.h +++ b/drivers/gpu/drm/i915/gvt/mpt.h @@ -230,17 +230,18 @@ static inline unsigned long intel_gvt_hypervisor_gfn_to_mfn( /** * intel_gvt_hypervisor_dma_map_guest_page - setup dma map for guest page * @vgpu: a vGPU - * @gpfn: guest pfn + * @gfn: guest pfn + * @size: page size * @dma_addr: retrieve allocated dma addr * * Returns: * 0 on success, negative error code if failed. */ static inline int intel_gvt_hypervisor_dma_map_guest_page( - struct intel_vgpu *vgpu, unsigned long gfn, + struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size, dma_addr_t *dma_addr) { - return intel_gvt_host.mpt->dma_map_guest_page(vgpu->handle, gfn, + return intel_gvt_host.mpt->dma_map_guest_page(vgpu->handle, gfn, size, dma_addr); } diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 83a43970783f..f6fa916517c3 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -46,6 +46,7 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu) vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) = VGT_CAPS_FULL_48BIT_PPGTT; vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) |= VGT_CAPS_HWSP_EMULATION; + vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) |= VGT_CAPS_HUGE_GTT; vgpu_vreg_t(vgpu, vgtif_reg(avail_rs.mappable_gmadr.base)) = vgpu_aperture_gmadr_base(vgpu); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 099f97ef2303..b3aefd623557 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -2592,6 +2592,41 @@ static const struct file_operations i915_guc_log_relay_fops = { .release = i915_guc_log_relay_release, }; +static int i915_psr_sink_status_show(struct seq_file *m, void *data) +{ + u8 val; + static const char * const sink_status[] = { + "inactive", + "transition to active, capture and display", + "active, display from RFB", + "active, capture and display on sink device timings", + "transition to inactive, capture and display, timing re-sync", + "reserved", + "reserved", + "sink internal error", + }; + struct drm_connector *connector = m->private; + struct intel_dp *intel_dp = + enc_to_intel_dp(&intel_attached_encoder(connector)->base); + + if (connector->status != connector_status_connected) + return -ENODEV; + + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val) == 1) { + const char *str = "unknown"; + + val &= DP_PSR_SINK_STATE_MASK; + if (val < ARRAY_SIZE(sink_status)) + str = sink_status[val]; + seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val, str); + } else { + DRM_ERROR("dpcd read (at %u) failed\n", DP_PSR_STATUS); + } + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(i915_psr_sink_status); + static void psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m) { @@ -2643,26 +2678,6 @@ psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m) seq_printf(m, "Source PSR status: 0x%x [%s]\n", psr_status, "unknown"); } -static const char *psr_sink_status(u8 val) -{ - static const char * const sink_status[] = { - "inactive", - "transition to active, capture and display", - "active, display from RFB", - "active, capture and display on sink device timings", - "transition to inactive, capture and display, timing re-sync", - "reserved", - "reserved", - "sink internal error" - }; - - val &= DP_PSR_SINK_STATE_MASK; - if (val < ARRAY_SIZE(sink_status)) - return sink_status[val]; - - return "unknown"; -} - static int i915_edp_psr_status(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -2706,15 +2721,6 @@ static int i915_edp_psr_status(struct seq_file *m, void *data) } psr_source_status(dev_priv, m); - - if (dev_priv->psr.enabled) { - struct drm_dp_aux *aux = &dev_priv->psr.enabled->aux; - u8 val; - - if (drm_dp_dpcd_readb(aux, DP_PSR_STATUS, &val) == 1) - seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val, - psr_sink_status(val)); - } mutex_unlock(&dev_priv->psr.lock); if (READ_ONCE(dev_priv->psr.debug)) { @@ -2761,86 +2767,6 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_edp_psr_debug_fops, i915_edp_psr_debug_get, i915_edp_psr_debug_set, "%llu\n"); -static int i915_sink_crc(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_device *dev = &dev_priv->drm; - struct intel_connector *connector; - struct drm_connector_list_iter conn_iter; - struct intel_dp *intel_dp = NULL; - struct drm_modeset_acquire_ctx ctx; - int ret; - u8 crc[6]; - - drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE); - - drm_connector_list_iter_begin(dev, &conn_iter); - - for_each_intel_connector_iter(connector, &conn_iter) { - struct drm_crtc *crtc; - struct drm_connector_state *state; - struct intel_crtc_state *crtc_state; - - if (connector->base.connector_type != DRM_MODE_CONNECTOR_eDP) - continue; - -retry: - ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx); - if (ret) - goto err; - - state = connector->base.state; - if (!state->best_encoder) - continue; - - crtc = state->crtc; - ret = drm_modeset_lock(&crtc->mutex, &ctx); - if (ret) - goto err; - - crtc_state = to_intel_crtc_state(crtc->state); - if (!crtc_state->base.active) - continue; - - /* - * We need to wait for all crtc updates to complete, to make - * sure any pending modesets and plane updates are completed. - */ - if (crtc_state->base.commit) { - ret = wait_for_completion_interruptible(&crtc_state->base.commit->hw_done); - - if (ret) - goto err; - } - - intel_dp = enc_to_intel_dp(state->best_encoder); - - ret = intel_dp_sink_crc(intel_dp, crtc_state, crc); - if (ret) - goto err; - - seq_printf(m, "%02x%02x%02x%02x%02x%02x\n", - crc[0], crc[1], crc[2], - crc[3], crc[4], crc[5]); - goto out; - -err: - if (ret == -EDEADLK) { - ret = drm_modeset_backoff(&ctx); - if (!ret) - goto retry; - } - goto out; - } - ret = -ENODEV; -out: - drm_connector_list_iter_end(&conn_iter); - drm_modeset_drop_locks(&ctx); - drm_modeset_acquire_fini(&ctx); - - return ret; -} - static int i915_energy_uJ(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -4786,7 +4712,6 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_ppgtt_info", i915_ppgtt_info, 0}, {"i915_llc", i915_llc, 0}, {"i915_edp_psr_status", i915_edp_psr_status, 0}, - {"i915_sink_crc_eDP1", i915_sink_crc, 0}, {"i915_energy_uJ", i915_energy_uJ, 0}, {"i915_runtime_pm_status", i915_runtime_pm_status, 0}, {"i915_power_domain_info", i915_power_domain_info, 0}, @@ -4968,9 +4893,12 @@ int i915_debugfs_connector_add(struct drm_connector *connector) debugfs_create_file("i915_dpcd", S_IRUGO, root, connector, &i915_dpcd_fops); - if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { debugfs_create_file("i915_panel_timings", S_IRUGO, root, connector, &i915_panel_fops); + debugfs_create_file("i915_psr_sink_status", S_IRUGO, root, + connector, &i915_psr_sink_status_fops); + } return 0; } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 0db3c83cce29..f8cfd16be534 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -104,8 +104,13 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level, vaf.fmt = fmt; vaf.va = &args; - dev_printk(level, kdev, "[" DRM_NAME ":%ps] %pV", - __builtin_return_address(0), &vaf); + if (is_error) + dev_printk(level, kdev, "%pV", &vaf); + else + dev_printk(level, kdev, "[" DRM_NAME ":%ps] %pV", + __builtin_return_address(0), &vaf); + + va_end(args); if (is_error && !shown_bug_once) { /* @@ -117,8 +122,6 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level, dev_notice(kdev, "%s", FDO_BUG_MSG); shown_bug_once = true; } - - va_end(args); } /* Map PCH device id to PCH type, or PCH_NONE if unknown. */ @@ -679,7 +682,7 @@ static int i915_load_modeset_init(struct drm_device *dev) ret = i915_gem_init(dev_priv); if (ret) - goto cleanup_irq; + goto cleanup_modeset; intel_setup_overlay(dev_priv); @@ -699,6 +702,8 @@ cleanup_gem: if (i915_gem_suspend(dev_priv)) DRM_ERROR("failed to idle hardware; continuing to unload!\n"); i915_gem_fini(dev_priv); +cleanup_modeset: + intel_modeset_cleanup(dev); cleanup_irq: drm_irq_uninstall(dev); intel_teardown_gmbus(dev_priv); @@ -895,7 +900,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv, spin_lock_init(&dev_priv->uncore.lock); mutex_init(&dev_priv->sb_lock); - mutex_init(&dev_priv->modeset_restore_lock); mutex_init(&dev_priv->av_mutex); mutex_init(&dev_priv->wm.wm_mutex); mutex_init(&dev_priv->pps_mutex); @@ -1149,8 +1153,6 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) intel_uncore_sanitize(dev_priv); - intel_opregion_setup(dev_priv); - i915_gem_load_init_fences(dev_priv); /* On the 945G/GM, the chipset reports the MSI capability on the @@ -1179,10 +1181,16 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) ret = intel_gvt_init(dev_priv); if (ret) - goto err_ggtt; + goto err_msi; + + intel_opregion_setup(dev_priv); return 0; +err_msi: + if (pdev->msi_enabled) + pci_disable_msi(pdev); + pm_qos_remove_request(&dev_priv->pm_qos); err_ggtt: i915_ggtt_cleanup_hw(dev_priv); err_perf: @@ -1415,6 +1423,7 @@ out_fini: drm_dev_fini(&dev_priv->drm); out_free: kfree(dev_priv); + pci_set_drvdata(pdev, NULL); return ret; } @@ -1560,11 +1569,6 @@ static int i915_drm_suspend(struct drm_device *dev) struct pci_dev *pdev = dev_priv->drm.pdev; pci_power_t opregion_target_state; - /* ignore lid events during suspend */ - mutex_lock(&dev_priv->modeset_restore_lock); - dev_priv->modeset_restore = MODESET_SUSPENDED; - mutex_unlock(&dev_priv->modeset_restore_lock); - disable_rpm_wakeref_asserts(dev_priv); /* We do a lot of poking in a lot of registers, make sure they work @@ -1577,7 +1581,7 @@ static int i915_drm_suspend(struct drm_device *dev) intel_display_suspend(dev); - intel_dp_mst_suspend(dev); + intel_dp_mst_suspend(dev_priv); intel_runtime_pm_disable_interrupts(dev_priv); intel_hpd_cancel_work(dev_priv); @@ -1742,7 +1746,7 @@ static int i915_drm_resume(struct drm_device *dev) dev_priv->display.hpd_irq_setup(dev_priv); spin_unlock_irq(&dev_priv->irq_lock); - intel_dp_mst_resume(dev); + intel_dp_mst_resume(dev_priv); intel_display_resume(dev); @@ -1760,10 +1764,6 @@ static int i915_drm_resume(struct drm_device *dev) intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING, false); - mutex_lock(&dev_priv->modeset_restore_lock); - dev_priv->modeset_restore = MODESET_DONE; - mutex_unlock(&dev_priv->modeset_restore_lock); - intel_opregion_notify_adapter(dev_priv, PCI_D0); enable_rpm_wakeref_asserts(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index eeb002a47032..0f49f9988dfa 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -86,8 +86,8 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20180709" -#define DRIVER_TIMESTAMP 1531175967 +#define DRIVER_DATE "20180719" +#define DRIVER_TIMESTAMP 1532015279 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and * WARN_ON()) for hw state sanity checks to check for unexpected conditions @@ -299,7 +299,6 @@ struct i915_hotplug { u32 event_bits; struct delayed_work reenable_work; - struct intel_digital_port *irq_port[I915_MAX_PORTS]; u32 long_port_mask; u32 short_port_mask; struct work_struct dig_port_work; @@ -650,6 +649,7 @@ enum intel_sbi_destination { #define QUIRK_BACKLIGHT_PRESENT (1<<3) #define QUIRK_PIN_SWIZZLED_PAGES (1<<5) #define QUIRK_INCREASE_T12_DELAY (1<<6) +#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7) struct intel_fbdev; struct intel_fbc_work; @@ -1002,12 +1002,6 @@ struct i915_gem_mm { #define I915_ENGINE_WEDGED_TIMEOUT (60 * HZ) /* Reset but no recovery? */ -enum modeset_restore { - MODESET_ON_LID_OPEN, - MODESET_DONE, - MODESET_SUSPENDED, -}; - #define DP_AUX_A 0x40 #define DP_AUX_B 0x10 #define DP_AUX_C 0x20 @@ -1730,8 +1724,6 @@ struct drm_i915_private { unsigned long quirks; - enum modeset_restore modeset_restore; - struct mutex modeset_restore_lock; struct drm_atomic_state *modeset_restore_state; struct drm_modeset_acquire_ctx reset_ctx; @@ -2557,6 +2549,9 @@ intel_info(const struct drm_i915_private *dev_priv) IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv)) #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4) +#define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \ + IS_GEMINILAKE(dev_priv) || \ + IS_KABYLAKE(dev_priv)) /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte * rows, which changed the alignment requirements and fence programming. @@ -2739,8 +2734,6 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, void intel_hpd_init(struct drm_i915_private *dev_priv); void intel_hpd_init_work(struct drm_i915_private *dev_priv); void intel_hpd_cancel_work(struct drm_i915_private *dev_priv); -enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv, - enum hpd_pin pin); enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv, enum port port); bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin); @@ -3304,7 +3297,7 @@ unsigned long i915_gem_shrink(struct drm_i915_private *i915, unsigned long i915_gem_shrink_all(struct drm_i915_private *i915); void i915_gem_shrinker_register(struct drm_i915_private *i915); void i915_gem_shrinker_unregister(struct drm_i915_private *i915); - +void i915_gem_shrinker_taints_mutex(struct mutex *mutex); /* i915_gem_tiling.c */ static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index b35cbfd16c9c..fcc73a6ab503 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -802,7 +802,7 @@ void i915_gem_flush_ggtt_writes(struct drm_i915_private *dev_priv) * that was!). */ - wmb(); + i915_gem_chipset_flush(dev_priv); intel_runtime_pm_get(dev_priv); spin_lock_irq(&dev_priv->uncore.lock); @@ -1627,6 +1627,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, goto err; } + /* Writes not allowed into this read-only object */ + if (i915_gem_object_is_readonly(obj)) { + ret = -EINVAL; + goto err; + } + trace_i915_gem_object_pwrite(obj, args->offset, args->size); ret = -ENODEV; @@ -2012,6 +2018,10 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf) pgoff_t page_offset; int ret; + /* Sanity check that we allow writing into this object */ + if (i915_gem_object_is_readonly(obj) && write) + return VM_FAULT_SIGBUS; + /* We don't use vmf->pgoff since that has the fake offset */ page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT; @@ -5029,32 +5039,32 @@ void i915_gem_sanitize(struct drm_i915_private *i915) mutex_unlock(&i915->drm.struct_mutex); } -int i915_gem_suspend(struct drm_i915_private *dev_priv) +int i915_gem_suspend(struct drm_i915_private *i915) { - struct drm_device *dev = &dev_priv->drm; int ret; GEM_TRACE("\n"); - intel_runtime_pm_get(dev_priv); - intel_suspend_gt_powersave(dev_priv); + intel_runtime_pm_get(i915); + intel_suspend_gt_powersave(i915); - mutex_lock(&dev->struct_mutex); + mutex_lock(&i915->drm.struct_mutex); - /* We have to flush all the executing contexts to main memory so + /* + * We have to flush all the executing contexts to main memory so * that they can saved in the hibernation image. To ensure the last * context image is coherent, we have to switch away from it. That - * leaves the dev_priv->kernel_context still active when + * leaves the i915->kernel_context still active when * we actually suspend, and its image in memory may not match the GPU * state. Fortunately, the kernel_context is disposable and we do * not rely on its state. */ - if (!i915_terminally_wedged(&dev_priv->gpu_error)) { - ret = i915_gem_switch_to_kernel_context(dev_priv); + if (!i915_terminally_wedged(&i915->gpu_error)) { + ret = i915_gem_switch_to_kernel_context(i915); if (ret) goto err_unlock; - ret = i915_gem_wait_for_idle(dev_priv, + ret = i915_gem_wait_for_idle(i915, I915_WAIT_INTERRUPTIBLE | I915_WAIT_LOCKED | I915_WAIT_FOR_IDLE_BOOST, @@ -5062,33 +5072,37 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv) if (ret && ret != -EIO) goto err_unlock; - assert_kernel_context_is_current(dev_priv); + assert_kernel_context_is_current(i915); } - mutex_unlock(&dev->struct_mutex); + i915_retire_requests(i915); /* ensure we flush after wedging */ - intel_uc_suspend(dev_priv); + mutex_unlock(&i915->drm.struct_mutex); + + intel_uc_suspend(i915); - cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work); - cancel_delayed_work_sync(&dev_priv->gt.retire_work); + cancel_delayed_work_sync(&i915->gpu_error.hangcheck_work); + cancel_delayed_work_sync(&i915->gt.retire_work); - /* As the idle_work is rearming if it detects a race, play safe and + /* + * As the idle_work is rearming if it detects a race, play safe and * repeat the flush until it is definitely idle. */ - drain_delayed_work(&dev_priv->gt.idle_work); + drain_delayed_work(&i915->gt.idle_work); - /* Assert that we sucessfully flushed all the work and + /* + * Assert that we successfully flushed all the work and * reset the GPU back to its idle, low power state. */ - WARN_ON(dev_priv->gt.awake); - if (WARN_ON(!intel_engines_are_idle(dev_priv))) - i915_gem_set_wedged(dev_priv); /* no hope, discard everything */ + WARN_ON(i915->gt.awake); + if (WARN_ON(!intel_engines_are_idle(i915))) + i915_gem_set_wedged(i915); /* no hope, discard everything */ - intel_runtime_pm_put(dev_priv); + intel_runtime_pm_put(i915); return 0; err_unlock: - mutex_unlock(&dev->struct_mutex); - intel_runtime_pm_put(dev_priv); + mutex_unlock(&i915->drm.struct_mutex); + intel_runtime_pm_put(i915); return ret; } @@ -5311,13 +5325,17 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv) ret = __i915_gem_restart_engines(dev_priv); if (ret) goto cleanup_uc; -out: + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); - return ret; + + return 0; cleanup_uc: intel_uc_fini_hw(dev_priv); - goto out; +out: + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); + + return ret; } static int __intel_engines_record_defaults(struct drm_i915_private *i915) @@ -5548,6 +5566,8 @@ err_init_hw: WARN_ON(i915_gem_suspend(dev_priv)); i915_gem_suspend_late(dev_priv); + i915_gem_drain_workqueue(dev_priv); + mutex_lock(&dev_priv->drm.struct_mutex); intel_uc_fini_hw(dev_priv); err_uc_init: diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index abd81fb9b0b6..f00c7fbef79e 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -204,9 +204,9 @@ static int ppgtt_bind_vma(struct i915_vma *vma, return err; } - /* Currently applicable only to VLV */ + /* Applicable to VLV, and gen8+ */ pte_flags = 0; - if (vma->obj->gt_ro) + if (i915_gem_object_is_readonly(vma->obj)) pte_flags |= PTE_READ_ONLY; vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags); @@ -244,10 +244,13 @@ static void clear_pages(struct i915_vma *vma) } static gen8_pte_t gen8_pte_encode(dma_addr_t addr, - enum i915_cache_level level) + enum i915_cache_level level, + u32 flags) { - gen8_pte_t pte = _PAGE_PRESENT | _PAGE_RW; - pte |= addr; + gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW; + + if (unlikely(flags & PTE_READ_ONLY)) + pte &= ~_PAGE_RW; switch (level) { case I915_CACHE_NONE: @@ -531,6 +534,14 @@ static void vm_free_page(struct i915_address_space *vm, struct page *page) static void i915_address_space_init(struct i915_address_space *vm, struct drm_i915_private *dev_priv) { + /* + * The vm->mutex must be reclaim safe (for use in the shrinker). + * Do a dummy acquire now under fs_reclaim so that any allocation + * attempt holding the lock is immediately reported by lockdep. + */ + mutex_init(&vm->mutex); + i915_gem_shrinker_taints_mutex(&vm->mutex); + GEM_BUG_ON(!vm->total); drm_mm_init(&vm->mm, 0, vm->total); vm->mm.head_node.color = I915_COLOR_UNEVICTABLE; @@ -551,6 +562,8 @@ static void i915_address_space_fini(struct i915_address_space *vm) spin_unlock(&vm->free_pages.lock); drm_mm_takedown(&vm->mm); + + mutex_destroy(&vm->mutex); } static int __setup_page_dma(struct i915_address_space *vm, @@ -711,7 +724,7 @@ static void gen8_initialize_pt(struct i915_address_space *vm, struct i915_page_table *pt) { fill_px(vm, pt, - gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC)); + gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0)); } static void gen6_initialize_pt(struct gen6_hw_ppgtt *ppgtt, @@ -859,7 +872,7 @@ static bool gen8_ppgtt_clear_pt(struct i915_address_space *vm, unsigned int pte = gen8_pte_index(start); unsigned int pte_end = pte + num_entries; const gen8_pte_t scratch_pte = - gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC); + gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0); gen8_pte_t *vaddr; GEM_BUG_ON(num_entries > pt->used_ptes); @@ -1031,10 +1044,11 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt, struct i915_page_directory_pointer *pdp, struct sgt_dma *iter, struct gen8_insert_pte *idx, - enum i915_cache_level cache_level) + enum i915_cache_level cache_level, + u32 flags) { struct i915_page_directory *pd; - const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level); + const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags); gen8_pte_t *vaddr; bool ret; @@ -1085,14 +1099,14 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt, static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm, struct i915_vma *vma, enum i915_cache_level cache_level, - u32 unused) + u32 flags) { struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); struct sgt_dma iter = sgt_dma(vma); struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start); gen8_ppgtt_insert_pte_entries(ppgtt, &ppgtt->pdp, &iter, &idx, - cache_level); + cache_level, flags); vma->page_sizes.gtt = I915_GTT_PAGE_SIZE; } @@ -1100,9 +1114,10 @@ static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm, static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma, struct i915_page_directory_pointer **pdps, struct sgt_dma *iter, - enum i915_cache_level cache_level) + enum i915_cache_level cache_level, + u32 flags) { - const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level); + const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags); u64 start = vma->node.start; dma_addr_t rem = iter->sg->length; @@ -1218,19 +1233,21 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma, static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm, struct i915_vma *vma, enum i915_cache_level cache_level, - u32 unused) + u32 flags) { struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); struct sgt_dma iter = sgt_dma(vma); struct i915_page_directory_pointer **pdps = ppgtt->pml4.pdps; if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) { - gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level); + gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level, + flags); } else { struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start); while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++], - &iter, &idx, cache_level)) + &iter, &idx, cache_level, + flags)) GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4); vma->page_sizes.gtt = I915_GTT_PAGE_SIZE; @@ -1568,7 +1585,7 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) { struct i915_address_space *vm = &ppgtt->vm; const gen8_pte_t scratch_pte = - gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC); + gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0); u64 start = 0, length = ppgtt->vm.total; if (use_4lvl(vm)) { @@ -1645,6 +1662,13 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915) 1ULL << 48 : 1ULL << 32; + /* + * From bdw, there is support for read-only pages in the PPGTT. + * + * XXX GVT is not honouring the lack of RW in the PTE bits. + */ + ppgtt->vm.has_read_only = !intel_vgpu_active(i915); + i915_address_space_init(&ppgtt->vm, i915); /* There are only few exceptions for gen >=6. chv and bxt. @@ -2451,7 +2475,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm, gen8_pte_t __iomem *pte = (gen8_pte_t __iomem *)ggtt->gsm + (offset >> PAGE_SHIFT); - gen8_set_pte(pte, gen8_pte_encode(addr, level)); + gen8_set_pte(pte, gen8_pte_encode(addr, level, 0)); ggtt->invalidate(vm->i915); } @@ -2459,14 +2483,19 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm, static void gen8_ggtt_insert_entries(struct i915_address_space *vm, struct i915_vma *vma, enum i915_cache_level level, - u32 unused) + u32 flags) { struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); struct sgt_iter sgt_iter; gen8_pte_t __iomem *gtt_entries; - const gen8_pte_t pte_encode = gen8_pte_encode(0, level); + const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0); dma_addr_t addr; + /* + * Note that we ignore PTE_READ_ONLY here. The caller must be careful + * not to allow the user to override access to a read only page. + */ + gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm; gtt_entries += vma->node.start >> PAGE_SHIFT; for_each_sgt_dma(addr, sgt_iter, vma->pages) @@ -2532,7 +2561,7 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm, unsigned first_entry = start >> PAGE_SHIFT; unsigned num_entries = length >> PAGE_SHIFT; const gen8_pte_t scratch_pte = - gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC); + gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0); gen8_pte_t __iomem *gtt_base = (gen8_pte_t __iomem *)ggtt->gsm + first_entry; const int max_entries = ggtt_total_entries(ggtt) - first_entry; @@ -2593,13 +2622,14 @@ struct insert_entries { struct i915_address_space *vm; struct i915_vma *vma; enum i915_cache_level level; + u32 flags; }; static int bxt_vtd_ggtt_insert_entries__cb(void *_arg) { struct insert_entries *arg = _arg; - gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, 0); + gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags); bxt_vtd_ggtt_wa(arg->vm); return 0; @@ -2608,9 +2638,9 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg) static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm, struct i915_vma *vma, enum i915_cache_level level, - u32 unused) + u32 flags) { - struct insert_entries arg = { vm, vma, level }; + struct insert_entries arg = { vm, vma, level, flags }; stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL); } @@ -2701,9 +2731,9 @@ static int ggtt_bind_vma(struct i915_vma *vma, struct drm_i915_gem_object *obj = vma->obj; u32 pte_flags; - /* Currently applicable only to VLV */ + /* Applicable to VLV (gen8+ do not support RO in the GGTT) */ pte_flags = 0; - if (obj->gt_ro) + if (i915_gem_object_is_readonly(obj)) pte_flags |= PTE_READ_ONLY; intel_runtime_pm_get(i915); @@ -2741,7 +2771,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma, /* Currently applicable only to VLV */ pte_flags = 0; - if (vma->obj->gt_ro) + if (i915_gem_object_is_readonly(vma->obj)) pte_flags |= PTE_READ_ONLY; if (flags & I915_VMA_LOCAL_BIND) { @@ -3581,6 +3611,10 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv) */ mutex_lock(&dev_priv->drm.struct_mutex); i915_address_space_init(&ggtt->vm, dev_priv); + + /* Only VLV supports read-only GGTT mappings */ + ggtt->vm.has_read_only = IS_VALLEYVIEW(dev_priv); + if (!HAS_LLC(dev_priv) && !USES_PPGTT(dev_priv)) ggtt->vm.mm.color_adjust = i915_gtt_color_adjust; mutex_unlock(&dev_priv->drm.struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index feda45dfd481..2a116a91420b 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -293,6 +293,8 @@ struct i915_address_space { bool closed; + struct mutex mutex; /* protects vma and our lists */ + struct i915_page_dma scratch_page; struct i915_page_table *scratch_pt; struct i915_page_directory *scratch_pd; @@ -329,7 +331,12 @@ struct i915_address_space { struct list_head unbound_list; struct pagestash free_pages; - bool pt_kmap_wc; + + /* Some systems require uncached updates of the page directories */ + bool pt_kmap_wc:1; + + /* Some systems support read-only mappings for GGTT and/or PPGTT */ + bool has_read_only:1; /* FIXME: Need a more generic return type */ gen6_pte_t (*pte_encode)(dma_addr_t addr, diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h index c3c6f2e588fb..83e5e01fa9ea 100644 --- a/drivers/gpu/drm/i915/i915_gem_object.h +++ b/drivers/gpu/drm/i915/i915_gem_object.h @@ -141,7 +141,6 @@ struct drm_i915_gem_object { * Is the object to be mapped as read-only to the GPU * Only honoured if hardware has relevant pte bit */ - unsigned long gt_ro:1; unsigned int cache_level:3; unsigned int cache_coherent:2; #define I915_BO_CACHE_COHERENT_FOR_READ BIT(0) @@ -268,7 +267,6 @@ struct drm_i915_gem_object { union { struct i915_gem_userptr { uintptr_t ptr; - unsigned read_only :1; struct i915_mm_struct *mm; struct i915_mmu_object *mmu_object; @@ -358,6 +356,18 @@ static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj) reservation_object_unlock(obj->resv); } +static inline void +i915_gem_object_set_readonly(struct drm_i915_gem_object *obj) +{ + obj->base.vma_node.readonly = true; +} + +static inline bool +i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj) +{ + return obj->base.vma_node.readonly; +} + static inline bool i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj) { diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index c61f5b80fee3..ea90d3a0d511 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -23,6 +23,7 @@ */ #include <linux/oom.h> +#include <linux/sched/mm.h> #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/swap.h> @@ -531,3 +532,14 @@ void i915_gem_shrinker_unregister(struct drm_i915_private *i915) WARN_ON(unregister_oom_notifier(&i915->mm.oom_notifier)); unregister_shrinker(&i915->mm.shrinker); } + +void i915_gem_shrinker_taints_mutex(struct mutex *mutex) +{ + if (!IS_ENABLED(CONFIG_LOCKDEP)) + return; + + fs_reclaim_acquire(GFP_KERNEL); + mutex_lock(mutex); + mutex_unlock(mutex); + fs_reclaim_release(GFP_KERNEL); +} diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 055f8687776d..53440bf87650 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -344,6 +344,35 @@ static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv, *size = stolen_top - *base; } +static void icl_get_stolen_reserved(struct drm_i915_private *dev_priv, + resource_size_t *base, + resource_size_t *size) +{ + u64 reg_val = I915_READ64(GEN6_STOLEN_RESERVED); + + DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val); + + *base = reg_val & GEN11_STOLEN_RESERVED_ADDR_MASK; + + switch (reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK) { + case GEN8_STOLEN_RESERVED_1M: + *size = 1024 * 1024; + break; + case GEN8_STOLEN_RESERVED_2M: + *size = 2 * 1024 * 1024; + break; + case GEN8_STOLEN_RESERVED_4M: + *size = 4 * 1024 * 1024; + break; + case GEN8_STOLEN_RESERVED_8M: + *size = 8 * 1024 * 1024; + break; + default: + *size = 8 * 1024 * 1024; + MISSING_CASE(reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK); + } +} + int i915_gem_init_stolen(struct drm_i915_private *dev_priv) { resource_size_t reserved_base, stolen_top; @@ -400,7 +429,9 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv) gen7_get_stolen_reserved(dev_priv, &reserved_base, &reserved_size); break; - default: + case 8: + case 9: + case 10: if (IS_LP(dev_priv)) chv_get_stolen_reserved(dev_priv, &reserved_base, &reserved_size); @@ -408,6 +439,11 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv) bdw_get_stolen_reserved(dev_priv, &reserved_base, &reserved_size); break; + case 11: + default: + icl_get_stolen_reserved(dev_priv, &reserved_base, + &reserved_size); + break; } /* diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 854bd51b9478..dcd6e230d16a 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -507,7 +507,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) struct mm_struct *mm = obj->userptr.mm->mm; unsigned int flags = 0; - if (!obj->userptr.read_only) + if (!i915_gem_object_is_readonly(obj)) flags |= FOLL_WRITE; ret = -EFAULT; @@ -643,7 +643,7 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) if (pvec) /* defer to worker if malloc fails */ pinned = __get_user_pages_fast(obj->userptr.ptr, num_pages, - !obj->userptr.read_only, + !i915_gem_object_is_readonly(obj), pvec); } @@ -789,10 +789,15 @@ i915_gem_userptr_ioctl(struct drm_device *dev, return -EFAULT; if (args->flags & I915_USERPTR_READ_ONLY) { - /* On almost all of the current hw, we cannot tell the GPU that a - * page is readonly, so this is just a placeholder in the uAPI. + struct i915_hw_ppgtt *ppgtt; + + /* + * On almost all of the older hw, we cannot tell the GPU that + * a page is readonly. */ - return -ENODEV; + ppgtt = dev_priv->kernel_context->ppgtt; + if (!ppgtt || !ppgtt->vm.has_read_only) + return -ENODEV; } obj = i915_gem_object_alloc(dev_priv); @@ -806,7 +811,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev, i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC); obj->userptr.ptr = args->user_ptr; - obj->userptr.read_only = !!(args->flags & I915_USERPTR_READ_ONLY); + if (args->flags & I915_USERPTR_READ_ONLY) + i915_gem_object_set_readonly(obj); /* And keep a pointer to the current->mm for resolving the user pages * at binding. This means that we need to hook into the mmu_notifier diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 495b9d27990e..5dadefca2ad2 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -263,9 +263,9 @@ static u32 gen11_gt_engine_identity(struct drm_i915_private * const i915, const unsigned int bank, const unsigned int bit); -bool gen11_reset_one_iir(struct drm_i915_private * const i915, - const unsigned int bank, - const unsigned int bit) +static bool gen11_reset_one_iir(struct drm_i915_private * const i915, + const unsigned int bank, + const unsigned int bit) { void __iomem * const regs = i915->regs; u32 dw; @@ -1576,122 +1576,122 @@ static void gen8_gt_irq_handler(struct drm_i915_private *i915, } } -static bool gen11_port_hotplug_long_detect(enum port port, u32 val) +static bool gen11_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { - switch (port) { - case PORT_C: + switch (pin) { + case HPD_PORT_C: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC1); - case PORT_D: + case HPD_PORT_D: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC2); - case PORT_E: + case HPD_PORT_E: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC3); - case PORT_F: + case HPD_PORT_F: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC4); default: return false; } } -static bool bxt_port_hotplug_long_detect(enum port port, u32 val) +static bool bxt_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { - switch (port) { - case PORT_A: + switch (pin) { + case HPD_PORT_A: return val & PORTA_HOTPLUG_LONG_DETECT; - case PORT_B: + case HPD_PORT_B: return val & PORTB_HOTPLUG_LONG_DETECT; - case PORT_C: + case HPD_PORT_C: return val & PORTC_HOTPLUG_LONG_DETECT; default: return false; } } -static bool icp_ddi_port_hotplug_long_detect(enum port port, u32 val) +static bool icp_ddi_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { - switch (port) { - case PORT_A: + switch (pin) { + case HPD_PORT_A: return val & ICP_DDIA_HPD_LONG_DETECT; - case PORT_B: + case HPD_PORT_B: return val & ICP_DDIB_HPD_LONG_DETECT; default: return false; } } -static bool icp_tc_port_hotplug_long_detect(enum port port, u32 val) +static bool icp_tc_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { - switch (port) { - case PORT_C: + switch (pin) { + case HPD_PORT_C: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC1); - case PORT_D: + case HPD_PORT_D: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC2); - case PORT_E: + case HPD_PORT_E: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC3); - case PORT_F: + case HPD_PORT_F: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC4); default: return false; } } -static bool spt_port_hotplug2_long_detect(enum port port, u32 val) +static bool spt_port_hotplug2_long_detect(enum hpd_pin pin, u32 val) { - switch (port) { - case PORT_E: + switch (pin) { + case HPD_PORT_E: return val & PORTE_HOTPLUG_LONG_DETECT; default: return false; } } -static bool spt_port_hotplug_long_detect(enum port port, u32 val) +static bool spt_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { - switch (port) { - case PORT_A: + switch (pin) { + case HPD_PORT_A: return val & PORTA_HOTPLUG_LONG_DETECT; - case PORT_B: + case HPD_PORT_B: return val & PORTB_HOTPLUG_LONG_DETECT; - case PORT_C: + case HPD_PORT_C: return val & PORTC_HOTPLUG_LONG_DETECT; - case PORT_D: + case HPD_PORT_D: return val & PORTD_HOTPLUG_LONG_DETECT; default: return false; } } -static bool ilk_port_hotplug_long_detect(enum port port, u32 val) +static bool ilk_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { - switch (port) { - case PORT_A: + switch (pin) { + case HPD_PORT_A: return val & DIGITAL_PORTA_HOTPLUG_LONG_DETECT; default: return false; } } -static bool pch_port_hotplug_long_detect(enum port port, u32 val) +static bool pch_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { - switch (port) { - case PORT_B: + switch (pin) { + case HPD_PORT_B: return val & PORTB_HOTPLUG_LONG_DETECT; - case PORT_C: + case HPD_PORT_C: return val & PORTC_HOTPLUG_LONG_DETECT; - case PORT_D: + case HPD_PORT_D: return val & PORTD_HOTPLUG_LONG_DETECT; default: return false; } } -static bool i9xx_port_hotplug_long_detect(enum port port, u32 val) +static bool i9xx_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { - switch (port) { - case PORT_B: + switch (pin) { + case HPD_PORT_B: return val & PORTB_HOTPLUG_INT_LONG_PULSE; - case PORT_C: + case HPD_PORT_C: return val & PORTC_HOTPLUG_INT_LONG_PULSE; - case PORT_D: + case HPD_PORT_D: return val & PORTD_HOTPLUG_INT_LONG_PULSE; default: return false; @@ -1709,27 +1709,22 @@ static void intel_get_hpd_pins(struct drm_i915_private *dev_priv, u32 *pin_mask, u32 *long_mask, u32 hotplug_trigger, u32 dig_hotplug_reg, const u32 hpd[HPD_NUM_PINS], - bool long_pulse_detect(enum port port, u32 val)) + bool long_pulse_detect(enum hpd_pin pin, u32 val)) { - enum port port; - int i; + enum hpd_pin pin; - for_each_hpd_pin(i) { - if ((hpd[i] & hotplug_trigger) == 0) + for_each_hpd_pin(pin) { + if ((hpd[pin] & hotplug_trigger) == 0) continue; - *pin_mask |= BIT(i); - - port = intel_hpd_pin_to_port(dev_priv, i); - if (port == PORT_NONE) - continue; + *pin_mask |= BIT(pin); - if (long_pulse_detect(port, dig_hotplug_reg)) - *long_mask |= BIT(i); + if (long_pulse_detect(pin, dig_hotplug_reg)) + *long_mask |= BIT(pin); } - DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x\n", - hotplug_trigger, dig_hotplug_reg, *pin_mask); + DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x, long 0x%08x\n", + hotplug_trigger, dig_hotplug_reg, *pin_mask, *long_mask); } diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 49fcc4679db6..295e981e4a39 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -44,10 +44,6 @@ i915_param_named(modeset, int, 0400, "Use kernel modesetting [KMS] (0=disable, " "1=on, -1=force vga console preference [default])"); -i915_param_named_unsafe(panel_ignore_lid, int, 0600, - "Override lid status (0=autodetect, 1=autodetect disabled [default], " - "-1=force lid closed, -2=force lid open)"); - i915_param_named_unsafe(enable_dc, int, 0400, "Enable power-saving display C-states. " "(-1=auto [default]; 0=disable; 1=up to DC5; 2=up to DC6)"); @@ -92,7 +88,7 @@ i915_param_named_unsafe(enable_ppgtt, int, 0400, i915_param_named_unsafe(enable_psr, int, 0600, "Enable PSR " - "(0=disabled, 1=enabled - link mode chosen per-platform, 2=force link-standby mode, 3=force link-off mode) " + "(0=disabled, 1=enabled) " "Default: -1 (use per-chip default)"); i915_param_named_unsafe(alpha_support, bool, 0400, diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h index aebe0469ddaa..6c4d4a21474b 100644 --- a/drivers/gpu/drm/i915/i915_params.h +++ b/drivers/gpu/drm/i915/i915_params.h @@ -36,7 +36,6 @@ struct drm_printer; #define I915_PARAMS_FOR_EACH(param) \ param(char *, vbt_firmware, NULL) \ param(int, modeset, -1) \ - param(int, panel_ignore_lid, 1) \ param(int, lvds_channel_mode, 0) \ param(int, panel_use_ssc, -1) \ param(int, vbt_sdvo_panel_type, -1) \ diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 55543f1b0236..6a4d1388ad2d 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -674,10 +674,16 @@ MODULE_DEVICE_TABLE(pci, pciidlist); static void i915_pci_remove(struct pci_dev *pdev) { - struct drm_device *dev = pci_get_drvdata(pdev); + struct drm_device *dev; + + dev = pci_get_drvdata(pdev); + if (!dev) /* driver load aborted, nothing to cleanup */ + return; i915_driver_unload(dev); drm_dev_put(dev); + + pci_set_drvdata(pdev, NULL); } static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -712,6 +718,11 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; + if (i915_inject_load_failure()) { + i915_pci_remove(pdev); + return -ENODEV; + } + err = i915_live_selftests(pdev); if (err) { i915_pci_remove(pdev); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0424e45f88db..8af945d8a995 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -412,6 +412,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN8_STOLEN_RESERVED_4M (2 << 7) #define GEN8_STOLEN_RESERVED_8M (3 << 7) #define GEN6_STOLEN_RESERVED_ENABLE (1 << 0) +#define GEN11_STOLEN_RESERVED_ADDR_MASK (0xFFFFFFFFFFFULL << 20) /* VGA stuff */ @@ -3122,6 +3123,7 @@ enum i915_power_well_id { #define GMBUS_RATE_400KHZ (2 << 8) /* reserved on Pineview */ #define GMBUS_RATE_1MHZ (3 << 8) /* reserved on Pineview */ #define GMBUS_HOLD_EXT (1 << 7) /* 300ns hold time, rsvd on Pineview */ +#define GMBUS_BYTE_CNT_OVERRIDE (1 << 6) #define GMBUS_PIN_DISABLED 0 #define GMBUS_PIN_SSC 1 #define GMBUS_PIN_VGADDC 2 @@ -3151,6 +3153,7 @@ enum i915_power_well_id { #define GMBUS_CYCLE_STOP (4 << 25) #define GMBUS_BYTE_COUNT_SHIFT 16 #define GMBUS_BYTE_COUNT_MAX 256U +#define GEN9_GMBUS_BYTE_COUNT_MAX 511U #define GMBUS_SLAVE_INDEX_SHIFT 8 #define GMBUS_SLAVE_ADDR_SHIFT 1 #define GMBUS_SLAVE_READ (1 << 0) @@ -4602,6 +4605,16 @@ enum { #define VIDEO_DIP_ENABLE_GMP_HSW (1 << 4) #define VIDEO_DIP_ENABLE_SPD_HSW (1 << 0) +#define DRM_DIP_ENABLE (1 << 28) +#define PSR_VSC_BIT_7_SET (1 << 27) +#define VSC_SELECT_MASK (0x3 << 26) +#define VSC_SELECT_SHIFT 26 +#define VSC_DIP_HW_HEA_DATA (0 << 26) +#define VSC_DIP_HW_HEA_SW_DATA (1 << 26) +#define VSC_DIP_HW_DATA_SW_HEA (2 << 26) +#define VSC_DIP_SW_HEA_DATA (3 << 26) +#define VDIP_ENABLE_PPS (1 << 24) + /* Panel power sequencing */ #define PPS_BASE 0x61200 #define VLV_PPS_BASE (VLV_DISPLAY_BASE + PPS_BASE) @@ -7665,6 +7678,110 @@ enum { #define SHOTPLUG_CTL_TC _MMIO(0xc4034) #define ICP_TC_HPD_ENABLE(tc_port) (8 << (tc_port) * 4) +/* Icelake DSC Rate Control Range Parameter Registers */ +#define DSCA_RC_RANGE_PARAMETERS_0 _MMIO(0x6B240) +#define DSCA_RC_RANGE_PARAMETERS_0_UDW _MMIO(0x6B240 + 4) +#define DSCC_RC_RANGE_PARAMETERS_0 _MMIO(0x6BA40) +#define DSCC_RC_RANGE_PARAMETERS_0_UDW _MMIO(0x6BA40 + 4) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_PB (0x78208) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PB (0x78208 + 4) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_PB (0x78308) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PB (0x78308 + 4) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_PC (0x78408) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PC (0x78408 + 4) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_PC (0x78508) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PC (0x78508 + 4) +#define ICL_DSC0_RC_RANGE_PARAMETERS_0(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_0_PB, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_0_PC) +#define ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PB, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PC) +#define ICL_DSC1_RC_RANGE_PARAMETERS_0(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_0_PB, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_0_PC) +#define ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PB, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PC) +#define RC_BPG_OFFSET_SHIFT 10 +#define RC_MAX_QP_SHIFT 5 +#define RC_MIN_QP_SHIFT 0 + +#define DSCA_RC_RANGE_PARAMETERS_1 _MMIO(0x6B248) +#define DSCA_RC_RANGE_PARAMETERS_1_UDW _MMIO(0x6B248 + 4) +#define DSCC_RC_RANGE_PARAMETERS_1 _MMIO(0x6BA48) +#define DSCC_RC_RANGE_PARAMETERS_1_UDW _MMIO(0x6BA48 + 4) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_PB (0x78210) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PB (0x78210 + 4) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_PB (0x78310) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PB (0x78310 + 4) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_PC (0x78410) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PC (0x78410 + 4) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_PC (0x78510) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PC (0x78510 + 4) +#define ICL_DSC0_RC_RANGE_PARAMETERS_1(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_1_PB, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_1_PC) +#define ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PB, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PC) +#define ICL_DSC1_RC_RANGE_PARAMETERS_1(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_1_PB, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_1_PC) +#define ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PB, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PC) + +#define DSCA_RC_RANGE_PARAMETERS_2 _MMIO(0x6B250) +#define DSCA_RC_RANGE_PARAMETERS_2_UDW _MMIO(0x6B250 + 4) +#define DSCC_RC_RANGE_PARAMETERS_2 _MMIO(0x6BA50) +#define DSCC_RC_RANGE_PARAMETERS_2_UDW _MMIO(0x6BA50 + 4) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_PB (0x78218) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PB (0x78218 + 4) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_PB (0x78318) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PB (0x78318 + 4) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_PC (0x78418) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PC (0x78418 + 4) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_PC (0x78518) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PC (0x78518 + 4) +#define ICL_DSC0_RC_RANGE_PARAMETERS_2(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_2_PB, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_2_PC) +#define ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PB, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PC) +#define ICL_DSC1_RC_RANGE_PARAMETERS_2(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_2_PB, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_2_PC) +#define ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PB, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PC) + +#define DSCA_RC_RANGE_PARAMETERS_3 _MMIO(0x6B258) +#define DSCA_RC_RANGE_PARAMETERS_3_UDW _MMIO(0x6B258 + 4) +#define DSCC_RC_RANGE_PARAMETERS_3 _MMIO(0x6BA58) +#define DSCC_RC_RANGE_PARAMETERS_3_UDW _MMIO(0x6BA58 + 4) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_PB (0x78220) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PB (0x78220 + 4) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_PB (0x78320) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PB (0x78320 + 4) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_PC (0x78420) +#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PC (0x78420 + 4) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_PC (0x78520) +#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PC (0x78520 + 4) +#define ICL_DSC0_RC_RANGE_PARAMETERS_3(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_3_PB, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_3_PC) +#define ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PB, \ + _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PC) +#define ICL_DSC1_RC_RANGE_PARAMETERS_3(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_3_PB, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_3_PC) +#define ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PB, \ + _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PC) + #define ICP_TC_HPD_LONG_DETECT(tc_port) (2 << (tc_port) * 4) #define ICP_TC_HPD_SHORT_DETECT(tc_port) (1 << (tc_port) * 4) @@ -7840,12 +7957,25 @@ enum { #define _HSW_VIDEO_DIP_VSC_ECC_B 0x61344 #define _HSW_VIDEO_DIP_GCP_B 0x61210 +/* Icelake PPS_DATA and _ECC DIP Registers. + * These are available for transcoders B,C and eDP. + * Adding the _A so as to reuse the _MMIO_TRANS2 + * definition, with which it offsets to the right location. + */ + +#define _ICL_VIDEO_DIP_PPS_DATA_A 0x60350 +#define _ICL_VIDEO_DIP_PPS_DATA_B 0x61350 +#define _ICL_VIDEO_DIP_PPS_ECC_A 0x603D4 +#define _ICL_VIDEO_DIP_PPS_ECC_B 0x613D4 + #define HSW_TVIDEO_DIP_CTL(trans) _MMIO_TRANS2(trans, _HSW_VIDEO_DIP_CTL_A) #define HSW_TVIDEO_DIP_AVI_DATA(trans, i) _MMIO_TRANS2(trans, _HSW_VIDEO_DIP_AVI_DATA_A + (i) * 4) #define HSW_TVIDEO_DIP_VS_DATA(trans, i) _MMIO_TRANS2(trans, _HSW_VIDEO_DIP_VS_DATA_A + (i) * 4) #define HSW_TVIDEO_DIP_SPD_DATA(trans, i) _MMIO_TRANS2(trans, _HSW_VIDEO_DIP_SPD_DATA_A + (i) * 4) #define HSW_TVIDEO_DIP_GCP(trans) _MMIO_TRANS2(trans, _HSW_VIDEO_DIP_GCP_A) #define HSW_TVIDEO_DIP_VSC_DATA(trans, i) _MMIO_TRANS2(trans, _HSW_VIDEO_DIP_VSC_DATA_A + (i) * 4) +#define ICL_VIDEO_DIP_PPS_DATA(trans, i) _MMIO_TRANS2(trans, _ICL_VIDEO_DIP_PPS_DATA_A + (i) * 4) +#define ICL_VIDEO_DIP_PPS_ECC(trans, i) _MMIO_TRANS2(trans, _ICL_VIDEO_DIP_PPS_ECC_A + (i) * 4) #define _HSW_STEREO_3D_CTL_A 0x70020 #define S3D_ENABLE (1 << 31) @@ -10218,4 +10348,310 @@ enum skl_power_gate { _ICL_PHY_MISC_B) #define ICL_PHY_MISC_DE_IO_COMP_PWR_DOWN (1 << 23) +/* Icelake Display Stream Compression Registers */ +#define DSCA_PICTURE_PARAMETER_SET_0 0x6B200 +#define DSCC_PICTURE_PARAMETER_SET_0 0x6BA00 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB 0x78270 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB 0x78370 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC 0x78470 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PC 0x78570 +#define ICL_DSC0_PICTURE_PARAMETER_SET_0(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_0(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_0_PC) +#define DSC_VBR_ENABLE (1 << 19) +#define DSC_422_ENABLE (1 << 18) +#define DSC_COLOR_SPACE_CONVERSION (1 << 17) +#define DSC_BLOCK_PREDICTION (1 << 16) +#define DSC_LINE_BUF_DEPTH_SHIFT 12 +#define DSC_BPC_SHIFT 8 +#define DSC_VER_MIN_SHIFT 4 +#define DSC_VER_MAJ (0x1 << 0) + +#define DSCA_PICTURE_PARAMETER_SET_1 0x6B204 +#define DSCC_PICTURE_PARAMETER_SET_1 0x6BA04 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_1_PB 0x78274 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_1_PB 0x78374 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_1_PC 0x78474 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_1_PC 0x78574 +#define ICL_DSC0_PICTURE_PARAMETER_SET_1(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_1_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_1_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_1(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_1_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_1_PC) +#define DSC_BPP(bpp) ((bpp) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_2 0x6B208 +#define DSCC_PICTURE_PARAMETER_SET_2 0x6BA08 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_2_PB 0x78278 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_2_PB 0x78378 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_2_PC 0x78478 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_2_PC 0x78578 +#define ICL_DSC0_PICTURE_PARAMETER_SET_2(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_2_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_2_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_2(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_2_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_2_PC) +#define DSC_PIC_WIDTH(pic_width) ((pic_width) << 16) +#define DSC_PIC_HEIGHT(pic_height) ((pic_height) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_3 0x6B20C +#define DSCC_PICTURE_PARAMETER_SET_3 0x6BA0C +#define _ICL_DSC0_PICTURE_PARAMETER_SET_3_PB 0x7827C +#define _ICL_DSC1_PICTURE_PARAMETER_SET_3_PB 0x7837C +#define _ICL_DSC0_PICTURE_PARAMETER_SET_3_PC 0x7847C +#define _ICL_DSC1_PICTURE_PARAMETER_SET_3_PC 0x7857C +#define ICL_DSC0_PICTURE_PARAMETER_SET_3(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_3_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_3_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_3(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_3_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_3_PC) +#define DSC_SLICE_WIDTH(slice_width) ((slice_width) << 16) +#define DSC_SLICE_HEIGHT(slice_height) ((slice_height) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_4 0x6B210 +#define DSCC_PICTURE_PARAMETER_SET_4 0x6BA10 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB 0x78280 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_4_PB 0x78380 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC 0x78480 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC 0x78580 +#define ICL_DSC0_PICTURE_PARAMETER_SET_4(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_4(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC) +#define DSC_INITIAL_DEC_DELAY(dec_delay) ((dec_delay) << 16) +#define DSC_INITIAL_XMIT_DELAY(xmit_delay) ((xmit_delay) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_5 0x6B214 +#define DSCC_PICTURE_PARAMETER_SET_5 0x6BA14 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB 0x78284 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_5_PB 0x78384 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC 0x78484 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC 0x78584 +#define ICL_DSC0_PICTURE_PARAMETER_SET_5(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_5(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC) +#define DSC_SCALE_DEC_INTINT(scale_dec) ((scale_dec) << 16) +#define DSC_SCALE_INC_INT(scale_inc) ((scale_inc) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_6 0x6B218 +#define DSCC_PICTURE_PARAMETER_SET_6 0x6BA18 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_6_PB 0x78288 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_6_PB 0x78388 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_6_PC 0x78488 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_6_PC 0x78588 +#define ICL_DSC0_PICTURE_PARAMETER_SET_6(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_6_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_6_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_6(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_6_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_6_PC) +#define DSC_FLATNESS_MAX_QP(max_qp) (qp << 24) +#define DSC_FLATNESS_MIN_QP(min_qp) (qp << 16) +#define DSC_FIRST_LINE_BPG_OFFSET(offset) ((offset) << 8) +#define DSC_INITIAL_SCALE_VALUE(value) ((value) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_7 0x6B21C +#define DSCC_PICTURE_PARAMETER_SET_7 0x6BA1C +#define _ICL_DSC0_PICTURE_PARAMETER_SET_7_PB 0x7828C +#define _ICL_DSC1_PICTURE_PARAMETER_SET_7_PB 0x7838C +#define _ICL_DSC0_PICTURE_PARAMETER_SET_7_PC 0x7848C +#define _ICL_DSC1_PICTURE_PARAMETER_SET_7_PC 0x7858C +#define ICL_DSC0_PICTURE_PARAMETER_SET_7(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_7_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_7_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_7(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_7_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_7_PC) +#define DSC_NFL_BPG_OFFSET(bpg_offset) ((bpg_offset) << 16) +#define DSC_SLICE_BPG_OFFSET(bpg_offset) ((bpg_offset) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_8 0x6B220 +#define DSCC_PICTURE_PARAMETER_SET_8 0x6BA20 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_8_PB 0x78290 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_8_PB 0x78390 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_8_PC 0x78490 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_8_PC 0x78590 +#define ICL_DSC0_PICTURE_PARAMETER_SET_8(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_8_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_8_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_8(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_8_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_8_PC) +#define DSC_INITIAL_OFFSET(initial_offset) ((initial_offset) << 16) +#define DSC_FINAL_OFFSET(final_offset) ((final_offset) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_9 0x6B224 +#define DSCC_PICTURE_PARAMETER_SET_9 0x6BA24 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_9_PB 0x78294 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_9_PB 0x78394 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_9_PC 0x78494 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_9_PC 0x78594 +#define ICL_DSC0_PICTURE_PARAMETER_SET_9(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_9_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_9_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_9(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_9_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_9_PC) +#define DSC_RC_EDGE_FACTOR(rc_edge_fact) ((rc_edge_fact) << 16) +#define DSC_RC_MODEL_SIZE(rc_model_size) ((rc_model_size) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_10 0x6B228 +#define DSCC_PICTURE_PARAMETER_SET_10 0x6BA28 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_10_PB 0x78298 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_10_PB 0x78398 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_10_PC 0x78498 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_10_PC 0x78598 +#define ICL_DSC0_PICTURE_PARAMETER_SET_10(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_10_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_10_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_10(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_10_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_10_PC) +#define DSC_RC_TARGET_OFF_LOW(rc_tgt_off_low) ((rc_tgt_off_low) << 20) +#define DSC_RC_TARGET_OFF_HIGH(rc_tgt_off_high) ((rc_tgt_off_high) << 16) +#define DSC_RC_QUANT_INC_LIMIT1(lim) ((lim) << 8) +#define DSC_RC_QUANT_INC_LIMIT0(lim) ((lim) << 0) + +#define DSCA_PICTURE_PARAMETER_SET_11 0x6B22C +#define DSCC_PICTURE_PARAMETER_SET_11 0x6BA2C +#define _ICL_DSC0_PICTURE_PARAMETER_SET_11_PB 0x7829C +#define _ICL_DSC1_PICTURE_PARAMETER_SET_11_PB 0x7839C +#define _ICL_DSC0_PICTURE_PARAMETER_SET_11_PC 0x7849C +#define _ICL_DSC1_PICTURE_PARAMETER_SET_11_PC 0x7859C +#define ICL_DSC0_PICTURE_PARAMETER_SET_11(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_11_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_11_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_11(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_11_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_11_PC) + +#define DSCA_PICTURE_PARAMETER_SET_12 0x6B260 +#define DSCC_PICTURE_PARAMETER_SET_12 0x6BA60 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_12_PB 0x782A0 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_12_PB 0x783A0 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_12_PC 0x784A0 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_12_PC 0x785A0 +#define ICL_DSC0_PICTURE_PARAMETER_SET_12(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_12_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_12_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_12(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_12_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_12_PC) + +#define DSCA_PICTURE_PARAMETER_SET_13 0x6B264 +#define DSCC_PICTURE_PARAMETER_SET_13 0x6BA64 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_13_PB 0x782A4 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_13_PB 0x783A4 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_13_PC 0x784A4 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_13_PC 0x785A4 +#define ICL_DSC0_PICTURE_PARAMETER_SET_13(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_13_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_13_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_13(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_13_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_13_PC) + +#define DSCA_PICTURE_PARAMETER_SET_14 0x6B268 +#define DSCC_PICTURE_PARAMETER_SET_14 0x6BA68 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_14_PB 0x782A8 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_14_PB 0x783A8 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_14_PC 0x784A8 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_14_PC 0x785A8 +#define ICL_DSC0_PICTURE_PARAMETER_SET_14(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_14_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_14_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_14(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_14_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_14_PC) + +#define DSCA_PICTURE_PARAMETER_SET_15 0x6B26C +#define DSCC_PICTURE_PARAMETER_SET_15 0x6BA6C +#define _ICL_DSC0_PICTURE_PARAMETER_SET_15_PB 0x782AC +#define _ICL_DSC1_PICTURE_PARAMETER_SET_15_PB 0x783AC +#define _ICL_DSC0_PICTURE_PARAMETER_SET_15_PC 0x784AC +#define _ICL_DSC1_PICTURE_PARAMETER_SET_15_PC 0x785AC +#define ICL_DSC0_PICTURE_PARAMETER_SET_15(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_15_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_15_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_15(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_15_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_15_PC) + +#define DSCA_PICTURE_PARAMETER_SET_16 0x6B270 +#define DSCC_PICTURE_PARAMETER_SET_16 0x6BA70 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_16_PB 0x782B0 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_16_PB 0x783B0 +#define _ICL_DSC0_PICTURE_PARAMETER_SET_16_PC 0x784B0 +#define _ICL_DSC1_PICTURE_PARAMETER_SET_16_PC 0x785B0 +#define ICL_DSC0_PICTURE_PARAMETER_SET_16(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_16_PB, \ + _ICL_DSC0_PICTURE_PARAMETER_SET_16_PC) +#define ICL_DSC1_PICTURE_PARAMETER_SET_16(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_16_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_16_PC) +#define DSC_SLICE_PER_LINE(slice_per_line) ((slice_per_line) << 16) +#define DSC_SLICE_CHUNK_SIZE(slice_chunk_aize) (slice_chunk_size << 0) + +/* Icelake Rate Control Buffer Threshold Registers */ +#define DSCA_RC_BUF_THRESH_0 _MMIO(0x6B230) +#define DSCA_RC_BUF_THRESH_0_UDW _MMIO(0x6B230 + 4) +#define DSCC_RC_BUF_THRESH_0 _MMIO(0x6BA30) +#define DSCC_RC_BUF_THRESH_0_UDW _MMIO(0x6BA30 + 4) +#define _ICL_DSC0_RC_BUF_THRESH_0_PB (0x78254) +#define _ICL_DSC0_RC_BUF_THRESH_0_UDW_PB (0x78254 + 4) +#define _ICL_DSC1_RC_BUF_THRESH_0_PB (0x78354) +#define _ICL_DSC1_RC_BUF_THRESH_0_UDW_PB (0x78354 + 4) +#define _ICL_DSC0_RC_BUF_THRESH_0_PC (0x78454) +#define _ICL_DSC0_RC_BUF_THRESH_0_UDW_PC (0x78454 + 4) +#define _ICL_DSC1_RC_BUF_THRESH_0_PC (0x78554) +#define _ICL_DSC1_RC_BUF_THRESH_0_UDW_PC (0x78554 + 4) +#define ICL_DSC0_RC_BUF_THRESH_0(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_BUF_THRESH_0_PB, \ + _ICL_DSC0_RC_BUF_THRESH_0_PC) +#define ICL_DSC0_RC_BUF_THRESH_0_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_BUF_THRESH_0_UDW_PB, \ + _ICL_DSC0_RC_BUF_THRESH_0_UDW_PC) +#define ICL_DSC1_RC_BUF_THRESH_0(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_BUF_THRESH_0_PB, \ + _ICL_DSC1_RC_BUF_THRESH_0_PC) +#define ICL_DSC1_RC_BUF_THRESH_0_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_BUF_THRESH_0_UDW_PB, \ + _ICL_DSC1_RC_BUF_THRESH_0_UDW_PC) + +#define DSCA_RC_BUF_THRESH_1 _MMIO(0x6B238) +#define DSCA_RC_BUF_THRESH_1_UDW _MMIO(0x6B238 + 4) +#define DSCC_RC_BUF_THRESH_1 _MMIO(0x6BA38) +#define DSCC_RC_BUF_THRESH_1_UDW _MMIO(0x6BA38 + 4) +#define _ICL_DSC0_RC_BUF_THRESH_1_PB (0x7825C) +#define _ICL_DSC0_RC_BUF_THRESH_1_UDW_PB (0x7825C + 4) +#define _ICL_DSC1_RC_BUF_THRESH_1_PB (0x7835C) +#define _ICL_DSC1_RC_BUF_THRESH_1_UDW_PB (0x7835C + 4) +#define _ICL_DSC0_RC_BUF_THRESH_1_PC (0x7845C) +#define _ICL_DSC0_RC_BUF_THRESH_1_UDW_PC (0x7845C + 4) +#define _ICL_DSC1_RC_BUF_THRESH_1_PC (0x7855C) +#define _ICL_DSC1_RC_BUF_THRESH_1_UDW_PC (0x7855C + 4) +#define ICL_DSC0_RC_BUF_THRESH_1(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_BUF_THRESH_1_PB, \ + _ICL_DSC0_RC_BUF_THRESH_1_PC) +#define ICL_DSC0_RC_BUF_THRESH_1_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC0_RC_BUF_THRESH_1_UDW_PB, \ + _ICL_DSC0_RC_BUF_THRESH_1_UDW_PC) +#define ICL_DSC1_RC_BUF_THRESH_1(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_BUF_THRESH_1_PB, \ + _ICL_DSC1_RC_BUF_THRESH_1_PC) +#define ICL_DSC1_RC_BUF_THRESH_1_UDW(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ + _ICL_DSC1_RC_BUF_THRESH_1_UDW_PB, \ + _ICL_DSC1_RC_BUF_THRESH_1_UDW_PC) + #endif /* _I915_REG_H_ */ diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h index 9766e806dce6..a73472dd12fd 100644 --- a/drivers/gpu/drm/i915/i915_selftest.h +++ b/drivers/gpu/drm/i915/i915_selftest.h @@ -99,6 +99,6 @@ __printf(2, 3) bool __igt_timeout(unsigned long timeout, const char *fmt, ...); #define igt_timeout(t, fmt, ...) \ - __igt_timeout((t), KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) + __igt_timeout((t), KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* !__I915_SELFTEST_H__ */ diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index ed4e0fb558f7..11d834f94220 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -942,6 +942,14 @@ static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx) } active = kmalloc(sizeof(*active), GFP_KERNEL); + + /* kmalloc may retire the vma->last_active request (thanks shrinker)! */ + if (unlikely(!i915_gem_active_raw(&vma->last_active, + &vma->vm->i915->drm.struct_mutex))) { + kfree(active); + goto out; + } + if (unlikely(!active)) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 32838ed89ee7..39d66f8493fa 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1808,15 +1808,24 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state) I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp); } -void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder) +void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder); uint32_t val = I915_READ(reg); val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK | TRANS_DDI_DP_VC_PAYLOAD_ALLOC); val |= TRANS_DDI_PORT_NONE; I915_WRITE(reg, val); + + if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME && + intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) { + DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n"); + /* Quirk time at 100ms for reliable operation */ + msleep(100); + } } int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, @@ -3630,7 +3639,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) goto err; intel_dig_port->hpd_pulse = intel_dp_hpd_pulse; - dev_priv->hotplug.irq_port[port] = intel_dig_port; } /* In theory we don't need the encoder->type check, but leave it just in diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index e348b27e901f..87e4cfbfd096 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -5837,7 +5837,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state, intel_ddi_set_vc_payload_alloc(old_crtc_state, false); if (!transcoder_is_dsi(cpu_transcoder)) - intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder); + intel_ddi_disable_transcoder_func(old_crtc_state); if (INTEL_GEN(dev_priv) >= 9) skylake_scaler_disable(intel_crtc); @@ -14849,6 +14849,18 @@ static void quirk_increase_t12_delay(struct drm_device *dev) DRM_INFO("Applying T12 delay quirk\n"); } +/* + * GeminiLake NUC HDMI outputs require additional off time + * this allows the onboard retimer to correctly sync to signal + */ +static void quirk_increase_ddi_disabled_time(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + + dev_priv->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME; + DRM_INFO("Applying Increase DDI Disabled quirk\n"); +} + struct intel_quirk { int device; int subsystem_vendor; @@ -14935,6 +14947,13 @@ static struct intel_quirk intel_quirks[] = { /* Toshiba Satellite P50-C-18C */ { 0x191B, 0x1179, 0xF840, quirk_increase_t12_delay }, + + /* GeminiLake NUC */ + { 0x3185, 0x8086, 0x2072, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x8086, 0x2072, quirk_increase_ddi_disabled_time }, + /* ASRock ITX*/ + { 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, }; static void intel_init_quirks(struct drm_device *dev) @@ -15890,6 +15909,8 @@ void intel_modeset_cleanup(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); + flush_workqueue(dev_priv->modeset_wq); + flush_work(&dev_priv->atomic_helper.free_work); WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list)); diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h index ca5a10f3400d..9292001cdd14 100644 --- a/drivers/gpu/drm/i915/intel_display.h +++ b/drivers/gpu/drm/i915/intel_display.h @@ -289,6 +289,10 @@ struct intel_link_m_n { &(dev)->mode_config.encoder_list, \ base.head) +#define for_each_intel_dp(dev, intel_encoder) \ + for_each_intel_encoder(dev, intel_encoder) \ + for_each_if(intel_encoder_is_dp(intel_encoder)) + #define for_each_intel_connector_iter(intel_connector, iter) \ while ((intel_connector = to_intel_connector(drm_connector_list_iter_next(iter)))) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 53302bb77ad6..cd0f649b57a5 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -600,14 +600,8 @@ static enum pipe vlv_find_free_pps(struct drm_i915_private *dev_priv) * We don't have power sequencer currently. * Pick one that's not used by other ports. */ - for_each_intel_encoder(&dev_priv->drm, encoder) { - struct intel_dp *intel_dp; - - if (encoder->type != INTEL_OUTPUT_DP && - encoder->type != INTEL_OUTPUT_EDP) - continue; - - intel_dp = enc_to_intel_dp(&encoder->base); + for_each_intel_dp(&dev_priv->drm, encoder) { + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); if (encoder->type == INTEL_OUTPUT_EDP) { WARN_ON(intel_dp->active_pipe != INVALID_PIPE && @@ -799,19 +793,8 @@ void intel_power_sequencer_reset(struct drm_i915_private *dev_priv) * should use them always. */ - for_each_intel_encoder(&dev_priv->drm, encoder) { - struct intel_dp *intel_dp; - - if (encoder->type != INTEL_OUTPUT_DP && - encoder->type != INTEL_OUTPUT_EDP && - encoder->type != INTEL_OUTPUT_DDI) - continue; - - intel_dp = enc_to_intel_dp(&encoder->base); - - /* Skip pure DVI/HDMI DDI encoders */ - if (!i915_mmio_reg_valid(intel_dp->output_reg)) - continue; + for_each_intel_dp(&dev_priv->drm, encoder) { + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); WARN_ON(intel_dp->active_pipe != INVALID_PIPE); @@ -2830,10 +2813,6 @@ static void vlv_disable_dp(struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); - - intel_psr_disable(intel_dp, old_crtc_state); - intel_disable_dp(encoder, old_crtc_state, old_conn_state); } @@ -3046,10 +3025,7 @@ static void vlv_enable_dp(struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { - struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); - intel_edp_backlight_on(pipe_config, conn_state); - intel_psr_enable(intel_dp, pipe_config); } static void g4x_pre_enable_dp(struct intel_encoder *encoder, @@ -3104,16 +3080,9 @@ static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv, lockdep_assert_held(&dev_priv->pps_mutex); - for_each_intel_encoder(&dev_priv->drm, encoder) { - struct intel_dp *intel_dp; - enum port port; - - if (encoder->type != INTEL_OUTPUT_DP && - encoder->type != INTEL_OUTPUT_EDP) - continue; - - intel_dp = enc_to_intel_dp(&encoder->base); - port = dp_to_dig_port(intel_dp)->base.port; + for_each_intel_dp(&dev_priv->drm, encoder) { + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + enum port port = encoder->port; WARN(intel_dp->active_pipe == pipe, "stealing pipe %c power sequencer from active (e)DP port %c\n", @@ -3905,129 +3874,6 @@ intel_dp_configure_mst(struct intel_dp *intel_dp) intel_dp->is_mst); } -static int intel_dp_sink_crc_stop(struct intel_dp *intel_dp, - struct intel_crtc_state *crtc_state, bool disable_wa) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc); - u8 buf; - int ret = 0; - int count = 0; - int attempts = 10; - - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0) { - DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n"); - ret = -EIO; - goto out; - } - - if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK, - buf & ~DP_TEST_SINK_START) < 0) { - DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n"); - ret = -EIO; - goto out; - } - - do { - intel_wait_for_vblank(dev_priv, intel_crtc->pipe); - - if (drm_dp_dpcd_readb(&intel_dp->aux, - DP_TEST_SINK_MISC, &buf) < 0) { - ret = -EIO; - goto out; - } - count = buf & DP_TEST_COUNT_MASK; - } while (--attempts && count); - - if (attempts == 0) { - DRM_DEBUG_KMS("TIMEOUT: Sink CRC counter is not zeroed after calculation is stopped\n"); - ret = -ETIMEDOUT; - } - - out: - if (disable_wa) - hsw_enable_ips(crtc_state); - return ret; -} - -static int intel_dp_sink_crc_start(struct intel_dp *intel_dp, - struct intel_crtc_state *crtc_state) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc); - u8 buf; - int ret; - - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0) - return -EIO; - - if (!(buf & DP_TEST_CRC_SUPPORTED)) - return -ENOTTY; - - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0) - return -EIO; - - if (buf & DP_TEST_SINK_START) { - ret = intel_dp_sink_crc_stop(intel_dp, crtc_state, false); - if (ret) - return ret; - } - - hsw_disable_ips(crtc_state); - - if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK, - buf | DP_TEST_SINK_START) < 0) { - hsw_enable_ips(crtc_state); - return -EIO; - } - - intel_wait_for_vblank(dev_priv, intel_crtc->pipe); - return 0; -} - -int intel_dp_sink_crc(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state, u8 *crc) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc); - u8 buf; - int count, ret; - int attempts = 6; - - ret = intel_dp_sink_crc_start(intel_dp, crtc_state); - if (ret) - return ret; - - do { - intel_wait_for_vblank(dev_priv, intel_crtc->pipe); - - if (drm_dp_dpcd_readb(&intel_dp->aux, - DP_TEST_SINK_MISC, &buf) < 0) { - ret = -EIO; - goto stop; - } - count = buf & DP_TEST_COUNT_MASK; - - } while (--attempts && count == 0); - - if (attempts == 0) { - DRM_ERROR("Panel is unable to calculate any CRC after 6 vblanks\n"); - ret = -ETIMEDOUT; - goto stop; - } - - if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0) { - ret = -EIO; - goto stop; - } - -stop: - intel_dp_sink_crc_stop(intel_dp, crtc_state, true); - return ret; -} - static bool intel_dp_get_sink_irq(struct intel_dp *intel_dp, u8 *sink_irq_vector) { @@ -4563,14 +4409,7 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp) static enum drm_connector_status edp_detect(struct intel_dp *intel_dp) { - struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp)); - enum drm_connector_status status; - - status = intel_panel_detect(dev_priv); - if (status == connector_status_unknown) - status = connector_status_connected; - - return status; + return connector_status_connected; } static bool ibx_digital_port_connected(struct intel_encoder *encoder) @@ -4833,7 +4672,7 @@ intel_dp_long_pulse(struct intel_connector *connector) intel_display_power_get(dev_priv, intel_dp->aux_power_domain); - /* Can't disconnect eDP, but you can close the lid... */ + /* Can't disconnect eDP */ if (intel_dp_is_edp(intel_dp)) status = edp_detect(intel_dp); else if (intel_digital_port_connected(&dp_to_dig_port(intel_dp)->base)) @@ -6508,7 +6347,6 @@ bool intel_dp_init(struct drm_i915_private *dev_priv, intel_encoder->port = port; intel_dig_port->hpd_pulse = intel_dp_hpd_pulse; - dev_priv->hotplug.irq_port[port] = intel_dig_port; if (port != PORT_A) intel_infoframe_init(intel_dig_port); @@ -6527,37 +6365,44 @@ err_connector_alloc: return false; } -void intel_dp_mst_suspend(struct drm_device *dev) +void intel_dp_mst_suspend(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(dev); - int i; + struct intel_encoder *encoder; + + for_each_intel_encoder(&dev_priv->drm, encoder) { + struct intel_dp *intel_dp; - /* disable MST */ - for (i = 0; i < I915_MAX_PORTS; i++) { - struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i]; + if (encoder->type != INTEL_OUTPUT_DDI) + continue; - if (!intel_dig_port || !intel_dig_port->dp.can_mst) + intel_dp = enc_to_intel_dp(&encoder->base); + + if (!intel_dp->can_mst) continue; - if (intel_dig_port->dp.is_mst) - drm_dp_mst_topology_mgr_suspend(&intel_dig_port->dp.mst_mgr); + if (intel_dp->is_mst) + drm_dp_mst_topology_mgr_suspend(&intel_dp->mst_mgr); } } -void intel_dp_mst_resume(struct drm_device *dev) +void intel_dp_mst_resume(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(dev); - int i; + struct intel_encoder *encoder; - for (i = 0; i < I915_MAX_PORTS; i++) { - struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i]; + for_each_intel_encoder(&dev_priv->drm, encoder) { + struct intel_dp *intel_dp; int ret; - if (!intel_dig_port || !intel_dig_port->dp.can_mst) + if (encoder->type != INTEL_OUTPUT_DDI) + continue; + + intel_dp = enc_to_intel_dp(&encoder->base); + + if (!intel_dp->can_mst) continue; - ret = drm_dp_mst_topology_mgr_resume(&intel_dig_port->dp.mst_mgr); + ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst_mgr); if (ret) - intel_dp_check_mst_status(&intel_dig_port->dp); + intel_dp_check_mst_status(intel_dp); } } diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 6fa0acddf014..c275f91244a6 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -304,6 +304,8 @@ struct intel_panel { } backlight; }; +struct intel_digital_port; + /* * This structure serves as a translation layer between the generic HDCP code * and the bus-specific code. What that means is that HDCP over HDMI differs @@ -1246,23 +1248,29 @@ intel_attached_encoder(struct drm_connector *connector) return to_intel_connector(connector)->encoder; } -static inline struct intel_digital_port * -enc_to_dig_port(struct drm_encoder *encoder) +static inline bool intel_encoder_is_dig_port(struct intel_encoder *encoder) { - struct intel_encoder *intel_encoder = to_intel_encoder(encoder); - - switch (intel_encoder->type) { + switch (encoder->type) { case INTEL_OUTPUT_DDI: - WARN_ON(!HAS_DDI(to_i915(encoder->dev))); - /* fall through */ case INTEL_OUTPUT_DP: case INTEL_OUTPUT_EDP: case INTEL_OUTPUT_HDMI: + return true; + default: + return false; + } +} + +static inline struct intel_digital_port * +enc_to_dig_port(struct drm_encoder *encoder) +{ + struct intel_encoder *intel_encoder = to_intel_encoder(encoder); + + if (intel_encoder_is_dig_port(intel_encoder)) return container_of(encoder, struct intel_digital_port, base.base); - default: + else return NULL; - } } static inline struct intel_dp_mst_encoder * @@ -1276,6 +1284,20 @@ static inline struct intel_dp *enc_to_intel_dp(struct drm_encoder *encoder) return &enc_to_dig_port(encoder)->dp; } +static inline bool intel_encoder_is_dp(struct intel_encoder *encoder) +{ + switch (encoder->type) { + case INTEL_OUTPUT_DP: + case INTEL_OUTPUT_EDP: + return true; + case INTEL_OUTPUT_DDI: + /* Skip pure HDMI/DVI DDI encoders */ + return i915_mmio_reg_valid(enc_to_intel_dp(&encoder->base)->output_reg); + default: + return false; + } +} + static inline struct intel_digital_port * dp_to_dig_port(struct intel_dp *intel_dp) { @@ -1332,9 +1354,6 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv); void intel_check_pch_fifo_underruns(struct drm_i915_private *dev_priv); /* i915_irq.c */ -bool gen11_reset_one_iir(struct drm_i915_private * const i915, - const unsigned int bank, - const unsigned int bit); void gen5_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask); void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask); void gen6_mask_pm_irq(struct drm_i915_private *dev_priv, u32 mask); @@ -1385,8 +1404,7 @@ void hsw_fdi_link_train(struct intel_crtc *crtc, void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port); bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe); void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state); -void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder); +void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state); void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state); void intel_ddi_disable_pipe_clock(const struct intel_crtc_state *crtc_state); void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state); @@ -1665,8 +1683,6 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode); void intel_dp_encoder_reset(struct drm_encoder *encoder); void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder); void intel_dp_encoder_destroy(struct drm_encoder *encoder); -int intel_dp_sink_crc(struct intel_dp *intel_dp, - struct intel_crtc_state *crtc_state, u8 *crc); bool intel_dp_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state); @@ -1680,8 +1696,8 @@ void intel_edp_backlight_off(const struct drm_connector_state *conn_state); void intel_edp_panel_vdd_on(struct intel_dp *intel_dp); void intel_edp_panel_on(struct intel_dp *intel_dp); void intel_edp_panel_off(struct intel_dp *intel_dp); -void intel_dp_mst_suspend(struct drm_device *dev); -void intel_dp_mst_resume(struct drm_device *dev); +void intel_dp_mst_suspend(struct drm_i915_private *dev_priv); +void intel_dp_mst_resume(struct drm_i915_private *dev_priv); int intel_dp_max_link_rate(struct intel_dp *intel_dp); int intel_dp_max_lane_count(struct intel_dp *intel_dp); int intel_dp_rate_select(struct intel_dp *intel_dp, int rate); @@ -1874,7 +1890,6 @@ void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state); void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state); void intel_panel_destroy_backlight(struct drm_connector *connector); -enum drm_connector_status intel_panel_detect(struct drm_i915_private *dev_priv); extern struct drm_display_mode *intel_find_panel_downclock( struct drm_i915_private *dev_priv, struct drm_display_mode *fixed_mode, @@ -1923,7 +1938,7 @@ void intel_psr_compute_config(struct intel_dp *intel_dp, void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug); void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir); void intel_psr_short_pulse(struct intel_dp *intel_dp); -int intel_psr_wait_for_idle(struct drm_i915_private *dev_priv); +int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state); /* intel_runtime_pm.c */ int intel_power_domains_init(struct drm_i915_private *); diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 0ac497275a51..2d1952849d69 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -467,8 +467,7 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine) GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS); execlists->queue_priority = INT_MIN; - execlists->queue = RB_ROOT; - execlists->first = NULL; + execlists->queue = RB_ROOT_CACHED; } /** @@ -990,21 +989,23 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine) /* Waiting to drain ELSP? */ if (READ_ONCE(engine->execlists.active)) { - struct intel_engine_execlists *execlists = &engine->execlists; + struct tasklet_struct *t = &engine->execlists.tasklet; local_bh_disable(); - if (tasklet_trylock(&execlists->tasklet)) { - execlists->tasklet.func(execlists->tasklet.data); - tasklet_unlock(&execlists->tasklet); + if (tasklet_trylock(t)) { + /* Must wait for any GPU reset in progress. */ + if (__tasklet_is_enabled(t)) + t->func(t->data); + tasklet_unlock(t); } local_bh_enable(); - if (READ_ONCE(execlists->active)) + if (READ_ONCE(engine->execlists.active)) return false; } /* ELSP is empty, but there are ready requests? E.g. after reset */ - if (READ_ONCE(engine->execlists.first)) + if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root)) return false; /* Ring stopped? */ @@ -1540,7 +1541,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, last = NULL; count = 0; drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority); - for (rb = execlists->first; rb; rb = rb_next(rb)) { + for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) { struct i915_priolist *p = rb_entry(rb, typeof(*p), node); diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c index e12bd259df17..560c7406ae40 100644 --- a/drivers/gpu/drm/i915/intel_guc.c +++ b/drivers/gpu/drm/i915/intel_guc.c @@ -466,11 +466,13 @@ void intel_guc_to_host_event_handler_mmio(struct intel_guc *guc) * could happen that GuC sets the bit for 2nd interrupt but Host * clears out the bit on handling the 1st interrupt. */ + disable_rpm_wakeref_asserts(dev_priv); spin_lock(&guc->irq_lock); val = I915_READ(SOFT_SCRATCH(15)); msg = val & guc->msg_enabled_mask; I915_WRITE(SOFT_SCRATCH(15), val & ~msg); spin_unlock(&guc->irq_lock); + enable_rpm_wakeref_asserts(dev_priv); intel_guc_to_host_process_recv_msg(guc, msg); } diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c index f3945258fe1b..4aa5e6463e7b 100644 --- a/drivers/gpu/drm/i915/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/intel_guc_submission.c @@ -628,13 +628,14 @@ static void complete_preempt_context(struct intel_engine_cs *engine) GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT)); + if (inject_preempt_hang(execlists)) + return; + execlists_cancel_port_requests(execlists); execlists_unwind_incomplete_requests(execlists); wait_for_guc_preempt_report(engine); intel_write_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX, 0); - - execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT); } /** @@ -695,9 +696,6 @@ static bool __guc_dequeue(struct intel_engine_cs *engine) lockdep_assert_held(&engine->timeline.lock); - rb = execlists->first; - GEM_BUG_ON(rb_first(&execlists->queue) != rb); - if (port_isset(port)) { if (intel_engine_has_preemption(engine)) { struct guc_preempt_work *preempt_work = @@ -719,7 +717,7 @@ static bool __guc_dequeue(struct intel_engine_cs *engine) } GEM_BUG_ON(port_isset(port)); - while (rb) { + while ((rb = rb_first_cached(&execlists->queue))) { struct i915_priolist *p = to_priolist(rb); struct i915_request *rq, *rn; @@ -744,15 +742,13 @@ static bool __guc_dequeue(struct intel_engine_cs *engine) submit = true; } - rb = rb_next(rb); - rb_erase(&p->node, &execlists->queue); + rb_erase_cached(&p->node, &execlists->queue); INIT_LIST_HEAD(&p->requests); if (p->priority != I915_PRIORITY_NORMAL) kmem_cache_free(engine->i915->priorities, p); } done: execlists->queue_priority = rb ? to_priolist(rb)->priority : INT_MIN; - execlists->first = rb; if (submit) port_assign(port, last); if (last) @@ -761,7 +757,8 @@ done: /* We must always keep the beast fed if we have work piled up */ GEM_BUG_ON(port_isset(execlists->port) && !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER)); - GEM_BUG_ON(execlists->first && !port_isset(execlists->port)); + GEM_BUG_ON(rb_first_cached(&execlists->queue) && + !port_isset(execlists->port)); return submit; } @@ -914,8 +911,12 @@ static void guc_clients_doorbell_fini(struct intel_guc *guc) __update_doorbell_desc(guc->preempt_client, GUC_DOORBELL_INVALID); } - __destroy_doorbell(guc->execbuf_client); - __update_doorbell_desc(guc->execbuf_client, GUC_DOORBELL_INVALID); + + if (guc->execbuf_client) { + __destroy_doorbell(guc->execbuf_client); + __update_doorbell_desc(guc->execbuf_client, + GUC_DOORBELL_INVALID); + } } /** @@ -1128,7 +1129,8 @@ static void guc_clients_destroy(struct intel_guc *guc) guc_client_free(client); client = fetch_and_zero(&guc->execbuf_client); - guc_client_free(client); + if (client) + guc_client_free(client); } /* @@ -1183,7 +1185,8 @@ void intel_guc_submission_fini(struct intel_guc *guc) guc_clients_destroy(guc); WARN_ON(!guc_verify_doorbells(guc)); - guc_stage_desc_pool_destroy(guc); + if (guc->stage_desc_pool) + guc_stage_desc_pool_destroy(guc); } static void guc_interrupts_capture(struct drm_i915_private *dev_priv) @@ -1266,6 +1269,31 @@ static void guc_submission_unpark(struct intel_engine_cs *engine) intel_engine_pin_breadcrumbs_irq(engine); } +static void guc_set_default_submission(struct intel_engine_cs *engine) +{ + /* + * We inherit a bunch of functions from execlists that we'd like + * to keep using: + * + * engine->submit_request = execlists_submit_request; + * engine->cancel_requests = execlists_cancel_requests; + * engine->schedule = execlists_schedule; + * + * But we need to override the actual submission backend in order + * to talk to the GuC. + */ + intel_execlists_set_default_submission(engine); + + engine->execlists.tasklet.func = guc_submission_tasklet; + + engine->park = guc_submission_park; + engine->unpark = guc_submission_unpark; + + engine->reset.prepare = guc_reset_prepare; + + engine->flags &= ~I915_ENGINE_SUPPORTS_STATS; +} + int intel_guc_submission_enable(struct intel_guc *guc) { struct drm_i915_private *dev_priv = guc_to_i915(guc); @@ -1304,17 +1332,8 @@ int intel_guc_submission_enable(struct intel_guc *guc) guc_interrupts_capture(dev_priv); for_each_engine(engine, dev_priv, id) { - struct intel_engine_execlists * const execlists = - &engine->execlists; - - execlists->tasklet.func = guc_submission_tasklet; - - engine->reset.prepare = guc_reset_prepare; - - engine->park = guc_submission_park; - engine->unpark = guc_submission_unpark; - - engine->flags &= ~I915_ENGINE_SUPPORTS_STATS; + engine->set_default_submission = guc_set_default_submission; + engine->set_default_submission(engine); } return 0; @@ -1328,9 +1347,6 @@ void intel_guc_submission_disable(struct intel_guc *guc) guc_interrupts_release(dev_priv); guc_clients_doorbell_fini(guc); - - /* Revert back to manual ELSP submission */ - intel_engines_reset_default_submission(dev_priv); } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c index a6291f60545b..c22b3e18a0f5 100644 --- a/drivers/gpu/drm/i915/intel_gvt.c +++ b/drivers/gpu/drm/i915/intel_gvt.c @@ -92,6 +92,9 @@ int intel_gvt_init(struct drm_i915_private *dev_priv) { int ret; + if (i915_inject_load_failure()) + return -ENODEV; + if (!i915_modparams.enable_gvt) { DRM_DEBUG_DRIVER("GVT-g is disabled by kernel params\n"); return 0; diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c index 43aa92beff2a..648a13c6043c 100644 --- a/drivers/gpu/drm/i915/intel_hotplug.c +++ b/drivers/gpu/drm/i915/intel_hotplug.c @@ -77,37 +77,6 @@ */ /** - * intel_hpd_port - return port hard associated with certain pin. - * @dev_priv: private driver data pointer - * @pin: the hpd pin to get associated port - * - * Return port that is associatade with @pin and PORT_NONE if no port is - * hard associated with that @pin. - */ -enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv, - enum hpd_pin pin) -{ - switch (pin) { - case HPD_PORT_A: - return PORT_A; - case HPD_PORT_B: - return PORT_B; - case HPD_PORT_C: - return PORT_C; - case HPD_PORT_D: - return PORT_D; - case HPD_PORT_E: - if (IS_CNL_WITH_PORT_F(dev_priv)) - return PORT_F; - return PORT_E; - case HPD_PORT_F: - return PORT_F; - default: - return PORT_NONE; /* no port for this pin */ - } -} - -/** * intel_hpd_pin_default - return default pin associated with certain port. * @dev_priv: private driver data pointer * @port: the hpd port to get associated pin @@ -241,25 +210,25 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work) container_of(work, typeof(*dev_priv), hotplug.reenable_work.work); struct drm_device *dev = &dev_priv->drm; - int i; + enum hpd_pin pin; intel_runtime_pm_get(dev_priv); spin_lock_irq(&dev_priv->irq_lock); - for_each_hpd_pin(i) { + for_each_hpd_pin(pin) { struct drm_connector *connector; struct drm_connector_list_iter conn_iter; - if (dev_priv->hotplug.stats[i].state != HPD_DISABLED) + if (dev_priv->hotplug.stats[pin].state != HPD_DISABLED) continue; - dev_priv->hotplug.stats[i].state = HPD_ENABLED; + dev_priv->hotplug.stats[pin].state = HPD_ENABLED; drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { struct intel_connector *intel_connector = to_intel_connector(connector); - if (intel_connector->encoder->hpd_pin == i) { + if (intel_connector->encoder->hpd_pin == pin) { if (connector->polled != intel_connector->polled) DRM_DEBUG_DRIVER("Reenabling HPD on connector %s\n", connector->name); @@ -301,13 +270,18 @@ bool intel_encoder_hotplug(struct intel_encoder *encoder, return true; } +static bool intel_encoder_has_hpd_pulse(struct intel_encoder *encoder) +{ + return intel_encoder_is_dig_port(encoder) && + enc_to_dig_port(&encoder->base)->hpd_pulse != NULL; +} + static void i915_digport_work_func(struct work_struct *work) { struct drm_i915_private *dev_priv = container_of(work, struct drm_i915_private, hotplug.dig_port_work); u32 long_port_mask, short_port_mask; - struct intel_digital_port *intel_dig_port; - int i; + struct intel_encoder *encoder; u32 old_bits = 0; spin_lock_irq(&dev_priv->irq_lock); @@ -317,27 +291,27 @@ static void i915_digport_work_func(struct work_struct *work) dev_priv->hotplug.short_port_mask = 0; spin_unlock_irq(&dev_priv->irq_lock); - for (i = 0; i < I915_MAX_PORTS; i++) { - bool valid = false; - bool long_hpd = false; - intel_dig_port = dev_priv->hotplug.irq_port[i]; - if (!intel_dig_port || !intel_dig_port->hpd_pulse) + for_each_intel_encoder(&dev_priv->drm, encoder) { + struct intel_digital_port *dig_port; + enum port port = encoder->port; + bool long_hpd, short_hpd; + enum irqreturn ret; + + if (!intel_encoder_has_hpd_pulse(encoder)) continue; - if (long_port_mask & (1 << i)) { - valid = true; - long_hpd = true; - } else if (short_port_mask & (1 << i)) - valid = true; + long_hpd = long_port_mask & BIT(port); + short_hpd = short_port_mask & BIT(port); - if (valid) { - enum irqreturn ret; + if (!long_hpd && !short_hpd) + continue; - ret = intel_dig_port->hpd_pulse(intel_dig_port, long_hpd); - if (ret == IRQ_NONE) { - /* fall back to old school hpd */ - old_bits |= (1 << intel_dig_port->base.hpd_pin); - } + dig_port = enc_to_dig_port(&encoder->base); + + ret = dig_port->hpd_pulse(dig_port, long_hpd); + if (ret == IRQ_NONE) { + /* fall back to old school hpd */ + old_bits |= BIT(encoder->hpd_pin); } } @@ -418,26 +392,24 @@ static void i915_hotplug_work_func(struct work_struct *work) void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 pin_mask, u32 long_mask) { - int i; - enum port port; + struct intel_encoder *encoder; bool storm_detected = false; bool queue_dig = false, queue_hp = false; - bool is_dig_port; if (!pin_mask) return; spin_lock(&dev_priv->irq_lock); - for_each_hpd_pin(i) { - if (!(BIT(i) & pin_mask)) - continue; + for_each_intel_encoder(&dev_priv->drm, encoder) { + enum hpd_pin pin = encoder->hpd_pin; + bool has_hpd_pulse = intel_encoder_has_hpd_pulse(encoder); - port = intel_hpd_pin_to_port(dev_priv, i); - is_dig_port = port != PORT_NONE && - dev_priv->hotplug.irq_port[port]; + if (!(BIT(pin) & pin_mask)) + continue; - if (is_dig_port) { - bool long_hpd = long_mask & BIT(i); + if (has_hpd_pulse) { + bool long_hpd = long_mask & BIT(pin); + enum port port = encoder->port; DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port), long_hpd ? "long" : "short"); @@ -455,7 +427,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, } } - if (dev_priv->hotplug.stats[i].state == HPD_DISABLED) { + if (dev_priv->hotplug.stats[pin].state == HPD_DISABLED) { /* * On GMCH platforms the interrupt mask bits only * prevent irq generation, not the setting of the @@ -463,20 +435,20 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, * interrupts on saner platforms. */ WARN_ONCE(!HAS_GMCH_DISPLAY(dev_priv), - "Received HPD interrupt on pin %d although disabled\n", i); + "Received HPD interrupt on pin %d although disabled\n", pin); continue; } - if (dev_priv->hotplug.stats[i].state != HPD_ENABLED) + if (dev_priv->hotplug.stats[pin].state != HPD_ENABLED) continue; - if (!is_dig_port) { - dev_priv->hotplug.event_bits |= BIT(i); + if (!has_hpd_pulse) { + dev_priv->hotplug.event_bits |= BIT(pin); queue_hp = true; } - if (intel_hpd_irq_storm_detect(dev_priv, i)) { - dev_priv->hotplug.event_bits &= ~BIT(i); + if (intel_hpd_irq_storm_detect(dev_priv, pin)) { + dev_priv->hotplug.event_bits &= ~BIT(pin); storm_detected = true; } } diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 97606c1be70d..bef32b7c248e 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -361,15 +361,39 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv) return ret; } +static inline +unsigned int gmbus_max_xfer_size(struct drm_i915_private *dev_priv) +{ + return INTEL_GEN(dev_priv) >= 9 ? GEN9_GMBUS_BYTE_COUNT_MAX : + GMBUS_BYTE_COUNT_MAX; +} + static int gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv, unsigned short addr, u8 *buf, unsigned int len, - u32 gmbus1_index) + u32 gmbus0_reg, u32 gmbus1_index) { + unsigned int size = len; + bool burst_read = len > gmbus_max_xfer_size(dev_priv); + bool extra_byte_added = false; + + if (burst_read) { + /* + * As per HW Spec, for 512Bytes need to read extra Byte and + * Ignore the extra byte read. + */ + if (len == 512) { + extra_byte_added = true; + len++; + } + size = len % 256 + 256; + I915_WRITE_FW(GMBUS0, gmbus0_reg | GMBUS_BYTE_CNT_OVERRIDE); + } + I915_WRITE_FW(GMBUS1, gmbus1_index | GMBUS_CYCLE_WAIT | - (len << GMBUS_BYTE_COUNT_SHIFT) | + (size << GMBUS_BYTE_COUNT_SHIFT) | (addr << GMBUS_SLAVE_ADDR_SHIFT) | GMBUS_SLAVE_READ | GMBUS_SW_RDY); while (len) { @@ -382,17 +406,34 @@ gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv, val = I915_READ_FW(GMBUS3); do { + if (extra_byte_added && len == 1) + break; + *buf++ = val & 0xff; val >>= 8; } while (--len && ++loop < 4); + + if (burst_read && len == size - 4) + /* Reset the override bit */ + I915_WRITE_FW(GMBUS0, gmbus0_reg); } return 0; } +/* + * HW spec says that 512Bytes in Burst read need special treatment. + * But it doesn't talk about other multiple of 256Bytes. And couldn't locate + * an I2C slave, which supports such a lengthy burst read too for experiments. + * + * So until things get clarified on HW support, to avoid the burst read length + * in fold of 256Bytes except 512, max burst read length is fixed at 767Bytes. + */ +#define INTEL_GMBUS_BURST_READ_MAX_LEN 767U + static int gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, - u32 gmbus1_index) + u32 gmbus0_reg, u32 gmbus1_index) { u8 *buf = msg->buf; unsigned int rx_size = msg->len; @@ -400,10 +441,13 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, int ret; do { - len = min(rx_size, GMBUS_BYTE_COUNT_MAX); + if (HAS_GMBUS_BURST_READ(dev_priv)) + len = min(rx_size, INTEL_GMBUS_BURST_READ_MAX_LEN); + else + len = min(rx_size, gmbus_max_xfer_size(dev_priv)); - ret = gmbus_xfer_read_chunk(dev_priv, msg->addr, - buf, len, gmbus1_index); + ret = gmbus_xfer_read_chunk(dev_priv, msg->addr, buf, len, + gmbus0_reg, gmbus1_index); if (ret) return ret; @@ -462,7 +506,7 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg, int ret; do { - len = min(tx_size, GMBUS_BYTE_COUNT_MAX); + len = min(tx_size, gmbus_max_xfer_size(dev_priv)); ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len, gmbus1_index); @@ -491,7 +535,8 @@ gmbus_is_index_xfer(struct i2c_msg *msgs, int i, int num) } static int -gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs) +gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs, + u32 gmbus0_reg) { u32 gmbus1_index = 0; u32 gmbus5 = 0; @@ -509,7 +554,8 @@ gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs) I915_WRITE_FW(GMBUS5, gmbus5); if (msgs[1].flags & I2C_M_RD) - ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus1_index); + ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus0_reg, + gmbus1_index); else ret = gmbus_xfer_write(dev_priv, &msgs[1], gmbus1_index); @@ -544,10 +590,12 @@ retry: for (; i < num; i += inc) { inc = 1; if (gmbus_is_index_xfer(msgs, i, num)) { - ret = gmbus_index_xfer(dev_priv, &msgs[i]); + ret = gmbus_index_xfer(dev_priv, &msgs[i], + gmbus0_source | bus->reg0); inc = 2; /* an index transmission is two msgs */ } else if (msgs[i].flags & I2C_M_RD) { - ret = gmbus_xfer_read(dev_priv, &msgs[i], 0); + ret = gmbus_xfer_read(dev_priv, &msgs[i], + gmbus0_source | bus->reg0, 0); } else { ret = gmbus_xfer_write(dev_priv, &msgs[i], 0); } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index ab89dabc2965..174479232e94 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -273,7 +273,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio) find_priolist: /* most positive priority is scheduled first, equal priorities fifo */ rb = NULL; - parent = &execlists->queue.rb_node; + parent = &execlists->queue.rb_root.rb_node; while (*parent) { rb = *parent; p = to_priolist(rb); @@ -311,10 +311,7 @@ find_priolist: p->priority = prio; INIT_LIST_HEAD(&p->requests); rb_link_node(&p->node, rb, parent); - rb_insert_color(&p->node, &execlists->queue); - - if (first) - execlists->first = &p->node; + rb_insert_color_cached(&p->node, &execlists->queue, first); return p; } @@ -456,6 +453,16 @@ static void execlists_submit_ports(struct intel_engine_cs *engine) unsigned int n; /* + * We can skip acquiring intel_runtime_pm_get() here as it was taken + * on our behalf by the request (see i915_gem_mark_busy()) and it will + * not be relinquished until the device is idle (see + * i915_gem_idle_work_handler()). As a precaution, we make sure + * that all ELSP are drained i.e. we have processed the CSB, + * before allowing ourselves to idle and calling intel_runtime_pm_put(). + */ + GEM_BUG_ON(!engine->i915->gt.awake); + + /* * ELSQ note: the submit queue is not cleared after being submitted * to the HW so we need to make sure we always clean it up. This is * currently ensured by the fact that we always write the same number @@ -562,12 +569,13 @@ static void complete_preempt_context(struct intel_engine_execlists *execlists) { GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT)); + if (inject_preempt_hang(execlists)) + return; + execlists_cancel_port_requests(execlists); __unwind_incomplete_requests(container_of(execlists, struct intel_engine_cs, execlists)); - - execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT); } static void execlists_dequeue(struct intel_engine_cs *engine) @@ -602,9 +610,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * and context switches) submission. */ - rb = execlists->first; - GEM_BUG_ON(rb_first(&execlists->queue) != rb); - if (last) { /* * Don't resubmit or switch until all outstanding @@ -666,7 +671,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) last->tail = last->wa_tail; } - while (rb) { + while ((rb = rb_first_cached(&execlists->queue))) { struct i915_priolist *p = to_priolist(rb); struct i915_request *rq, *rn; @@ -725,8 +730,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) submit = true; } - rb = rb_next(rb); - rb_erase(&p->node, &execlists->queue); + rb_erase_cached(&p->node, &execlists->queue); INIT_LIST_HEAD(&p->requests); if (p->priority != I915_PRIORITY_NORMAL) kmem_cache_free(engine->i915->priorities, p); @@ -752,14 +756,14 @@ done: execlists->queue_priority = port != execlists->port ? rq_prio(last) : INT_MIN; - execlists->first = rb; if (submit) { port_assign(port, last); execlists_submit_ports(engine); } /* We must always keep the beast fed if we have work piled up */ - GEM_BUG_ON(execlists->first && !port_isset(execlists->port)); + GEM_BUG_ON(rb_first_cached(&execlists->queue) && + !port_isset(execlists->port)); /* Re-evaluate the executing context setup after each preemptive kick */ if (last) @@ -799,73 +803,7 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists) port++; } - execlists_user_end(execlists); -} - -static void clear_gtiir(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int i; - - /* - * Clear any pending interrupt state. - * - * We do it twice out of paranoia that some of the IIR are - * double buffered, and so if we only reset it once there may - * still be an interrupt pending. - */ - if (INTEL_GEN(dev_priv) >= 11) { - static const struct { - u8 bank; - u8 bit; - } gen11_gtiir[] = { - [RCS] = {0, GEN11_RCS0}, - [BCS] = {0, GEN11_BCS}, - [_VCS(0)] = {1, GEN11_VCS(0)}, - [_VCS(1)] = {1, GEN11_VCS(1)}, - [_VCS(2)] = {1, GEN11_VCS(2)}, - [_VCS(3)] = {1, GEN11_VCS(3)}, - [_VECS(0)] = {1, GEN11_VECS(0)}, - [_VECS(1)] = {1, GEN11_VECS(1)}, - }; - unsigned long irqflags; - - GEM_BUG_ON(engine->id >= ARRAY_SIZE(gen11_gtiir)); - - spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - for (i = 0; i < 2; i++) { - gen11_reset_one_iir(dev_priv, - gen11_gtiir[engine->id].bank, - gen11_gtiir[engine->id].bit); - } - spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); - } else { - static const u8 gtiir[] = { - [RCS] = 0, - [BCS] = 0, - [VCS] = 1, - [VCS2] = 1, - [VECS] = 3, - }; - - GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir)); - - for (i = 0; i < 2; i++) { - I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]), - engine->irq_keep_mask); - POSTING_READ(GEN8_GT_IIR(gtiir[engine->id])); - } - GEM_BUG_ON(I915_READ(GEN8_GT_IIR(gtiir[engine->id])) & - engine->irq_keep_mask); - } -} - -static void reset_irq(struct intel_engine_cs *engine) -{ - /* Mark all CS interrupts as complete */ - smp_store_mb(engine->execlists.active, 0); - - clear_gtiir(engine); + execlists_clear_all_active(execlists); } static void reset_csb_pointers(struct intel_engine_execlists *execlists) @@ -883,6 +821,11 @@ static void reset_csb_pointers(struct intel_engine_execlists *execlists) WRITE_ONCE(*execlists->csb_write, execlists->csb_write_reset); } +static void nop_submission_tasklet(unsigned long data) +{ + /* The driver is wedged; don't process any more events. */ +} + static void execlists_cancel_requests(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; @@ -911,7 +854,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) /* Cancel the requests on the HW and clear the ELSP tracker. */ execlists_cancel_port_requests(execlists); - reset_irq(engine); + execlists_user_end(execlists); /* Mark all executing requests as skipped. */ list_for_each_entry(rq, &engine->timeline.requests, link) { @@ -921,8 +864,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) } /* Flush the queued requests to the timeline list (for retiring). */ - rb = execlists->first; - while (rb) { + while ((rb = rb_first_cached(&execlists->queue))) { struct i915_priolist *p = to_priolist(rb); list_for_each_entry_safe(rq, rn, &p->requests, sched.link) { @@ -932,8 +874,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) __i915_request_submit(rq); } - rb = rb_next(rb); - rb_erase(&p->node, &execlists->queue); + rb_erase_cached(&p->node, &execlists->queue); INIT_LIST_HEAD(&p->requests); if (p->priority != I915_PRIORITY_NORMAL) kmem_cache_free(engine->i915->priorities, p); @@ -942,10 +883,12 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) /* Remaining _unready_ requests will be nop'ed when submitted */ execlists->queue_priority = INT_MIN; - execlists->queue = RB_ROOT; - execlists->first = NULL; + execlists->queue = RB_ROOT_CACHED; GEM_BUG_ON(port_isset(execlists->port)); + GEM_BUG_ON(__tasklet_is_enabled(&execlists->tasklet)); + execlists->tasklet.func = nop_submission_tasklet; + spin_unlock_irqrestore(&engine->timeline.lock, flags); } @@ -1110,16 +1053,6 @@ static void __execlists_submission_tasklet(struct intel_engine_cs *const engine) { lockdep_assert_held(&engine->timeline.lock); - /* - * We can skip acquiring intel_runtime_pm_get() here as it was taken - * on our behalf by the request (see i915_gem_mark_busy()) and it will - * not be relinquished until the device is idle (see - * i915_gem_idle_work_handler()). As a precaution, we make sure - * that all ELSP are drained i.e. we have processed the CSB, - * before allowing ourselves to idle and calling intel_runtime_pm_put(). - */ - GEM_BUG_ON(!engine->i915->gt.awake); - process_csb(engine); if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT)) execlists_dequeue(engine); @@ -1140,10 +1073,7 @@ static void execlists_submission_tasklet(unsigned long data) engine->execlists.active); spin_lock_irqsave(&engine->timeline.lock, flags); - - if (engine->i915->gt.awake) /* we may be delayed until after we idle! */ - __execlists_submission_tasklet(engine); - + __execlists_submission_tasklet(engine); spin_unlock_irqrestore(&engine->timeline.lock, flags); } @@ -1191,7 +1121,7 @@ static void execlists_submit_request(struct i915_request *request) queue_request(engine, &request->sched, rq_prio(request)); - GEM_BUG_ON(!engine->execlists.first); + GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root)); GEM_BUG_ON(list_empty(&request->sched.link)); submit_queue(engine, rq_prio(request)); @@ -1852,7 +1782,6 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine) return ret; intel_engine_reset_breadcrumbs(engine); - intel_engine_init_hangcheck(engine); if (GEM_SHOW_DEBUG() && unexpected_starting_state(engine)) { struct drm_printer p = drm_debug_printer(__func__); @@ -1986,7 +1915,6 @@ static void execlists_reset(struct intel_engine_cs *engine, * requests were completed. */ execlists_cancel_port_requests(execlists); - reset_irq(engine); /* Push back any incomplete requests for replay after the reset. */ __unwind_incomplete_requests(engine); @@ -2044,7 +1972,7 @@ static void execlists_reset_finish(struct intel_engine_cs *engine) struct intel_engine_execlists * const execlists = &engine->execlists; /* After a GPU reset, we may have requests to replay */ - if (execlists->first) + if (!RB_EMPTY_ROOT(&execlists->queue.rb_root)) tasklet_schedule(&execlists->tasklet); /* @@ -2364,7 +2292,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine) kfree(engine); } -static void execlists_set_default_submission(struct intel_engine_cs *engine) +void intel_execlists_set_default_submission(struct intel_engine_cs *engine) { engine->submit_request = execlists_submit_request; engine->cancel_requests = execlists_cancel_requests; @@ -2404,7 +2332,7 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) engine->emit_breadcrumb = gen8_emit_breadcrumb; engine->emit_breadcrumb_sz = gen8_emit_breadcrumb_sz; - engine->set_default_submission = execlists_set_default_submission; + engine->set_default_submission = intel_execlists_set_default_submission; if (INTEL_GEN(engine->i915) < 11) { engine->irq_enable = gen8_logical_ring_enable_irq; diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h index 1593194e930c..4dfb78e3ec7e 100644 --- a/drivers/gpu/drm/i915/intel_lrc.h +++ b/drivers/gpu/drm/i915/intel_lrc.h @@ -104,4 +104,6 @@ struct i915_gem_context; void intel_lr_context_resume(struct drm_i915_private *dev_priv); +void intel_execlists_set_default_submission(struct intel_engine_cs *engine); + #endif /* _INTEL_LRC_H_ */ diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index ca55b0a82ba6..f9f3b0885ba5 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -44,8 +44,6 @@ /* Private structure for the integrated LVDS support */ struct intel_lvds_connector { struct intel_connector base; - - struct notifier_block lid_notifier; }; struct intel_lvds_pps { @@ -452,26 +450,9 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder, return true; } -/* - * Detect the LVDS connection. - * - * Since LVDS doesn't have hotlug, we use the lid as a proxy. Open means - * connected and closed means disconnected. We also send hotplug events as - * needed, using lid status notification from the input layer. - */ static enum drm_connector_status intel_lvds_detect(struct drm_connector *connector, bool force) { - struct drm_i915_private *dev_priv = to_i915(connector->dev); - enum drm_connector_status status; - - DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, connector->name); - - status = intel_panel_detect(dev_priv); - if (status != connector_status_unknown) - return status; - return connector_status_connected; } @@ -496,117 +477,6 @@ static int intel_lvds_get_modes(struct drm_connector *connector) return 1; } -static int intel_no_modeset_on_lid_dmi_callback(const struct dmi_system_id *id) -{ - DRM_INFO("Skipping forced modeset for %s\n", id->ident); - return 1; -} - -/* The GPU hangs up on these systems if modeset is performed on LID open */ -static const struct dmi_system_id intel_no_modeset_on_lid[] = { - { - .callback = intel_no_modeset_on_lid_dmi_callback, - .ident = "Toshiba Tecra A11", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "TECRA A11"), - }, - }, - - { } /* terminating entry */ -}; - -/* - * Lid events. Note the use of 'modeset': - * - we set it to MODESET_ON_LID_OPEN on lid close, - * and set it to MODESET_DONE on open - * - we use it as a "only once" bit (ie we ignore - * duplicate events where it was already properly set) - * - the suspend/resume paths will set it to - * MODESET_SUSPENDED and ignore the lid open event, - * because they restore the mode ("lid open"). - */ -static int intel_lid_notify(struct notifier_block *nb, unsigned long val, - void *unused) -{ - struct intel_lvds_connector *lvds_connector = - container_of(nb, struct intel_lvds_connector, lid_notifier); - struct drm_connector *connector = &lvds_connector->base.base; - struct drm_device *dev = connector->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - - if (dev->switch_power_state != DRM_SWITCH_POWER_ON) - return NOTIFY_OK; - - mutex_lock(&dev_priv->modeset_restore_lock); - if (dev_priv->modeset_restore == MODESET_SUSPENDED) - goto exit; - /* - * check and update the status of LVDS connector after receiving - * the LID nofication event. - */ - connector->status = connector->funcs->detect(connector, false); - - /* Don't force modeset on machines where it causes a GPU lockup */ - if (dmi_check_system(intel_no_modeset_on_lid)) - goto exit; - if (!acpi_lid_open()) { - /* do modeset on next lid open event */ - dev_priv->modeset_restore = MODESET_ON_LID_OPEN; - goto exit; - } - - if (dev_priv->modeset_restore == MODESET_DONE) - goto exit; - - /* - * Some old platform's BIOS love to wreak havoc while the lid is closed. - * We try to detect this here and undo any damage. The split for PCH - * platforms is rather conservative and a bit arbitrary expect that on - * those platforms VGA disabling requires actual legacy VGA I/O access, - * and as part of the cleanup in the hw state restore we also redisable - * the vga plane. - */ - if (!HAS_PCH_SPLIT(dev_priv)) - intel_display_resume(dev); - - dev_priv->modeset_restore = MODESET_DONE; - -exit: - mutex_unlock(&dev_priv->modeset_restore_lock); - return NOTIFY_OK; -} - -static int -intel_lvds_connector_register(struct drm_connector *connector) -{ - struct intel_lvds_connector *lvds = to_lvds_connector(connector); - int ret; - - ret = intel_connector_register(connector); - if (ret) - return ret; - - lvds->lid_notifier.notifier_call = intel_lid_notify; - if (acpi_lid_notifier_register(&lvds->lid_notifier)) { - DRM_DEBUG_KMS("lid notifier registration failed\n"); - lvds->lid_notifier.notifier_call = NULL; - } - - return 0; -} - -static void -intel_lvds_connector_unregister(struct drm_connector *connector) -{ - struct intel_lvds_connector *lvds = to_lvds_connector(connector); - - if (lvds->lid_notifier.notifier_call) - acpi_lid_notifier_unregister(&lvds->lid_notifier); - - intel_connector_unregister(connector); -} - /** * intel_lvds_destroy - unregister and free LVDS structures * @connector: connector to free @@ -639,8 +509,8 @@ static const struct drm_connector_funcs intel_lvds_connector_funcs = { .fill_modes = drm_helper_probe_single_connector_modes, .atomic_get_property = intel_digital_connector_atomic_get_property, .atomic_set_property = intel_digital_connector_atomic_set_property, - .late_register = intel_lvds_connector_register, - .early_unregister = intel_lvds_connector_unregister, + .late_register = intel_connector_register, + .early_unregister = intel_connector_unregister, .destroy = intel_lvds_destroy, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, .atomic_duplicate_state = intel_digital_connector_duplicate_state, @@ -1114,8 +984,6 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) * 2) check for VBT data * 3) check to see if LVDS is already on * if none of the above, no panel - * 4) make sure lid is open - * if closed, act like it's not there for now */ /* diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 14b827ec5427..4a9f139e7b73 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -375,26 +375,6 @@ out: pipe_config->gmch_pfit.lvds_border_bits = border; } -enum drm_connector_status -intel_panel_detect(struct drm_i915_private *dev_priv) -{ - /* Assume that the BIOS does not lie through the OpRegion... */ - if (!i915_modparams.panel_ignore_lid && dev_priv->opregion.lid_state) { - return *dev_priv->opregion.lid_state & 0x1 ? - connector_status_connected : - connector_status_disconnected; - } - - switch (i915_modparams.panel_ignore_lid) { - case -2: - return connector_status_connected; - case -1: - return connector_status_disconnected; - default: - return connector_status_unknown; - } -} - /** * scale - scale values from one range to another * @source_val: value in range [@source_min..@source_max] diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 53aaaa3e6886..7312ecb73415 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -7347,11 +7347,11 @@ out: static void valleyview_cleanup_pctx(struct drm_i915_private *dev_priv) { - if (WARN_ON(!dev_priv->vlv_pctx)) - return; + struct drm_i915_gem_object *pctx; - i915_gem_object_put(dev_priv->vlv_pctx); - dev_priv->vlv_pctx = NULL; + pctx = fetch_and_zero(&dev_priv->vlv_pctx); + if (pctx) + i915_gem_object_put(pctx); } static void vlv_init_gpll_ref_freq(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c index 23acc9ac8d4d..4bd5768731ee 100644 --- a/drivers/gpu/drm/i915/intel_psr.c +++ b/drivers/gpu/drm/i915/intel_psr.c @@ -717,11 +717,16 @@ void intel_psr_disable(struct intel_dp *intel_dp, cancel_work_sync(&dev_priv->psr.work); } -int intel_psr_wait_for_idle(struct drm_i915_private *dev_priv) +int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); i915_reg_t reg; u32 mask; + if (!new_crtc_state->has_psr) + return 0; + /* * The sole user right now is intel_pipe_update_start(), * which won't race with psr_enable/disable, which is @@ -966,16 +971,6 @@ void intel_psr_init(struct drm_i915_private *dev_priv) /* For new platforms let's respect VBT back again */ dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link; - /* Override link_standby x link_off defaults */ - if (i915_modparams.enable_psr == 2 && !dev_priv->psr.link_standby) { - DRM_DEBUG_KMS("PSR: Forcing link standby\n"); - dev_priv->psr.link_standby = true; - } - if (i915_modparams.enable_psr == 3 && dev_priv->psr.link_standby) { - DRM_DEBUG_KMS("PSR: Forcing main link off\n"); - dev_priv->psr.link_standby = false; - } - INIT_WORK(&dev_priv->psr.work, intel_psr_work); mutex_init(&dev_priv->psr.lock); } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 700f94c371b3..33faad3197fe 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -524,8 +524,6 @@ static int init_ring_common(struct intel_engine_cs *engine) goto out; } - intel_engine_init_hangcheck(engine); - if (INTEL_GEN(dev_priv) > 2) I915_WRITE_MODE(engine, _MASKED_BIT_DISABLE(STOP_RING)); @@ -1089,6 +1087,7 @@ void intel_ring_unpin(struct intel_ring *ring) static struct i915_vma * intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) { + struct i915_address_space *vm = &dev_priv->ggtt.vm; struct drm_i915_gem_object *obj; struct i915_vma *vma; @@ -1098,10 +1097,14 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) if (IS_ERR(obj)) return ERR_CAST(obj); - /* mark ring buffers as read-only from GPU side by default */ - obj->gt_ro = 1; + /* + * Mark ring buffers as read-only from GPU side (so no stray overwrites) + * if supported by the platform's GGTT. + */ + if (vm->has_read_only) + i915_gem_object_set_readonly(obj); - vma = i915_vma_instance(obj, &dev_priv->ggtt.vm, NULL); + vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) goto err; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index ce6cc2a6cf7a..f5ffa6d31e82 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -193,6 +193,11 @@ struct i915_priolist { int priority; }; +struct st_preempt_hang { + struct completion completion; + bool inject_hang; +}; + /** * struct intel_engine_execlists - execlist submission queue and port state * @@ -292,12 +297,7 @@ struct intel_engine_execlists { /** * @queue: queue of requests, in priority lists */ - struct rb_root queue; - - /** - * @first: leftmost level in priority @queue - */ - struct rb_node *first; + struct rb_root_cached queue; /** * @csb_read: control register for Context Switch buffer @@ -338,6 +338,8 @@ struct intel_engine_execlists { * @csb_head: context status buffer head */ u8 csb_head; + + I915_SELFTEST_DECLARE(struct st_preempt_hang preempt_hang;) }; #define INTEL_ENGINE_CS_MAX_NAME 8 @@ -688,6 +690,12 @@ execlists_clear_active(struct intel_engine_execlists *execlists, __clear_bit(bit, (unsigned long *)&execlists->active); } +static inline void +execlists_clear_all_active(struct intel_engine_execlists *execlists) +{ + execlists->active = 0; +} + static inline bool execlists_is_active(const struct intel_engine_execlists *execlists, unsigned int bit) @@ -1154,4 +1162,24 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine); ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine); +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) + +static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists) +{ + if (!execlists->preempt_hang.inject_hang) + return false; + + complete(&execlists->preempt_hang.completion); + return true; +} + +#else + +static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists) +{ + return false; +} + +#endif + #endif /* _INTEL_RINGBUFFER_H_ */ diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 4b9b1d4224d8..f7026e887fa9 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -104,7 +104,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) * VBL interrupts will start the PSR exit and prevent a PSR * re-entry as well. */ - if (CAN_PSR(dev_priv) && intel_psr_wait_for_idle(dev_priv)) + if (intel_psr_wait_for_idle(new_crtc_state)) DRM_ERROR("PSR idle timed out, atomic update may fail\n"); local_irq_disable(); diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 24dc368fdaa1..b5b04cb892e9 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1347,8 +1347,7 @@ intel_tv_get_modes(struct drm_connector *connector) mode_ptr = drm_mode_create(connector->dev); if (!mode_ptr) continue; - strncpy(mode_ptr->name, input->name, DRM_DISPLAY_MODE_LEN); - mode_ptr->name[DRM_DISPLAY_MODE_LEN - 1] = '\0'; + strlcpy(mode_ptr->name, input->name, DRM_DISPLAY_MODE_LEN); mode_ptr->hdisplay = hactive_s; mode_ptr->hsync_start = hactive_s + 1; diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c index d9f439f6219f..7efb326badcd 100644 --- a/drivers/gpu/drm/i915/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/selftests/huge_pages.c @@ -570,6 +570,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg) i915_vma_close(vma); i915_gem_object_unpin_pages(obj); + __i915_gem_object_put_pages(obj, I915_MM_NORMAL); i915_gem_object_put(obj); } @@ -597,6 +598,7 @@ static void close_object_list(struct list_head *objects, list_del(&obj->st_link); i915_gem_object_unpin_pages(obj); + __i915_gem_object_put_pages(obj, I915_MM_NORMAL); i915_gem_object_put(obj); } } @@ -866,6 +868,7 @@ static int igt_mock_ppgtt_64K(void *arg) i915_vma_close(vma); i915_gem_object_unpin_pages(obj); + __i915_gem_object_put_pages(obj, I915_MM_NORMAL); i915_gem_object_put(obj); } } @@ -1265,6 +1268,7 @@ static int igt_ppgtt_exhaust_huge(void *arg) } i915_gem_object_unpin_pages(obj); + __i915_gem_object_put_pages(obj, I915_MM_NORMAL); i915_gem_object_put(obj); } } @@ -1326,6 +1330,7 @@ static int igt_ppgtt_internal_huge(void *arg) } i915_gem_object_unpin_pages(obj); + __i915_gem_object_put_pages(obj, I915_MM_NORMAL); i915_gem_object_put(obj); } @@ -1394,6 +1399,7 @@ static int igt_ppgtt_gemfs_huge(void *arg) } i915_gem_object_unpin_pages(obj); + __i915_gem_object_put_pages(obj, I915_MM_NORMAL); i915_gem_object_put(obj); } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c index ab2590242033..1c92560d35da 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c @@ -23,6 +23,7 @@ */ #include "../i915_selftest.h" +#include "i915_random.h" #include "igt_flush_test.h" #include "mock_drm.h" @@ -252,9 +253,9 @@ static int cpu_check(struct drm_i915_gem_object *obj, unsigned int max) } for (; m < DW_PER_PAGE; m++) { - if (map[m] != 0xdeadbeef) { + if (map[m] != STACK_MAGIC) { pr_err("Invalid value at page %d, offset %d: found %x expected %x\n", - n, m, map[m], 0xdeadbeef); + n, m, map[m], STACK_MAGIC); err = -EINVAL; goto out_unmap; } @@ -310,7 +311,7 @@ create_test_object(struct i915_gem_context *ctx, if (err) return ERR_PTR(err); - err = cpu_fill(obj, 0xdeadbeef); + err = cpu_fill(obj, STACK_MAGIC); if (err) { pr_err("Failed to fill object with cpu, err=%d\n", err); @@ -432,6 +433,111 @@ out_unlock: return err; } +static int igt_ctx_readonly(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct drm_i915_gem_object *obj = NULL; + struct drm_file *file; + I915_RND_STATE(prng); + IGT_TIMEOUT(end_time); + LIST_HEAD(objects); + struct i915_gem_context *ctx; + struct i915_hw_ppgtt *ppgtt; + unsigned long ndwords, dw; + int err = -ENODEV; + + /* + * Create a few read-only objects (with the occasional writable object) + * and try to write into these object checking that the GPU discards + * any write to a read-only object. + */ + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + mutex_lock(&i915->drm.struct_mutex); + + ctx = i915_gem_create_context(i915, file->driver_priv); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out_unlock; + } + + ppgtt = ctx->ppgtt ?: i915->mm.aliasing_ppgtt; + if (!ppgtt || !ppgtt->vm.has_read_only) { + err = 0; + goto out_unlock; + } + + ndwords = 0; + dw = 0; + while (!time_after(jiffies, end_time)) { + struct intel_engine_cs *engine; + unsigned int id; + + for_each_engine(engine, i915, id) { + if (!intel_engine_can_store_dword(engine)) + continue; + + if (!obj) { + obj = create_test_object(ctx, file, &objects); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto out_unlock; + } + + if (prandom_u32_state(&prng) & 1) + i915_gem_object_set_readonly(obj); + } + + intel_runtime_pm_get(i915); + err = gpu_fill(obj, ctx, engine, dw); + intel_runtime_pm_put(i915); + if (err) { + pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n", + ndwords, dw, max_dwords(obj), + engine->name, ctx->hw_id, + yesno(!!ctx->ppgtt), err); + goto out_unlock; + } + + if (++dw == max_dwords(obj)) { + obj = NULL; + dw = 0; + } + ndwords++; + } + } + pr_info("Submitted %lu dwords (across %u engines)\n", + ndwords, INTEL_INFO(i915)->num_rings); + + dw = 0; + list_for_each_entry(obj, &objects, st_link) { + unsigned int rem = + min_t(unsigned int, ndwords - dw, max_dwords(obj)); + unsigned int num_writes; + + num_writes = rem; + if (i915_gem_object_is_readonly(obj)) + num_writes = 0; + + err = cpu_check(obj, num_writes); + if (err) + break; + + dw += rem; + } + +out_unlock: + if (igt_flush_test(i915, I915_WAIT_LOCKED)) + err = -EIO; + mutex_unlock(&i915->drm.struct_mutex); + + mock_file_free(i915, file); + return err; +} + static __maybe_unused const char * __engine_name(struct drm_i915_private *i915, unsigned int engines) { @@ -608,6 +714,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv) static const struct i915_subtest tests[] = { SUBTEST(igt_switch_to_kernel_context), SUBTEST(igt_ctx_exec), + SUBTEST(igt_ctx_readonly), }; bool fake_alias = false; int err; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 600a3bcbd3d6..8e2e269db97e 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -1244,6 +1244,7 @@ static int exercise_mock(struct drm_i915_private *i915, u64 hole_start, u64 hole_end, unsigned long end_time)) { + const u64 limit = totalram_pages << PAGE_SHIFT; struct i915_gem_context *ctx; struct i915_hw_ppgtt *ppgtt; IGT_TIMEOUT(end_time); @@ -1256,7 +1257,7 @@ static int exercise_mock(struct drm_i915_private *i915, ppgtt = ctx->ppgtt; GEM_BUG_ON(!ppgtt); - err = func(i915, &ppgtt->vm, 0, ppgtt->vm.total, end_time); + err = func(i915, &ppgtt->vm, 0, min(ppgtt->vm.total, limit), end_time); mock_context_close(ctx); return err; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c index d77acf4cc439..c69cbd5aed52 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c @@ -375,7 +375,8 @@ static int igt_partial_tiling(void *arg) } GEM_BUG_ON(tile.swizzle == I915_BIT_6_SWIZZLE_UNKNOWN); - if (tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17) + if (tile.swizzle == I915_BIT_6_SWIZZLE_9_17 || + tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17) continue; if (INTEL_GEN(i915) <= 2) { diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c index addc5a599c4a..86c54ea37f48 100644 --- a/drivers/gpu/drm/i915/selftests/i915_selftest.c +++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c @@ -210,6 +210,8 @@ int __i915_subtests(const char *caller, return -EINTR; pr_debug(DRIVER_NAME ": Running %s/%s\n", caller, st->name); + GEM_TRACE("Running %s/%s\n", caller, st->name); + err = st->func(data); if (err && err != -EINTR) { pr_err(DRIVER_NAME "/%s: %s failed with error %d\n", diff --git a/drivers/gpu/drm/i915/selftests/igt_wedge_me.h b/drivers/gpu/drm/i915/selftests/igt_wedge_me.h new file mode 100644 index 000000000000..08e5ff11bbd9 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/igt_wedge_me.h @@ -0,0 +1,58 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#ifndef IGT_WEDGE_ME_H +#define IGT_WEDGE_ME_H + +#include <linux/workqueue.h> + +#include "../i915_gem.h" + +struct drm_i915_private; + +struct igt_wedge_me { + struct delayed_work work; + struct drm_i915_private *i915; + const char *name; +}; + +static void __igt_wedge_me(struct work_struct *work) +{ + struct igt_wedge_me *w = container_of(work, typeof(*w), work.work); + + pr_err("%s timed out, cancelling test.\n", w->name); + + GEM_TRACE("%s timed out.\n", w->name); + GEM_TRACE_DUMP(); + + i915_gem_set_wedged(w->i915); +} + +static void __igt_init_wedge(struct igt_wedge_me *w, + struct drm_i915_private *i915, + long timeout, + const char *name) +{ + w->i915 = i915; + w->name = name; + + INIT_DELAYED_WORK_ONSTACK(&w->work, __igt_wedge_me); + schedule_delayed_work(&w->work, timeout); +} + +static void __igt_fini_wedge(struct igt_wedge_me *w) +{ + cancel_delayed_work_sync(&w->work); + destroy_delayed_work_on_stack(&w->work); + w->i915 = NULL; +} + +#define igt_wedge_on_timeout(W, DEV, TIMEOUT) \ + for (__igt_init_wedge((W), (DEV), (TIMEOUT), __func__); \ + (W)->i915; \ + __igt_fini_wedge((W))) + +#endif /* IGT_WEDGE_ME_H */ diff --git a/drivers/gpu/drm/i915/selftests/intel_guc.c b/drivers/gpu/drm/i915/selftests/intel_guc.c index fb74e2cf8a0a..407c98fb9170 100644 --- a/drivers/gpu/drm/i915/selftests/intel_guc.c +++ b/drivers/gpu/drm/i915/selftests/intel_guc.c @@ -196,19 +196,23 @@ static int igt_guc_clients(void *args) } unreserve_doorbell(guc->execbuf_client); - err = guc_clients_doorbell_init(guc); + + __create_doorbell(guc->execbuf_client); + err = __guc_allocate_doorbell(guc, guc->execbuf_client->stage_id); if (err != -EIO) { pr_err("unexpected (err = %d)", err); - goto out; + goto out_db; } if (!available_dbs(guc, guc->execbuf_client->priority)) { pr_err("doorbell not available when it should\n"); err = -EIO; - goto out; + goto out_db; } +out_db: /* clean after test */ + __destroy_doorbell(guc->execbuf_client); err = reserve_doorbell(guc->execbuf_client); if (err) { pr_err("failed to reserve back the doorbell back\n"); diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c index 73462a65a330..65d66cdedd26 100644 --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c @@ -27,6 +27,7 @@ #include "../i915_selftest.h" #include "i915_random.h" #include "igt_flush_test.h" +#include "igt_wedge_me.h" #include "mock_context.h" #include "mock_drm.h" @@ -921,7 +922,7 @@ static u32 fake_hangcheck(struct i915_request *rq, u32 mask) return reset_count; } -static int igt_wait_reset(void *arg) +static int igt_reset_wait(void *arg) { struct drm_i915_private *i915 = arg; struct i915_request *rq; @@ -995,6 +996,170 @@ unlock: return err; } +struct evict_vma { + struct completion completion; + struct i915_vma *vma; +}; + +static int evict_vma(void *data) +{ + struct evict_vma *arg = data; + struct i915_address_space *vm = arg->vma->vm; + struct drm_i915_private *i915 = vm->i915; + struct drm_mm_node evict = arg->vma->node; + int err; + + complete(&arg->completion); + + mutex_lock(&i915->drm.struct_mutex); + err = i915_gem_evict_for_node(vm, &evict, 0); + mutex_unlock(&i915->drm.struct_mutex); + + return err; +} + +static int __igt_reset_evict_vma(struct drm_i915_private *i915, + struct i915_address_space *vm) +{ + struct drm_i915_gem_object *obj; + struct task_struct *tsk = NULL; + struct i915_request *rq; + struct evict_vma arg; + struct hang h; + int err; + + if (!intel_engine_can_store_dword(i915->engine[RCS])) + return 0; + + /* Check that we can recover an unbind stuck on a hanging request */ + + global_reset_lock(i915); + + mutex_lock(&i915->drm.struct_mutex); + err = hang_init(&h, i915); + if (err) + goto unlock; + + obj = i915_gem_object_create_internal(i915, PAGE_SIZE); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto fini; + } + + arg.vma = i915_vma_instance(obj, vm, NULL); + if (IS_ERR(arg.vma)) { + err = PTR_ERR(arg.vma); + goto out_obj; + } + + rq = hang_create_request(&h, i915->engine[RCS]); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto out_obj; + } + + err = i915_vma_pin(arg.vma, 0, 0, + i915_vma_is_ggtt(arg.vma) ? PIN_GLOBAL : PIN_USER); + if (err) + goto out_obj; + + err = i915_vma_move_to_active(arg.vma, rq, EXEC_OBJECT_WRITE); + i915_vma_unpin(arg.vma); + + i915_request_get(rq); + i915_request_add(rq); + if (err) + goto out_rq; + + mutex_unlock(&i915->drm.struct_mutex); + + if (!wait_until_running(&h, rq)) { + struct drm_printer p = drm_info_printer(i915->drm.dev); + + pr_err("%s: Failed to start request %x, at %x\n", + __func__, rq->fence.seqno, hws_seqno(&h, rq)); + intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name); + + i915_gem_set_wedged(i915); + goto out_reset; + } + + init_completion(&arg.completion); + + tsk = kthread_run(evict_vma, &arg, "igt/evict_vma"); + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + tsk = NULL; + goto out_reset; + } + + wait_for_completion(&arg.completion); + + if (wait_for(waitqueue_active(&rq->execute), 10)) { + struct drm_printer p = drm_info_printer(i915->drm.dev); + + pr_err("igt/evict_vma kthread did not wait\n"); + intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name); + + i915_gem_set_wedged(i915); + goto out_reset; + } + +out_reset: + fake_hangcheck(rq, intel_engine_flag(rq->engine)); + + if (tsk) { + struct igt_wedge_me w; + + /* The reset, even indirectly, should take less than 10ms. */ + igt_wedge_on_timeout(&w, i915, HZ / 10 /* 100ms timeout*/) + err = kthread_stop(tsk); + } + + mutex_lock(&i915->drm.struct_mutex); +out_rq: + i915_request_put(rq); +out_obj: + i915_gem_object_put(obj); +fini: + hang_fini(&h); +unlock: + mutex_unlock(&i915->drm.struct_mutex); + global_reset_unlock(i915); + + if (i915_terminally_wedged(&i915->gpu_error)) + return -EIO; + + return err; +} + +static int igt_reset_evict_ggtt(void *arg) +{ + struct drm_i915_private *i915 = arg; + + return __igt_reset_evict_vma(i915, &i915->ggtt.vm); +} + +static int igt_reset_evict_ppgtt(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct i915_gem_context *ctx; + int err; + + mutex_lock(&i915->drm.struct_mutex); + ctx = kernel_context(i915); + mutex_unlock(&i915->drm.struct_mutex); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + err = 0; + if (ctx->ppgtt) /* aliasing == global gtt locking, covered above */ + err = __igt_reset_evict_vma(i915, &ctx->ppgtt->vm); + + kernel_context_close(ctx); + return err; +} + static int wait_for_others(struct drm_i915_private *i915, struct intel_engine_cs *exclude) { @@ -1240,8 +1405,10 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_reset_idle_engine), SUBTEST(igt_reset_active_engine), SUBTEST(igt_reset_engines), - SUBTEST(igt_wait_reset), SUBTEST(igt_reset_queue), + SUBTEST(igt_reset_wait), + SUBTEST(igt_reset_evict_ggtt), + SUBTEST(igt_reset_evict_ppgtt), SUBTEST(igt_handle_error), }; bool saved_hangcheck; diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c index 636cb68191e3..582566faef09 100644 --- a/drivers/gpu/drm/i915/selftests/intel_lrc.c +++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c @@ -451,12 +451,127 @@ err_wedged: goto err_ctx_lo; } +static int live_preempt_hang(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct i915_gem_context *ctx_hi, *ctx_lo; + struct spinner spin_hi, spin_lo; + struct intel_engine_cs *engine; + enum intel_engine_id id; + int err = -ENOMEM; + + if (!HAS_LOGICAL_RING_PREEMPTION(i915)) + return 0; + + if (!intel_has_reset_engine(i915)) + return 0; + + mutex_lock(&i915->drm.struct_mutex); + + if (spinner_init(&spin_hi, i915)) + goto err_unlock; + + if (spinner_init(&spin_lo, i915)) + goto err_spin_hi; + + ctx_hi = kernel_context(i915); + if (!ctx_hi) + goto err_spin_lo; + ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY; + + ctx_lo = kernel_context(i915); + if (!ctx_lo) + goto err_ctx_hi; + ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY; + + for_each_engine(engine, i915, id) { + struct i915_request *rq; + + if (!intel_engine_has_preemption(engine)) + continue; + + rq = spinner_create_request(&spin_lo, ctx_lo, engine, + MI_ARB_CHECK); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto err_ctx_lo; + } + + i915_request_add(rq); + if (!wait_for_spinner(&spin_lo, rq)) { + GEM_TRACE("lo spinner failed to start\n"); + GEM_TRACE_DUMP(); + i915_gem_set_wedged(i915); + err = -EIO; + goto err_ctx_lo; + } + + rq = spinner_create_request(&spin_hi, ctx_hi, engine, + MI_ARB_CHECK); + if (IS_ERR(rq)) { + spinner_end(&spin_lo); + err = PTR_ERR(rq); + goto err_ctx_lo; + } + + init_completion(&engine->execlists.preempt_hang.completion); + engine->execlists.preempt_hang.inject_hang = true; + + i915_request_add(rq); + + if (!wait_for_completion_timeout(&engine->execlists.preempt_hang.completion, + HZ / 10)) { + pr_err("Preemption did not occur within timeout!"); + GEM_TRACE_DUMP(); + i915_gem_set_wedged(i915); + err = -EIO; + goto err_ctx_lo; + } + + set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); + i915_reset_engine(engine, NULL); + clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); + + engine->execlists.preempt_hang.inject_hang = false; + + if (!wait_for_spinner(&spin_hi, rq)) { + GEM_TRACE("hi spinner failed to start\n"); + GEM_TRACE_DUMP(); + i915_gem_set_wedged(i915); + err = -EIO; + goto err_ctx_lo; + } + + spinner_end(&spin_hi); + spinner_end(&spin_lo); + if (igt_flush_test(i915, I915_WAIT_LOCKED)) { + err = -EIO; + goto err_ctx_lo; + } + } + + err = 0; +err_ctx_lo: + kernel_context_close(ctx_lo); +err_ctx_hi: + kernel_context_close(ctx_hi); +err_spin_lo: + spinner_fini(&spin_lo); +err_spin_hi: + spinner_fini(&spin_hi); +err_unlock: + igt_flush_test(i915, I915_WAIT_LOCKED); + mutex_unlock(&i915->drm.struct_mutex); + return err; +} + int intel_execlists_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(live_sanitycheck), SUBTEST(live_preempt), SUBTEST(live_late_preempt), + SUBTEST(live_preempt_hang), }; if (!HAS_EXECLISTS(i915)) diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c index fafdec3fe83e..0d39b3bf0c0d 100644 --- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c +++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c @@ -6,6 +6,7 @@ #include "../i915_selftest.h" +#include "igt_wedge_me.h" #include "mock_context.h" static struct drm_i915_gem_object * @@ -111,6 +112,7 @@ static int check_whitelist(const struct whitelist *w, struct intel_engine_cs *engine) { struct drm_i915_gem_object *results; + struct igt_wedge_me wedge; u32 *vaddr; int err; int i; @@ -119,7 +121,11 @@ static int check_whitelist(const struct whitelist *w, if (IS_ERR(results)) return PTR_ERR(results); - err = i915_gem_object_set_to_cpu_domain(results, false); + err = 0; + igt_wedge_on_timeout(&wedge, ctx->i915, HZ / 5) /* a safety net! */ + err = i915_gem_object_set_to_cpu_domain(results, false); + if (i915_terminally_wedged(&ctx->i915->gpu_error)) + err = -EIO; if (err) goto out_put; diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h index 8758df94e9a0..c7987daeaed0 100644 --- a/include/drm/drm_vma_manager.h +++ b/include/drm/drm_vma_manager.h @@ -41,6 +41,7 @@ struct drm_vma_offset_node { rwlock_t vm_lock; struct drm_mm_node vm_node; struct rb_root vm_files; + bool readonly:1; }; struct drm_vma_offset_manager { diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index c9e5a6621b95..c44703f471b3 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -95,7 +95,9 @@ extern struct resource intel_graphics_stolen_res; #define I845_TSEG_SIZE_512K (2 << 1) #define I845_TSEG_SIZE_1M (3 << 1) -#define INTEL_BSM 0x5c +#define INTEL_BSM 0x5c +#define INTEL_GEN11_BSM_DW0 0xc0 +#define INTEL_GEN11_BSM_DW1 0xc4 #define INTEL_BSM_MASK (-(1u << 20)) #endif /* _I915_DRM_H_ */ |