diff options
51 files changed, 400 insertions, 361 deletions
diff --git a/Documentation/virt/kvm/nested-vmx.rst b/Documentation/virt/kvm/nested-vmx.rst index 6ab4e35cee23..ac2095d41f02 100644 --- a/Documentation/virt/kvm/nested-vmx.rst +++ b/Documentation/virt/kvm/nested-vmx.rst @@ -37,8 +37,10 @@ call L2. Running nested VMX ------------------ -The nested VMX feature is disabled by default. It can be enabled by giving -the "nested=1" option to the kvm-intel module. +The nested VMX feature is enabled by default since Linux kernel v4.20. For +older Linux kernel, it can be enabled by giving the "nested=1" option to the +kvm-intel module. + No modifications are required to user space (qemu). However, qemu's default emulated CPU type (qemu64) does not list the "VMX" CPU feature, so it must be diff --git a/Documentation/virt/kvm/running-nested-guests.rst b/Documentation/virt/kvm/running-nested-guests.rst index d0a1fc754c84..bd70c69468ae 100644 --- a/Documentation/virt/kvm/running-nested-guests.rst +++ b/Documentation/virt/kvm/running-nested-guests.rst @@ -74,7 +74,7 @@ few: Enabling "nested" (x86) ----------------------- -From Linux kernel v4.19 onwards, the ``nested`` KVM parameter is enabled +From Linux kernel v4.20 onwards, the ``nested`` KVM parameter is enabled by default for Intel and AMD. (Though your Linux distribution might override this default.) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index 31b060a44045..b17bf19217f1 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -47,6 +47,8 @@ __invalid: b . /* + * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers. + * * x0: SMCCC function ID * x1: struct kvm_nvhe_init_params PA */ @@ -70,9 +72,9 @@ __do_hyp_init: eret 1: mov x0, x1 - mov x4, lr - bl ___kvm_hyp_init - mov lr, x4 + mov x3, lr + bl ___kvm_hyp_init // Clobbers x0..x2 + mov lr, x3 /* Hello, World! */ mov x0, #SMCCC_RET_SUCCESS @@ -82,8 +84,8 @@ SYM_CODE_END(__kvm_hyp_init) /* * Initialize the hypervisor in EL2. * - * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers - * and leave x4 for the caller. + * Only uses x0..x2 so as to not clobber callee-saved SMCCC registers + * and leave x3 for the caller. * * x0: struct kvm_nvhe_init_params PA */ @@ -112,9 +114,9 @@ alternative_else_nop_endif /* * Set the PS bits in TCR_EL2. */ - ldr x1, [x0, #NVHE_INIT_TCR_EL2] - tcr_compute_pa_size x1, #TCR_EL2_PS_SHIFT, x2, x3 - msr tcr_el2, x1 + ldr x0, [x0, #NVHE_INIT_TCR_EL2] + tcr_compute_pa_size x0, #TCR_EL2_PS_SHIFT, x1, x2 + msr tcr_el2, x0 isb @@ -193,7 +195,7 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu) /* Enable MMU, set vectors and stack. */ mov x0, x28 - bl ___kvm_hyp_init // Clobbers x0..x3 + bl ___kvm_hyp_init // Clobbers x0..x2 /* Leave idmap. */ mov x0, x29 diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 13036cf0b912..38172ca627d3 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -321,7 +321,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, if (cpuid->nent < vcpu->arch.cpuid_nent) goto out; r = -EFAULT; - if (copy_to_user(entries, &vcpu->arch.cpuid_entries, + if (copy_to_user(entries, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) goto out; return 0; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 56cae1ff9e3f..66a08322988f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2879,6 +2879,8 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data); *reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data : (u32)msr_data; + if (efer & EFER_LMA) + ctxt->mode = X86EMUL_MODE_PROT64; return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 2ef8615f9dba..b56d604809b8 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1049,8 +1049,8 @@ bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) } /* - * Clear non-leaf entries (and free associated page tables) which could - * be replaced by large mappings, for GFNs within the slot. + * Clear leaf entries which could be replaced by large mappings, for + * GFNs within the slot. */ static void zap_collapsible_spte_range(struct kvm *kvm, struct kvm_mmu_page *root, @@ -1062,7 +1062,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm, tdp_root_for_each_pte(iter, root, start, end) { if (!is_shadow_present_pte(iter.old_spte) || - is_last_spte(iter.old_spte, iter.level)) + !is_last_spte(iter.old_spte, iter.level)) continue; pfn = spte_to_pfn(iter.old_spte); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 7a605ad8254d..db30670dd8c4 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -231,6 +231,7 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control) static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) { + struct kvm_vcpu *vcpu = &svm->vcpu; bool vmcb12_lma; if ((vmcb12->save.efer & EFER_SVME) == 0) @@ -244,18 +245,10 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) vmcb12_lma = (vmcb12->save.efer & EFER_LME) && (vmcb12->save.cr0 & X86_CR0_PG); - if (!vmcb12_lma) { - if (vmcb12->save.cr4 & X86_CR4_PAE) { - if (vmcb12->save.cr3 & MSR_CR3_LEGACY_PAE_RESERVED_MASK) - return false; - } else { - if (vmcb12->save.cr3 & MSR_CR3_LEGACY_RESERVED_MASK) - return false; - } - } else { + if (vmcb12_lma) { if (!(vmcb12->save.cr4 & X86_CR4_PAE) || !(vmcb12->save.cr0 & X86_CR0_PE) || - (vmcb12->save.cr3 & MSR_CR3_LONG_MBZ_MASK)) + (vmcb12->save.cr3 & vcpu->arch.cr3_lm_rsvd_bits)) return false; } if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4)) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index ac652bc476ae..48017fef1cd9 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -342,6 +342,8 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, unsigned long first, last; int ret; + lockdep_assert_held(&kvm->lock); + if (ulen == 0 || uaddr + ulen < uaddr) return ERR_PTR(-EINVAL); @@ -1119,12 +1121,20 @@ int svm_register_enc_region(struct kvm *kvm, if (!region) return -ENOMEM; + mutex_lock(&kvm->lock); region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1); if (IS_ERR(region->pages)) { ret = PTR_ERR(region->pages); + mutex_unlock(&kvm->lock); goto e_free; } + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are @@ -1133,13 +1143,6 @@ int svm_register_enc_region(struct kvm *kvm, */ sev_clflush_pages(region->pages, region->npages); - region->uaddr = range->addr; - region->size = range->size; - - mutex_lock(&kvm->lock); - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - return ret; e_free: diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index f923e14e87df..3442d44ca53b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -454,6 +454,11 @@ static int has_svm(void) return 0; } + if (sev_active()) { + pr_info("KVM is unsupported when running as an SEV guest\n"); + return 0; + } + return 1; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 0fe874ae5498..6e7d070f8b86 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -403,9 +403,6 @@ static inline bool gif_set(struct vcpu_svm *svm) } /* svm.c */ -#define MSR_CR3_LEGACY_RESERVED_MASK 0xfe7U -#define MSR_CR3_LEGACY_PAE_RESERVED_MASK 0x7U -#define MSR_CR3_LONG_MBZ_MASK 0xfff0000000000000U #define MSR_INVALID 0xffffffffU extern int sev; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index cc60b1fc3ee7..eb69fef57485 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6860,11 +6860,20 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) switch (index) { case MSR_IA32_TSX_CTRL: /* - * No need to pass TSX_CTRL_CPUID_CLEAR through, so - * let's avoid changing CPUID bits under the host - * kernel's feet. + * TSX_CTRL_CPUID_CLEAR is handled in the CPUID + * interception. Keep the host value unchanged to avoid + * changing CPUID bits under the host kernel's feet. + * + * hle=0, rtm=0, tsx_ctrl=1 can be found with some + * combinations of new kernel and old userspace. If + * those guests run on a tsx=off host, do allow guests + * to use TSX_CTRL, but do not change the value on the + * host so that TSX remains always disabled. */ - vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + if (boot_cpu_has(X86_FEATURE_RTM)) + vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + else + vmx->guest_uret_msrs[j].mask = 0; break; default: vmx->guest_uret_msrs[j].mask = -1ull; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 76bce832cade..1b404e4d7dd8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1394,16 +1394,24 @@ static u64 kvm_get_arch_capabilities(void) if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; - /* - * On TAA affected systems: - * - nothing to do if TSX is disabled on the host. - * - we emulate TSX_CTRL if present on the host. - * This lets the guest use VERW to clear CPU buffers. - */ - if (!boot_cpu_has(X86_FEATURE_RTM)) - data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR); - else if (!boot_cpu_has_bug(X86_BUG_TAA)) + if (!boot_cpu_has(X86_FEATURE_RTM)) { + /* + * If RTM=0 because the kernel has disabled TSX, the host might + * have TAA_NO or TSX_CTRL. Clear TAA_NO (the guest sees RTM=0 + * and therefore knows that there cannot be TAA) but keep + * TSX_CTRL: some buggy userspaces leave it set on tsx=on hosts, + * and we want to allow migrating those guests to tsx=off hosts. + */ + data &= ~ARCH_CAP_TAA_NO; + } else if (!boot_cpu_has_bug(X86_BUG_TAA)) { data |= ARCH_CAP_TAA_NO; + } else { + /* + * Nothing to do here; we emulate TSX_CTRL if present on the + * host so the guest can choose between disabling TSX or + * using VERW to clear CPU buffers. + */ + } return data; } @@ -9616,6 +9624,8 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; + if (sregs->cr3 & vcpu->arch.cr3_lm_rsvd_bits) + return false; } else { /* * Not in 64-bit mode: EFER.LMA is clear and the code @@ -9993,6 +10003,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) fx_init(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; @@ -10494,7 +10505,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, return 0; old_npages = slot->npages; - hva = 0; + hva = slot->userspace_addr; } for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index c5ee0f5ce0f1..0f727b50bd3d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -425,6 +425,8 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); __reserved_bits |= X86_CR4_UMIP; \ if (!__cpu_has(__c, X86_FEATURE_VMX)) \ __reserved_bits |= X86_CR4_VMXE; \ + if (!__cpu_has(__c, X86_FEATURE_PCID)) \ + __reserved_bits |= X86_CR4_PCIDE; \ __reserved_bits; \ }) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index c79e5736ab2b..c3d5f0236f35 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -382,6 +382,7 @@ bool sev_active(void) { return sev_status & MSR_AMD64_SEV_ENABLED; } +EXPORT_SYMBOL_GPL(sev_active); /* Needs to be called from non-instrumentable code */ bool noinstr sev_es_active(void) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 2d991da2cead..d1ed4f8df2b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -26,6 +26,7 @@ #include <linux/sched/task.h> #include "amdgpu_object.h" +#include "amdgpu_gem.h" #include "amdgpu_vm.h" #include "amdgpu_amdkfd.h" #include "amdgpu_dma_buf.h" @@ -1152,7 +1153,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( struct sg_table *sg = NULL; uint64_t user_addr = 0; struct amdgpu_bo *bo; - struct amdgpu_bo_param bp; + struct drm_gem_object *gobj; u32 domain, alloc_domain; u64 alloc_flags; int ret; @@ -1220,19 +1221,14 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s\n", va, size, domain_string(alloc_domain)); - memset(&bp, 0, sizeof(bp)); - bp.size = size; - bp.byte_align = 1; - bp.domain = alloc_domain; - bp.flags = alloc_flags; - bp.type = bo_type; - bp.resv = NULL; - ret = amdgpu_bo_create(adev, &bp, &bo); + ret = amdgpu_gem_object_create(adev, size, 1, alloc_domain, alloc_flags, + bo_type, NULL, &gobj); if (ret) { pr_debug("Failed to create BO on domain %s. ret %d\n", - domain_string(alloc_domain), ret); + domain_string(alloc_domain), ret); goto err_bo_create; } + bo = gem_to_amdgpu_bo(gobj); if (bo_type == ttm_bo_type_sg) { bo->tbo.sg = sg; bo->tbo.ttm->sg = sg; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index f764803c53a4..48cb33e5b382 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -926,8 +926,10 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev, struct drm_file *file_priv, const struct drm_mode_fb_cmd2 *mode_cmd) { - struct drm_gem_object *obj; struct amdgpu_framebuffer *amdgpu_fb; + struct drm_gem_object *obj; + struct amdgpu_bo *bo; + uint32_t domains; int ret; obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[0]); @@ -938,7 +940,9 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev, } /* Handle is imported dma-buf, so cannot be migrated to VRAM for scanout */ - if (obj->import_attach) { + bo = gem_to_amdgpu_bo(obj); + domains = amdgpu_display_supported_domains(drm_to_adev(dev), bo->flags); + if (obj->import_attach && !(domains & AMDGPU_GEM_DOMAIN_GTT)) { drm_dbg_kms(dev, "Cannot create framebuffer from imported dma_buf\n"); return ERR_PTR(-EINVAL); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index d0a1fee1f5f6..174a73eb23f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -269,8 +269,8 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data, resv = vm->root.base.bo->tbo.base.resv; } -retry: initial_domain = (u32)(0xffffffff & args->in.domains); +retry: r = amdgpu_gem_object_create(adev, size, args->in.alignment, initial_domain, flags, ttm_bo_type_device, resv, &gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 25ec4d57333f..b4c8e5d5c763 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -897,7 +897,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, return -EINVAL; /* A shared bo cannot be migrated to VRAM */ - if (bo->prime_shared_count) { + if (bo->prime_shared_count || bo->tbo.base.import_attach) { if (domain & AMDGPU_GEM_DOMAIN_GTT) domain = AMDGPU_GEM_DOMAIN_GTT; else diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 346963e3cf73..d86b42a36560 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -99,6 +99,10 @@ #define mmGCR_GENERAL_CNTL_Sienna_Cichlid 0x1580 #define mmGCR_GENERAL_CNTL_Sienna_Cichlid_BASE_IDX 0 +#define mmCGTS_TCC_DISABLE_Vangogh 0x5006 +#define mmCGTS_TCC_DISABLE_Vangogh_BASE_IDX 1 +#define mmCGTS_USER_TCC_DISABLE_Vangogh 0x5007 +#define mmCGTS_USER_TCC_DISABLE_Vangogh_BASE_IDX 1 #define mmGOLDEN_TSC_COUNT_UPPER_Vangogh 0x0025 #define mmGOLDEN_TSC_COUNT_UPPER_Vangogh_BASE_IDX 1 #define mmGOLDEN_TSC_COUNT_LOWER_Vangogh 0x0026 @@ -4936,8 +4940,18 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev) static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev) { /* TCCs are global (not instanced). */ - uint32_t tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) | - RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE); + uint32_t tcc_disable; + + switch (adev->asic_type) { + case CHIP_VANGOGH: + tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE_Vangogh) | + RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE_Vangogh); + break; + default: + tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) | + RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE); + break; + } adev->gfx.config.tcc_disabled_mask = REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, TCC_DISABLE) | diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c6da89df055d..961abf1cf040 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1833,8 +1833,8 @@ static void emulated_link_detect(struct dc_link *link) link->type = dc_connection_none; prev_sink = link->local_sink; - if (prev_sink != NULL) - dc_sink_retain(prev_sink); + if (prev_sink) + dc_sink_release(prev_sink); switch (link->connector_signal) { case SIGNAL_TYPE_HDMI_TYPE_A: { @@ -1934,7 +1934,7 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state, dc_commit_updates_for_stream( dm->dc, bundle->surface_updates, dc_state->stream_status->plane_count, - dc_state->streams[k], &bundle->stream_update, dc_state); + dc_state->streams[k], &bundle->stream_update); } cleanup: @@ -1965,8 +1965,7 @@ static void dm_set_dpms_off(struct dc_link *link) stream_update.stream = stream_state; dc_commit_updates_for_stream(stream_state->ctx->dc, NULL, 0, - stream_state, &stream_update, - stream_state->ctx->dc->current_state); + stream_state, &stream_update); mutex_unlock(&adev->dm.dc_lock); } @@ -2330,8 +2329,10 @@ void amdgpu_dm_update_connector_after_detect( * TODO: check if we still need the S3 mode update workaround. * If yes, put it here. */ - if (aconnector->dc_sink) + if (aconnector->dc_sink) { amdgpu_dm_update_freesync_caps(connector, NULL); + dc_sink_release(aconnector->dc_sink); + } aconnector->dc_sink = sink; dc_sink_retain(aconnector->dc_sink); @@ -2347,8 +2348,6 @@ void amdgpu_dm_update_connector_after_detect( drm_connector_update_edid_property(connector, aconnector->edid); - drm_add_edid_modes(connector, aconnector->edid); - if (aconnector->dc_link->aux_mode) drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, aconnector->edid); @@ -7549,7 +7548,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, struct drm_crtc *pcrtc, bool wait_for_vblank) { - uint32_t i; + int i; uint64_t timestamp_ns; struct drm_plane *plane; struct drm_plane_state *old_plane_state, *new_plane_state; @@ -7590,7 +7589,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, amdgpu_dm_commit_cursors(state); /* update planes when needed */ - for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { + for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) { struct drm_crtc *crtc = new_plane_state->crtc; struct drm_crtc_state *new_crtc_state; struct drm_framebuffer *fb = new_plane_state->fb; @@ -7813,8 +7812,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->surface_updates, planes_count, acrtc_state->stream, - &bundle->stream_update, - dc_state); + &bundle->stream_update); /** * Enable or disable the interrupts on the backend. @@ -8150,13 +8148,13 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state); struct dm_connector_state *dm_old_con_state = to_dm_connector_state(old_con_state); struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc); - struct dc_surface_update dummy_updates[MAX_SURFACES]; + struct dc_surface_update surface_updates[MAX_SURFACES]; struct dc_stream_update stream_update; struct dc_info_packet hdr_packet; struct dc_stream_status *status = NULL; bool abm_changed, hdr_changed, scaling_changed; - memset(&dummy_updates, 0, sizeof(dummy_updates)); + memset(&surface_updates, 0, sizeof(surface_updates)); memset(&stream_update, 0, sizeof(stream_update)); if (acrtc) { @@ -8213,16 +8211,15 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) * To fix this, DC should permit updating only stream properties. */ for (j = 0; j < status->plane_count; j++) - dummy_updates[j].surface = status->plane_states[0]; + surface_updates[j].surface = status->plane_states[j]; mutex_lock(&dm->dc_lock); dc_commit_updates_for_stream(dm->dc, - dummy_updates, + surface_updates, status->plane_count, dm_new_crtc_state->stream, - &stream_update, - dc_state); + &stream_update); mutex_unlock(&dm->dc_lock); } @@ -8359,14 +8356,14 @@ static int dm_force_atomic_commit(struct drm_connector *connector) ret = PTR_ERR_OR_ZERO(conn_state); if (ret) - goto err; + goto out; /* Attach crtc to drm_atomic_state*/ crtc_state = drm_atomic_get_crtc_state(state, &disconnected_acrtc->base); ret = PTR_ERR_OR_ZERO(crtc_state); if (ret) - goto err; + goto out; /* force a restore */ crtc_state->mode_changed = true; @@ -8376,17 +8373,15 @@ static int dm_force_atomic_commit(struct drm_connector *connector) ret = PTR_ERR_OR_ZERO(plane_state); if (ret) - goto err; - + goto out; /* Call commit internally with the state we just constructed */ ret = drm_atomic_commit(state); - if (!ret) - return 0; -err: - DRM_ERROR("Restoring old state failed with %i\n", ret); +out: drm_atomic_state_put(state); + if (ret) + DRM_ERROR("Restoring old state failed with %i\n", ret); return ret; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 8ab0b9060d2b..f2d8cf34be46 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -833,6 +833,9 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, if (computed_streams[i]) continue; + if (dcn20_remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK) + return false; + mutex_lock(&aconnector->mst_mgr.lock); if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link)) { mutex_unlock(&aconnector->mst_mgr.lock); @@ -850,7 +853,8 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, stream = dc_state->streams[i]; if (stream->timing.flags.DSC == 1) - dc_stream_add_dsc_to_resource(stream->ctx->dc, dc_state, stream); + if (dc_stream_add_dsc_to_resource(stream->ctx->dc, dc_state, stream) != DC_OK) + return false; } return true; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 58eb0d69873a..6cf1a5a2a5ec 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2679,8 +2679,7 @@ void dc_commit_updates_for_stream(struct dc *dc, struct dc_surface_update *srf_updates, int surface_count, struct dc_stream_state *stream, - struct dc_stream_update *stream_update, - struct dc_state *state) + struct dc_stream_update *stream_update) { const struct dc_stream_status *stream_status; enum surface_update_type update_type; @@ -2699,6 +2698,12 @@ void dc_commit_updates_for_stream(struct dc *dc, if (update_type >= UPDATE_TYPE_FULL) { + struct dc_plane_state *new_planes[MAX_SURFACES]; + + memset(new_planes, 0, sizeof(new_planes)); + + for (i = 0; i < surface_count; i++) + new_planes[i] = srf_updates[i].surface; /* initialize scratch memory for building context */ context = dc_create_state(dc); @@ -2707,15 +2712,21 @@ void dc_commit_updates_for_stream(struct dc *dc, return; } - dc_resource_state_copy_construct(state, context); + dc_resource_state_copy_construct( + dc->current_state, context); - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i]; - struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + /*remove old surfaces from context */ + if (!dc_rem_all_planes_for_stream(dc, stream, context)) { + DC_ERROR("Failed to remove streams for new validate context!\n"); + return; + } - if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state) - new_pipe->plane_state->force_full_update = true; + /* add surface to context */ + if (!dc_add_all_planes_for_stream(dc, stream, new_planes, surface_count, context)) { + DC_ERROR("Failed to add streams for new validate context!\n"); + return; } + } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index f95bade59624..1e4794e2825c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -892,13 +892,13 @@ static uint32_t translate_training_aux_read_interval(uint32_t dpcd_aux_read_inte switch (dpcd_aux_read_interval) { case 0x01: - aux_rd_interval_us = 400; + aux_rd_interval_us = 4000; break; case 0x02: - aux_rd_interval_us = 4000; + aux_rd_interval_us = 8000; break; case 0x03: - aux_rd_interval_us = 8000; + aux_rd_interval_us = 12000; break; case 0x04: aux_rd_interval_us = 16000; diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index b7910976b81a..e243c01b9672 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -283,8 +283,7 @@ void dc_commit_updates_for_stream(struct dc *dc, struct dc_surface_update *srf_updates, int surface_count, struct dc_stream_state *stream, - struct dc_stream_update *stream_update, - struct dc_state *state); + struct dc_stream_update *stream_update); /* * Log the current stream state. */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index b000b43a820d..674376428916 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -906,6 +906,8 @@ enum dcn20_clk_src_array_id { DCN20_CLK_SRC_PLL0, DCN20_CLK_SRC_PLL1, DCN20_CLK_SRC_PLL2, + DCN20_CLK_SRC_PLL3, + DCN20_CLK_SRC_PLL4, DCN20_CLK_SRC_TOTAL_DCN21 }; @@ -2030,6 +2032,14 @@ static bool dcn21_resource_construct( dcn21_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL2, &clk_src_regs[2], false); + pool->base.clock_sources[DCN20_CLK_SRC_PLL3] = + dcn21_clock_source_create(ctx, ctx->dc_bios, + CLOCK_SOURCE_COMBO_PHY_PLL3, + &clk_src_regs[3], false); + pool->base.clock_sources[DCN20_CLK_SRC_PLL4] = + dcn21_clock_source_create(ctx, ctx->dc_bios, + CLOCK_SOURCE_COMBO_PHY_PLL4, + &clk_src_regs[4], false); pool->base.clk_src_count = DCN20_CLK_SRC_TOTAL_DCN21; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 5c1482d4ca43..92ad2cdbae10 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -591,14 +591,17 @@ static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, gpu_metrics->average_socket_power = metrics.CurrentSocketPower; gpu_metrics->average_cpu_power = metrics.Power[0]; gpu_metrics->average_soc_power = metrics.Power[1]; + gpu_metrics->average_gfx_power = metrics.Power[2]; memcpy(&gpu_metrics->average_core_power[0], &metrics.CorePower[0], sizeof(uint16_t) * 8); gpu_metrics->average_gfxclk_frequency = metrics.GfxclkFrequency; gpu_metrics->average_socclk_frequency = metrics.SocclkFrequency; + gpu_metrics->average_uclk_frequency = metrics.MemclkFrequency; gpu_metrics->average_fclk_frequency = metrics.MemclkFrequency; gpu_metrics->average_vclk_frequency = metrics.VclkFrequency; + gpu_metrics->average_dclk_frequency = metrics.DclkFrequency; memcpy(&gpu_metrics->current_coreclk[0], &metrics.CoreFrequency[0], diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c index 0c98d27f84ac..fee27952ec6d 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c @@ -14,6 +14,7 @@ #include <linux/regmap.h> #include <linux/regulator/consumer.h> #include <linux/wait.h> +#include <linux/workqueue.h> #include <sound/hdmi-codec.h> @@ -36,6 +37,7 @@ struct lt9611uxc { struct mutex ocm_lock; struct wait_queue_head wq; + struct work_struct work; struct device_node *dsi0_node; struct device_node *dsi1_node; @@ -52,6 +54,8 @@ struct lt9611uxc { bool hpd_supported; bool edid_read; + /* can be accessed from different threads, so protect this with ocm_lock */ + bool hdmi_connected; uint8_t fw_version; }; @@ -143,21 +147,41 @@ static irqreturn_t lt9611uxc_irq_thread_handler(int irq, void *dev_id) if (irq_status) regmap_write(lt9611uxc->regmap, 0xb022, 0); - lt9611uxc_unlock(lt9611uxc); - - if (irq_status & BIT(0)) + if (irq_status & BIT(0)) { lt9611uxc->edid_read = !!(hpd_status & BIT(0)); + wake_up_all(<9611uxc->wq); + } if (irq_status & BIT(1)) { - if (lt9611uxc->connector.dev) - drm_kms_helper_hotplug_event(lt9611uxc->connector.dev); - else - drm_bridge_hpd_notify(<9611uxc->bridge, !!(hpd_status & BIT(1))); + lt9611uxc->hdmi_connected = hpd_status & BIT(1); + schedule_work(<9611uxc->work); } + lt9611uxc_unlock(lt9611uxc); + return IRQ_HANDLED; } +static void lt9611uxc_hpd_work(struct work_struct *work) +{ + struct lt9611uxc *lt9611uxc = container_of(work, struct lt9611uxc, work); + bool connected; + + if (lt9611uxc->connector.dev) + drm_kms_helper_hotplug_event(lt9611uxc->connector.dev); + else { + + mutex_lock(<9611uxc->ocm_lock); + connected = lt9611uxc->hdmi_connected; + mutex_unlock(<9611uxc->ocm_lock); + + drm_bridge_hpd_notify(<9611uxc->bridge, + connected ? + connector_status_connected : + connector_status_disconnected); + } +} + static void lt9611uxc_reset(struct lt9611uxc *lt9611uxc) { gpiod_set_value_cansleep(lt9611uxc->reset_gpio, 1); @@ -445,18 +469,21 @@ static enum drm_connector_status lt9611uxc_bridge_detect(struct drm_bridge *brid struct lt9611uxc *lt9611uxc = bridge_to_lt9611uxc(bridge); unsigned int reg_val = 0; int ret; - int connected = 1; + bool connected = true; + + lt9611uxc_lock(lt9611uxc); if (lt9611uxc->hpd_supported) { - lt9611uxc_lock(lt9611uxc); ret = regmap_read(lt9611uxc->regmap, 0xb023, ®_val); - lt9611uxc_unlock(lt9611uxc); if (ret) dev_err(lt9611uxc->dev, "failed to read hpd status: %d\n", ret); else connected = reg_val & BIT(1); } + lt9611uxc->hdmi_connected = connected; + + lt9611uxc_unlock(lt9611uxc); return connected ? connector_status_connected : connector_status_disconnected; @@ -465,7 +492,7 @@ static enum drm_connector_status lt9611uxc_bridge_detect(struct drm_bridge *brid static int lt9611uxc_wait_for_edid(struct lt9611uxc *lt9611uxc) { return wait_event_interruptible_timeout(lt9611uxc->wq, lt9611uxc->edid_read, - msecs_to_jiffies(100)); + msecs_to_jiffies(500)); } static int lt9611uxc_get_edid_block(void *data, u8 *buf, unsigned int block, size_t len) @@ -503,7 +530,10 @@ static struct edid *lt9611uxc_bridge_get_edid(struct drm_bridge *bridge, ret = lt9611uxc_wait_for_edid(lt9611uxc); if (ret < 0) { dev_err(lt9611uxc->dev, "wait for EDID failed: %d\n", ret); - return ERR_PTR(ret); + return NULL; + } else if (ret == 0) { + dev_err(lt9611uxc->dev, "wait for EDID timeout\n"); + return NULL; } return drm_do_get_edid(connector, lt9611uxc_get_edid_block, lt9611uxc); @@ -926,6 +956,8 @@ retry: lt9611uxc->fw_version = ret; init_waitqueue_head(<9611uxc->wq); + INIT_WORK(<9611uxc->work, lt9611uxc_hpd_work); + ret = devm_request_threaded_irq(dev, client->irq, NULL, lt9611uxc_irq_thread_handler, IRQF_ONESHOT, "lt9611uxc", lt9611uxc); @@ -962,6 +994,7 @@ static int lt9611uxc_remove(struct i2c_client *client) struct lt9611uxc *lt9611uxc = i2c_get_clientdata(client); disable_irq(client->irq); + flush_scheduled_work(); lt9611uxc_audio_exit(lt9611uxc); drm_bridge_remove(<9611uxc->bridge); diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 0401b2f47500..8781deefeae3 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -3629,14 +3629,26 @@ static int drm_dp_send_up_ack_reply(struct drm_dp_mst_topology_mgr *mgr, return 0; } -static int drm_dp_get_vc_payload_bw(u8 dp_link_bw, u8 dp_link_count) +/** + * drm_dp_get_vc_payload_bw - get the VC payload BW for an MST link + * @link_rate: link rate in 10kbits/s units + * @link_lane_count: lane count + * + * Calculate the total bandwidth of a MultiStream Transport link. The returned + * value is in units of PBNs/(timeslots/1 MTP). This value can be used to + * convert the number of PBNs required for a given stream to the number of + * timeslots this stream requires in each MTP. + */ +int drm_dp_get_vc_payload_bw(int link_rate, int link_lane_count) { - if (dp_link_bw == 0 || dp_link_count == 0) - DRM_DEBUG_KMS("invalid link bandwidth in DPCD: %x (link count: %d)\n", - dp_link_bw, dp_link_count); + if (link_rate == 0 || link_lane_count == 0) + DRM_DEBUG_KMS("invalid link rate/lane count: (%d / %d)\n", + link_rate, link_lane_count); - return dp_link_bw * dp_link_count / 2; + /* See DP v2.0 2.6.4.2, VCPayload_Bandwidth_for_OneTimeSlotPer_MTP_Allocation */ + return link_rate * link_lane_count / 54000; } +EXPORT_SYMBOL(drm_dp_get_vc_payload_bw); /** * drm_dp_read_mst_cap() - check whether or not a sink supports MST @@ -3692,7 +3704,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms goto out_unlock; } - mgr->pbn_div = drm_dp_get_vc_payload_bw(mgr->dpcd[1], + mgr->pbn_div = drm_dp_get_vc_payload_bw(drm_dp_bw_code_to_link_rate(mgr->dpcd[1]), mgr->dpcd[2] & DP_MAX_LANE_COUNT_MASK); if (mgr->pbn_div == 0) { ret = -EINVAL; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index bf17365857ca..dc13d1814d95 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -2754,6 +2754,9 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder, int n_entries, ln; u32 val; + if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT) + return; + ddi_translations = icl_get_mg_buf_trans(encoder, crtc_state, &n_entries); if (level >= n_entries) { drm_dbg_kms(&dev_priv->drm, @@ -2890,6 +2893,9 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, u32 val, dpcnt_mask, dpcnt_val; int n_entries, ln; + if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT) + return; + ddi_translations = tgl_get_dkl_buf_trans(encoder, crtc_state, &n_entries); if (level >= n_entries) @@ -3531,6 +3537,23 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder, intel_de_posting_read(dev_priv, dp_tp_ctl_reg(encoder, crtc_state)); } +static void intel_ddi_power_up_lanes(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_digital_port *dig_port = enc_to_dig_port(encoder); + enum phy phy = intel_port_to_phy(i915, encoder->port); + + if (intel_phy_is_combo(i915, phy)) { + bool lane_reversal = + dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL; + + intel_combo_phy_power_up_lanes(i915, phy, false, + crtc_state->lane_count, + lane_reversal); + } +} + static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state, struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, @@ -3620,14 +3643,7 @@ static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state, * 7.f Combo PHY: Configure PORT_CL_DW10 Static Power Down to power up * the used lanes of the DDI. */ - if (intel_phy_is_combo(dev_priv, phy)) { - bool lane_reversal = - dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL; - - intel_combo_phy_power_up_lanes(dev_priv, phy, false, - crtc_state->lane_count, - lane_reversal); - } + intel_ddi_power_up_lanes(encoder, crtc_state); /* * 7.g Configure and enable DDI_BUF_CTL @@ -3712,14 +3728,7 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, else intel_prepare_dp_ddi_buffers(encoder, crtc_state); - if (intel_phy_is_combo(dev_priv, phy)) { - bool lane_reversal = - dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL; - - intel_combo_phy_power_up_lanes(dev_priv, phy, false, - crtc_state->lane_count, - lane_reversal); - } + intel_ddi_power_up_lanes(encoder, crtc_state); intel_ddi_init_dp_buf_reg(encoder, crtc_state); if (!is_mst) @@ -4205,6 +4214,8 @@ static void intel_enable_ddi_hdmi(struct intel_atomic_state *state, intel_de_write(dev_priv, reg, val); } + intel_ddi_power_up_lanes(encoder, crtc_state); + /* In HDMI/DVI mode, the port width, and swing/emphasis values * are ignored so nothing special needs to be done besides * enabling the port. diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 53a00cf3fa32..61be6bed9162 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -2309,7 +2309,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, */ ret = i915_vma_pin_fence(vma); if (ret != 0 && INTEL_GEN(dev_priv) < 4) { - i915_gem_object_unpin_from_display_plane(vma); + i915_vma_unpin(vma); vma = ERR_PTR(ret); goto err; } @@ -2327,12 +2327,9 @@ err: void intel_unpin_fb_vma(struct i915_vma *vma, unsigned long flags) { - i915_gem_object_lock(vma->obj, NULL); if (flags & PLANE_HAS_FENCE) i915_vma_unpin_fence(vma); - i915_gem_object_unpin_from_display_plane(vma); - i915_gem_object_unlock(vma->obj); - + i915_vma_unpin(vma); i915_vma_put(vma); } @@ -4807,6 +4804,8 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state, plane_color_ctl |= PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE; } else if (fb->format->is_yuv) { plane_color_ctl |= PLANE_COLOR_INPUT_CSC_ENABLE; + if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE) + plane_color_ctl |= PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE; } return plane_color_ctl; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 09123e8625c4..8a26307c4896 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4637,24 +4637,6 @@ ivb_cpu_edp_set_signal_levels(struct intel_dp *intel_dp, intel_de_posting_read(dev_priv, intel_dp->output_reg); } -void intel_dp_set_signal_levels(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) -{ - struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - u8 train_set = intel_dp->train_set[0]; - - drm_dbg_kms(&dev_priv->drm, "Using vswing level %d%s\n", - train_set & DP_TRAIN_VOLTAGE_SWING_MASK, - train_set & DP_TRAIN_MAX_SWING_REACHED ? " (max)" : ""); - drm_dbg_kms(&dev_priv->drm, "Using pre-emphasis level %d%s\n", - (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) >> - DP_TRAIN_PRE_EMPHASIS_SHIFT, - train_set & DP_TRAIN_MAX_PRE_EMPHASIS_REACHED ? - " (max)" : ""); - - intel_dp->set_signal_levels(intel_dp, crtc_state); -} - void intel_dp_program_link_training_pattern(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, @@ -5703,7 +5685,7 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp, intel_dp_autotest_phy_ddi_disable(intel_dp, crtc_state); - intel_dp_set_signal_levels(intel_dp, crtc_state); + intel_dp_set_signal_levels(intel_dp, crtc_state, DP_PHY_DPRX); intel_dp_phy_pattern_update(intel_dp, crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index 05f7ddf7a795..6620f9efdcbb 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -96,9 +96,6 @@ void intel_dp_program_link_training_pattern(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, u8 dp_train_pat); -void -intel_dp_set_signal_levels(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state); void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock, u8 *link_bw, u8 *rate_select); bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 91d3979902d0..d8c6d7054d11 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -334,6 +334,27 @@ intel_dp_set_link_train(struct intel_dp *intel_dp, return drm_dp_dpcd_write(&intel_dp->aux, reg, buf, len) == len; } +void intel_dp_set_signal_levels(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + enum drm_dp_phy dp_phy) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + u8 train_set = intel_dp->train_set[0]; + char phy_name[10]; + + drm_dbg_kms(&dev_priv->drm, "Using vswing level %d%s, pre-emphasis level %d%s, at %s\n", + train_set & DP_TRAIN_VOLTAGE_SWING_MASK, + train_set & DP_TRAIN_MAX_SWING_REACHED ? " (max)" : "", + (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) >> + DP_TRAIN_PRE_EMPHASIS_SHIFT, + train_set & DP_TRAIN_MAX_PRE_EMPHASIS_REACHED ? + " (max)" : "", + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name))); + + if (intel_dp_phy_is_downstream_of_source(intel_dp, dp_phy)) + intel_dp->set_signal_levels(intel_dp, crtc_state); +} + static bool intel_dp_reset_link_train(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, @@ -341,7 +362,7 @@ intel_dp_reset_link_train(struct intel_dp *intel_dp, u8 dp_train_pat) { memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set)); - intel_dp_set_signal_levels(intel_dp, crtc_state); + intel_dp_set_signal_levels(intel_dp, crtc_state, dp_phy); return intel_dp_set_link_train(intel_dp, crtc_state, dp_phy, dp_train_pat); } @@ -355,7 +376,7 @@ intel_dp_update_link_train(struct intel_dp *intel_dp, DP_TRAINING_LANE0_SET_PHY_REPEATER(dp_phy); int ret; - intel_dp_set_signal_levels(intel_dp, crtc_state); + intel_dp_set_signal_levels(intel_dp, crtc_state, dp_phy); ret = drm_dp_dpcd_write(&intel_dp->aux, reg, intel_dp->train_set, crtc_state->lane_count); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h index 86905aa24db7..6a1f76bd8c75 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h @@ -17,6 +17,9 @@ void intel_dp_get_adjust_train(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, enum drm_dp_phy dp_phy, const u8 link_status[DP_LINK_STATUS_SIZE]); +void intel_dp_set_signal_levels(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + enum drm_dp_phy dp_phy); void intel_dp_start_link_train(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state); void intel_dp_stop_link_train(struct intel_dp *intel_dp, diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 27f04aed8764..3286b232be0b 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -69,7 +69,9 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr, connector->port, - crtc_state->pbn, 0); + crtc_state->pbn, + drm_dp_get_vc_payload_bw(crtc_state->port_clock, + crtc_state->lane_count)); if (slots == -EDEADLK) return slots; if (slots >= 0) diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index 52b4f6193b4c..0095c8cac9b4 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -359,7 +359,7 @@ static void intel_overlay_release_old_vma(struct intel_overlay *overlay) intel_frontbuffer_flip_complete(overlay->i915, INTEL_FRONTBUFFER_OVERLAY(overlay->crtc->pipe)); - i915_gem_object_unpin_from_display_plane(vma); + i915_vma_unpin(vma); i915_vma_put(vma); } @@ -860,7 +860,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, return 0; out_unpin: - i915_gem_object_unpin_from_display_plane(vma); + i915_vma_unpin(vma); out_pin_section: atomic_dec(&dev_priv->gpu_error.pending_fb_pin); diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index 019a2d6d807a..3da2544fa1c0 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -618,13 +618,19 @@ skl_program_scaler(struct intel_plane *plane, /* Preoffset values for YUV to RGB Conversion */ #define PREOFF_YUV_TO_RGB_HI 0x1800 -#define PREOFF_YUV_TO_RGB_ME 0x1F00 +#define PREOFF_YUV_TO_RGB_ME 0x0000 #define PREOFF_YUV_TO_RGB_LO 0x1800 #define ROFF(x) (((x) & 0xffff) << 16) #define GOFF(x) (((x) & 0xffff) << 0) #define BOFF(x) (((x) & 0xffff) << 16) +/* + * Programs the input color space conversion stage for ICL HDR planes. + * Note that it is assumed that this stage always happens after YUV + * range correction. Thus, the input to this stage is assumed to be + * in full-range YCbCr. + */ static void icl_program_input_csc(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, @@ -672,52 +678,7 @@ icl_program_input_csc(struct intel_plane *plane, 0x0, 0x7800, 0x7F10, }, }; - - /* Matrix for Limited Range to Full Range Conversion */ - static const u16 input_csc_matrix_lr[][9] = { - /* - * BT.601 Limted range YCbCr -> full range RGB - * The matrix required is : - * [1.164384, 0.000, 1.596027, - * 1.164384, -0.39175, -0.812813, - * 1.164384, 2.017232, 0.0000] - */ - [DRM_COLOR_YCBCR_BT601] = { - 0x7CC8, 0x7950, 0x0, - 0x8D00, 0x7950, 0x9C88, - 0x0, 0x7950, 0x6810, - }, - /* - * BT.709 Limited range YCbCr -> full range RGB - * The matrix required is : - * [1.164384, 0.000, 1.792741, - * 1.164384, -0.213249, -0.532909, - * 1.164384, 2.112402, 0.0000] - */ - [DRM_COLOR_YCBCR_BT709] = { - 0x7E58, 0x7950, 0x0, - 0x8888, 0x7950, 0xADA8, - 0x0, 0x7950, 0x6870, - }, - /* - * BT.2020 Limited range YCbCr -> full range RGB - * The matrix required is : - * [1.164, 0.000, 1.678, - * 1.164, -0.1873, -0.6504, - * 1.164, 2.1417, 0.0000] - */ - [DRM_COLOR_YCBCR_BT2020] = { - 0x7D70, 0x7950, 0x0, - 0x8A68, 0x7950, 0xAC00, - 0x0, 0x7950, 0x6890, - }, - }; - const u16 *csc; - - if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE) - csc = input_csc_matrix[plane_state->hw.color_encoding]; - else - csc = input_csc_matrix_lr[plane_state->hw.color_encoding]; + const u16 *csc = input_csc_matrix[plane_state->hw.color_encoding]; intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 0), ROFF(csc[0]) | GOFF(csc[1])); @@ -734,14 +695,8 @@ icl_program_input_csc(struct intel_plane *plane, intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 0), PREOFF_YUV_TO_RGB_HI); - if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE) - intel_de_write_fw(dev_priv, - PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1), - 0); - else - intel_de_write_fw(dev_priv, - PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1), - PREOFF_YUV_TO_RGB_ME); + intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1), + PREOFF_YUV_TO_RGB_ME); intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 2), PREOFF_YUV_TO_RGB_LO); intel_de_write_fw(dev_priv, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index fcce6909f201..3d435bfff764 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -387,48 +387,6 @@ err: return vma; } -static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) -{ - struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct i915_vma *vma; - - if (list_empty(&obj->vma.list)) - return; - - mutex_lock(&i915->ggtt.vm.mutex); - spin_lock(&obj->vma.lock); - for_each_ggtt_vma(vma, obj) { - if (!drm_mm_node_allocated(&vma->node)) - continue; - - GEM_BUG_ON(vma->vm != &i915->ggtt.vm); - list_move_tail(&vma->vm_link, &vma->vm->bound_list); - } - spin_unlock(&obj->vma.lock); - mutex_unlock(&i915->ggtt.vm.mutex); - - if (i915_gem_object_is_shrinkable(obj)) { - unsigned long flags; - - spin_lock_irqsave(&i915->mm.obj_lock, flags); - - if (obj->mm.madv == I915_MADV_WILLNEED && - !atomic_read(&obj->mm.shrink_pin)) - list_move_tail(&obj->mm.link, &i915->mm.shrink_list); - - spin_unlock_irqrestore(&i915->mm.obj_lock, flags); - } -} - -void -i915_gem_object_unpin_from_display_plane(struct i915_vma *vma) -{ - /* Bump the LRU to try and avoid premature eviction whilst flipping */ - i915_gem_object_bump_inactive_ggtt(vma->obj); - - i915_vma_unpin(vma); -} - /** * Moves a single object to the CPU read, and possibly write domain. * @obj: object to act on @@ -569,9 +527,6 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, else err = i915_gem_object_set_to_cpu_domain(obj, write_domain); - /* And bump the LRU for this access */ - i915_gem_object_bump_inactive_ggtt(obj); - i915_gem_object_unlock(obj); if (write_domain) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index be14486f63a7..4556afe18f16 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -486,7 +486,6 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, u32 alignment, const struct i915_ggtt_view *view, unsigned int flags); -void i915_gem_object_unpin_from_display_plane(struct i915_vma *vma); void i915_gem_object_make_unshrinkable(struct drm_i915_gem_object *obj); void i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj); diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index 0625cbb3b431..1d1757584f49 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -187,18 +187,6 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl) intel_engine_add_retire(b->irq_engine, tl); } -static bool __signal_request(struct i915_request *rq) -{ - GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)); - - if (!__dma_fence_signal(&rq->fence)) { - i915_request_put(rq); - return false; - } - - return true; -} - static struct llist_node * slist_add(struct llist_node *node, struct llist_node *head) { @@ -269,9 +257,11 @@ static void signal_irq_work(struct irq_work *work) release = remove_signaling_context(b, ce); spin_unlock(&ce->signal_lock); - if (__signal_request(rq)) + if (__dma_fence_signal(&rq->fence)) /* We own signal_node now, xfer to local list */ signal = slist_add(&rq->signal_node, signal); + else + i915_request_put(rq); if (release) { add_retire(b, ce->timeline); @@ -358,6 +348,17 @@ void intel_breadcrumbs_free(struct intel_breadcrumbs *b) kfree(b); } +static void irq_signal_request(struct i915_request *rq, + struct intel_breadcrumbs *b) +{ + if (!__dma_fence_signal(&rq->fence)) + return; + + i915_request_get(rq); + if (llist_add(&rq->signal_node, &b->signaled_requests)) + irq_work_queue(&b->irq_work); +} + static void insert_breadcrumb(struct i915_request *rq) { struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs; @@ -367,17 +368,13 @@ static void insert_breadcrumb(struct i915_request *rq) if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) return; - i915_request_get(rq); - /* * If the request is already completed, we can transfer it * straight onto a signaled list, and queue the irq worker for * its signal completion. */ if (__i915_request_is_complete(rq)) { - if (__signal_request(rq) && - llist_add(&rq->signal_node, &b->signaled_requests)) - irq_work_queue(&b->irq_work); + irq_signal_request(rq, b); return; } @@ -408,6 +405,8 @@ static void insert_breadcrumb(struct i915_request *rq) break; } } + + i915_request_get(rq); list_add_rcu(&rq->signal_link, pos); GEM_BUG_ON(!check_signal_order(ce, rq)); GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)); @@ -448,19 +447,25 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq) void i915_request_cancel_breadcrumb(struct i915_request *rq) { + struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs; struct intel_context *ce = rq->context; bool release; - if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) + spin_lock(&ce->signal_lock); + if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) { + spin_unlock(&ce->signal_lock); return; + } - spin_lock(&ce->signal_lock); list_del_rcu(&rq->signal_link); - release = remove_signaling_context(rq->engine->breadcrumbs, ce); + release = remove_signaling_context(b, ce); spin_unlock(&ce->signal_lock); if (release) intel_context_put(ce); + if (__i915_request_is_complete(rq)) + irq_signal_request(rq, b); + i915_request_put(rq); } diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index c85b1af06b7b..7ea367a5444d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -547,7 +547,7 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo) { struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev); struct ttm_tt *ttm_dma = (struct ttm_tt *)nvbo->bo.ttm; - int i; + int i, j; if (!ttm_dma) return; @@ -556,10 +556,21 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo) if (nvbo->force_coherent) return; - for (i = 0; i < ttm_dma->num_pages; i++) + for (i = 0; i < ttm_dma->num_pages; ++i) { + struct page *p = ttm_dma->pages[i]; + size_t num_pages = 1; + + for (j = i + 1; j < ttm_dma->num_pages; ++j) { + if (++p != ttm_dma->pages[j]) + break; + + ++num_pages; + } dma_sync_single_for_device(drm->dev->dev, ttm_dma->dma_address[i], - PAGE_SIZE, DMA_TO_DEVICE); + num_pages * PAGE_SIZE, DMA_TO_DEVICE); + i += num_pages; + } } void @@ -567,7 +578,7 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo) { struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev); struct ttm_tt *ttm_dma = (struct ttm_tt *)nvbo->bo.ttm; - int i; + int i, j; if (!ttm_dma) return; @@ -576,9 +587,21 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo) if (nvbo->force_coherent) return; - for (i = 0; i < ttm_dma->num_pages; i++) + for (i = 0; i < ttm_dma->num_pages; ++i) { + struct page *p = ttm_dma->pages[i]; + size_t num_pages = 1; + + for (j = i + 1; j < ttm_dma->num_pages; ++j) { + if (++p != ttm_dma->pages[j]) + break; + + ++num_pages; + } + dma_sync_single_for_cpu(drm->dev->dev, ttm_dma->dma_address[i], - PAGE_SIZE, DMA_FROM_DEVICE); + num_pages * PAGE_SIZE, DMA_FROM_DEVICE); + i += num_pages; + } } void nouveau_bo_add_io_reserve_lru(struct ttm_buffer_object *bo) diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 11e0313db0ea..74bf1c84b637 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -84,7 +84,7 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags, * put_page() on a TTM allocated page is illegal. */ if (order) - gfp_flags |= __GFP_NOMEMALLOC | __GFP_NORETRY | + gfp_flags |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; if (!pool->use_dma_alloc) { diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c index 44bea5e4aeda..b23773583179 100644 --- a/drivers/mmc/core/sdio_cis.c +++ b/drivers/mmc/core/sdio_cis.c @@ -20,6 +20,8 @@ #include "sdio_cis.h" #include "sdio_ops.h" +#define SDIO_READ_CIS_TIMEOUT_MS (10 * 1000) /* 10s */ + static int cistpl_vers_1(struct mmc_card *card, struct sdio_func *func, const unsigned char *buf, unsigned size) { @@ -274,6 +276,8 @@ static int sdio_read_cis(struct mmc_card *card, struct sdio_func *func) do { unsigned char tpl_code, tpl_link; + unsigned long timeout = jiffies + + msecs_to_jiffies(SDIO_READ_CIS_TIMEOUT_MS); ret = mmc_io_rw_direct(card, 0, 0, ptr++, 0, &tpl_code); if (ret) @@ -326,6 +330,8 @@ static int sdio_read_cis(struct mmc_card *card, struct sdio_func *func) prev = &this->next; if (ret == -ENOENT) { + if (time_after(jiffies, timeout)) + break; /* warn about unknown tuples */ pr_warn_ratelimited("%s: queuing unknown" " CIS tuple 0x%02x (%u bytes)\n", diff --git a/drivers/mmc/host/sdhci-pltfm.h b/drivers/mmc/host/sdhci-pltfm.h index 6301b81cf573..9bd717ff784b 100644 --- a/drivers/mmc/host/sdhci-pltfm.h +++ b/drivers/mmc/host/sdhci-pltfm.h @@ -111,8 +111,13 @@ static inline void *sdhci_pltfm_priv(struct sdhci_pltfm_host *host) return host->private; } +extern const struct dev_pm_ops sdhci_pltfm_pmops; +#ifdef CONFIG_PM_SLEEP int sdhci_pltfm_suspend(struct device *dev); int sdhci_pltfm_resume(struct device *dev); -extern const struct dev_pm_ops sdhci_pltfm_pmops; +#else +static inline int sdhci_pltfm_suspend(struct device *dev) { return 0; } +static inline int sdhci_pltfm_resume(struct device *dev) { return 0; } +#endif #endif /* _DRIVERS_MMC_SDHCI_PLTFM_H */ diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b9fecc25d213..790393d1e318 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1558,7 +1558,6 @@ int pci_save_state(struct pci_dev *dev) return i; pci_save_ltr_state(dev); - pci_save_aspm_l1ss_state(dev); pci_save_dpc_state(dev); pci_save_aer_state(dev); pci_save_ptm_state(dev); @@ -1665,7 +1664,6 @@ void pci_restore_state(struct pci_dev *dev) * LTR itself (in the PCIe capability). */ pci_restore_ltr_state(dev); - pci_restore_aspm_l1ss_state(dev); pci_restore_pcie_state(dev); pci_restore_pasid_state(dev); @@ -3353,11 +3351,6 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev) if (error) pci_err(dev, "unable to allocate suspend buffer for LTR\n"); - error = pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_L1SS, - 2 * sizeof(u32)); - if (error) - pci_err(dev, "unable to allocate suspend buffer for ASPM-L1SS\n"); - pci_allocate_vc_save_buffers(dev); } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 5c59365092fa..a7bdf0b1d45d 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -582,15 +582,11 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); void pcie_aspm_pm_state_change(struct pci_dev *pdev); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); -void pci_save_aspm_l1ss_state(struct pci_dev *dev); -void pci_restore_aspm_l1ss_state(struct pci_dev *dev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } -static inline void pci_save_aspm_l1ss_state(struct pci_dev *dev) { } -static inline void pci_restore_aspm_l1ss_state(struct pci_dev *dev) { } #endif #ifdef CONFIG_PCIE_ECRC diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index a08e7d6dc248..ac0557a305af 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -734,50 +734,6 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state) PCI_L1SS_CTL1_L1SS_MASK, val); } -void pci_save_aspm_l1ss_state(struct pci_dev *dev) -{ - int aspm_l1ss; - struct pci_cap_saved_state *save_state; - u32 *cap; - - if (!pci_is_pcie(dev)) - return; - - aspm_l1ss = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_L1SS); - if (!aspm_l1ss) - return; - - save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_L1SS); - if (!save_state) - return; - - cap = (u32 *)&save_state->cap.data[0]; - pci_read_config_dword(dev, aspm_l1ss + PCI_L1SS_CTL1, cap++); - pci_read_config_dword(dev, aspm_l1ss + PCI_L1SS_CTL2, cap++); -} - -void pci_restore_aspm_l1ss_state(struct pci_dev *dev) -{ - int aspm_l1ss; - struct pci_cap_saved_state *save_state; - u32 *cap; - - if (!pci_is_pcie(dev)) - return; - - aspm_l1ss = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_L1SS); - if (!aspm_l1ss) - return; - - save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_L1SS); - if (!save_state) - return; - - cap = (u32 *)&save_state->cap.data[0]; - pci_write_config_dword(dev, aspm_l1ss + PCI_L1SS_CTL1, *cap++); - pci_write_config_dword(dev, aspm_l1ss + PCI_L1SS_CTL2, *cap++); -} - static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val) { pcie_capability_clear_and_set_word(pdev, PCI_EXP_LNKCTL, diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 88dde3455bfd..b5fe6d2ad22f 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -87,6 +87,7 @@ struct mlx5_vq_restore_info { u64 device_addr; u64 driver_addr; u16 avail_index; + u16 used_index; bool ready; struct vdpa_callback cb; bool restore; @@ -121,6 +122,7 @@ struct mlx5_vdpa_virtqueue { u32 virtq_id; struct mlx5_vdpa_net *ndev; u16 avail_idx; + u16 used_idx; int fw_state; /* keep last in the struct */ @@ -804,6 +806,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque obj_context = MLX5_ADDR_OF(create_virtio_net_q_in, in, obj_context); MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx); + MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx); MLX5_SET(virtio_net_q_object, obj_context, queue_feature_bit_mask_12_3, get_features_12_3(ndev->mvdev.actual_features)); vq_ctx = MLX5_ADDR_OF(virtio_net_q_object, obj_context, virtio_q_context); @@ -1022,6 +1025,7 @@ static int connect_qps(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m struct mlx5_virtq_attr { u8 state; u16 available_index; + u16 used_index; }; static int query_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, @@ -1052,6 +1056,7 @@ static int query_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueu memset(attr, 0, sizeof(*attr)); attr->state = MLX5_GET(virtio_net_q_object, obj_context, state); attr->available_index = MLX5_GET(virtio_net_q_object, obj_context, hw_available_index); + attr->used_index = MLX5_GET(virtio_net_q_object, obj_context, hw_used_index); kfree(out); return 0; @@ -1535,6 +1540,16 @@ static void teardown_virtqueues(struct mlx5_vdpa_net *ndev) } } +static void clear_virtqueues(struct mlx5_vdpa_net *ndev) +{ + int i; + + for (i = ndev->mvdev.max_vqs - 1; i >= 0; i--) { + ndev->vqs[i].avail_idx = 0; + ndev->vqs[i].used_idx = 0; + } +} + /* TODO: cross-endian support */ static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev) { @@ -1610,6 +1625,7 @@ static int save_channel_info(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqu return err; ri->avail_index = attr.available_index; + ri->used_index = attr.used_index; ri->ready = mvq->ready; ri->num_ent = mvq->num_ent; ri->desc_addr = mvq->desc_addr; @@ -1654,6 +1670,7 @@ static void restore_channels_info(struct mlx5_vdpa_net *ndev) continue; mvq->avail_idx = ri->avail_index; + mvq->used_idx = ri->used_index; mvq->ready = ri->ready; mvq->num_ent = ri->num_ent; mvq->desc_addr = ri->desc_addr; @@ -1768,6 +1785,7 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) if (!status) { mlx5_vdpa_info(mvdev, "performing device reset\n"); teardown_driver(ndev); + clear_virtqueues(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status = 0; ndev->mvdev.mlx_features = 0; diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index f5e92fe9151c..bd1c39907b92 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -783,6 +783,7 @@ drm_dp_mst_detect_port(struct drm_connector *connector, struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); +int drm_dp_get_vc_payload_bw(int link_rate, int link_lane_count); int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index b3f0e2018c62..efa96263b81b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -616,7 +616,10 @@ static inline void dev_iommu_fwspec_set(struct device *dev, static inline void *dev_iommu_priv_get(struct device *dev) { - return dev->iommu->priv; + if (dev->iommu) + return dev->iommu->priv; + else + return NULL; } static inline void dev_iommu_priv_set(struct device *dev, void *priv) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index c9766d07eb81..5a809c64dc7b 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1113,14 +1113,15 @@ static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg, unsigned int offset, len, remaining; struct bio_vec *bvec; - bvec = xdr->bvec; - offset = xdr->page_base; + bvec = xdr->bvec + (xdr->page_base >> PAGE_SHIFT); + offset = offset_in_page(xdr->page_base); remaining = xdr->page_len; flags = MSG_MORE | MSG_SENDPAGE_NOTLAST; while (remaining > 0) { if (remaining <= PAGE_SIZE && tail->iov_len == 0) flags = 0; - len = min(remaining, bvec->bv_len); + + len = min(remaining, bvec->bv_len - offset); ret = kernel_sendpage(sock, bvec->bv_page, bvec->bv_offset + offset, len, flags); |