summaryrefslogtreecommitdiff
path: root/drivers/gpu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c11
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c20
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mes_v11_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mes_v12_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c6
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c5
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c5
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c5
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_queue.c4
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c86
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c14
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc_resource.c3
-rw-r--r--drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c25
-rw-r--r--drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c8
-rw-r--r--drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c26
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c12
-rw-r--r--drivers/gpu/drm/drm_fbdev_dma.c217
-rw-r--r--drivers/gpu/drm/i915/display/intel_ddi.c9
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp_mst.c3
-rw-r--r--drivers/gpu/drm/imagination/Makefile2
-rw-r--r--drivers/gpu/drm/imagination/pvr_fw_meta.c6
-rw-r--r--drivers/gpu/drm/imagination/pvr_fw_trace.c4
-rw-r--r--drivers/gpu/drm/imagination/pvr_queue.c18
-rw-r--r--drivers/gpu/drm/imagination/pvr_queue.h4
-rw-r--r--drivers/gpu/drm/imagination/pvr_vm.c134
-rw-r--r--drivers/gpu/drm/imagination/pvr_vm.h3
-rw-r--r--drivers/gpu/drm/nouveau/Kconfig1
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_connector.c1
-rw-r--r--drivers/gpu/drm/radeon/r300.c3
-rw-r--r--drivers/gpu/drm/radeon/radeon_asic.h1
-rw-r--r--drivers/gpu/drm/radeon/rs400.c18
-rw-r--r--drivers/gpu/drm/scheduler/gpu_scheduler_trace.h4
-rw-r--r--drivers/gpu/drm/tiny/bochs.c5
-rw-r--r--drivers/gpu/drm/vkms/vkms_composer.c2
-rw-r--r--drivers/gpu/drm/xe/display/xe_plane_initial.c10
-rw-r--r--drivers/gpu/drm/xe/regs/xe_engine_regs.h1
-rw-r--r--drivers/gpu/drm/xe/xe_gt.c4
-rw-r--r--drivers/gpu/drm/xe/xe_guc_submit.c2
-rw-r--r--drivers/gpu/drm/xe/xe_hmm.c188
-rw-r--r--drivers/gpu/drm/xe/xe_hmm.h7
-rw-r--r--drivers/gpu/drm/xe/xe_oa.c5
-rw-r--r--drivers/gpu/drm/xe/xe_pt.c96
-rw-r--r--drivers/gpu/drm/xe/xe_pt_walk.c3
-rw-r--r--drivers/gpu/drm/xe/xe_pt_walk.h4
-rw-r--r--drivers/gpu/drm/xe/xe_vm.c140
-rw-r--r--drivers/gpu/drm/xe/xe_vm.h10
-rw-r--r--drivers/gpu/drm/xe/xe_vm_types.h8
51 files changed, 847 insertions, 318 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d100bb7a137c..018dfccd771b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1638,6 +1638,13 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev)
if (amdgpu_sriov_vf(adev))
return 0;
+ /* resizing on Dell G5 SE platforms causes problems with runtime pm */
+ if ((amdgpu_runtime_pm != 0) &&
+ adev->pdev->vendor == PCI_VENDOR_ID_ATI &&
+ adev->pdev->device == 0x731f &&
+ adev->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL)
+ return 0;
+
/* PCI_EXT_CAP_ID_VNDR extended capability is located at 0x100 */
if (!pci_find_ext_capability(adev->pdev, PCI_EXT_CAP_ID_VNDR))
DRM_WARN("System can't access extended configuration space, please check!!\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 784b03abb3a4..c1f35ded684e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1638,22 +1638,19 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev,
}
mutex_lock(&adev->enforce_isolation_mutex);
-
for (i = 0; i < num_partitions; i++) {
- if (adev->enforce_isolation[i] && !partition_values[i]) {
+ if (adev->enforce_isolation[i] && !partition_values[i])
/* Going from enabled to disabled */
amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i));
- amdgpu_mes_set_enforce_isolation(adev, i, false);
- } else if (!adev->enforce_isolation[i] && partition_values[i]) {
+ else if (!adev->enforce_isolation[i] && partition_values[i])
/* Going from disabled to enabled */
amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i));
- amdgpu_mes_set_enforce_isolation(adev, i, true);
- }
adev->enforce_isolation[i] = partition_values[i];
}
-
mutex_unlock(&adev->enforce_isolation_mutex);
+ amdgpu_mes_update_enforce_isolation(adev);
+
return count;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 32b27a1658e7..709c11cbeabd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -1681,7 +1681,8 @@ bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev)
}
/* Fix me -- node_id is used to identify the correct MES instances in the future */
-int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable)
+static int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev,
+ uint32_t node_id, bool enable)
{
struct mes_misc_op_input op_input = {0};
int r;
@@ -1703,6 +1704,23 @@ error:
return r;
}
+int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev)
+{
+ int i, r = 0;
+
+ if (adev->enable_mes && adev->gfx.enable_cleaner_shader) {
+ mutex_lock(&adev->enforce_isolation_mutex);
+ for (i = 0; i < (adev->xcp_mgr ? adev->xcp_mgr->num_xcps : 1); i++) {
+ if (adev->enforce_isolation[i])
+ r |= amdgpu_mes_set_enforce_isolation(adev, i, true);
+ else
+ r |= amdgpu_mes_set_enforce_isolation(adev, i, false);
+ }
+ mutex_unlock(&adev->enforce_isolation_mutex);
+ }
+ return r;
+}
+
#if defined(CONFIG_DEBUG_FS)
static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 2df2444ee892..e98ea7ede1ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -534,6 +534,6 @@ static inline void amdgpu_mes_unlock(struct amdgpu_mes *mes)
bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev);
-int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable);
+int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev);
#endif /* __AMDGPU_MES_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 01ae2f88dec8..262bd010a283 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2281,7 +2281,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
struct amdgpu_res_cursor cursor;
u64 addr;
- int r;
+ int r = 0;
if (!adev->mman.buffer_funcs_enabled)
return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 65f389eb65e5..f9a4d08eef92 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -1633,6 +1633,10 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block)
goto failure;
}
+ r = amdgpu_mes_update_enforce_isolation(adev);
+ if (r)
+ goto failure;
+
out:
/*
* Disable KIQ ring usage from the driver once MES is enabled.
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 901e924e69ad..0fd0fa6ed518 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -1743,6 +1743,10 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block)
goto failure;
}
+ r = amdgpu_mes_update_enforce_isolation(adev);
+ if (r)
+ goto failure;
+
out:
/*
* Disable KIQ ring usage from the driver once MES is enabled.
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 2eff37aaf827..1695dd78ede8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -107,6 +107,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
+ m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+ m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
m->cp_mqd_base_addr_lo = lower_32_bits(addr);
@@ -167,10 +169,10 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
m = get_mqd(mqd);
- m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+ m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
m->cp_hqd_pq_control |=
ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
- m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 68dbc0399c87..3c0ae28c5923 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -154,6 +154,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
+ m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+ m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
m->cp_mqd_base_addr_lo = lower_32_bits(addr);
@@ -221,10 +223,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
m = get_mqd(mqd);
- m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+ m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
m->cp_hqd_pq_control |=
ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
- m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
index 2b72d5b4949b..565858b9044d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
@@ -121,6 +121,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
+ m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+ m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
m->cp_mqd_base_addr_lo = lower_32_bits(addr);
@@ -184,10 +186,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
m = get_mqd(mqd);
- m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+ m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
m->cp_hqd_pq_control |=
ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
- m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index ff417d5361c4..3014925d95ff 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -183,6 +183,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
+ m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+ m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
m->cp_mqd_base_addr_lo = lower_32_bits(addr);
@@ -245,7 +248,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
m = get_mqd(mqd);
- m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+ m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index ecccd7adbab4..24396a2c77bd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -266,8 +266,8 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
/* EOP buffer is not required for all ASICs */
if (properties->eop_ring_buffer_address) {
if (properties->eop_ring_buffer_size != topo_dev->node_props.eop_buffer_size) {
- pr_debug("queue eop bo size 0x%lx not equal to node eop buf size 0x%x\n",
- properties->eop_buf_bo->tbo.base.size,
+ pr_debug("queue eop bo size 0x%x not equal to node eop buf size 0x%x\n",
+ properties->eop_ring_buffer_size,
topo_dev->node_props.eop_buffer_size);
err = -EINVAL;
goto out_err_unreserve;
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 ac3fd81fecef..9d9645a2d18e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1618,75 +1618,130 @@ static bool dm_should_disable_stutter(struct pci_dev *pdev)
return false;
}
-static const struct dmi_system_id hpd_disconnect_quirk_table[] = {
+struct amdgpu_dm_quirks {
+ bool aux_hpd_discon;
+ bool support_edp0_on_dp1;
+};
+
+static struct amdgpu_dm_quirks quirk_entries = {
+ .aux_hpd_discon = false,
+ .support_edp0_on_dp1 = false
+};
+
+static int edp0_on_dp1_callback(const struct dmi_system_id *id)
+{
+ quirk_entries.support_edp0_on_dp1 = true;
+ return 0;
+}
+
+static int aux_hpd_discon_callback(const struct dmi_system_id *id)
+{
+ quirk_entries.aux_hpd_discon = true;
+ return 0;
+}
+
+static const struct dmi_system_id dmi_quirk_table[] = {
{
+ .callback = aux_hpd_discon_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3660"),
},
},
{
+ .callback = aux_hpd_discon_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3260"),
},
},
{
+ .callback = aux_hpd_discon_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"),
},
},
{
+ .callback = aux_hpd_discon_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower Plus 7010"),
},
},
{
+ .callback = aux_hpd_discon_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower 7010"),
},
},
{
+ .callback = aux_hpd_discon_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF Plus 7010"),
},
},
{
+ .callback = aux_hpd_discon_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF 7010"),
},
},
{
+ .callback = aux_hpd_discon_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro Plus 7010"),
},
},
{
+ .callback = aux_hpd_discon_callback,
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro 7010"),
},
},
+ {
+ .callback = edp0_on_dp1_callback,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Elite mt645 G8 Mobile Thin Client"),
+ },
+ },
+ {
+ .callback = edp0_on_dp1_callback,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 665 16 inch G11 Notebook PC"),
+ },
+ },
{}
/* TODO: refactor this from a fixed table to a dynamic option */
};
-static void retrieve_dmi_info(struct amdgpu_display_manager *dm)
+static void retrieve_dmi_info(struct amdgpu_display_manager *dm, struct dc_init_data *init_data)
{
- const struct dmi_system_id *dmi_id;
+ int dmi_id;
+ struct drm_device *dev = dm->ddev;
dm->aux_hpd_discon_quirk = false;
+ init_data->flags.support_edp0_on_dp1 = false;
+
+ dmi_id = dmi_check_system(dmi_quirk_table);
+
+ if (!dmi_id)
+ return;
- dmi_id = dmi_first_match(hpd_disconnect_quirk_table);
- if (dmi_id) {
+ if (quirk_entries.aux_hpd_discon) {
dm->aux_hpd_discon_quirk = true;
- DRM_INFO("aux_hpd_discon_quirk attached\n");
+ drm_info(dev, "aux_hpd_discon_quirk attached\n");
+ }
+ if (quirk_entries.support_edp0_on_dp1) {
+ init_data->flags.support_edp0_on_dp1 = true;
+ drm_info(dev, "aux_hpd_discon_quirk attached\n");
}
}
@@ -1994,7 +2049,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0))
init_data.num_virtual_links = 1;
- retrieve_dmi_info(&adev->dm);
+ retrieve_dmi_info(&adev->dm, &init_data);
if (adev->dm.bb_from_dmub)
init_data.bb_from_dmub = adev->dm.bb_from_dmub;
@@ -7240,8 +7295,14 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
struct dc_link *dc_link = aconnector->dc_link;
struct dc_sink *dc_em_sink = aconnector->dc_em_sink;
const struct drm_edid *drm_edid;
+ struct i2c_adapter *ddc;
+
+ if (dc_link && dc_link->aux_mode)
+ ddc = &aconnector->dm_dp_aux.aux.ddc;
+ else
+ ddc = &aconnector->i2c->base;
- drm_edid = drm_edid_read(connector);
+ drm_edid = drm_edid_read_ddc(connector, ddc);
drm_edid_connector_update(connector, drm_edid);
if (!drm_edid) {
DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
@@ -7286,14 +7347,21 @@ static int get_modes(struct drm_connector *connector)
static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
{
struct drm_connector *connector = &aconnector->base;
+ struct dc_link *dc_link = aconnector->dc_link;
struct dc_sink_init_data init_params = {
.link = aconnector->dc_link,
.sink_signal = SIGNAL_TYPE_VIRTUAL
};
const struct drm_edid *drm_edid;
const struct edid *edid;
+ struct i2c_adapter *ddc;
+
+ if (dc_link && dc_link->aux_mode)
+ ddc = &aconnector->dm_dp_aux.aux.ddc;
+ else
+ ddc = &aconnector->i2c->base;
- drm_edid = drm_edid_read(connector);
+ drm_edid = drm_edid_read_ddc(connector, ddc);
drm_edid_connector_update(connector, drm_edid);
if (!drm_edid) {
DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 3390f0d8420a..c4a7fd453e5f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -894,6 +894,7 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
struct drm_device *dev = adev_to_drm(adev);
struct drm_connector *connector;
struct drm_connector_list_iter iter;
+ int i;
drm_connector_list_iter_begin(dev, &iter);
drm_for_each_connector_iter(connector, &iter) {
@@ -920,6 +921,12 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
}
}
drm_connector_list_iter_end(&iter);
+
+ /* Update reference counts for HPDs */
+ for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
+ if (amdgpu_irq_get(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
+ drm_err(dev, "DM_IRQ: Failed get HPD for source=%d)!\n", i);
+ }
}
/**
@@ -935,6 +942,7 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
struct drm_device *dev = adev_to_drm(adev);
struct drm_connector *connector;
struct drm_connector_list_iter iter;
+ int i;
drm_connector_list_iter_begin(dev, &iter);
drm_for_each_connector_iter(connector, &iter) {
@@ -960,4 +968,10 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
}
}
drm_connector_list_iter_end(&iter);
+
+ /* Update reference counts for HPDs */
+ for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
+ if (amdgpu_irq_put(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
+ drm_err(dev, "DM_IRQ: Failed put HPD for source=%d!\n", i);
+ }
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index 45858bf1523d..e140b7a04d72 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -54,7 +54,8 @@ static bool link_supports_psrsu(struct dc_link *link)
if (amdgpu_dc_debug_mask & DC_DISABLE_PSR_SU)
return false;
- return dc_dmub_check_min_version(dc->ctx->dmub_srv->dmub);
+ /* Temporarily disable PSR-SU to avoid glitches */
+ return false;
}
/*
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 520a34a42827..a45037cb4cc0 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1455,7 +1455,8 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
/* Invalid input */
- if (!plane_state->dst_rect.width ||
+ if (!plane_state ||
+ !plane_state->dst_rect.width ||
!plane_state->dst_rect.height ||
!plane_state->src_rect.width ||
!plane_state->src_rect.height) {
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
index 67a8e22b1126..e237ea1185a7 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
@@ -3042,6 +3042,7 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block)
if (!amdgpu_dpm)
return 0;
+ mutex_lock(&adev->pm.mutex);
kv_dpm_setup_asic(adev);
ret = kv_dpm_enable(adev);
if (ret)
@@ -3049,6 +3050,8 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block)
else
adev->pm.dpm_enabled = true;
amdgpu_legacy_dpm_compute_clocks(adev);
+ mutex_unlock(&adev->pm.mutex);
+
return ret;
}
@@ -3066,32 +3069,42 @@ static int kv_dpm_suspend(struct amdgpu_ip_block *ip_block)
{
struct amdgpu_device *adev = ip_block->adev;
+ cancel_work_sync(&adev->pm.dpm.thermal.work);
+
if (adev->pm.dpm_enabled) {
+ mutex_lock(&adev->pm.mutex);
+ adev->pm.dpm_enabled = false;
/* disable dpm */
kv_dpm_disable(adev);
/* reset the power state */
adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+ mutex_unlock(&adev->pm.mutex);
}
return 0;
}
static int kv_dpm_resume(struct amdgpu_ip_block *ip_block)
{
- int ret;
+ int ret = 0;
struct amdgpu_device *adev = ip_block->adev;
- if (adev->pm.dpm_enabled) {
+ if (!amdgpu_dpm)
+ return 0;
+
+ if (!adev->pm.dpm_enabled) {
+ mutex_lock(&adev->pm.mutex);
/* asic init will reset to the boot state */
kv_dpm_setup_asic(adev);
ret = kv_dpm_enable(adev);
- if (ret)
+ if (ret) {
adev->pm.dpm_enabled = false;
- else
+ } else {
adev->pm.dpm_enabled = true;
- if (adev->pm.dpm_enabled)
amdgpu_legacy_dpm_compute_clocks(adev);
+ }
+ mutex_unlock(&adev->pm.mutex);
}
- return 0;
+ return ret;
}
static bool kv_dpm_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
index e861355ebd75..c7518b13e787 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
@@ -1009,9 +1009,12 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL;
int temp, size = sizeof(temp);
- if (!adev->pm.dpm_enabled)
- return;
+ mutex_lock(&adev->pm.mutex);
+ if (!adev->pm.dpm_enabled) {
+ mutex_unlock(&adev->pm.mutex);
+ return;
+ }
if (!pp_funcs->read_sensor(adev->powerplay.pp_handle,
AMDGPU_PP_SENSOR_GPU_TEMP,
(void *)&temp,
@@ -1033,4 +1036,5 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
adev->pm.dpm.state = dpm_state;
amdgpu_legacy_dpm_compute_clocks(adev->powerplay.pp_handle);
+ mutex_unlock(&adev->pm.mutex);
}
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index a87dcf0974bc..d6dfe2599ebe 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -7786,6 +7786,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block)
if (!amdgpu_dpm)
return 0;
+ mutex_lock(&adev->pm.mutex);
si_dpm_setup_asic(adev);
ret = si_dpm_enable(adev);
if (ret)
@@ -7793,6 +7794,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block)
else
adev->pm.dpm_enabled = true;
amdgpu_legacy_dpm_compute_clocks(adev);
+ mutex_unlock(&adev->pm.mutex);
return ret;
}
@@ -7810,32 +7812,44 @@ static int si_dpm_suspend(struct amdgpu_ip_block *ip_block)
{
struct amdgpu_device *adev = ip_block->adev;
+ cancel_work_sync(&adev->pm.dpm.thermal.work);
+
if (adev->pm.dpm_enabled) {
+ mutex_lock(&adev->pm.mutex);
+ adev->pm.dpm_enabled = false;
/* disable dpm */
si_dpm_disable(adev);
/* reset the power state */
adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+ mutex_unlock(&adev->pm.mutex);
}
+
return 0;
}
static int si_dpm_resume(struct amdgpu_ip_block *ip_block)
{
- int ret;
+ int ret = 0;
struct amdgpu_device *adev = ip_block->adev;
- if (adev->pm.dpm_enabled) {
+ if (!amdgpu_dpm)
+ return 0;
+
+ if (!adev->pm.dpm_enabled) {
/* asic init will reset to the boot state */
+ mutex_lock(&adev->pm.mutex);
si_dpm_setup_asic(adev);
ret = si_dpm_enable(adev);
- if (ret)
+ if (ret) {
adev->pm.dpm_enabled = false;
- else
+ } else {
adev->pm.dpm_enabled = true;
- if (adev->pm.dpm_enabled)
amdgpu_legacy_dpm_compute_clocks(adev);
+ }
+ mutex_unlock(&adev->pm.mutex);
}
- return 0;
+
+ return ret;
}
static bool si_dpm_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 9b2f4fe1578b..ddb6444406d2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -1895,16 +1895,6 @@ static int smu_v14_0_allow_ih_interrupt(struct smu_context *smu)
NULL);
}
-static int smu_v14_0_process_pending_interrupt(struct smu_context *smu)
-{
- int ret = 0;
-
- if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_ACDC_BIT))
- ret = smu_v14_0_allow_ih_interrupt(smu);
-
- return ret;
-}
-
int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
{
int ret = 0;
@@ -1916,7 +1906,7 @@ int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
if (ret)
return ret;
- return smu_v14_0_process_pending_interrupt(smu);
+ return smu_v14_0_allow_ih_interrupt(smu);
}
int smu_v14_0_disable_thermal_alert(struct smu_context *smu)
diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c
index b14b581c059d..02a516e77192 100644
--- a/drivers/gpu/drm/drm_fbdev_dma.c
+++ b/drivers/gpu/drm/drm_fbdev_dma.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: MIT
#include <linux/fb.h>
+#include <linux/vmalloc.h>
#include <drm/drm_drv.h>
#include <drm/drm_fbdev_dma.h>
@@ -70,37 +71,102 @@ static const struct fb_ops drm_fbdev_dma_fb_ops = {
.fb_destroy = drm_fbdev_dma_fb_destroy,
};
-FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma,
+FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma_shadowed,
drm_fb_helper_damage_range,
drm_fb_helper_damage_area);
-static int drm_fbdev_dma_deferred_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
+static void drm_fbdev_dma_shadowed_fb_destroy(struct fb_info *info)
{
struct drm_fb_helper *fb_helper = info->par;
- struct drm_framebuffer *fb = fb_helper->fb;
- struct drm_gem_dma_object *dma = drm_fb_dma_get_gem_obj(fb, 0);
+ void *shadow = info->screen_buffer;
+
+ if (!fb_helper->dev)
+ return;
- if (!dma->map_noncoherent)
- vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+ if (info->fbdefio)
+ fb_deferred_io_cleanup(info);
+ drm_fb_helper_fini(fb_helper);
+ vfree(shadow);
- return fb_deferred_io_mmap(info, vma);
+ drm_client_buffer_vunmap(fb_helper->buffer);
+ drm_client_framebuffer_delete(fb_helper->buffer);
+ drm_client_release(&fb_helper->client);
+ drm_fb_helper_unprepare(fb_helper);
+ kfree(fb_helper);
}
-static const struct fb_ops drm_fbdev_dma_deferred_fb_ops = {
+static const struct fb_ops drm_fbdev_dma_shadowed_fb_ops = {
.owner = THIS_MODULE,
.fb_open = drm_fbdev_dma_fb_open,
.fb_release = drm_fbdev_dma_fb_release,
- __FB_DEFAULT_DEFERRED_OPS_RDWR(drm_fbdev_dma),
+ FB_DEFAULT_DEFERRED_OPS(drm_fbdev_dma_shadowed),
DRM_FB_HELPER_DEFAULT_OPS,
- __FB_DEFAULT_DEFERRED_OPS_DRAW(drm_fbdev_dma),
- .fb_mmap = drm_fbdev_dma_deferred_fb_mmap,
- .fb_destroy = drm_fbdev_dma_fb_destroy,
+ .fb_destroy = drm_fbdev_dma_shadowed_fb_destroy,
};
/*
* struct drm_fb_helper
*/
+static void drm_fbdev_dma_damage_blit_real(struct drm_fb_helper *fb_helper,
+ struct drm_clip_rect *clip,
+ struct iosys_map *dst)
+{
+ struct drm_framebuffer *fb = fb_helper->fb;
+ size_t offset = clip->y1 * fb->pitches[0];
+ size_t len = clip->x2 - clip->x1;
+ unsigned int y;
+ void *src;
+
+ switch (drm_format_info_bpp(fb->format, 0)) {
+ case 1:
+ offset += clip->x1 / 8;
+ len = DIV_ROUND_UP(len + clip->x1 % 8, 8);
+ break;
+ case 2:
+ offset += clip->x1 / 4;
+ len = DIV_ROUND_UP(len + clip->x1 % 4, 4);
+ break;
+ case 4:
+ offset += clip->x1 / 2;
+ len = DIV_ROUND_UP(len + clip->x1 % 2, 2);
+ break;
+ default:
+ offset += clip->x1 * fb->format->cpp[0];
+ len *= fb->format->cpp[0];
+ break;
+ }
+
+ src = fb_helper->info->screen_buffer + offset;
+ iosys_map_incr(dst, offset); /* go to first pixel within clip rect */
+
+ for (y = clip->y1; y < clip->y2; y++) {
+ iosys_map_memcpy_to(dst, 0, src, len);
+ iosys_map_incr(dst, fb->pitches[0]);
+ src += fb->pitches[0];
+ }
+}
+
+static int drm_fbdev_dma_damage_blit(struct drm_fb_helper *fb_helper,
+ struct drm_clip_rect *clip)
+{
+ struct drm_client_buffer *buffer = fb_helper->buffer;
+ struct iosys_map dst;
+
+ /*
+ * For fbdev emulation, we only have to protect against fbdev modeset
+ * operations. Nothing else will involve the client buffer's BO. So it
+ * is sufficient to acquire struct drm_fb_helper.lock here.
+ */
+ mutex_lock(&fb_helper->lock);
+
+ dst = buffer->map;
+ drm_fbdev_dma_damage_blit_real(fb_helper, clip, &dst);
+
+ mutex_unlock(&fb_helper->lock);
+
+ return 0;
+}
static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper,
struct drm_clip_rect *clip)
{
@@ -112,6 +178,10 @@ static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper,
return 0;
if (helper->fb->funcs->dirty) {
+ ret = drm_fbdev_dma_damage_blit(helper, clip);
+ if (drm_WARN_ONCE(dev, ret, "Damage blitter failed: ret=%d\n", ret))
+ return ret;
+
ret = helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1);
if (drm_WARN_ONCE(dev, ret, "Dirty helper failed: ret=%d\n", ret))
return ret;
@@ -128,14 +198,80 @@ static const struct drm_fb_helper_funcs drm_fbdev_dma_helper_funcs = {
* struct drm_fb_helper
*/
+static int drm_fbdev_dma_driver_fbdev_probe_tail(struct drm_fb_helper *fb_helper,
+ struct drm_fb_helper_surface_size *sizes)
+{
+ struct drm_device *dev = fb_helper->dev;
+ struct drm_client_buffer *buffer = fb_helper->buffer;
+ struct drm_gem_dma_object *dma_obj = to_drm_gem_dma_obj(buffer->gem);
+ struct drm_framebuffer *fb = fb_helper->fb;
+ struct fb_info *info = fb_helper->info;
+ struct iosys_map map = buffer->map;
+
+ info->fbops = &drm_fbdev_dma_fb_ops;
+
+ /* screen */
+ info->flags |= FBINFO_VIRTFB; /* system memory */
+ if (dma_obj->map_noncoherent)
+ info->flags |= FBINFO_READS_FAST; /* signal caching */
+ info->screen_size = sizes->surface_height * fb->pitches[0];
+ info->screen_buffer = map.vaddr;
+ if (!(info->flags & FBINFO_HIDE_SMEM_START)) {
+ if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer)))
+ info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
+ }
+ info->fix.smem_len = info->screen_size;
+
+ return 0;
+}
+
+static int drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(struct drm_fb_helper *fb_helper,
+ struct drm_fb_helper_surface_size *sizes)
+{
+ struct drm_client_buffer *buffer = fb_helper->buffer;
+ struct fb_info *info = fb_helper->info;
+ size_t screen_size = buffer->gem->size;
+ void *screen_buffer;
+ int ret;
+
+ /*
+ * Deferred I/O requires struct page for framebuffer memory,
+ * which is not guaranteed for all DMA ranges. We thus create
+ * a shadow buffer in system memory.
+ */
+ screen_buffer = vzalloc(screen_size);
+ if (!screen_buffer)
+ return -ENOMEM;
+
+ info->fbops = &drm_fbdev_dma_shadowed_fb_ops;
+
+ /* screen */
+ info->flags |= FBINFO_VIRTFB; /* system memory */
+ info->flags |= FBINFO_READS_FAST; /* signal caching */
+ info->screen_buffer = screen_buffer;
+ info->fix.smem_len = screen_size;
+
+ fb_helper->fbdefio.delay = HZ / 20;
+ fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
+
+ info->fbdefio = &fb_helper->fbdefio;
+ ret = fb_deferred_io_init(info);
+ if (ret)
+ goto err_vfree;
+
+ return 0;
+
+err_vfree:
+ vfree(screen_buffer);
+ return ret;
+}
+
int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
struct drm_fb_helper_surface_size *sizes)
{
struct drm_client_dev *client = &fb_helper->client;
struct drm_device *dev = fb_helper->dev;
- bool use_deferred_io = false;
struct drm_client_buffer *buffer;
- struct drm_gem_dma_object *dma_obj;
struct drm_framebuffer *fb;
struct fb_info *info;
u32 format;
@@ -152,19 +288,9 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
sizes->surface_height, format);
if (IS_ERR(buffer))
return PTR_ERR(buffer);
- dma_obj = to_drm_gem_dma_obj(buffer->gem);
fb = buffer->fb;
- /*
- * Deferred I/O requires struct page for framebuffer memory,
- * which is not guaranteed for all DMA ranges. We thus only
- * install deferred I/O if we have a framebuffer that requires
- * it.
- */
- if (fb->funcs->dirty)
- use_deferred_io = true;
-
ret = drm_client_buffer_vmap(buffer, &map);
if (ret) {
goto err_drm_client_buffer_delete;
@@ -185,45 +311,12 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
drm_fb_helper_fill_info(info, fb_helper, sizes);
- if (use_deferred_io)
- info->fbops = &drm_fbdev_dma_deferred_fb_ops;
+ if (fb->funcs->dirty)
+ ret = drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(fb_helper, sizes);
else
- info->fbops = &drm_fbdev_dma_fb_ops;
-
- /* screen */
- info->flags |= FBINFO_VIRTFB; /* system memory */
- if (dma_obj->map_noncoherent)
- info->flags |= FBINFO_READS_FAST; /* signal caching */
- info->screen_size = sizes->surface_height * fb->pitches[0];
- info->screen_buffer = map.vaddr;
- if (!(info->flags & FBINFO_HIDE_SMEM_START)) {
- if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer)))
- info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
- }
- info->fix.smem_len = info->screen_size;
-
- /*
- * Only set up deferred I/O if the screen buffer supports
- * it. If this disagrees with the previous test for ->dirty,
- * mmap on the /dev/fb file might not work correctly.
- */
- if (!is_vmalloc_addr(info->screen_buffer) && info->fix.smem_start) {
- unsigned long pfn = info->fix.smem_start >> PAGE_SHIFT;
-
- if (drm_WARN_ON(dev, !pfn_to_page(pfn)))
- use_deferred_io = false;
- }
-
- /* deferred I/O */
- if (use_deferred_io) {
- fb_helper->fbdefio.delay = HZ / 20;
- fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
-
- info->fbdefio = &fb_helper->fbdefio;
- ret = fb_deferred_io_init(info);
- if (ret)
- goto err_drm_fb_helper_release_info;
- }
+ ret = drm_fbdev_dma_driver_fbdev_probe_tail(fb_helper, sizes);
+ if (ret)
+ goto err_drm_fb_helper_release_info;
return 0;
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 18c66992aa1d..ff2cf3daa7a2 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -866,7 +866,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
encoder->base.base.id, encoder->base.name);
if (!mst_pipe_mask && dp128b132b_pipe_mask) {
- struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+ struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
/*
* If we don't have 8b/10b MST, but have more than one
@@ -878,7 +878,8 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
* we don't expect MST to have been enabled at that point, and
* can assume it's SST.
*/
- if (hweight8(dp128b132b_pipe_mask) > 1 || intel_dp->is_mst)
+ if (hweight8(dp128b132b_pipe_mask) > 1 ||
+ intel_dp_mst_encoder_active_links(dig_port))
mst_pipe_mask = dp128b132b_pipe_mask;
}
@@ -4151,13 +4152,13 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder,
} else if (ddi_mode == TRANS_DDI_MODE_SELECT_DP_MST) {
intel_ddi_read_func_ctl_dp_mst(encoder, pipe_config, ddi_func_ctl);
} else if (ddi_mode == TRANS_DDI_MODE_SELECT_FDI_OR_128B132B && HAS_DP20(display)) {
- struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+ struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
/*
* If this is true, we know we're being called from mst stream
* encoder's ->get_config().
*/
- if (intel_dp->is_mst)
+ if (intel_dp_mst_encoder_active_links(dig_port))
intel_ddi_read_func_ctl_dp_mst(encoder, pipe_config, ddi_func_ctl);
else
intel_ddi_read_func_ctl_dp_sst(encoder, pipe_config, ddi_func_ctl);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index a65cf97ad12d..86d6185fda50 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1867,7 +1867,8 @@ intel_dp_mst_encoder_init(struct intel_digital_port *dig_port, int conn_base_id)
/* create encoders */
mst_stream_encoders_create(dig_port);
ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, display->drm,
- &intel_dp->aux, 16, 3, conn_base_id);
+ &intel_dp->aux, 16,
+ INTEL_NUM_PIPES(display), conn_base_id);
if (ret) {
intel_dp->mst_mgr.cbs = NULL;
return ret;
diff --git a/drivers/gpu/drm/imagination/Makefile b/drivers/gpu/drm/imagination/Makefile
index 9bc6a3884c22..3d9d4d40fb80 100644
--- a/drivers/gpu/drm/imagination/Makefile
+++ b/drivers/gpu/drm/imagination/Makefile
@@ -1,8 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only OR MIT
# Copyright (c) 2023 Imagination Technologies Ltd.
-subdir-ccflags-y := -I$(src)
-
powervr-y := \
pvr_ccb.o \
pvr_cccb.o \
diff --git a/drivers/gpu/drm/imagination/pvr_fw_meta.c b/drivers/gpu/drm/imagination/pvr_fw_meta.c
index c39beb70c317..6d13864851fc 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_meta.c
+++ b/drivers/gpu/drm/imagination/pvr_fw_meta.c
@@ -527,8 +527,10 @@ pvr_meta_vm_map(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
static void
pvr_meta_vm_unmap(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
{
- pvr_vm_unmap(pvr_dev->kernel_vm_ctx, fw_obj->fw_mm_node.start,
- fw_obj->fw_mm_node.size);
+ struct pvr_gem_object *pvr_obj = fw_obj->gem;
+
+ pvr_vm_unmap_obj(pvr_dev->kernel_vm_ctx, pvr_obj,
+ fw_obj->fw_mm_node.start, fw_obj->fw_mm_node.size);
}
static bool
diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c
index 73707daa4e52..5dbb636d7d4f 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_trace.c
+++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c
@@ -333,8 +333,8 @@ static int fw_trace_seq_show(struct seq_file *s, void *v)
if (sf_id == ROGUE_FW_SF_LAST)
return -EINVAL;
- timestamp = read_fw_trace(trace_seq_data, 1) |
- ((u64)read_fw_trace(trace_seq_data, 2) << 32);
+ timestamp = ((u64)read_fw_trace(trace_seq_data, 1) << 32) |
+ read_fw_trace(trace_seq_data, 2);
timestamp = (timestamp & ~ROGUE_FWT_TIMESTAMP_TIME_CLRMSK) >>
ROGUE_FWT_TIMESTAMP_TIME_SHIFT;
diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c
index c4f08432882b..43411be930a2 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.c
+++ b/drivers/gpu/drm/imagination/pvr_queue.c
@@ -109,12 +109,20 @@ pvr_queue_fence_get_driver_name(struct dma_fence *f)
return PVR_DRIVER_NAME;
}
+static void pvr_queue_fence_release_work(struct work_struct *w)
+{
+ struct pvr_queue_fence *fence = container_of(w, struct pvr_queue_fence, release_work);
+
+ pvr_context_put(fence->queue->ctx);
+ dma_fence_free(&fence->base);
+}
+
static void pvr_queue_fence_release(struct dma_fence *f)
{
struct pvr_queue_fence *fence = container_of(f, struct pvr_queue_fence, base);
+ struct pvr_device *pvr_dev = fence->queue->ctx->pvr_dev;
- pvr_context_put(fence->queue->ctx);
- dma_fence_free(f);
+ queue_work(pvr_dev->sched_wq, &fence->release_work);
}
static const char *
@@ -268,6 +276,7 @@ pvr_queue_fence_init(struct dma_fence *f,
pvr_context_get(queue->ctx);
fence->queue = queue;
+ INIT_WORK(&fence->release_work, pvr_queue_fence_release_work);
dma_fence_init(&fence->base, fence_ops,
&fence_ctx->lock, fence_ctx->id,
atomic_inc_return(&fence_ctx->seqno));
@@ -304,8 +313,9 @@ pvr_queue_cccb_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
static void
pvr_queue_job_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
{
- pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
- &queue->job_fence_ctx);
+ if (!fence->ops)
+ pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
+ &queue->job_fence_ctx);
}
/**
diff --git a/drivers/gpu/drm/imagination/pvr_queue.h b/drivers/gpu/drm/imagination/pvr_queue.h
index e06ced69302f..93fe9ac9f58c 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.h
+++ b/drivers/gpu/drm/imagination/pvr_queue.h
@@ -5,6 +5,7 @@
#define PVR_QUEUE_H
#include <drm/gpu_scheduler.h>
+#include <linux/workqueue.h>
#include "pvr_cccb.h"
#include "pvr_device.h"
@@ -63,6 +64,9 @@ struct pvr_queue_fence {
/** @queue: Queue that created this fence. */
struct pvr_queue *queue;
+
+ /** @release_work: Fence release work structure. */
+ struct work_struct release_work;
};
/**
diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c
index 363f885a7098..2896fa7501b1 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.c
+++ b/drivers/gpu/drm/imagination/pvr_vm.c
@@ -293,8 +293,9 @@ err_bind_op_fini:
static int
pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
- struct pvr_vm_context *vm_ctx, u64 device_addr,
- u64 size)
+ struct pvr_vm_context *vm_ctx,
+ struct pvr_gem_object *pvr_obj,
+ u64 device_addr, u64 size)
{
int err;
@@ -318,6 +319,7 @@ pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
goto err_bind_op_fini;
}
+ bind_op->pvr_obj = pvr_obj;
bind_op->vm_ctx = vm_ctx;
bind_op->device_addr = device_addr;
bind_op->size = size;
@@ -598,20 +600,6 @@ err_free:
}
/**
- * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
- * @vm_ctx: Target VM context.
- *
- * This function ensures that no mappings are left dangling by unmapping them
- * all in order of ascending device-virtual address.
- */
-void
-pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
-{
- WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start,
- vm_ctx->gpuvm_mgr.mm_range));
-}
-
-/**
* pvr_vm_context_release() - Teardown a VM context.
* @ref_count: Pointer to reference counter of the VM context.
*
@@ -703,11 +691,7 @@ pvr_vm_lock_extra(struct drm_gpuvm_exec *vm_exec)
struct pvr_vm_bind_op *bind_op = vm_exec->extra.priv;
struct pvr_gem_object *pvr_obj = bind_op->pvr_obj;
- /* Unmap operations don't have an object to lock. */
- if (!pvr_obj)
- return 0;
-
- /* Acquire lock on the GEM being mapped. */
+ /* Acquire lock on the GEM object being mapped/unmapped. */
return drm_exec_lock_obj(&vm_exec->exec, gem_from_pvr_gem(pvr_obj));
}
@@ -772,8 +756,10 @@ err_cleanup:
}
/**
- * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * pvr_vm_unmap_obj_locked() - Unmap an already mapped section of device-virtual
+ * memory.
* @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
* @device_addr: Virtual device address at the start of the target mapping.
* @size: Size of the target mapping.
*
@@ -784,9 +770,13 @@ err_cleanup:
* * Any error encountered while performing internal operations required to
* destroy the mapping (returned from pvr_vm_gpuva_unmap or
* pvr_vm_gpuva_remap).
+ *
+ * The vm_ctx->lock must be held when calling this function.
*/
-int
-pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+static int
+pvr_vm_unmap_obj_locked(struct pvr_vm_context *vm_ctx,
+ struct pvr_gem_object *pvr_obj,
+ u64 device_addr, u64 size)
{
struct pvr_vm_bind_op bind_op = {0};
struct drm_gpuvm_exec vm_exec = {
@@ -799,11 +789,13 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
},
};
- int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, device_addr,
- size);
+ int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, pvr_obj,
+ device_addr, size);
if (err)
return err;
+ pvr_gem_object_get(pvr_obj);
+
err = drm_gpuvm_exec_lock(&vm_exec);
if (err)
goto err_cleanup;
@@ -818,6 +810,96 @@ err_cleanup:
return err;
}
+/**
+ * pvr_vm_unmap_obj() - Unmap an already mapped section of device-virtual
+ * memory.
+ * @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ * * 0 on success,
+ * * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
+ u64 device_addr, u64 size)
+{
+ int err;
+
+ mutex_lock(&vm_ctx->lock);
+ err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, device_addr, size);
+ mutex_unlock(&vm_ctx->lock);
+
+ return err;
+}
+
+/**
+ * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * @vm_ctx: Target VM context.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ * * 0 on success,
+ * * Any error encountered by drm_gpuva_find,
+ * * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+{
+ struct pvr_gem_object *pvr_obj;
+ struct drm_gpuva *va;
+ int err;
+
+ mutex_lock(&vm_ctx->lock);
+
+ va = drm_gpuva_find(&vm_ctx->gpuvm_mgr, device_addr, size);
+ if (va) {
+ pvr_obj = gem_to_pvr_gem(va->gem.obj);
+ err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+ va->va.addr, va->va.range);
+ } else {
+ err = -ENOENT;
+ }
+
+ mutex_unlock(&vm_ctx->lock);
+
+ return err;
+}
+
+/**
+ * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
+ * @vm_ctx: Target VM context.
+ *
+ * This function ensures that no mappings are left dangling by unmapping them
+ * all in order of ascending device-virtual address.
+ */
+void
+pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
+{
+ mutex_lock(&vm_ctx->lock);
+
+ for (;;) {
+ struct pvr_gem_object *pvr_obj;
+ struct drm_gpuva *va;
+
+ va = drm_gpuva_find_first(&vm_ctx->gpuvm_mgr,
+ vm_ctx->gpuvm_mgr.mm_start,
+ vm_ctx->gpuvm_mgr.mm_range);
+ if (!va)
+ break;
+
+ pvr_obj = gem_to_pvr_gem(va->gem.obj);
+
+ WARN_ON(pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+ va->va.addr, va->va.range));
+ }
+
+ mutex_unlock(&vm_ctx->lock);
+}
+
/* Static data areas are determined by firmware. */
static const struct drm_pvr_static_data_area static_data_areas[] = {
{
diff --git a/drivers/gpu/drm/imagination/pvr_vm.h b/drivers/gpu/drm/imagination/pvr_vm.h
index 79406243617c..b0528dffa7f1 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.h
+++ b/drivers/gpu/drm/imagination/pvr_vm.h
@@ -38,6 +38,9 @@ struct pvr_vm_context *pvr_vm_create_context(struct pvr_device *pvr_dev,
int pvr_vm_map(struct pvr_vm_context *vm_ctx,
struct pvr_gem_object *pvr_obj, u64 pvr_obj_offset,
u64 device_addr, u64 size);
+int pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx,
+ struct pvr_gem_object *pvr_obj,
+ u64 device_addr, u64 size);
int pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size);
void pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx);
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index ce840300578d..1050a4617fc1 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -4,6 +4,7 @@ config DRM_NOUVEAU
depends on DRM && PCI && MMU
select IOMMU_API
select FW_LOADER
+ select FW_CACHE if PM_SLEEP
select DRM_CLIENT_SELECTION
select DRM_DISPLAY_DP_HELPER
select DRM_DISPLAY_HDMI_HELPER
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 8d5c9c74cbb9..eac0d1d2dbda 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -775,7 +775,6 @@ nouveau_connector_force(struct drm_connector *connector)
if (!nv_encoder) {
NV_ERROR(drm, "can't find encoder to force %s on!\n",
connector->name);
- connector->status = connector_status_disconnected;
return;
}
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 05c13102a8cb..d22889fbfa9c 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -359,7 +359,8 @@ int r300_mc_wait_for_idle(struct radeon_device *rdev)
return -1;
}
-static void r300_gpu_init(struct radeon_device *rdev)
+/* rs400_gpu_init also calls this! */
+void r300_gpu_init(struct radeon_device *rdev)
{
uint32_t gb_tile_config, tmp;
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 1e00f6b99f94..8f5e07834fcc 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -165,6 +165,7 @@ void r200_set_safe_registers(struct radeon_device *rdev);
*/
extern int r300_init(struct radeon_device *rdev);
extern void r300_fini(struct radeon_device *rdev);
+extern void r300_gpu_init(struct radeon_device *rdev);
extern int r300_suspend(struct radeon_device *rdev);
extern int r300_resume(struct radeon_device *rdev);
extern int r300_asic_reset(struct radeon_device *rdev, bool hard);
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index d6c18fd740ec..13cd0a688a65 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -256,8 +256,22 @@ int rs400_mc_wait_for_idle(struct radeon_device *rdev)
static void rs400_gpu_init(struct radeon_device *rdev)
{
- /* FIXME: is this correct ? */
- r420_pipes_init(rdev);
+ /* Earlier code was calling r420_pipes_init and then
+ * rs400_mc_wait_for_idle(rdev). The problem is that
+ * at least on my Mobility Radeon Xpress 200M RC410 card
+ * that ends up in this code path ends up num_gb_pipes == 3
+ * while the card seems to have only one pipe. With the
+ * r420 pipe initialization method.
+ *
+ * Problems shown up as HyperZ glitches, see:
+ * https://bugs.freedesktop.org/show_bug.cgi?id=110897
+ *
+ * Delegating initialization to r300 code seems to work
+ * and results in proper pipe numbers. The rs400 cards
+ * are said to be not r400, but r300 kind of cards.
+ */
+ r300_gpu_init(rdev);
+
if (rs400_mc_wait_for_idle(rdev)) {
pr_warn("rs400: Failed to wait MC idle while programming pipes. Bad things might happen. %08x\n",
RREG32(RADEON_MC_STATUS));
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
index c75302ca3427..f56e77e7f6d0 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
@@ -21,7 +21,7 @@
*
*/
-#if !defined(_GPU_SCHED_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#if !defined(_GPU_SCHED_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
#define _GPU_SCHED_TRACE_H_
#include <linux/stringify.h>
@@ -106,7 +106,7 @@ TRACE_EVENT(drm_sched_job_wait_dep,
__entry->seqno)
);
-#endif
+#endif /* _GPU_SCHED_TRACE_H_ */
/* This part must be outside protection */
#undef TRACE_INCLUDE_PATH
diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c
index c67e1f906785..8706763af8fb 100644
--- a/drivers/gpu/drm/tiny/bochs.c
+++ b/drivers/gpu/drm/tiny/bochs.c
@@ -335,8 +335,6 @@ static void bochs_hw_setmode(struct bochs_device *bochs, struct drm_display_mode
bochs->xres, bochs->yres, bochs->bpp,
bochs->yres_virtual);
- bochs_hw_blank(bochs, false);
-
bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, 0);
bochs_dispi_write(bochs, VBE_DISPI_INDEX_BPP, bochs->bpp);
bochs_dispi_write(bochs, VBE_DISPI_INDEX_XRES, bochs->xres);
@@ -506,6 +504,9 @@ static int bochs_crtc_helper_atomic_check(struct drm_crtc *crtc,
static void bochs_crtc_helper_atomic_enable(struct drm_crtc *crtc,
struct drm_atomic_state *state)
{
+ struct bochs_device *bochs = to_bochs_device(crtc->dev);
+
+ bochs_hw_blank(bochs, false);
}
static void bochs_crtc_helper_atomic_disable(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index b20ac1705726..fa269d279e25 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -67,7 +67,7 @@ static u16 lerp_u16(u16 a, u16 b, s64 t)
s64 delta = drm_fixp_mul(b_fp - a_fp, t);
- return drm_fixp2int(a_fp + delta);
+ return drm_fixp2int_round(a_fp + delta);
}
static s64 get_lut_index(const struct vkms_color_lut *lut, u16 channel_value)
diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c
index 2eb9633f163a..2a2f250fa495 100644
--- a/drivers/gpu/drm/xe/display/xe_plane_initial.c
+++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c
@@ -194,8 +194,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
to_intel_plane(crtc->base.primary);
struct intel_plane_state *plane_state =
to_intel_plane_state(plane->base.state);
- struct intel_crtc_state *crtc_state =
- to_intel_crtc_state(crtc->base.state);
struct drm_framebuffer *fb;
struct i915_vma *vma;
@@ -241,14 +239,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
atomic_or(plane->frontbuffer_bit, &to_intel_frontbuffer(fb)->bits);
plane_config->vma = vma;
-
- /*
- * Flip to the newly created mapping ASAP, so we can re-use the
- * first part of GGTT for WOPCM, prevent flickering, and prevent
- * the lookup of sysmem scratch pages.
- */
- plane->check_plane(crtc_state, plane_state);
- plane->async_flip(NULL, plane, crtc_state, plane_state, true);
return;
nofb:
diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index d86219dedde2..b732c89816df 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -53,7 +53,6 @@
#define RING_CTL(base) XE_REG((base) + 0x3c)
#define RING_CTL_SIZE(size) ((size) - PAGE_SIZE) /* in bytes -> pages */
-#define RING_CTL_SIZE(size) ((size) - PAGE_SIZE) /* in bytes -> pages */
#define RING_START_UDW(base) XE_REG((base) + 0x48)
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 5d6fb79957b6..9f4f27d1ef4a 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -380,9 +380,7 @@ int xe_gt_init_early(struct xe_gt *gt)
if (err)
return err;
- xe_wa_process_gt(gt);
xe_wa_process_oob(gt);
- xe_tuning_process_gt(gt);
xe_force_wake_init_gt(gt, gt_to_fw(gt));
spin_lock_init(&gt->global_invl_lock);
@@ -474,6 +472,8 @@ static int all_fw_domain_init(struct xe_gt *gt)
}
xe_gt_mcr_set_implicit_defaults(gt);
+ xe_wa_process_gt(gt);
+ xe_tuning_process_gt(gt);
xe_reg_sr_apply_mmio(&gt->reg_sr, gt);
err = xe_gt_clock_init(gt);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 913c74d6e2ae..b6a2dd742ebd 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1248,6 +1248,8 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
if (xe_exec_queue_is_lr(q))
cancel_work_sync(&ge->lr_tdr);
+ /* Confirm no work left behind accessing device structures */
+ cancel_delayed_work_sync(&ge->sched.base.work_tdr);
release_guc_id(guc, q);
xe_sched_entity_fini(&ge->entity);
xe_sched_fini(&ge->sched);
diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 089834467880..392102515f3d 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -19,11 +19,10 @@ static u64 xe_npages_in_range(unsigned long start, unsigned long end)
return (end - start) >> PAGE_SHIFT;
}
-/*
+/**
* xe_mark_range_accessed() - mark a range is accessed, so core mm
* have such information for memory eviction or write back to
* hard disk
- *
* @range: the range to mark
* @write: if write to this range, we mark pages in this range
* as dirty
@@ -43,15 +42,51 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
}
}
-/*
+static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st,
+ struct hmm_range *range, struct rw_semaphore *notifier_sem)
+{
+ unsigned long i, npages, hmm_pfn;
+ unsigned long num_chunks = 0;
+ int ret;
+
+ /* HMM docs says this is needed. */
+ ret = down_read_interruptible(notifier_sem);
+ if (ret)
+ return ret;
+
+ if (mmu_interval_read_retry(range->notifier, range->notifier_seq)) {
+ up_read(notifier_sem);
+ return -EAGAIN;
+ }
+
+ npages = xe_npages_in_range(range->start, range->end);
+ for (i = 0; i < npages;) {
+ unsigned long len;
+
+ hmm_pfn = range->hmm_pfns[i];
+ xe_assert(xe, hmm_pfn & HMM_PFN_VALID);
+
+ len = 1UL << hmm_pfn_to_map_order(hmm_pfn);
+
+ /* If order > 0 the page may extend beyond range->start */
+ len -= (hmm_pfn & ~HMM_PFN_FLAGS) & (len - 1);
+ i += len;
+ num_chunks++;
+ }
+ up_read(notifier_sem);
+
+ return sg_alloc_table(st, num_chunks, GFP_KERNEL);
+}
+
+/**
* xe_build_sg() - build a scatter gather table for all the physical pages/pfn
* in a hmm_range. dma-map pages if necessary. dma-address is save in sg table
* and will be used to program GPU page table later.
- *
* @xe: the xe device who will access the dma-address in sg table
* @range: the hmm range that we build the sg table from. range->hmm_pfns[]
* has the pfn numbers of pages that back up this hmm address range.
* @st: pointer to the sg table.
+ * @notifier_sem: The xe notifier lock.
* @write: whether we write to this range. This decides dma map direction
* for system pages. If write we map it bi-diretional; otherwise
* DMA_TO_DEVICE
@@ -78,43 +113,84 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
* Returns 0 if successful; -ENOMEM if fails to allocate memory
*/
static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
- struct sg_table *st, bool write)
+ struct sg_table *st,
+ struct rw_semaphore *notifier_sem,
+ bool write)
{
+ unsigned long npages = xe_npages_in_range(range->start, range->end);
struct device *dev = xe->drm.dev;
- struct page **pages;
- u64 i, npages;
- int ret;
+ struct scatterlist *sgl;
+ struct page *page;
+ unsigned long i, j;
- npages = xe_npages_in_range(range->start, range->end);
- pages = kvmalloc_array(npages, sizeof(*pages), GFP_KERNEL);
- if (!pages)
- return -ENOMEM;
+ lockdep_assert_held(notifier_sem);
- for (i = 0; i < npages; i++) {
- pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]);
- xe_assert(xe, !is_device_private_page(pages[i]));
+ i = 0;
+ for_each_sg(st->sgl, sgl, st->nents, j) {
+ unsigned long hmm_pfn, size;
+
+ hmm_pfn = range->hmm_pfns[i];
+ page = hmm_pfn_to_page(hmm_pfn);
+ xe_assert(xe, !is_device_private_page(page));
+
+ size = 1UL << hmm_pfn_to_map_order(hmm_pfn);
+ size -= page_to_pfn(page) & (size - 1);
+ i += size;
+
+ if (unlikely(j == st->nents - 1)) {
+ if (i > npages)
+ size -= (i - npages);
+ sg_mark_end(sgl);
+ }
+ sg_set_page(sgl, page, size << PAGE_SHIFT, 0);
}
+ xe_assert(xe, i == npages);
- ret = sg_alloc_table_from_pages_segment(st, pages, npages, 0, npages << PAGE_SHIFT,
- xe_sg_segment_size(dev), GFP_KERNEL);
- if (ret)
- goto free_pages;
+ return dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
+}
+
+static void xe_hmm_userptr_set_mapped(struct xe_userptr_vma *uvma)
+{
+ struct xe_userptr *userptr = &uvma->userptr;
+ struct xe_vm *vm = xe_vma_vm(&uvma->vma);
+
+ lockdep_assert_held_write(&vm->lock);
+ lockdep_assert_held(&vm->userptr.notifier_lock);
+
+ mutex_lock(&userptr->unmap_mutex);
+ xe_assert(vm->xe, !userptr->mapped);
+ userptr->mapped = true;
+ mutex_unlock(&userptr->unmap_mutex);
+}
+
+void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma)
+{
+ struct xe_userptr *userptr = &uvma->userptr;
+ struct xe_vma *vma = &uvma->vma;
+ bool write = !xe_vma_read_only(vma);
+ struct xe_vm *vm = xe_vma_vm(vma);
+ struct xe_device *xe = vm->xe;
- ret = dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
- if (ret) {
- sg_free_table(st);
- st = NULL;
+ if (!lockdep_is_held_type(&vm->userptr.notifier_lock, 0) &&
+ !lockdep_is_held_type(&vm->lock, 0) &&
+ !(vma->gpuva.flags & XE_VMA_DESTROYED)) {
+ /* Don't unmap in exec critical section. */
+ xe_vm_assert_held(vm);
+ /* Don't unmap while mapping the sg. */
+ lockdep_assert_held(&vm->lock);
}
-free_pages:
- kvfree(pages);
- return ret;
+ mutex_lock(&userptr->unmap_mutex);
+ if (userptr->sg && userptr->mapped)
+ dma_unmap_sgtable(xe->drm.dev, userptr->sg,
+ write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0);
+ userptr->mapped = false;
+ mutex_unlock(&userptr->unmap_mutex);
}
-/*
+/**
* xe_hmm_userptr_free_sg() - Free the scatter gather table of userptr
- *
* @uvma: the userptr vma which hold the scatter gather table
*
* With function xe_userptr_populate_range, we allocate storage of
@@ -124,16 +200,9 @@ free_pages:
void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma)
{
struct xe_userptr *userptr = &uvma->userptr;
- struct xe_vma *vma = &uvma->vma;
- bool write = !xe_vma_read_only(vma);
- struct xe_vm *vm = xe_vma_vm(vma);
- struct xe_device *xe = vm->xe;
- struct device *dev = xe->drm.dev;
-
- xe_assert(xe, userptr->sg);
- dma_unmap_sgtable(dev, userptr->sg,
- write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0);
+ xe_assert(xe_vma_vm(&uvma->vma)->xe, userptr->sg);
+ xe_hmm_userptr_unmap(uvma);
sg_free_table(userptr->sg);
userptr->sg = NULL;
}
@@ -166,13 +235,20 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
{
unsigned long timeout =
jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
- unsigned long *pfns, flags = HMM_PFN_REQ_FAULT;
+ unsigned long *pfns;
struct xe_userptr *userptr;
struct xe_vma *vma = &uvma->vma;
u64 userptr_start = xe_vma_userptr(vma);
u64 userptr_end = userptr_start + xe_vma_size(vma);
struct xe_vm *vm = xe_vma_vm(vma);
- struct hmm_range hmm_range;
+ struct hmm_range hmm_range = {
+ .pfn_flags_mask = 0, /* ignore pfns */
+ .default_flags = HMM_PFN_REQ_FAULT,
+ .start = userptr_start,
+ .end = userptr_end,
+ .notifier = &uvma->userptr.notifier,
+ .dev_private_owner = vm->xe,
+ };
bool write = !xe_vma_read_only(vma);
unsigned long notifier_seq;
u64 npages;
@@ -199,19 +275,14 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
return -ENOMEM;
if (write)
- flags |= HMM_PFN_REQ_WRITE;
+ hmm_range.default_flags |= HMM_PFN_REQ_WRITE;
if (!mmget_not_zero(userptr->notifier.mm)) {
ret = -EFAULT;
goto free_pfns;
}
- hmm_range.default_flags = flags;
hmm_range.hmm_pfns = pfns;
- hmm_range.notifier = &userptr->notifier;
- hmm_range.start = userptr_start;
- hmm_range.end = userptr_end;
- hmm_range.dev_private_owner = vm->xe;
while (true) {
hmm_range.notifier_seq = mmu_interval_read_begin(&userptr->notifier);
@@ -238,16 +309,37 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
if (ret)
goto free_pfns;
- ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt, write);
+ ret = xe_alloc_sg(vm->xe, &userptr->sgt, &hmm_range, &vm->userptr.notifier_lock);
if (ret)
goto free_pfns;
+ ret = down_read_interruptible(&vm->userptr.notifier_lock);
+ if (ret)
+ goto free_st;
+
+ if (mmu_interval_read_retry(hmm_range.notifier, hmm_range.notifier_seq)) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
+
+ ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt,
+ &vm->userptr.notifier_lock, write);
+ if (ret)
+ goto out_unlock;
+
xe_mark_range_accessed(&hmm_range, write);
userptr->sg = &userptr->sgt;
+ xe_hmm_userptr_set_mapped(uvma);
userptr->notifier_seq = hmm_range.notifier_seq;
+ up_read(&vm->userptr.notifier_lock);
+ kvfree(pfns);
+ return 0;
+out_unlock:
+ up_read(&vm->userptr.notifier_lock);
+free_st:
+ sg_free_table(&userptr->sgt);
free_pfns:
kvfree(pfns);
return ret;
}
-
diff --git a/drivers/gpu/drm/xe/xe_hmm.h b/drivers/gpu/drm/xe/xe_hmm.h
index 909dc2bdcd97..0ea98d8e7bbc 100644
--- a/drivers/gpu/drm/xe/xe_hmm.h
+++ b/drivers/gpu/drm/xe/xe_hmm.h
@@ -3,9 +3,16 @@
* Copyright © 2024 Intel Corporation
*/
+#ifndef _XE_HMM_H_
+#define _XE_HMM_H_
+
#include <linux/types.h>
struct xe_userptr_vma;
int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, bool is_mm_mmap_locked);
+
void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma);
+
+void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma);
+#endif
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index fa873f3d0a9d..eb6cd91e1e22 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -1689,7 +1689,7 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
stream->oa_buffer.format = &stream->oa->oa_formats[param->oa_format];
stream->sample = param->sample;
- stream->periodic = param->period_exponent > 0;
+ stream->periodic = param->period_exponent >= 0;
stream->period_exponent = param->period_exponent;
stream->no_preempt = param->no_preempt;
stream->wait_num_reports = param->wait_num_reports;
@@ -1970,6 +1970,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
}
param.xef = xef;
+ param.period_exponent = -1;
ret = xe_oa_user_extensions(oa, XE_OA_USER_EXTN_FROM_OPEN, data, 0, &param);
if (ret)
return ret;
@@ -2024,7 +2025,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
goto err_exec_q;
}
- if (param.period_exponent > 0) {
+ if (param.period_exponent >= 0) {
u64 oa_period, oa_freq_hz;
/* Requesting samples from OAG buffer is a privileged operation */
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 1ddcc7e79a93..dc24baa84092 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -28,6 +28,8 @@ struct xe_pt_dir {
struct xe_pt pt;
/** @children: Array of page-table child nodes */
struct xe_ptw *children[XE_PDES];
+ /** @staging: Array of page-table staging nodes */
+ struct xe_ptw *staging[XE_PDES];
};
#if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM)
@@ -48,9 +50,10 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt)
return container_of(pt, struct xe_pt_dir, pt);
}
-static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index)
+static struct xe_pt *
+xe_pt_entry_staging(struct xe_pt_dir *pt_dir, unsigned int index)
{
- return container_of(pt_dir->children[index], struct xe_pt, base);
+ return container_of(pt_dir->staging[index], struct xe_pt, base);
}
static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
@@ -125,6 +128,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
}
pt->bo = bo;
pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL;
+ pt->base.staging = level ? as_xe_pt_dir(pt)->staging : NULL;
if (vm->xef)
xe_drm_client_add_bo(vm->xef->client, pt->bo);
@@ -206,8 +210,8 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
struct xe_pt_dir *pt_dir = as_xe_pt_dir(pt);
for (i = 0; i < XE_PDES; i++) {
- if (xe_pt_entry(pt_dir, i))
- xe_pt_destroy(xe_pt_entry(pt_dir, i), flags,
+ if (xe_pt_entry_staging(pt_dir, i))
+ xe_pt_destroy(xe_pt_entry_staging(pt_dir, i), flags,
deferred);
}
}
@@ -376,8 +380,10 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent,
/* Continue building a non-connected subtree. */
struct iosys_map *map = &parent->bo->vmap;
- if (unlikely(xe_child))
+ if (unlikely(xe_child)) {
parent->base.children[offset] = &xe_child->base;
+ parent->base.staging[offset] = &xe_child->base;
+ }
xe_pt_write(xe_walk->vm->xe, map, offset, pte);
parent->num_live++;
@@ -614,6 +620,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
.ops = &xe_pt_stage_bind_ops,
.shifts = xe_normal_pt_shifts,
.max_level = XE_PT_HIGHEST_LEVEL,
+ .staging = true,
},
.vm = xe_vma_vm(vma),
.tile = tile,
@@ -873,7 +880,7 @@ static void xe_pt_cancel_bind(struct xe_vma *vma,
}
}
-static void xe_pt_commit_locks_assert(struct xe_vma *vma)
+static void xe_pt_commit_prepare_locks_assert(struct xe_vma *vma)
{
struct xe_vm *vm = xe_vma_vm(vma);
@@ -885,6 +892,16 @@ static void xe_pt_commit_locks_assert(struct xe_vma *vma)
xe_vm_assert_held(vm);
}
+static void xe_pt_commit_locks_assert(struct xe_vma *vma)
+{
+ struct xe_vm *vm = xe_vma_vm(vma);
+
+ xe_pt_commit_prepare_locks_assert(vma);
+
+ if (xe_vma_is_userptr(vma))
+ lockdep_assert_held_read(&vm->userptr.notifier_lock);
+}
+
static void xe_pt_commit(struct xe_vma *vma,
struct xe_vm_pgtable_update *entries,
u32 num_entries, struct llist_head *deferred)
@@ -895,13 +912,17 @@ static void xe_pt_commit(struct xe_vma *vma,
for (i = 0; i < num_entries; i++) {
struct xe_pt *pt = entries[i].pt;
+ struct xe_pt_dir *pt_dir;
if (!pt->level)
continue;
+ pt_dir = as_xe_pt_dir(pt);
for (j = 0; j < entries[i].qwords; j++) {
struct xe_pt *oldpte = entries[i].pt_entries[j].pt;
+ int j_ = j + entries[i].ofs;
+ pt_dir->children[j_] = pt_dir->staging[j_];
xe_pt_destroy(oldpte, xe_vma_vm(vma)->flags, deferred);
}
}
@@ -913,7 +934,7 @@ static void xe_pt_abort_bind(struct xe_vma *vma,
{
int i, j;
- xe_pt_commit_locks_assert(vma);
+ xe_pt_commit_prepare_locks_assert(vma);
for (i = num_entries - 1; i >= 0; --i) {
struct xe_pt *pt = entries[i].pt;
@@ -928,10 +949,10 @@ static void xe_pt_abort_bind(struct xe_vma *vma,
pt_dir = as_xe_pt_dir(pt);
for (j = 0; j < entries[i].qwords; j++) {
u32 j_ = j + entries[i].ofs;
- struct xe_pt *newpte = xe_pt_entry(pt_dir, j_);
+ struct xe_pt *newpte = xe_pt_entry_staging(pt_dir, j_);
struct xe_pt *oldpte = entries[i].pt_entries[j].pt;
- pt_dir->children[j_] = oldpte ? &oldpte->base : 0;
+ pt_dir->staging[j_] = oldpte ? &oldpte->base : 0;
xe_pt_destroy(newpte, xe_vma_vm(vma)->flags, NULL);
}
}
@@ -943,7 +964,7 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma,
{
u32 i, j;
- xe_pt_commit_locks_assert(vma);
+ xe_pt_commit_prepare_locks_assert(vma);
for (i = 0; i < num_entries; i++) {
struct xe_pt *pt = entries[i].pt;
@@ -961,10 +982,10 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma,
struct xe_pt *newpte = entries[i].pt_entries[j].pt;
struct xe_pt *oldpte = NULL;
- if (xe_pt_entry(pt_dir, j_))
- oldpte = xe_pt_entry(pt_dir, j_);
+ if (xe_pt_entry_staging(pt_dir, j_))
+ oldpte = xe_pt_entry_staging(pt_dir, j_);
- pt_dir->children[j_] = &newpte->base;
+ pt_dir->staging[j_] = &newpte->base;
entries[i].pt_entries[j].pt = oldpte;
}
}
@@ -1213,42 +1234,22 @@ static int vma_check_userptr(struct xe_vm *vm, struct xe_vma *vma,
return 0;
uvma = to_userptr_vma(vma);
- notifier_seq = uvma->userptr.notifier_seq;
+ if (xe_pt_userptr_inject_eagain(uvma))
+ xe_vma_userptr_force_invalidate(uvma);
- if (uvma->userptr.initial_bind && !xe_vm_in_fault_mode(vm))
- return 0;
+ notifier_seq = uvma->userptr.notifier_seq;
if (!mmu_interval_read_retry(&uvma->userptr.notifier,
- notifier_seq) &&
- !xe_pt_userptr_inject_eagain(uvma))
+ notifier_seq))
return 0;
- if (xe_vm_in_fault_mode(vm)) {
+ if (xe_vm_in_fault_mode(vm))
return -EAGAIN;
- } else {
- spin_lock(&vm->userptr.invalidated_lock);
- list_move_tail(&uvma->userptr.invalidate_link,
- &vm->userptr.invalidated);
- spin_unlock(&vm->userptr.invalidated_lock);
-
- if (xe_vm_in_preempt_fence_mode(vm)) {
- struct dma_resv_iter cursor;
- struct dma_fence *fence;
- long err;
-
- dma_resv_iter_begin(&cursor, xe_vm_resv(vm),
- DMA_RESV_USAGE_BOOKKEEP);
- dma_resv_for_each_fence_unlocked(&cursor, fence)
- dma_fence_enable_sw_signaling(fence);
- dma_resv_iter_end(&cursor);
-
- err = dma_resv_wait_timeout(xe_vm_resv(vm),
- DMA_RESV_USAGE_BOOKKEEP,
- false, MAX_SCHEDULE_TIMEOUT);
- XE_WARN_ON(err <= 0);
- }
- }
+ /*
+ * Just continue the operation since exec or rebind worker
+ * will take care of rebinding.
+ */
return 0;
}
@@ -1514,6 +1515,7 @@ static unsigned int xe_pt_stage_unbind(struct xe_tile *tile, struct xe_vma *vma,
.ops = &xe_pt_stage_unbind_ops,
.shifts = xe_normal_pt_shifts,
.max_level = XE_PT_HIGHEST_LEVEL,
+ .staging = true,
},
.tile = tile,
.modified_start = xe_vma_start(vma),
@@ -1555,7 +1557,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma,
{
int i, j;
- xe_pt_commit_locks_assert(vma);
+ xe_pt_commit_prepare_locks_assert(vma);
for (i = num_entries - 1; i >= 0; --i) {
struct xe_vm_pgtable_update *entry = &entries[i];
@@ -1568,7 +1570,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma,
continue;
for (j = entry->ofs; j < entry->ofs + entry->qwords; j++)
- pt_dir->children[j] =
+ pt_dir->staging[j] =
entries[i].pt_entries[j - entry->ofs].pt ?
&entries[i].pt_entries[j - entry->ofs].pt->base : NULL;
}
@@ -1581,7 +1583,7 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma,
{
int i, j;
- xe_pt_commit_locks_assert(vma);
+ xe_pt_commit_prepare_locks_assert(vma);
for (i = 0; i < num_entries; ++i) {
struct xe_vm_pgtable_update *entry = &entries[i];
@@ -1595,8 +1597,8 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma,
pt_dir = as_xe_pt_dir(pt);
for (j = entry->ofs; j < entry->ofs + entry->qwords; j++) {
entry->pt_entries[j - entry->ofs].pt =
- xe_pt_entry(pt_dir, j);
- pt_dir->children[j] = NULL;
+ xe_pt_entry_staging(pt_dir, j);
+ pt_dir->staging[j] = NULL;
}
}
}
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c
index b8b3d2aea492..be602a763ff3 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.c
+++ b/drivers/gpu/drm/xe/xe_pt_walk.c
@@ -74,7 +74,8 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level,
u64 addr, u64 end, struct xe_pt_walk *walk)
{
pgoff_t offset = xe_pt_offset(addr, level, walk);
- struct xe_ptw **entries = parent->children ? parent->children : NULL;
+ struct xe_ptw **entries = walk->staging ? (parent->staging ?: NULL) :
+ (parent->children ?: NULL);
const struct xe_pt_walk_ops *ops = walk->ops;
enum page_walk_action action;
struct xe_ptw *child;
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h
index 5ecc4d2f0f65..5c02c244f7de 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.h
+++ b/drivers/gpu/drm/xe/xe_pt_walk.h
@@ -11,12 +11,14 @@
/**
* struct xe_ptw - base class for driver pagetable subclassing.
* @children: Pointer to an array of children if any.
+ * @staging: Pointer to an array of staging if any.
*
* Drivers could subclass this, and if it's a page-directory, typically
* embed an array of xe_ptw pointers.
*/
struct xe_ptw {
struct xe_ptw **children;
+ struct xe_ptw **staging;
};
/**
@@ -41,6 +43,8 @@ struct xe_pt_walk {
* as shared pagetables.
*/
bool shared_pt_mode;
+ /** @staging: Walk staging PT structure */
+ bool staging;
};
/**
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 690330352d4c..ec6ec18ab3fa 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -579,51 +579,26 @@ out_unlock_outer:
trace_xe_vm_rebind_worker_exit(vm);
}
-static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
- const struct mmu_notifier_range *range,
- unsigned long cur_seq)
+static void __vma_userptr_invalidate(struct xe_vm *vm, struct xe_userptr_vma *uvma)
{
- struct xe_userptr *userptr = container_of(mni, typeof(*userptr), notifier);
- struct xe_userptr_vma *uvma = container_of(userptr, typeof(*uvma), userptr);
+ struct xe_userptr *userptr = &uvma->userptr;
struct xe_vma *vma = &uvma->vma;
- struct xe_vm *vm = xe_vma_vm(vma);
struct dma_resv_iter cursor;
struct dma_fence *fence;
long err;
- xe_assert(vm->xe, xe_vma_is_userptr(vma));
- trace_xe_vma_userptr_invalidate(vma);
-
- if (!mmu_notifier_range_blockable(range))
- return false;
-
- vm_dbg(&xe_vma_vm(vma)->xe->drm,
- "NOTIFIER: addr=0x%016llx, range=0x%016llx",
- xe_vma_start(vma), xe_vma_size(vma));
-
- down_write(&vm->userptr.notifier_lock);
- mmu_interval_set_seq(mni, cur_seq);
-
- /* No need to stop gpu access if the userptr is not yet bound. */
- if (!userptr->initial_bind) {
- up_write(&vm->userptr.notifier_lock);
- return true;
- }
-
/*
* Tell exec and rebind worker they need to repin and rebind this
* userptr.
*/
if (!xe_vm_in_fault_mode(vm) &&
- !(vma->gpuva.flags & XE_VMA_DESTROYED) && vma->tile_present) {
+ !(vma->gpuva.flags & XE_VMA_DESTROYED)) {
spin_lock(&vm->userptr.invalidated_lock);
list_move_tail(&userptr->invalidate_link,
&vm->userptr.invalidated);
spin_unlock(&vm->userptr.invalidated_lock);
}
- up_write(&vm->userptr.notifier_lock);
-
/*
* Preempt fences turn into schedule disables, pipeline these.
* Note that even in fault mode, we need to wait for binds and
@@ -641,11 +616,37 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
false, MAX_SCHEDULE_TIMEOUT);
XE_WARN_ON(err <= 0);
- if (xe_vm_in_fault_mode(vm)) {
+ if (xe_vm_in_fault_mode(vm) && userptr->initial_bind) {
err = xe_vm_invalidate_vma(vma);
XE_WARN_ON(err);
}
+ xe_hmm_userptr_unmap(uvma);
+}
+
+static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
+ const struct mmu_notifier_range *range,
+ unsigned long cur_seq)
+{
+ struct xe_userptr_vma *uvma = container_of(mni, typeof(*uvma), userptr.notifier);
+ struct xe_vma *vma = &uvma->vma;
+ struct xe_vm *vm = xe_vma_vm(vma);
+
+ xe_assert(vm->xe, xe_vma_is_userptr(vma));
+ trace_xe_vma_userptr_invalidate(vma);
+
+ if (!mmu_notifier_range_blockable(range))
+ return false;
+
+ vm_dbg(&xe_vma_vm(vma)->xe->drm,
+ "NOTIFIER: addr=0x%016llx, range=0x%016llx",
+ xe_vma_start(vma), xe_vma_size(vma));
+
+ down_write(&vm->userptr.notifier_lock);
+ mmu_interval_set_seq(mni, cur_seq);
+
+ __vma_userptr_invalidate(vm, uvma);
+ up_write(&vm->userptr.notifier_lock);
trace_xe_vma_userptr_invalidate_complete(vma);
return true;
@@ -655,6 +656,34 @@ static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = {
.invalidate = vma_userptr_invalidate,
};
+#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
+/**
+ * xe_vma_userptr_force_invalidate() - force invalidate a userptr
+ * @uvma: The userptr vma to invalidate
+ *
+ * Perform a forced userptr invalidation for testing purposes.
+ */
+void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma)
+{
+ struct xe_vm *vm = xe_vma_vm(&uvma->vma);
+
+ /* Protect against concurrent userptr pinning */
+ lockdep_assert_held(&vm->lock);
+ /* Protect against concurrent notifiers */
+ lockdep_assert_held(&vm->userptr.notifier_lock);
+ /*
+ * Protect against concurrent instances of this function and
+ * the critical exec sections
+ */
+ xe_vm_assert_held(vm);
+
+ if (!mmu_interval_read_retry(&uvma->userptr.notifier,
+ uvma->userptr.notifier_seq))
+ uvma->userptr.notifier_seq -= 2;
+ __vma_userptr_invalidate(vm, uvma);
+}
+#endif
+
int xe_vm_userptr_pin(struct xe_vm *vm)
{
struct xe_userptr_vma *uvma, *next;
@@ -666,20 +695,33 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
/* Collect invalidated userptrs */
spin_lock(&vm->userptr.invalidated_lock);
+ xe_assert(vm->xe, list_empty(&vm->userptr.repin_list));
list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated,
userptr.invalidate_link) {
list_del_init(&uvma->userptr.invalidate_link);
- list_move_tail(&uvma->userptr.repin_link,
- &vm->userptr.repin_list);
+ list_add_tail(&uvma->userptr.repin_link,
+ &vm->userptr.repin_list);
}
spin_unlock(&vm->userptr.invalidated_lock);
- /* Pin and move to temporary list */
+ /* Pin and move to bind list */
list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
userptr.repin_link) {
err = xe_vma_userptr_pin_pages(uvma);
if (err == -EFAULT) {
list_del_init(&uvma->userptr.repin_link);
+ /*
+ * We might have already done the pin once already, but
+ * then had to retry before the re-bind happened, due
+ * some other condition in the caller, but in the
+ * meantime the userptr got dinged by the notifier such
+ * that we need to revalidate here, but this time we hit
+ * the EFAULT. In such a case make sure we remove
+ * ourselves from the rebind list to avoid going down in
+ * flames.
+ */
+ if (!list_empty(&uvma->vma.combined_links.rebind))
+ list_del_init(&uvma->vma.combined_links.rebind);
/* Wait for pending binds */
xe_vm_lock(vm, false);
@@ -690,10 +732,10 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
err = xe_vm_invalidate_vma(&uvma->vma);
xe_vm_unlock(vm);
if (err)
- return err;
+ break;
} else {
- if (err < 0)
- return err;
+ if (err)
+ break;
list_del_init(&uvma->userptr.repin_link);
list_move_tail(&uvma->vma.combined_links.rebind,
@@ -701,7 +743,19 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
}
}
- return 0;
+ if (err) {
+ down_write(&vm->userptr.notifier_lock);
+ spin_lock(&vm->userptr.invalidated_lock);
+ list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
+ userptr.repin_link) {
+ list_del_init(&uvma->userptr.repin_link);
+ list_move_tail(&uvma->userptr.invalidate_link,
+ &vm->userptr.invalidated);
+ }
+ spin_unlock(&vm->userptr.invalidated_lock);
+ up_write(&vm->userptr.notifier_lock);
+ }
+ return err;
}
/**
@@ -987,6 +1041,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
INIT_LIST_HEAD(&userptr->invalidate_link);
INIT_LIST_HEAD(&userptr->repin_link);
vma->gpuva.gem.offset = bo_offset_or_userptr;
+ mutex_init(&userptr->unmap_mutex);
err = mmu_interval_notifier_insert(&userptr->notifier,
current->mm,
@@ -1028,6 +1083,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
* them anymore
*/
mmu_interval_notifier_remove(&userptr->notifier);
+ mutex_destroy(&userptr->unmap_mutex);
xe_vm_put(vm);
} else if (xe_vma_is_null(vma)) {
xe_vm_put(vm);
@@ -1066,6 +1122,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED);
spin_lock(&vm->userptr.invalidated_lock);
+ xe_assert(vm->xe, list_empty(&to_userptr_vma(vma)->userptr.repin_link));
list_del(&to_userptr_vma(vma)->userptr.invalidate_link);
spin_unlock(&vm->userptr.invalidated_lock);
} else if (!xe_vma_is_null(vma)) {
@@ -2260,8 +2317,17 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
break;
}
case DRM_GPUVA_OP_UNMAP:
+ xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask);
+ break;
case DRM_GPUVA_OP_PREFETCH:
- /* FIXME: Need to skip some prefetch ops */
+ vma = gpuva_to_vma(op->base.prefetch.va);
+
+ if (xe_vma_is_userptr(vma)) {
+ err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+ if (err)
+ return err;
+ }
+
xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask);
break;
default:
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 23adb7442881..b882bfb31bd0 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -274,9 +274,17 @@ static inline void vm_dbg(const struct drm_device *dev,
const char *format, ...)
{ /* noop */ }
#endif
-#endif
struct xe_vm_snapshot *xe_vm_snapshot_capture(struct xe_vm *vm);
void xe_vm_snapshot_capture_delayed(struct xe_vm_snapshot *snap);
void xe_vm_snapshot_print(struct xe_vm_snapshot *snap, struct drm_printer *p);
void xe_vm_snapshot_free(struct xe_vm_snapshot *snap);
+
+#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
+void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma);
+#else
+static inline void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma)
+{
+}
+#endif
+#endif
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 7f9a303e51d8..a4b4091cfd0d 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -59,12 +59,16 @@ struct xe_userptr {
struct sg_table *sg;
/** @notifier_seq: notifier sequence number */
unsigned long notifier_seq;
+ /** @unmap_mutex: Mutex protecting dma-unmapping */
+ struct mutex unmap_mutex;
/**
* @initial_bind: user pointer has been bound at least once.
* write: vm->userptr.notifier_lock in read mode and vm->resv held.
* read: vm->userptr.notifier_lock in write mode or vm->resv held.
*/
bool initial_bind;
+ /** @mapped: Whether the @sgt sg-table is dma-mapped. Protected by @unmap_mutex. */
+ bool mapped;
#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
u32 divisor;
#endif
@@ -227,8 +231,8 @@ struct xe_vm {
* up for revalidation. Protected from access with the
* @invalidated_lock. Removing items from the list
* additionally requires @lock in write mode, and adding
- * items to the list requires the @userptr.notifer_lock in
- * write mode.
+ * items to the list requires either the @userptr.notifer_lock in
+ * write mode, OR @lock in write mode.
*/
struct list_head invalidated;
} userptr;