Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.5-2023-06-02:

amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates

amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions

radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero

ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()

UAPI:
- Add new ctx query flag to better handle GPU resets
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
  Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3

amd-drm-next-6.5-2023-06-09:

amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class

amdkfd:
- Add debugger support for gdb

radeon:
- Fix possible UAF

drm:
- Add Colorspace functionality

UAPI:
- Add debugger interface for enabling gdb
  Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
  Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com

1 files changed, 19 insertions, 12 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index ec1bf611624e..808ee010520a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -109,11 +109,11 @@ int kfd_iommu_device_init(struct kfd_dev *kfd)
  */
 int kfd_iommu_bind_process_to_device(struct kfd_process_device *pdd)
 {
-	struct kfd_dev *dev = pdd->dev;
+	struct kfd_node *dev = pdd->dev;
 	struct kfd_process *p = pdd->process;
 	int err;
 
-	if (!dev->use_iommu_v2 || pdd->bound == PDD_BOUND)
+	if (!dev->kfd->use_iommu_v2 || pdd->bound == PDD_BOUND)
 		return 0;
 
 	if (unlikely(pdd->bound == PDD_BOUND_SUSPENDED)) {
@@ -121,6 +121,12 @@ int kfd_iommu_bind_process_to_device(struct kfd_process_device *pdd)
 		return -EINVAL;
 	}
 
+	if (!kfd_is_first_node(dev)) {
+		dev_warn_once(kfd_device,
+				"IOMMU supported only on first node\n");
+		return 0;
+	}
+
 	err = amd_iommu_bind_pasid(dev->adev->pdev, p->pasid, p->lead_thread);
 	if (!err)
 		pdd->bound = PDD_BOUND;
@@ -138,7 +144,8 @@ void kfd_iommu_unbind_process(struct kfd_process *p)
 	int i;
 
 	for (i = 0; i < p->n_pdds; i++)
-		if (p->pdds[i]->bound == PDD_BOUND)
+		if ((p->pdds[i]->bound == PDD_BOUND) &&
+		    (kfd_is_first_node((p->pdds[i]->dev))))
 			amd_iommu_unbind_pasid(p->pdds[i]->dev->adev->pdev,
 					       p->pasid);
 }
@@ -146,7 +153,7 @@ void kfd_iommu_unbind_process(struct kfd_process *p)
 /* Callback for process shutdown invoked by the IOMMU driver */
 static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, u32 pasid)
 {
-	struct kfd_dev *dev = kfd_device_by_pci_dev(pdev);
+	struct kfd_node *dev = kfd_device_by_pci_dev(pdev);
 	struct kfd_process *p;
 	struct kfd_process_device *pdd;
 
@@ -182,7 +189,7 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, u32 pasid)
 static int iommu_invalid_ppr_cb(struct pci_dev *pdev, u32 pasid,
 				unsigned long address, u16 flags)
 {
-	struct kfd_dev *dev;
+	struct kfd_node *dev;
 
 	dev_warn_ratelimited(kfd_device,
 			"Invalid PPR device %x:%x.%x pasid 0x%x address 0x%lX flags 0x%X",
@@ -205,7 +212,7 @@ static int iommu_invalid_ppr_cb(struct pci_dev *pdev, u32 pasid,
  * Bind processes do the device that have been temporarily unbound
  * (PDD_BOUND_SUSPENDED) in kfd_unbind_processes_from_device.
  */
-static int kfd_bind_processes_to_device(struct kfd_dev *kfd)
+static int kfd_bind_processes_to_device(struct kfd_node *knode)
 {
 	struct kfd_process_device *pdd;
 	struct kfd_process *p;
@@ -216,14 +223,14 @@ static int kfd_bind_processes_to_device(struct kfd_dev *kfd)
 
 	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
 		mutex_lock(&p->mutex);
-		pdd = kfd_get_process_device_data(kfd, p);
+		pdd = kfd_get_process_device_data(knode, p);
 
 		if (WARN_ON(!pdd) || pdd->bound != PDD_BOUND_SUSPENDED) {
 			mutex_unlock(&p->mutex);
 			continue;
 		}
 
-		err = amd_iommu_bind_pasid(kfd->adev->pdev, p->pasid,
+		err = amd_iommu_bind_pasid(knode->adev->pdev, p->pasid,
 				p->lead_thread);
 		if (err < 0) {
 			pr_err("Unexpected pasid 0x%x binding failure\n",
@@ -246,7 +253,7 @@ static int kfd_bind_processes_to_device(struct kfd_dev *kfd)
  * processes will be restored to PDD_BOUND state in
  * kfd_bind_processes_to_device.
  */
-static void kfd_unbind_processes_from_device(struct kfd_dev *kfd)
+static void kfd_unbind_processes_from_device(struct kfd_node *knode)
 {
 	struct kfd_process_device *pdd;
 	struct kfd_process *p;
@@ -256,7 +263,7 @@ static void kfd_unbind_processes_from_device(struct kfd_dev *kfd)
 
 	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
 		mutex_lock(&p->mutex);
-		pdd = kfd_get_process_device_data(kfd, p);
+		pdd = kfd_get_process_device_data(knode, p);
 
 		if (WARN_ON(!pdd)) {
 			mutex_unlock(&p->mutex);
@@ -281,7 +288,7 @@ void kfd_iommu_suspend(struct kfd_dev *kfd)
 	if (!kfd->use_iommu_v2)
 		return;
 
-	kfd_unbind_processes_from_device(kfd);
+	kfd_unbind_processes_from_device(kfd->nodes[0]);
 
 	amd_iommu_set_invalidate_ctx_cb(kfd->adev->pdev, NULL);
 	amd_iommu_set_invalid_ppr_cb(kfd->adev->pdev, NULL);
@@ -312,7 +319,7 @@ int kfd_iommu_resume(struct kfd_dev *kfd)
 	amd_iommu_set_invalid_ppr_cb(kfd->adev->pdev,
 				     iommu_invalid_ppr_cb);
 
-	err = kfd_bind_processes_to_device(kfd);
+	err = kfd_bind_processes_to_device(kfd->nodes[0]);
 	if (err) {
 		amd_iommu_set_invalidate_ctx_cb(kfd->adev->pdev, NULL);
 		amd_iommu_set_invalid_ppr_cb(kfd->adev->pdev, NULL);