Merge tag 'drm-amdkfd-next-2018-03-27' of git://people.freedesktop.org/~gabbayo/linux into drm-next

- GPUVM support for dGPUs
- KFD events support for dGPUs
- Fix live-lock situation when restoring multiple evicted processes
- Fix VM page table allocation on large-bar systems
- Fix for build failure on frv architecture

* tag 'drm-amdkfd-next-2018-03-27' of git://people.freedesktop.org/~gabbayo/linux:
  drm/amdkfd: Use ordered workqueue to restore processes
  drm/amdgpu: Fix acquiring VM on large-BAR systems
  drm/amdkfd: Add module option for testing large-BAR functionality
  drm/amdkfd: Kmap event page for dGPUs
  drm/amdkfd: Add ioctls for GPUVM memory management
  drm/amdkfd: Add TC flush on VMID deallocation for Hawaii
  drm/amdkfd: Allocate CWSR trap handler memory for dGPUs
  drm/amdkfd: Add per-process IDR for buffer handles
  drm/amdkfd: Aperture setup for dGPUs
  drm/amdkfd: Remove limit on number of GPUs
  drm/amdkfd: Populate DRM render device minor
  drm/amdkfd: Create KFD VMs on demand
  drm/amdgpu: Add kfd2kgd interface to acquire an existing VM
  drm/amdgpu: Add helper to turn an existing VM into a compute VM
  drm/amdgpu: Fix initial validation of PD BO for KFD VMs
  drm/amdgpu: Move KFD-specific fields into struct amdgpu_vm
  drm/amdkfd: fix uninitialized variable use
  drm/amdkfd: add missing include of mm.h

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h

@@ -26,6 +26,7 @@
 #define AMDGPU_AMDKFD_H_INCLUDED
 
 #include <linux/types.h>
+#include <linux/mm.h>
 #include <linux/mmu_context.h>
 #include <kgd_kfd_interface.h>
 #include <drm/ttm/ttm_execbuf_util.h>
@@ -92,27 +93,6 @@ struct amdkfd_process_info {
 	struct amdgpu_amdkfd_fence *eviction_fence;
 };
 
-/* struct amdkfd_vm -
- * For Memory Eviction KGD requires a mechanism to keep track of all KFD BOs
- * belonging to a KFD process. All the VMs belonging to the same process point
- * to the same amdkfd_process_info.
- */
-struct amdkfd_vm {
-	/* Keep base as the first parameter for pointer compatibility between
-	 * amdkfd_vm and amdgpu_vm.
-	 */
-	struct amdgpu_vm base;
-
-	/* List node in amdkfd_process_info.vm_list_head*/
-	struct list_head vm_list_node;
-
-	struct amdgpu_device *adev;
-	/* Points to the KFD process VM info*/
-	struct amdkfd_process_info *process_info;
-
-	uint64_t pd_phys_addr;
-};
-
 int amdgpu_amdkfd_init(void);
 void amdgpu_amdkfd_fini(void);
 
@@ -165,6 +145,12 @@ uint64_t amdgpu_amdkfd_get_vram_usage(struct kgd_dev *kgd);
 int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, void **vm,
 					  void **process_info,
 					  struct dma_fence **ef);
+int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
+					   struct file *filp,
+					   void **vm, void **process_info,
+					   struct dma_fence **ef);
+void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
+				    struct amdgpu_vm *vm);
 void amdgpu_amdkfd_gpuvm_destroy_process_vm(struct kgd_dev *kgd, void *vm);
 uint32_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *vm);
 int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c

@@ -205,6 +205,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.get_cu_info = get_cu_info,
 	.get_vram_usage = amdgpu_amdkfd_get_vram_usage,
 	.create_process_vm = amdgpu_amdkfd_gpuvm_create_process_vm,
+	.acquire_process_vm = amdgpu_amdkfd_gpuvm_acquire_process_vm,
 	.destroy_process_vm = amdgpu_amdkfd_gpuvm_destroy_process_vm,
 	.get_process_page_dir = amdgpu_amdkfd_gpuvm_get_process_page_dir,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c

@@ -165,6 +165,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.get_cu_info = get_cu_info,
 	.get_vram_usage = amdgpu_amdkfd_get_vram_usage,
 	.create_process_vm = amdgpu_amdkfd_gpuvm_create_process_vm,
+	.acquire_process_vm = amdgpu_amdkfd_gpuvm_acquire_process_vm,
 	.destroy_process_vm = amdgpu_amdkfd_gpuvm_destroy_process_vm,
 	.get_process_page_dir = amdgpu_amdkfd_gpuvm_get_process_page_dir,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

@@ -32,6 +32,7 @@
 #include <drm/amdgpu_drm.h>
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
+#include "amdgpu_amdkfd.h"
 
 /*
  * GPUVM
@@ -2405,8 +2406,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (vm->use_cpu_for_update)
 		flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
 	else
-		flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
-				AMDGPU_GEM_CREATE_SHADOW);
+		flags |= AMDGPU_GEM_CREATE_SHADOW;
 
 	size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level);
 	r = amdgpu_bo_create(adev, size, align, AMDGPU_GEM_DOMAIN_VRAM, flags,
@@ -2461,6 +2461,73 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	return r;
 }
 
+/**
+ * amdgpu_vm_make_compute - Turn a GFX VM into a compute VM
+ *
+ * This only works on GFX VMs that don't have any BOs added and no
+ * page tables allocated yet.
+ *
+ * Changes the following VM parameters:
+ * - use_cpu_for_update
+ * - pte_supports_ats
+ * - pasid (old PASID is released, because compute manages its own PASIDs)
+ *
+ * Reinitializes the page directory to reflect the changed ATS
+ * setting. May leave behind an unused shadow BO for the page
+ * directory when switching from SDMA updates to CPU updates.
+ *
+ * Returns 0 for success, -errno for errors.
+ */
+int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
+{
+	bool pte_support_ats = (adev->asic_type == CHIP_RAVEN);
+	int r;
+
+	r = amdgpu_bo_reserve(vm->root.base.bo, true);
+	if (r)
+		return r;
+
+	/* Sanity checks */
+	if (!RB_EMPTY_ROOT(&vm->va.rb_root) || vm->root.entries) {
+		r = -EINVAL;
+		goto error;
+	}
+
+	/* Check if PD needs to be reinitialized and do it before
+	 * changing any other state, in case it fails.
+	 */
+	if (pte_support_ats != vm->pte_support_ats) {
+		r = amdgpu_vm_clear_bo(adev, vm, vm->root.base.bo,
+			       adev->vm_manager.root_level,
+			       pte_support_ats);
+		if (r)
+			goto error;
+	}
+
+	/* Update VM state */
+	vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
+				    AMDGPU_VM_USE_CPU_FOR_COMPUTE);
+	vm->pte_support_ats = pte_support_ats;
+	DRM_DEBUG_DRIVER("VM update mode is %s\n",
+			 vm->use_cpu_for_update ? "CPU" : "SDMA");
+	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_vm_is_large_bar(adev)),
+		  "CPU update of VM recommended only for large BAR system\n");
+
+	if (vm->pasid) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
+		idr_remove(&adev->vm_manager.pasid_idr, vm->pasid);
+		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
+
+		vm->pasid = 0;
+	}
+
+error:
+	amdgpu_bo_unreserve(vm->root.base.bo);
+	return r;
+}
+
 /**
  * amdgpu_vm_free_levels - free PD/PT levels
  *
@@ -2508,6 +2575,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	u64 fault;
 	int i, r;
 
+	amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm);
+
 	/* Clear pending page faults from IH when the VM is destroyed */
 	while (kfifo_get(&vm->faults, &fault))
 		amdgpu_ih_clear_fault(adev, fault);

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h

@@ -207,6 +207,15 @@ struct amdgpu_vm {
 
 	/* Limit non-retry fault storms */
 	unsigned int		fault_credit;
+
+	/* Points to the KFD process VM info */
+	struct amdkfd_process_info *process_info;
+
+	/* List node in amdkfd_process_info.vm_list_head */
+	struct list_head	vm_list_node;
+
+	/* Valid while the PD is reserved or fenced */
+	uint64_t		pd_phys_addr;
 };
 
 struct amdgpu_vm_manager {
@@ -251,6 +260,7 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev);
 void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		   int vm_context, unsigned int pasid);
+int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
 				  unsigned int pasid);

drivers/gpu/drm/amd/amdkfd/kfd_crat.c

@@ -882,7 +882,7 @@ static int kfd_create_vcrat_image_cpu(void *pcrat_image, size_t *size)
 	crat_table->length = sizeof(struct crat_header);
 
 	status = acpi_get_table("DSDT", 0, &acpi_table);
-	if (status == AE_NOT_FOUND)
+	if (status != AE_OK)
 		pr_warn("DSDT table not found for OEM information\n");
 	else {
 		crat_table->oem_revision = acpi_table->revision;
@@ -1117,6 +1117,9 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 	sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
 			sub_type_hdr->length);
 
+	if (debug_largebar)
+		local_mem_info.local_mem_size_private = 0;
+
 	if (local_mem_info.local_mem_size_private == 0)
 		ret = kfd_fill_gpu_memory_affinity(&avail_size,
 				kdev, HSA_MEM_HEAP_TYPE_FB_PUBLIC,

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -142,12 +142,31 @@ static int allocate_vmid(struct device_queue_manager *dqm,
 	return 0;
 }
 
+static int flush_texture_cache_nocpsch(struct kfd_dev *kdev,
+				struct qcm_process_device *qpd)
+{
+	uint32_t len;
+
+	if (!qpd->ib_kaddr)
+		return -ENOMEM;
+
+	len = pm_create_release_mem(qpd->ib_base, (uint32_t *)qpd->ib_kaddr);
+
+	return kdev->kfd2kgd->submit_ib(kdev->kgd, KGD_ENGINE_MEC1, qpd->vmid,
+				qpd->ib_base, (uint32_t *)qpd->ib_kaddr, len);
+}
+
 static void deallocate_vmid(struct device_queue_manager *dqm,
 				struct qcm_process_device *qpd,
 				struct queue *q)
 {
 	int bit = qpd->vmid - dqm->dev->vm_info.first_vmid_kfd;
 
+	/* On GFX v7, CP doesn't flush TC at dequeue */
+	if (q->device->device_info->asic_family == CHIP_HAWAII)
+		if (flush_texture_cache_nocpsch(q->device, qpd))
+			pr_err("Failed to flush TC\n");
+
 	kfd_flush_tlb(qpd_to_pdd(qpd));
 
 	/* Release the vmid mapping */
@@ -792,11 +811,12 @@ static void uninitialize(struct device_queue_manager *dqm)
 static int start_nocpsch(struct device_queue_manager *dqm)
 {
 	init_interrupts(dqm);
-	return 0;
+	return pm_init(&dqm->packets, dqm);
 }
 
 static int stop_nocpsch(struct device_queue_manager *dqm)
 {
+	pm_uninit(&dqm->packets);
 	return 0;
 }
 

drivers/gpu/drm/amd/amdkfd/kfd_events.c

@@ -52,6 +52,7 @@ struct kfd_event_waiter {
 struct kfd_signal_page {
 	uint64_t *kernel_address;
 	uint64_t __user *user_address;
+	bool need_to_free_pages;
 };
 
 
@@ -79,6 +80,7 @@ static struct kfd_signal_page *allocate_signal_page(struct kfd_process *p)
 	       KFD_SIGNAL_EVENT_LIMIT * 8);
 
 	page->kernel_address = backing_store;
+	page->need_to_free_pages = true;
 	pr_debug("Allocated new event signal page at %p, for process %p\n",
 			page, p);
 
@@ -269,8 +271,9 @@ static void shutdown_signal_page(struct kfd_process *p)
 	struct kfd_signal_page *page = p->signal_page;
 
 	if (page) {
-		free_pages((unsigned long)page->kernel_address,
-				get_order(KFD_SIGNAL_EVENT_LIMIT * 8));
+		if (page->need_to_free_pages)
+			free_pages((unsigned long)page->kernel_address,
+				   get_order(KFD_SIGNAL_EVENT_LIMIT * 8));
 		kfree(page);
 	}
 }
@@ -292,6 +295,30 @@ static bool event_can_be_cpu_signaled(const struct kfd_event *ev)
 	return ev->type == KFD_EVENT_TYPE_SIGNAL;
 }
 
+int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
+		       uint64_t size)
+{
+	struct kfd_signal_page *page;
+
+	if (p->signal_page)
+		return -EBUSY;
+
+	page = kzalloc(sizeof(*page), GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	/* Initialize all events to unsignaled */
+	memset(kernel_address, (uint8_t) UNSIGNALED_EVENT_SLOT,
+	       KFD_SIGNAL_EVENT_LIMIT * 8);
+
+	page->kernel_address = kernel_address;
+
+	p->signal_page = page;
+	p->signal_mapped_size = size;
+
+	return 0;
+}
+
 int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint32_t event_type, bool auto_reset, uint32_t node_id,
 		     uint32_t *event_id, uint32_t *event_trigger_data,

drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c

@@ -278,21 +278,28 @@
 #define MAKE_GPUVM_APP_BASE(gpu_num) \
 	(((uint64_t)(gpu_num) << 61) + 0x1000000000000L)
 
-#define MAKE_GPUVM_APP_LIMIT(base) \
-	(((uint64_t)(base) & \
-		0xFFFFFF0000000000UL) | 0xFFFFFFFFFFL)
+#define MAKE_GPUVM_APP_LIMIT(base, size) \
+	(((uint64_t)(base) & 0xFFFFFF0000000000UL) + (size) - 1)
 
-#define MAKE_SCRATCH_APP_BASE(gpu_num) \
-	(((uint64_t)(gpu_num) << 61) + 0x100000000L)
+#define MAKE_SCRATCH_APP_BASE() \
+	(((uint64_t)(0x1UL) << 61) + 0x100000000L)
 
 #define MAKE_SCRATCH_APP_LIMIT(base) \
 	(((uint64_t)base & 0xFFFFFFFF00000000UL) | 0xFFFFFFFF)
 
-#define MAKE_LDS_APP_BASE(gpu_num) \
-	(((uint64_t)(gpu_num) << 61) + 0x0)
+#define MAKE_LDS_APP_BASE() \
+	(((uint64_t)(0x1UL) << 61) + 0x0)
 #define MAKE_LDS_APP_LIMIT(base) \
 	(((uint64_t)(base) & 0xFFFFFFFF00000000UL) | 0xFFFFFFFF)
 
+/* User mode manages most of the SVM aperture address space. The low
+ * 16MB are reserved for kernel use (CWSR trap handler and kernel IB
+ * for now).
+ */
+#define SVM_USER_BASE 0x1000000ull
+#define SVM_CWSR_BASE (SVM_USER_BASE - KFD_CWSR_TBA_TMA_SIZE)
+#define SVM_IB_BASE   (SVM_CWSR_BASE - PAGE_SIZE)
+
 int kfd_init_apertures(struct kfd_process *process)
 {
 	uint8_t id  = 0;
@@ -314,7 +321,7 @@ int kfd_init_apertures(struct kfd_process *process)
 			return -1;
 		}
 		/*
-		 * For 64 bit process aperture will be statically reserved in
+		 * For 64 bit process apertures will be statically reserved in
 		 * the x86_64 non canonical process address space
 		 * amdkfd doesn't currently support apertures for 32 bit process
 		 */
@@ -323,23 +330,35 @@ int kfd_init_apertures(struct kfd_process *process)
 			pdd->gpuvm_base = pdd->gpuvm_limit = 0;
 			pdd->scratch_base = pdd->scratch_limit = 0;
 		} else {
-			/*
-			 * node id couldn't be 0 - the three MSB bits of
-			 * aperture shoudn't be 0
+			/* Same LDS and scratch apertures can be used
+			 * on all GPUs. This allows using more dGPUs
+			 * than placement options for apertures.
 			 */
-			pdd->lds_base = MAKE_LDS_APP_BASE(id + 1);
-
+			pdd->lds_base = MAKE_LDS_APP_BASE();
 			pdd->lds_limit = MAKE_LDS_APP_LIMIT(pdd->lds_base);
 
-			pdd->gpuvm_base = MAKE_GPUVM_APP_BASE(id + 1);
-
-			pdd->gpuvm_limit =
-					MAKE_GPUVM_APP_LIMIT(pdd->gpuvm_base);
-
-			pdd->scratch_base = MAKE_SCRATCH_APP_BASE(id + 1);
-
+			pdd->scratch_base = MAKE_SCRATCH_APP_BASE();
 			pdd->scratch_limit =
 				MAKE_SCRATCH_APP_LIMIT(pdd->scratch_base);
+
+			if (dev->device_info->needs_iommu_device) {
+				/* APUs: GPUVM aperture in
+				 * non-canonical address space
+				 */
+				pdd->gpuvm_base = MAKE_GPUVM_APP_BASE(id + 1);
+				pdd->gpuvm_limit = MAKE_GPUVM_APP_LIMIT(
+					pdd->gpuvm_base,
+					dev->shared_resources.gpuvm_size);
+			} else {
+				/* dGPUs: SVM aperture starting at 0
+				 * with small reserved space for kernel
+				 */
+				pdd->gpuvm_base = SVM_USER_BASE;
+				pdd->gpuvm_limit =
+					dev->shared_resources.gpuvm_size - 1;
+				pdd->qpd.cwsr_base = SVM_CWSR_BASE;
+				pdd->qpd.ib_base = SVM_IB_BASE;
+			}
 		}
 
 		dev_dbg(kfd_device, "node id %u\n", id);

drivers/gpu/drm/amd/amdkfd/kfd_module.c

@@ -71,6 +71,11 @@ module_param(send_sigterm, int, 0444);
 MODULE_PARM_DESC(send_sigterm,
 	"Send sigterm to HSA process on unhandled exception (0 = disable, 1 = enable)");
 
+int debug_largebar;
+module_param(debug_largebar, int, 0444);
+MODULE_PARM_DESC(debug_largebar,
+	"Debug large-bar flag used to simulate large-bar capability on non-large bar machine (0 = disable, 1 = enable)");
+
 int ignore_crat;
 module_param(ignore_crat, int, 0444);
 MODULE_PARM_DESC(ignore_crat,
@@ -128,7 +133,9 @@ static int __init kfd_module_init(void)
 	if (err < 0)
 		goto err_topology;
 
-	kfd_process_create_wq();
+	err = kfd_process_create_wq();
+	if (err < 0)
+		goto err_create_wq;
 
 	kfd_debugfs_init();
 
@@ -138,6 +145,8 @@ static int __init kfd_module_init(void)
 
 	return 0;
 
+err_create_wq:
+	kfd_topology_shutdown();
 err_topology:
 	kfd_chardev_exit();
 err_ioctl:

drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c

@@ -356,6 +356,43 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
 	return retval;
 }
 
+/* pm_create_release_mem - Create a RELEASE_MEM packet and return the size
+ *     of this packet
+ *     @gpu_addr - GPU address of the packet. It's a virtual address.
+ *     @buffer - buffer to fill up with the packet. It's a CPU kernel pointer
+ *     Return - length of the packet
+ */
+uint32_t pm_create_release_mem(uint64_t gpu_addr, uint32_t *buffer)
+{
+	struct pm4_mec_release_mem *packet;
+
+	WARN_ON(!buffer);
+
+	packet = (struct pm4_mec_release_mem *)buffer;
+	memset(buffer, 0, sizeof(*packet));
+
+	packet->header.u32All = build_pm4_header(IT_RELEASE_MEM,
+						 sizeof(*packet));
+
+	packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
+	packet->bitfields2.event_index = event_index___release_mem__end_of_pipe;
+	packet->bitfields2.tcl1_action_ena = 1;
+	packet->bitfields2.tc_action_ena = 1;
+	packet->bitfields2.cache_policy = cache_policy___release_mem__lru;
+	packet->bitfields2.atc = 0;
+
+	packet->bitfields3.data_sel = data_sel___release_mem__send_32_bit_low;
+	packet->bitfields3.int_sel =
+		int_sel___release_mem__send_interrupt_after_write_confirm;
+
+	packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
+	packet->address_hi = upper_32_bits(gpu_addr);
+
+	packet->data_lo = 0;
+
+	return sizeof(*packet) / sizeof(unsigned int);
+}
+
 int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
 {
 	pm->dqm = dqm;

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -104,6 +104,12 @@ extern int cwsr_enable;
  */
 extern int send_sigterm;
 
+/*
+ * This kernel module is used to simulate large bar machine on non-large bar
+ * enabled machines.
+ */
+extern int debug_largebar;
+
 /*
  * Ignore CRAT table during KFD initialization, can be used to work around
  * broken CRAT tables on some AMD systems
@@ -488,8 +494,13 @@ struct qcm_process_device {
 
 	/* CWSR memory */
 	void *cwsr_kaddr;
+	uint64_t cwsr_base;
 	uint64_t tba_addr;
 	uint64_t tma_addr;
+
+	/* IB memory */
+	uint64_t ib_base;
+	void *ib_kaddr;
 };
 
 /* KFD Memory Eviction */
@@ -504,6 +515,14 @@ struct qcm_process_device {
 int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
 					       struct dma_fence *fence);
 
+/* 8 byte handle containing GPU ID in the most significant 4 bytes and
+ * idr_handle in the least significant 4 bytes
+ */
+#define MAKE_HANDLE(gpu_id, idr_handle) \
+	(((uint64_t)(gpu_id) << 32) + idr_handle)
+#define GET_GPU_ID(handle) (handle >> 32)
+#define GET_IDR_HANDLE(handle) (handle & 0xFFFFFFFF)
+
 enum kfd_pdd_bound {
 	PDD_UNBOUND = 0,
 	PDD_BOUND,
@@ -536,8 +555,12 @@ struct kfd_process_device {
 	uint64_t scratch_limit;
 
 	/* VM context for GPUVM allocations */
+	struct file *drm_file;
 	void *vm;
 
+	/* GPUVM allocations storage */
+	struct idr alloc_idr;
+
 	/* Flag used to tell the pdd has dequeued from the dqm.
 	 * This is used to prevent dev->dqm->ops.process_termination() from
 	 * being called twice when it is already called in IOMMU callback
@@ -651,7 +674,7 @@ struct amdkfd_ioctl_desc {
 	const char *name;
 };
 
-void kfd_process_create_wq(void);
+int kfd_process_create_wq(void);
 void kfd_process_destroy_wq(void);
 struct kfd_process *kfd_create_process(struct file *filep);
 struct kfd_process *kfd_get_process(const struct task_struct *);
@@ -661,6 +684,8 @@ void kfd_unref_process(struct kfd_process *p);
 void kfd_suspend_all_processes(void);
 int kfd_resume_all_processes(void);
 
+int kfd_process_device_init_vm(struct kfd_process_device *pdd,
+			       struct file *drm_file);
 struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev,
 						struct kfd_process *p);
 struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev,
@@ -671,6 +696,14 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 int kfd_reserved_mem_mmap(struct kfd_process *process,
 			  struct vm_area_struct *vma);
 
+/* KFD process API for creating and translating handles */
+int kfd_process_device_create_obj_handle(struct kfd_process_device *pdd,
+					void *mem);
+void *kfd_process_device_translate_handle(struct kfd_process_device *p,
+					int handle);
+void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd,
+					int handle);
+
 /* Process device data iterator */
 struct kfd_process_device *kfd_get_first_process_device_data(
 							struct kfd_process *p);
@@ -816,6 +849,8 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 
 void pm_release_ib(struct packet_manager *pm);
 
+uint32_t pm_create_release_mem(uint64_t gpu_addr, uint32_t *buffer);
+
 uint64_t kfd_get_number_elems(struct kfd_dev *kfd);
 
 /* Events */
@@ -837,6 +872,8 @@ void kfd_signal_iommu_event(struct kfd_dev *dev,
 void kfd_signal_hw_exception_event(unsigned int pasid);
 int kfd_set_event(struct kfd_process *p, uint32_t event_id);
 int kfd_reset_event(struct kfd_process *p, uint32_t event_id);
+int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
+		       uint64_t size);
 int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint32_t event_type, bool auto_reset, uint32_t node_id,
 		     uint32_t *event_id, uint32_t *event_trigger_data,

drivers/gpu/drm/amd/amdkfd/kfd_topology.c

@@ -441,6 +441,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			dev->node_props.device_id);
 	sysfs_show_32bit_prop(buffer, "location_id",
 			dev->node_props.location_id);
+	sysfs_show_32bit_prop(buffer, "drm_render_minor",
+			dev->node_props.drm_render_minor);
 
 	if (dev->gpu) {
 		log_max_watch_addr =
@@ -1214,6 +1216,8 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 		dev->gpu->kfd2kgd->get_max_engine_clock_in_mhz(dev->gpu->kgd);
 	dev->node_props.max_engine_clk_ccompute =
 		cpufreq_quick_get_max(0) / 1000;
+	dev->node_props.drm_render_minor =
+		gpu->shared_resources.drm_render_minor;
 
 	kfd_fill_mem_clk_max_info(dev);
 	kfd_fill_iolink_non_crat_info(dev);

drivers/gpu/drm/amd/amdkfd/kfd_topology.h

@@ -71,6 +71,7 @@ struct kfd_node_properties {
 	uint32_t location_id;
 	uint32_t max_engine_clk_fcompute;
 	uint32_t max_engine_clk_ccompute;
+	int32_t  drm_render_minor;
 	uint16_t marketing_name[KFD_TOPOLOGY_PUBLIC_NAME_SIZE];
 };
 

drivers/gpu/drm/amd/include/kgd_kfd_interface.h

@@ -130,6 +130,7 @@ struct tile_config {
 
 /*
  * Allocation flag domains
+ * NOTE: This must match the corresponding definitions in kfd_ioctl.h.
  */
 #define ALLOC_MEM_FLAGS_VRAM		(1 << 0)
 #define ALLOC_MEM_FLAGS_GTT		(1 << 1)
@@ -138,6 +139,7 @@ struct tile_config {
 
 /*
  * Allocation flags attributes/access options.
+ * NOTE: This must match the corresponding definitions in kfd_ioctl.h.
  */
 #define ALLOC_MEM_FLAGS_WRITABLE	(1 << 31)
 #define ALLOC_MEM_FLAGS_EXECUTABLE	(1 << 30)
@@ -336,6 +338,8 @@ struct kfd2kgd_calls {
 
 	int (*create_process_vm)(struct kgd_dev *kgd, void **vm,
 			void **process_info, struct dma_fence **ef);
+	int (*acquire_process_vm)(struct kgd_dev *kgd, struct file *filp,
+			void **vm, void **process_info, struct dma_fence **ef);
 	void (*destroy_process_vm)(struct kgd_dev *kgd, void *vm);
 	uint32_t (*get_process_page_dir)(void *vm);
 	void (*set_vm_context_page_table_base)(struct kgd_dev *kgd,

include/uapi/linux/kfd_ioctl.h

@@ -107,8 +107,6 @@ struct kfd_ioctl_get_clock_counters_args {
 	__u32 pad;
 };
 
-#define NUM_OF_SUPPORTED_GPUS 7
-
 struct kfd_process_device_apertures {
 	__u64 lds_base;		/* from KFD */
 	__u64 lds_limit;		/* from KFD */
@@ -120,6 +118,12 @@ struct kfd_process_device_apertures {
 	__u32 pad;
 };
 
+/*
+ * AMDKFD_IOC_GET_PROCESS_APERTURES is deprecated. Use
+ * AMDKFD_IOC_GET_PROCESS_APERTURES_NEW instead, which supports an
+ * unlimited number of GPUs.
+ */
+#define NUM_OF_SUPPORTED_GPUS 7
 struct kfd_ioctl_get_process_apertures_args {
 	struct kfd_process_device_apertures
 			process_apertures[NUM_OF_SUPPORTED_GPUS];/* from KFD */
@@ -129,6 +133,19 @@ struct kfd_ioctl_get_process_apertures_args {
 	__u32 pad;
 };
 
+struct kfd_ioctl_get_process_apertures_new_args {
+	/* User allocated. Pointer to struct kfd_process_device_apertures
+	 * filled in by Kernel
+	 */
+	__u64 kfd_process_device_apertures_ptr;
+	/* to KFD - indicates amount of memory present in
+	 *  kfd_process_device_apertures_ptr
+	 * from KFD - Number of entries filled by KFD.
+	 */
+	__u32 num_of_nodes;
+	__u32 pad;
+};
+
 #define MAX_ALLOWED_NUM_POINTS    100
 #define MAX_ALLOWED_AW_BUFF_SIZE 4096
 #define MAX_ALLOWED_WAC_BUFF_SIZE  128
@@ -269,6 +286,86 @@ struct kfd_ioctl_set_trap_handler_args {
 	__u32 pad;
 };
 
+struct kfd_ioctl_acquire_vm_args {
+	__u32 drm_fd;	/* to KFD */
+	__u32 gpu_id;	/* to KFD */
+};
+
+/* Allocation flags: memory types */
+#define KFD_IOC_ALLOC_MEM_FLAGS_VRAM		(1 << 0)
+#define KFD_IOC_ALLOC_MEM_FLAGS_GTT		(1 << 1)
+#define KFD_IOC_ALLOC_MEM_FLAGS_USERPTR		(1 << 2)
+#define KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL	(1 << 3)
+/* Allocation flags: attributes/access options */
+#define KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE	(1 << 31)
+#define KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE	(1 << 30)
+#define KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC		(1 << 29)
+#define KFD_IOC_ALLOC_MEM_FLAGS_NO_SUBSTITUTE	(1 << 28)
+#define KFD_IOC_ALLOC_MEM_FLAGS_AQL_QUEUE_MEM	(1 << 27)
+#define KFD_IOC_ALLOC_MEM_FLAGS_COHERENT	(1 << 26)
+
+/* Allocate memory for later SVM (shared virtual memory) mapping.
+ *
+ * @va_addr:     virtual address of the memory to be allocated
+ *               all later mappings on all GPUs will use this address
+ * @size:        size in bytes
+ * @handle:      buffer handle returned to user mode, used to refer to
+ *               this allocation for mapping, unmapping and freeing
+ * @mmap_offset: for CPU-mapping the allocation by mmapping a render node
+ *               for userptrs this is overloaded to specify the CPU address
+ * @gpu_id:      device identifier
+ * @flags:       memory type and attributes. See KFD_IOC_ALLOC_MEM_FLAGS above
+ */
+struct kfd_ioctl_alloc_memory_of_gpu_args {
+	__u64 va_addr;		/* to KFD */
+	__u64 size;		/* to KFD */
+	__u64 handle;		/* from KFD */
+	__u64 mmap_offset;	/* to KFD (userptr), from KFD (mmap offset) */
+	__u32 gpu_id;		/* to KFD */
+	__u32 flags;
+};
+
+/* Free memory allocated with kfd_ioctl_alloc_memory_of_gpu
+ *
+ * @handle: memory handle returned by alloc
+ */
+struct kfd_ioctl_free_memory_of_gpu_args {
+	__u64 handle;		/* to KFD */
+};
+
+/* Map memory to one or more GPUs
+ *
+ * @handle:                memory handle returned by alloc
+ * @device_ids_array_ptr:  array of gpu_ids (__u32 per device)
+ * @n_devices:             number of devices in the array
+ * @n_success:             number of devices mapped successfully
+ *
+ * @n_success returns information to the caller how many devices from
+ * the start of the array have mapped the buffer successfully. It can
+ * be passed into a subsequent retry call to skip those devices. For
+ * the first call the caller should initialize it to 0.
+ *
+ * If the ioctl completes with return code 0 (success), n_success ==
+ * n_devices.
+ */
+struct kfd_ioctl_map_memory_to_gpu_args {
+	__u64 handle;			/* to KFD */
+	__u64 device_ids_array_ptr;	/* to KFD */
+	__u32 n_devices;		/* to KFD */
+	__u32 n_success;		/* to/from KFD */
+};
+
+/* Unmap memory from one or more GPUs
+ *
+ * same arguments as for mapping
+ */
+struct kfd_ioctl_unmap_memory_from_gpu_args {
+	__u64 handle;			/* to KFD */
+	__u64 device_ids_array_ptr;	/* to KFD */
+	__u32 n_devices;		/* to KFD */
+	__u32 n_success;		/* to/from KFD */
+};
+
 #define AMDKFD_IOCTL_BASE 'K'
 #define AMDKFD_IO(nr)			_IO(AMDKFD_IOCTL_BASE, nr)
 #define AMDKFD_IOR(nr, type)		_IOR(AMDKFD_IOCTL_BASE, nr, type)
@@ -332,7 +429,26 @@ struct kfd_ioctl_set_trap_handler_args {
 #define AMDKFD_IOC_SET_TRAP_HANDLER		\
 		AMDKFD_IOW(0x13, struct kfd_ioctl_set_trap_handler_args)
 
+#define AMDKFD_IOC_GET_PROCESS_APERTURES_NEW	\
+		AMDKFD_IOWR(0x14,		\
+			struct kfd_ioctl_get_process_apertures_new_args)
+
+#define AMDKFD_IOC_ACQUIRE_VM			\
+		AMDKFD_IOW(0x15, struct kfd_ioctl_acquire_vm_args)
+
+#define AMDKFD_IOC_ALLOC_MEMORY_OF_GPU		\
+		AMDKFD_IOWR(0x16, struct kfd_ioctl_alloc_memory_of_gpu_args)
+
+#define AMDKFD_IOC_FREE_MEMORY_OF_GPU		\
+		AMDKFD_IOW(0x17, struct kfd_ioctl_free_memory_of_gpu_args)
+
+#define AMDKFD_IOC_MAP_MEMORY_TO_GPU		\
+		AMDKFD_IOWR(0x18, struct kfd_ioctl_map_memory_to_gpu_args)
+
+#define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU	\
+		AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x14
+#define AMDKFD_COMMAND_END		0x1A
 
 #endif