drm/amdkfd: Add TC flush on VMID deallocation for Hawaii

On GFX7 the CP does not perform a TC flush when queues are unmapped.
To avoid TC eviction from accessing an invalid VMID, flush it
explicitly before releasing a VMID.

v2: Fix unnecessary list_for_each_entry_safe
v3: Moved allocation to kfd_process_device_init_vm

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

4 files changed, 95 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index b3b6dab71638..c18e048f23c6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/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;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 0ecbd1f9b606..7614375489a4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/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;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index b2b5ef8c4536..aaed005ce1f5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -494,6 +494,7 @@ struct qcm_process_device {
 
         /* IB memory */
         uint64_t ib_base;
+        void *ib_kaddr;
 };
 
 /* KFD Memory Eviction */
@@ -834,6 +835,8 @@ 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 */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index aeb339db8a90..45ef2d03a975 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -149,6 +149,36 @@ err_alloc_mem:
         return err;
 }
 
+/* kfd_process_device_reserve_ib_mem - Reserve memory inside the
+ *      process for IB usage The memory reserved is for KFD to submit
+ *      IB to AMDGPU from kernel.  If the memory is reserved
+ *      successfully, ib_kaddr will have the CPU/kernel
+ *      address. Check ib_kaddr before accessing the memory.
+ */
+static int kfd_process_device_reserve_ib_mem(struct kfd_process_device *pdd)
+{
+        struct qcm_process_device *qpd = &pdd->qpd;
+        uint32_t flags = ALLOC_MEM_FLAGS_GTT |
+                         ALLOC_MEM_FLAGS_NO_SUBSTITUTE |
+                         ALLOC_MEM_FLAGS_WRITABLE |
+                         ALLOC_MEM_FLAGS_EXECUTABLE;
+        void *kaddr;
+        int ret;
+
+        if (qpd->ib_kaddr || !qpd->ib_base)
+                return 0;
+
+        /* ib_base is only set for dGPU */
+        ret = kfd_process_alloc_gpuvm(pdd, qpd->ib_base, PAGE_SIZE, flags,
+                                      &kaddr);
+        if (ret)
+                return ret;
+
+        qpd->ib_kaddr = kaddr;
+
+        return 0;
+}
+
 struct kfd_process *kfd_create_process(struct file *filep)
 {
         struct kfd_process *process;
@@ -610,6 +640,9 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd,
                 return ret;
         }
 
+        ret = kfd_process_device_reserve_ib_mem(pdd);
+        if (ret)
+                goto err_reserve_ib_mem;
         ret = kfd_process_device_init_cwsr_dgpu(pdd);
         if (ret)
                 goto err_init_cwsr;
@@ -619,6 +652,7 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd,
         return 0;
 
 err_init_cwsr:
+err_reserve_ib_mem:
         kfd_process_device_free_bos(pdd);
         if (!drm_file)
                 dev->kfd2kgd->destroy_process_vm(dev->kgd, pdd->vm);