Merge tag 'amd-drm-next-5.8-2020-05-19' of git://people.freedesktop.o…

…rg/~agd5f/linux into drm-next

amd-drm-next-5.8-2020-05-19:

amdgpu:
- Improved handling for CTF (Critical Thermal Fault) situations
- Clarify AC/DC mode switches
- SR-IOV fixes
- XGMI fixes for RAS
- Misc cleanups
- Add autodump debugfs node to aid in GPU hang debugging

UAPI:
- Add a MEM_SYNC IB flag for handling proper acquire memory semantics if UMDs expect the kernel to handle this
  Used by AMDVLK: https://github.com/GPUOpen-Drivers/pal/blob/dev/src/core/os/amdgpu/amdgpuQueue.cpp#L1262

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200519202505.4126-1-alexander.deucher@amd.com

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

@@ -989,6 +989,8 @@ struct amdgpu_device {
 	char				product_number[16];
 	char				product_name[32];
 	char				serial[16];
+
+	struct amdgpu_autodump		autodump;
 };
 
 static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)

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

@@ -27,7 +27,7 @@
 #include <linux/pci.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
-
+#include <linux/poll.h>
 #include <drm/drm_debugfs.h>
 
 #include "amdgpu.h"
@@ -74,8 +74,82 @@ int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
 	return 0;
 }
 
+int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev)
+{
+#if defined(CONFIG_DEBUG_FS)
+	unsigned long timeout = 600 * HZ;
+	int ret;
+
+	wake_up_interruptible(&adev->autodump.gpu_hang);
+
+	ret = wait_for_completion_interruptible_timeout(&adev->autodump.dumping, timeout);
+	if (ret == 0) {
+		pr_err("autodump: timeout, move on to gpu recovery\n");
+		return -ETIMEDOUT;
+	}
+#endif
+	return 0;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
+static int amdgpu_debugfs_autodump_open(struct inode *inode, struct file *file)
+{
+	struct amdgpu_device *adev = inode->i_private;
+	int ret;
+
+	file->private_data = adev;
+
+	mutex_lock(&adev->lock_reset);
+	if (adev->autodump.dumping.done) {
+		reinit_completion(&adev->autodump.dumping);
+		ret = 0;
+	} else {
+		ret = -EBUSY;
+	}
+	mutex_unlock(&adev->lock_reset);
+
+	return ret;
+}
+
+static int amdgpu_debugfs_autodump_release(struct inode *inode, struct file *file)
+{
+	struct amdgpu_device *adev = file->private_data;
+
+	complete_all(&adev->autodump.dumping);
+	return 0;
+}
+
+static unsigned int amdgpu_debugfs_autodump_poll(struct file *file, struct poll_table_struct *poll_table)
+{
+	struct amdgpu_device *adev = file->private_data;
+
+	poll_wait(file, &adev->autodump.gpu_hang, poll_table);
+
+	if (adev->in_gpu_reset)
+		return POLLIN | POLLRDNORM | POLLWRNORM;
+
+	return 0;
+}
+
+static const struct file_operations autodump_debug_fops = {
+	.owner = THIS_MODULE,
+	.open = amdgpu_debugfs_autodump_open,
+	.poll = amdgpu_debugfs_autodump_poll,
+	.release = amdgpu_debugfs_autodump_release,
+};
+
+static void amdgpu_debugfs_autodump_init(struct amdgpu_device *adev)
+{
+	init_completion(&adev->autodump.dumping);
+	complete_all(&adev->autodump.dumping);
+	init_waitqueue_head(&adev->autodump.gpu_hang);
+
+	debugfs_create_file("amdgpu_autodump", 0600,
+		adev->ddev->primary->debugfs_root,
+		adev, &autodump_debug_fops);
+}
+
 /**
  * amdgpu_debugfs_process_reg_op - Handle MMIO register reads/writes
  *
@@ -1434,6 +1508,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 
 	amdgpu_ras_debugfs_create_all(adev);
 
+	amdgpu_debugfs_autodump_init(adev);
+
 	return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_list,
 					ARRAY_SIZE(amdgpu_debugfs_list));
 }

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

@@ -31,6 +31,11 @@ struct amdgpu_debugfs {
 	unsigned		num_files;
 };
 
+struct amdgpu_autodump {
+	struct completion		dumping;
+	struct wait_queue_head		gpu_hang;
+};
+
 int amdgpu_debugfs_regs_init(struct amdgpu_device *adev);
 int amdgpu_debugfs_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_fini(struct amdgpu_device *adev);
@@ -40,3 +45,4 @@ int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
 int amdgpu_debugfs_fence_init(struct amdgpu_device *adev);
 int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev);
 int amdgpu_debugfs_gem_init(struct amdgpu_device *adev);
+int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev);

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

@@ -3927,6 +3927,8 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	int i, r = 0;
 	bool need_full_reset  = *need_full_reset_arg;
 
+	amdgpu_debugfs_wait_dump(adev);
+
 	/* block all schedulers and reset given job's ring */
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];

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

@@ -1188,3 +1188,13 @@ int amdgpu_dpm_set_df_cstate(struct amdgpu_device *adev,
 
 	return ret;
 }
+
+int amdgpu_dpm_allow_xgmi_power_down(struct amdgpu_device *adev, bool en)
+{
+	struct smu_context *smu = &adev->smu;
+
+	if (is_support_sw_smu(adev))
+		return smu_allow_xgmi_power_down(smu, en);
+
+	return 0;
+}

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

@@ -538,4 +538,6 @@ int amdgpu_dpm_baco_enter(struct amdgpu_device *adev);
 int amdgpu_dpm_set_df_cstate(struct amdgpu_device *adev,
 			     uint32_t cstate);
 
+int amdgpu_dpm_allow_xgmi_power_down(struct amdgpu_device *adev, bool en);
+
 #endif

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

@@ -86,9 +86,10 @@
  * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
  * - 3.36.0 - Allow reading more status registers on si/cik
  * - 3.37.0 - L2 is invalidated before SDMA IBs, needed for correctness
+ * - 3.38.0 - Add AMDGPU_IB_FLAG_EMIT_MEM_SYNC
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	37
+#define KMS_DRIVER_MINOR	38
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;

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

@@ -189,6 +189,9 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		dma_fence_put(tmp);
 	}
 
+	if ((ib->flags & AMDGPU_IB_FLAG_EMIT_MEM_SYNC) && ring->funcs->emit_mem_sync)
+		ring->funcs->emit_mem_sync(ring);
+
 	if (ring->funcs->insert_start)
 		ring->funcs->insert_start(ring);