drm/amd/amdgpu: New debugfs interface for MMIO registers (v5)

This new debugfs interface uses an IOCTL interface in order to pass
along state information like SRBM and GRBM bank switching.  This
new interface also allows a full 32-bit MMIO address range which
the previous didn't.  With this new design we have room to grow
the flexibility of the file as need be.

(v2): Move read/write to .read/.write, fix style, add comment
      for IOCTL data structure

(v3): C style comments

(v4): use u32 in struct and remove offset variable

(v5): Drop flag clearing in op function, use 0xFFFFFFFF for broadcast
      instead of 0x3FF, use mutex for op/ioctl.

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -36,6 +36,7 @@
 #include "amdgpu_rap.h"
 #include "amdgpu_securedisplay.h"
 #include "amdgpu_fw_attestation.h"
+#include "amdgpu_umr.h"
 
 int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev)
 {
@@ -279,6 +280,145 @@ static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf,
 	return amdgpu_debugfs_process_reg_op(false, f, (char __user *)buf, size, pos);
 }
 
+static int amdgpu_debugfs_regs2_open(struct inode *inode, struct file *file)
+{
+	struct amdgpu_debugfs_regs2_data *rd;
+
+	rd = kzalloc(sizeof *rd, GFP_KERNEL);
+	if (!rd)
+		return -ENOMEM;
+	rd->adev = file_inode(file)->i_private;
+	file->private_data = rd;
+	mutex_init(&rd->lock);
+
+	return 0;
+}
+
+static int amdgpu_debugfs_regs2_release(struct inode *inode, struct file *file)
+{
+	struct amdgpu_debugfs_regs2_data *rd = file->private_data;
+	mutex_destroy(&rd->lock);
+	kfree(file->private_data);
+	return 0;
+}
+
+static ssize_t amdgpu_debugfs_regs2_op(struct file *f, char __user *buf, u32 offset, size_t size, int write_en)
+{
+	struct amdgpu_debugfs_regs2_data *rd = f->private_data;
+	struct amdgpu_device *adev = rd->adev;
+	ssize_t result = 0;
+	int r;
+	uint32_t value;
+
+	if (size & 0x3 || offset & 0x3)
+		return -EINVAL;
+
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
+	if (r < 0) {
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		return r;
+	}
+
+	r = amdgpu_virt_enable_access_debugfs(adev);
+	if (r < 0) {
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		return r;
+	}
+
+	mutex_lock(&rd->lock);
+
+	if (rd->id.use_grbm) {
+		if ((rd->id.grbm.sh != 0xFFFFFFFF && rd->id.grbm.sh >= adev->gfx.config.max_sh_per_se) ||
+		    (rd->id.grbm.se != 0xFFFFFFFF && rd->id.grbm.se >= adev->gfx.config.max_shader_engines)) {
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+			amdgpu_virt_disable_access_debugfs(adev);
+			mutex_unlock(&rd->lock);
+			return -EINVAL;
+		}
+		mutex_lock(&adev->grbm_idx_mutex);
+		amdgpu_gfx_select_se_sh(adev, rd->id.grbm.se,
+								rd->id.grbm.sh,
+								rd->id.grbm.instance);
+	}
+
+	if (rd->id.use_srbm) {
+		mutex_lock(&adev->srbm_mutex);
+		amdgpu_gfx_select_me_pipe_q(adev, rd->id.srbm.me, rd->id.srbm.pipe,
+									rd->id.srbm.queue, rd->id.srbm.vmid);
+	}
+
+	if (rd->id.pg_lock)
+		mutex_lock(&adev->pm.mutex);
+
+	while (size) {
+		if (!write_en) {
+			value = RREG32(offset >> 2);
+			r = put_user(value, (uint32_t *)buf);
+		} else {
+			r = get_user(value, (uint32_t *)buf);
+			if (!r)
+				amdgpu_mm_wreg_mmio_rlc(adev, offset >> 2, value);
+		}
+		if (r) {
+			result = r;
+			goto end;
+		}
+		offset += 4;
+		size -= 4;
+		result += 4;
+		buf += 4;
+	}
+end:
+	if (rd->id.use_grbm) {
+		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+		mutex_unlock(&adev->grbm_idx_mutex);
+	}
+
+	if (rd->id.use_srbm) {
+		amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0, 0);
+		mutex_unlock(&adev->srbm_mutex);
+	}
+
+	if (rd->id.pg_lock)
+		mutex_unlock(&adev->pm.mutex);
+
+	mutex_unlock(&rd->lock);
+
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+
+	amdgpu_virt_disable_access_debugfs(adev);
+	return result;
+}
+
+static long amdgpu_debugfs_regs2_ioctl(struct file *f, unsigned int cmd, unsigned long data)
+{
+	struct amdgpu_debugfs_regs2_data *rd = f->private_data;
+	int r;
+
+	switch (cmd) {
+	case AMDGPU_DEBUGFS_REGS2_IOC_SET_STATE:
+		mutex_lock(&rd->lock);
+		r = copy_from_user(&rd->id, (struct amdgpu_debugfs_regs2_iocdata *)data, sizeof rd->id);
+		mutex_unlock(&rd->lock);
+		return r ? -EINVAL : 0;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static ssize_t amdgpu_debugfs_regs2_read(struct file *f, char __user *buf, size_t size, loff_t *pos)
+{
+	return amdgpu_debugfs_regs2_op(f, buf, *pos, size, 0);
+}
+
+static ssize_t amdgpu_debugfs_regs2_write(struct file *f, const char __user *buf, size_t size, loff_t *pos)
+{
+	return amdgpu_debugfs_regs2_op(f, (char __user *)buf, *pos, size, 1);
+}
+
 
 /**
  * amdgpu_debugfs_regs_pcie_read - Read from a PCIE register
@@ -1091,6 +1231,16 @@ static ssize_t amdgpu_debugfs_gfxoff_read(struct file *f, char __user *buf,
 	return result;
 }
 
+static const struct file_operations amdgpu_debugfs_regs2_fops = {
+	.owner = THIS_MODULE,
+	.unlocked_ioctl = amdgpu_debugfs_regs2_ioctl,
+	.read = amdgpu_debugfs_regs2_read,
+	.write = amdgpu_debugfs_regs2_write,
+	.open = amdgpu_debugfs_regs2_open,
+	.release = amdgpu_debugfs_regs2_release,
+	.llseek = default_llseek
+};
+
 static const struct file_operations amdgpu_debugfs_regs_fops = {
 	.owner = THIS_MODULE,
 	.read = amdgpu_debugfs_regs_read,
@@ -1148,6 +1298,7 @@ static const struct file_operations amdgpu_debugfs_gfxoff_fops = {
 
 static const struct file_operations *debugfs_regs[] = {
 	&amdgpu_debugfs_regs_fops,
+	&amdgpu_debugfs_regs2_fops,
 	&amdgpu_debugfs_regs_didt_fops,
 	&amdgpu_debugfs_regs_pcie_fops,
 	&amdgpu_debugfs_regs_smc_fops,
@@ -1160,6 +1311,7 @@ static const struct file_operations *debugfs_regs[] = {
 
 static const char *debugfs_regs_names[] = {
 	"amdgpu_regs",
+	"amdgpu_regs2",
 	"amdgpu_regs_didt",
 	"amdgpu_regs_pcie",
 	"amdgpu_regs_smc",