Merge tag 'char-misc-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char/misc driver updates from Greg KH:
 "Here is the big char/misc driver patch pull request for 5.1-rc1.

  The largest thing by far is the new habanalabs driver for their AI
  accelerator chip. For now it is in the drivers/misc directory but will
  probably move to a new directory soon along with other drivers of this
  type.

  Other than that, just the usual set of individual driver updates and
  fixes. There's an "odd" merge in here from the DRM tree that they
  asked me to do as the MEI driver is starting to interact with the i915
  driver, and it needed some coordination. All of those patches have
  been properly acked by the relevant subsystem maintainers.

  All of these have been in linux-next with no reported issues, most for
  quite some time"

* tag 'char-misc-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (219 commits)
  habanalabs: adjust Kconfig to fix build errors
  habanalabs: use %px instead of %p in error print
  habanalabs: use do_div for 64-bit divisions
  intel_th: gth: Fix an off-by-one in output unassigning
  habanalabs: fix little-endian<->cpu conversion warnings
  habanalabs: use NULL to initialize array of pointers
  habanalabs: fix little-endian<->cpu conversion warnings
  habanalabs: soft-reset device if context-switch fails
  habanalabs: print pointer using %p
  habanalabs: fix memory leak with CBs with unaligned size
  habanalabs: return correct error code on MMU mapping failure
  habanalabs: add comments in uapi/misc/habanalabs.h
  habanalabs: extend QMAN0 job timeout
  habanalabs: set DMA0 completion to SOB 1007
  habanalabs: fix validation of WREG32 to DMA completion
  habanalabs: fix mmu cache registers init
  habanalabs: disable CPU access on timeouts
  habanalabs: add MMU DRAM default page mapping
  habanalabs: Dissociate RAZWI info from event types
  misc/habanalabs: adjust Kconfig to fix build errors
  ...

1 files changed, 445 insertions, 0 deletions

diff --git a/drivers/misc/habanalabs/command_buffer.c b/drivers/misc/habanalabs/command_buffer.c
new file mode 100644
index 000000000000..85f75806a9a7
--- /dev/null
+++ b/drivers/misc/habanalabs/command_buffer.c
@@ -0,0 +1,445 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include <uapi/misc/habanalabs.h>
+#include "habanalabs.h"
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+static void cb_fini(struct hl_device *hdev, struct hl_cb *cb)
+{
+	hdev->asic_funcs->dma_free_coherent(hdev, cb->size,
+			(void *) (uintptr_t) cb->kernel_address,
+			cb->bus_address);
+	kfree(cb);
+}
+
+static void cb_do_release(struct hl_device *hdev, struct hl_cb *cb)
+{
+	if (cb->is_pool) {
+		spin_lock(&hdev->cb_pool_lock);
+		list_add(&cb->pool_list, &hdev->cb_pool);
+		spin_unlock(&hdev->cb_pool_lock);
+	} else {
+		cb_fini(hdev, cb);
+	}
+}
+
+static void cb_release(struct kref *ref)
+{
+	struct hl_device *hdev;
+	struct hl_cb *cb;
+
+	cb = container_of(ref, struct hl_cb, refcount);
+	hdev = cb->hdev;
+
+	hl_debugfs_remove_cb(cb);
+
+	cb_do_release(hdev, cb);
+}
+
+static struct hl_cb *hl_cb_alloc(struct hl_device *hdev, u32 cb_size,
+					int ctx_id)
+{
+	struct hl_cb *cb;
+	void *p;
+
+	/*
+	 * We use of GFP_ATOMIC here because this function can be called from
+	 * the latency-sensitive code path for command submission. Due to H/W
+	 * limitations in some of the ASICs, the kernel must copy the user CB
+	 * that is designated for an external queue and actually enqueue
+	 * the kernel's copy. Hence, we must never sleep in this code section
+	 * and must use GFP_ATOMIC for all memory allocations.
+	 */
+	if (ctx_id == HL_KERNEL_ASID_ID)
+		cb = kzalloc(sizeof(*cb), GFP_ATOMIC);
+	else
+		cb = kzalloc(sizeof(*cb), GFP_KERNEL);
+
+	if (!cb)
+		return NULL;
+
+	if (ctx_id == HL_KERNEL_ASID_ID)
+		p = hdev->asic_funcs->dma_alloc_coherent(hdev, cb_size,
+						&cb->bus_address, GFP_ATOMIC);
+	else
+		p = hdev->asic_funcs->dma_alloc_coherent(hdev, cb_size,
+						&cb->bus_address,
+						GFP_USER | __GFP_ZERO);
+	if (!p) {
+		dev_err(hdev->dev,
+			"failed to allocate %d of dma memory for CB\n",
+			cb_size);
+		kfree(cb);
+		return NULL;
+	}
+
+	cb->kernel_address = (u64) (uintptr_t) p;
+	cb->size = cb_size;
+
+	return cb;
+}
+
+int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
+			u32 cb_size, u64 *handle, int ctx_id)
+{
+	struct hl_cb *cb;
+	bool alloc_new_cb = true;
+	int rc;
+
+	/*
+	 * Can't use generic function to check this because of special case
+	 * where we create a CB as part of the reset process
+	 */
+	if ((hdev->disabled) || ((atomic_read(&hdev->in_reset)) &&
+					(ctx_id != HL_KERNEL_ASID_ID))) {
+		dev_warn_ratelimited(hdev->dev,
+			"Device is disabled or in reset. Can't create new CBs\n");
+		rc = -EBUSY;
+		goto out_err;
+	}
+
+	if (cb_size > HL_MAX_CB_SIZE) {
+		dev_err(hdev->dev,
+			"CB size %d must be less then %d\n",
+			cb_size, HL_MAX_CB_SIZE);
+		rc = -EINVAL;
+		goto out_err;
+	}
+
+	/* Minimum allocation must be PAGE SIZE */
+	if (cb_size < PAGE_SIZE)
+		cb_size = PAGE_SIZE;
+
+	if (ctx_id == HL_KERNEL_ASID_ID &&
+			cb_size <= hdev->asic_prop.cb_pool_cb_size) {
+
+		spin_lock(&hdev->cb_pool_lock);
+		if (!list_empty(&hdev->cb_pool)) {
+			cb = list_first_entry(&hdev->cb_pool, typeof(*cb),
+					pool_list);
+			list_del(&cb->pool_list);
+			spin_unlock(&hdev->cb_pool_lock);
+			alloc_new_cb = false;
+		} else {
+			spin_unlock(&hdev->cb_pool_lock);
+			dev_dbg(hdev->dev, "CB pool is empty\n");
+		}
+	}
+
+	if (alloc_new_cb) {
+		cb = hl_cb_alloc(hdev, cb_size, ctx_id);
+		if (!cb) {
+			rc = -ENOMEM;
+			goto out_err;
+		}
+	}
+
+	cb->hdev = hdev;
+	cb->ctx_id = ctx_id;
+
+	spin_lock(&mgr->cb_lock);
+	rc = idr_alloc(&mgr->cb_handles, cb, 1, 0, GFP_ATOMIC);
+	spin_unlock(&mgr->cb_lock);
+
+	if (rc < 0) {
+		dev_err(hdev->dev, "Failed to allocate IDR for a new CB\n");
+		goto release_cb;
+	}
+
+	cb->id = rc;
+
+	kref_init(&cb->refcount);
+	spin_lock_init(&cb->lock);
+
+	/*
+	 * idr is 32-bit so we can safely OR it with a mask that is above
+	 * 32 bit
+	 */
+	*handle = cb->id | HL_MMAP_CB_MASK;
+	*handle <<= PAGE_SHIFT;
+
+	hl_debugfs_add_cb(cb);
+
+	return 0;
+
+release_cb:
+	cb_do_release(hdev, cb);
+out_err:
+	*handle = 0;
+
+	return rc;
+}
+
+int hl_cb_destroy(struct hl_device *hdev, struct hl_cb_mgr *mgr, u64 cb_handle)
+{
+	struct hl_cb *cb;
+	u32 handle;
+	int rc = 0;
+
+	/*
+	 * handle was given to user to do mmap, I need to shift it back to
+	 * how the idr module gave it to me
+	 */
+	cb_handle >>= PAGE_SHIFT;
+	handle = (u32) cb_handle;
+
+	spin_lock(&mgr->cb_lock);
+
+	cb = idr_find(&mgr->cb_handles, handle);
+	if (cb) {
+		idr_remove(&mgr->cb_handles, handle);
+		spin_unlock(&mgr->cb_lock);
+		kref_put(&cb->refcount, cb_release);
+	} else {
+		spin_unlock(&mgr->cb_lock);
+		dev_err(hdev->dev,
+			"CB destroy failed, no match to handle 0x%x\n", handle);
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+int hl_cb_ioctl(struct hl_fpriv *hpriv, void *data)
+{
+	union hl_cb_args *args = data;
+	struct hl_device *hdev = hpriv->hdev;
+	u64 handle;
+	int rc;
+
+	switch (args->in.op) {
+	case HL_CB_OP_CREATE:
+		rc = hl_cb_create(hdev, &hpriv->cb_mgr, args->in.cb_size,
+					&handle, hpriv->ctx->asid);
+		memset(args, 0, sizeof(*args));
+		args->out.cb_handle = handle;
+		break;
+	case HL_CB_OP_DESTROY:
+		rc = hl_cb_destroy(hdev, &hpriv->cb_mgr,
+					args->in.cb_handle);
+		break;
+	default:
+		rc = -ENOTTY;
+		break;
+	}
+
+	return rc;
+}
+
+static void cb_vm_close(struct vm_area_struct *vma)
+{
+	struct hl_cb *cb = (struct hl_cb *) vma->vm_private_data;
+	long new_mmap_size;
+
+	new_mmap_size = cb->mmap_size - (vma->vm_end - vma->vm_start);
+
+	if (new_mmap_size > 0) {
+		cb->mmap_size = new_mmap_size;
+		return;
+	}
+
+	spin_lock(&cb->lock);
+	cb->mmap = false;
+	spin_unlock(&cb->lock);
+
+	hl_cb_put(cb);
+	vma->vm_private_data = NULL;
+}
+
+static const struct vm_operations_struct cb_vm_ops = {
+	.close = cb_vm_close
+};
+
+int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_cb *cb;
+	phys_addr_t address;
+	u32 handle;
+	int rc;
+
+	handle = vma->vm_pgoff;
+
+	/* reference was taken here */
+	cb = hl_cb_get(hdev, &hpriv->cb_mgr, handle);
+	if (!cb) {
+		dev_err(hdev->dev,
+			"CB mmap failed, no match to handle %d\n", handle);
+		return -EINVAL;
+	}
+
+	/* Validation check */
+	if ((vma->vm_end - vma->vm_start) != ALIGN(cb->size, PAGE_SIZE)) {
+		dev_err(hdev->dev,
+			"CB mmap failed, mmap size 0x%lx != 0x%x cb size\n",
+			vma->vm_end - vma->vm_start, cb->size);
+		rc = -EINVAL;
+		goto put_cb;
+	}
+
+	spin_lock(&cb->lock);
+
+	if (cb->mmap) {
+		dev_err(hdev->dev,
+			"CB mmap failed, CB already mmaped to user\n");
+		rc = -EINVAL;
+		goto release_lock;
+	}
+
+	cb->mmap = true;
+
+	spin_unlock(&cb->lock);
+
+	vma->vm_ops = &cb_vm_ops;
+
+	/*
+	 * Note: We're transferring the cb reference to
+	 * vma->vm_private_data here.
+	 */
+
+	vma->vm_private_data = cb;
+
+	/* Calculate address for CB */
+	address = virt_to_phys((void *) (uintptr_t) cb->kernel_address);
+
+	rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address,
+					address, cb->size);
+
+	if (rc) {
+		spin_lock(&cb->lock);
+		cb->mmap = false;
+		goto release_lock;
+	}
+
+	cb->mmap_size = cb->size;
+
+	return 0;
+
+release_lock:
+	spin_unlock(&cb->lock);
+put_cb:
+	hl_cb_put(cb);
+	return rc;
+}
+
+struct hl_cb *hl_cb_get(struct hl_device *hdev, struct hl_cb_mgr *mgr,
+			u32 handle)
+{
+	struct hl_cb *cb;
+
+	spin_lock(&mgr->cb_lock);
+	cb = idr_find(&mgr->cb_handles, handle);
+
+	if (!cb) {
+		spin_unlock(&mgr->cb_lock);
+		dev_warn(hdev->dev,
+			"CB get failed, no match to handle %d\n", handle);
+		return NULL;
+	}
+
+	kref_get(&cb->refcount);
+
+	spin_unlock(&mgr->cb_lock);
+
+	return cb;
+
+}
+
+void hl_cb_put(struct hl_cb *cb)
+{
+	kref_put(&cb->refcount, cb_release);
+}
+
+void hl_cb_mgr_init(struct hl_cb_mgr *mgr)
+{
+	spin_lock_init(&mgr->cb_lock);
+	idr_init(&mgr->cb_handles);
+}
+
+void hl_cb_mgr_fini(struct hl_device *hdev, struct hl_cb_mgr *mgr)
+{
+	struct hl_cb *cb;
+	struct idr *idp;
+	u32 id;
+
+	idp = &mgr->cb_handles;
+
+	idr_for_each_entry(idp, cb, id) {
+		if (kref_put(&cb->refcount, cb_release) != 1)
+			dev_err(hdev->dev,
+				"CB %d for CTX ID %d is still alive\n",
+				id, cb->ctx_id);
+	}
+
+	idr_destroy(&mgr->cb_handles);
+}
+
+struct hl_cb *hl_cb_kernel_create(struct hl_device *hdev, u32 cb_size)
+{
+	u64 cb_handle;
+	struct hl_cb *cb;
+	int rc;
+
+	rc = hl_cb_create(hdev, &hdev->kernel_cb_mgr, cb_size, &cb_handle,
+			HL_KERNEL_ASID_ID);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to allocate CB for KMD %d\n", rc);
+		return NULL;
+	}
+
+	cb_handle >>= PAGE_SHIFT;
+	cb = hl_cb_get(hdev, &hdev->kernel_cb_mgr, (u32) cb_handle);
+	/* hl_cb_get should never fail here so use kernel WARN */
+	WARN(!cb, "Kernel CB handle invalid 0x%x\n", (u32) cb_handle);
+	if (!cb)
+		goto destroy_cb;
+
+	return cb;
+
+destroy_cb:
+	hl_cb_destroy(hdev, &hdev->kernel_cb_mgr, cb_handle << PAGE_SHIFT);
+
+	return NULL;
+}
+
+int hl_cb_pool_init(struct hl_device *hdev)
+{
+	struct hl_cb *cb;
+	int i;
+
+	INIT_LIST_HEAD(&hdev->cb_pool);
+	spin_lock_init(&hdev->cb_pool_lock);
+
+	for (i = 0 ; i < hdev->asic_prop.cb_pool_cb_cnt ; i++) {
+		cb = hl_cb_alloc(hdev, hdev->asic_prop.cb_pool_cb_size,
+				HL_KERNEL_ASID_ID);
+		if (cb) {
+			cb->is_pool = true;
+			list_add(&cb->pool_list, &hdev->cb_pool);
+		} else {
+			hl_cb_pool_fini(hdev);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+int hl_cb_pool_fini(struct hl_device *hdev)
+{
+	struct hl_cb *cb, *tmp;
+
+	list_for_each_entry_safe(cb, tmp, &hdev->cb_pool, pool_list) {
+		list_del(&cb->pool_list);
+		cb_fini(hdev, cb);
+	}
+
+	return 0;
+}