habanalabs: refactor MMU locks code

remove mmu_cache_lock as it protects a section which is already
protected by mmu_lock.

in addition, wrap mmu cache invalidate calls in hl_vm_ctx_fini with
mmu_lock.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

drivers/misc/habanalabs/common/device.c

@@ -373,7 +373,6 @@ static int device_early_init(struct hl_device *hdev)
 
 	mutex_init(&hdev->send_cpu_message_lock);
 	mutex_init(&hdev->debug_lock);
-	mutex_init(&hdev->mmu_cache_lock);
 	INIT_LIST_HEAD(&hdev->cs_mirror_list);
 	spin_lock_init(&hdev->cs_mirror_lock);
 	INIT_LIST_HEAD(&hdev->fpriv_list);
@@ -414,7 +413,6 @@ static void device_early_fini(struct hl_device *hdev)
 {
 	int i;
 
-	mutex_destroy(&hdev->mmu_cache_lock);
 	mutex_destroy(&hdev->debug_lock);
 	mutex_destroy(&hdev->send_cpu_message_lock);
 

drivers/misc/habanalabs/common/habanalabs.h

@@ -1764,7 +1764,6 @@ struct hl_mmu_funcs {
  * @asic_funcs: ASIC specific functions.
  * @asic_specific: ASIC specific information to use only from ASIC files.
  * @vm: virtual memory manager for MMU.
- * @mmu_cache_lock: protects MMU cache invalidation as it can serve one context.
  * @hwmon_dev: H/W monitor device.
  * @pm_mng_profile: current power management profile.
  * @hl_chip_info: ASIC's sensors information.
@@ -1879,7 +1878,6 @@ struct hl_device {
 	const struct hl_asic_funcs	*asic_funcs;
 	void				*asic_specific;
 	struct hl_vm			vm;
-	struct mutex			mmu_cache_lock;
 	struct device			*hwmon_dev;
 	enum hl_pm_mng_profile		pm_mng_profile;
 	struct hwmon_chip_info		*hl_chip_info;

drivers/misc/habanalabs/common/memory.c

@@ -1895,10 +1895,14 @@ void hl_vm_ctx_fini(struct hl_ctx *ctx)
 		unmap_device_va(ctx, hnode->vaddr, true);
 	}
 
+	mutex_lock(&ctx->mmu_lock);
+
 	/* invalidate the cache once after the unmapping loop */
 	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, VM_TYPE_USERPTR);
 	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, VM_TYPE_PHYS_PACK);
 
+	mutex_unlock(&ctx->mmu_lock);
+
 	spin_lock(&vm->idr_lock);
 	idr_for_each_entry(&vm->phys_pg_pack_handles, phys_pg_list, i)
 		if (phys_pg_list->asid == ctx->asid) {

drivers/misc/habanalabs/gaudi/gaudi.c

@@ -7330,8 +7330,6 @@ static int gaudi_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard,
 	else
 		timeout_usec = MMU_CONFIG_TIMEOUT_USEC;
 
-	mutex_lock(&hdev->mmu_cache_lock);
-
 	/* L0 & L1 invalidation */
 	WREG32(mmSTLB_INV_PS, 3);
 	WREG32(mmSTLB_CACHE_INV, gaudi->mmu_cache_inv_pi++);
@@ -7347,8 +7345,6 @@ static int gaudi_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard,
 
 	WREG32(mmSTLB_INV_SET, 0);
 
-	mutex_unlock(&hdev->mmu_cache_lock);
-
 	if (rc) {
 		dev_err_ratelimited(hdev->dev,
 					"MMU cache invalidation timeout\n");
@@ -7371,8 +7367,6 @@ static int gaudi_mmu_invalidate_cache_range(struct hl_device *hdev,
 		hdev->hard_reset_pending)
 		return 0;
 
-	mutex_lock(&hdev->mmu_cache_lock);
-
 	if (hdev->pldm)
 		timeout_usec = GAUDI_PLDM_MMU_TIMEOUT_USEC;
 	else
@@ -7400,8 +7394,6 @@ static int gaudi_mmu_invalidate_cache_range(struct hl_device *hdev,
 		1000,
 		timeout_usec);
 
-	mutex_unlock(&hdev->mmu_cache_lock);
-
 	if (rc) {
 		dev_err_ratelimited(hdev->dev,
 					"MMU cache invalidation timeout\n");

drivers/misc/habanalabs/goya/goya.c

@@ -5073,8 +5073,6 @@ static int goya_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard,
 	else
 		timeout_usec = MMU_CONFIG_TIMEOUT_USEC;
 
-	mutex_lock(&hdev->mmu_cache_lock);
-
 	/* L0 & L1 invalidation */
 	WREG32(mmSTLB_INV_ALL_START, 1);
 
@@ -5086,8 +5084,6 @@ static int goya_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard,
 		1000,
 		timeout_usec);
 
-	mutex_unlock(&hdev->mmu_cache_lock);
-
 	if (rc) {
 		dev_err_ratelimited(hdev->dev,
 					"MMU cache invalidation timeout\n");
@@ -5117,8 +5113,6 @@ static int goya_mmu_invalidate_cache_range(struct hl_device *hdev,
 	else
 		timeout_usec = MMU_CONFIG_TIMEOUT_USEC;
 
-	mutex_lock(&hdev->mmu_cache_lock);
-
 	/*
 	 * TODO: currently invalidate entire L0 & L1 as in regular hard
 	 * invalidation. Need to apply invalidation of specific cache lines with
@@ -5141,8 +5135,6 @@ static int goya_mmu_invalidate_cache_range(struct hl_device *hdev,
 		1000,
 		timeout_usec);
 
-	mutex_unlock(&hdev->mmu_cache_lock);
-
 	if (rc) {
 		dev_err_ratelimited(hdev->dev,
 					"MMU cache invalidation timeout\n");