6 files changed, 75 insertions, 24 deletions

diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index df847a6d19f4..9f19bee7b592 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -992,7 +992,6 @@ void hl_debugfs_add_device(struct hl_device *hdev)
 	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
 	int count = ARRAY_SIZE(hl_debugfs_list);
 	struct hl_debugfs_entry *entry;
-	struct dentry *ent;
 	int i;
 
 	dev_entry->hdev = hdev;
@@ -1105,13 +1104,11 @@ void hl_debugfs_add_device(struct hl_device *hdev)
 				&hl_security_violations_fops);
 
 	for (i = 0, entry = dev_entry->entry_arr ; i < count ; i++, entry++) {
-
-		ent = debugfs_create_file(hl_debugfs_list[i].name,
+		debugfs_create_file(hl_debugfs_list[i].name,
 					0444,
 					dev_entry->root,
 					entry,
 					&hl_debugfs_fops);
-		entry->dent = ent;
 		entry->info_ent = &hl_debugfs_list[i];
 		entry->dev_entry = dev_entry;
 	}
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 15fcb5c31c4b..334009e83823 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -93,12 +93,19 @@ void hl_hpriv_put(struct hl_fpriv *hpriv)
 static int hl_device_release(struct inode *inode, struct file *filp)
 {
 	struct hl_fpriv *hpriv = filp->private_data;
+	struct hl_device *hdev = hpriv->hdev;
+
+	filp->private_data = NULL;
+
+	if (!hdev) {
+		pr_crit("Closing FD after device was removed. Memory leak will occur and it is advised to reboot.\n");
+		put_pid(hpriv->taskpid);
+		return 0;
+	}
 
 	hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr);
 	hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
 
-	filp->private_data = NULL;
-
 	hl_hpriv_put(hpriv);
 
 	return 0;
@@ -107,15 +114,20 @@ static int hl_device_release(struct inode *inode, struct file *filp)
 static int hl_device_release_ctrl(struct inode *inode, struct file *filp)
 {
 	struct hl_fpriv *hpriv = filp->private_data;
-	struct hl_device *hdev;
+	struct hl_device *hdev = hpriv->hdev;
 
 	filp->private_data = NULL;
 
-	hdev = hpriv->hdev;
+	if (!hdev) {
+		pr_err("Closing FD after device was removed\n");
+		goto out;
+	}
 
 	mutex_lock(&hdev->fpriv_list_lock);
 	list_del(&hpriv->dev_node);
 	mutex_unlock(&hdev->fpriv_list_lock);
+out:
+	put_pid(hpriv->taskpid);
 
 	kfree(hpriv);
 
@@ -134,8 +146,14 @@ static int hl_device_release_ctrl(struct inode *inode, struct file *filp)
 static int hl_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct hl_fpriv *hpriv = filp->private_data;
+	struct hl_device *hdev = hpriv->hdev;
 	unsigned long vm_pgoff;
 
+	if (!hdev) {
+		pr_err_ratelimited("Trying to mmap after device was removed! Please close FD\n");
+		return -ENODEV;
+	}
+
 	vm_pgoff = vma->vm_pgoff;
 	vma->vm_pgoff = HL_MMAP_OFFSET_VALUE_GET(vm_pgoff);
 
@@ -883,6 +901,16 @@ wait_for_processes:
 	return -EBUSY;
 }
 
+static void device_disable_open_processes(struct hl_device *hdev)
+{
+	struct hl_fpriv *hpriv;
+
+	mutex_lock(&hdev->fpriv_list_lock);
+	list_for_each_entry(hpriv, &hdev->fpriv_list, dev_node)
+		hpriv->hdev = NULL;
+	mutex_unlock(&hdev->fpriv_list_lock);
+}
+
 /*
  * hl_device_reset - reset the device
  *
@@ -1556,8 +1584,10 @@ void hl_device_fini(struct hl_device *hdev)
 		HL_PENDING_RESET_LONG_SEC);
 
 	rc = device_kill_open_processes(hdev, HL_PENDING_RESET_LONG_SEC);
-	if (rc)
+	if (rc) {
 		dev_crit(hdev->dev, "Failed to kill all open processes\n");
+		device_disable_open_processes(hdev);
+	}
 
 	hl_cb_pool_fini(hdev);
 
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index d933878b24d1..4b321e4f8059 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -1465,12 +1465,10 @@ struct hl_info_list {
 
 /**
  * struct hl_debugfs_entry - debugfs dentry wrapper.
- * @dent: base debugfs entry structure.
  * @info_ent: dentry realted ops.
  * @dev_entry: ASIC specific debugfs manager.
  */
 struct hl_debugfs_entry {
-	struct dentry			*dent;
 	const struct hl_info_list	*info_ent;
 	struct hl_dbg_device_entry	*dev_entry;
 };
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index 03af61cecd37..083a30969c5f 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -5,6 +5,8 @@
  * All Rights Reserved.
  */
 
+#define pr_fmt(fmt)	"habanalabs: " fmt
+
 #include <uapi/misc/habanalabs.h>
 #include "habanalabs.h"
 
@@ -682,6 +684,11 @@ long hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	const struct hl_ioctl_desc *ioctl = NULL;
 	unsigned int nr = _IOC_NR(cmd);
 
+	if (!hdev) {
+		pr_err_ratelimited("Sending ioctl after device was removed! Please close FD\n");
+		return -ENODEV;
+	}
+
 	if ((nr >= HL_COMMAND_START) && (nr < HL_COMMAND_END)) {
 		ioctl = &hl_ioctls[nr];
 	} else {
@@ -700,6 +707,11 @@ long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg)
 	const struct hl_ioctl_desc *ioctl = NULL;
 	unsigned int nr = _IOC_NR(cmd);
 
+	if (!hdev) {
+		pr_err_ratelimited("Sending ioctl after device was removed! Please close FD\n");
+		return -ENODEV;
+	}
+
 	if (nr == _IOC_NR(HL_IOCTL_INFO)) {
 		ioctl = &hl_ioctls_control[nr];
 	} else {
diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c
index de53fb5f978a..44a0522b59b9 100644
--- a/drivers/misc/habanalabs/common/irq.c
+++ b/drivers/misc/habanalabs/common/irq.c
@@ -47,7 +47,7 @@ inline u32 hl_cq_inc_ptr(u32 ptr)
  * Increment ptr by 1. If it reaches the number of event queue
  * entries, set it to 0
  */
-inline u32 hl_eq_inc_ptr(u32 ptr)
+static inline u32 hl_eq_inc_ptr(u32 ptr)
 {
 	ptr++;
 	if (unlikely(ptr == HL_EQ_LENGTH))
diff --git a/drivers/misc/habanalabs/common/mmu/mmu.c b/drivers/misc/habanalabs/common/mmu/mmu.c
index 71703a32350f..93c9e5f587e1 100644
--- a/drivers/misc/habanalabs/common/mmu/mmu.c
+++ b/drivers/misc/habanalabs/common/mmu/mmu.c
@@ -499,18 +499,32 @@ static void hl_mmu_pa_page_with_offset(struct hl_ctx *ctx, u64 virt_addr,
 	else /* HL_VA_RANGE_TYPE_DRAM */
 		p = &prop->dmmu;
 
-	/*
-	 * find the correct hop shift field in hl_mmu_properties structure
-	 * in order to determine the right maks for the page offset.
-	 */
-	hop0_shift_off = offsetof(struct hl_mmu_properties, hop0_shift);
-	p = (char *)p + hop0_shift_off;
-	p = (char *)p + ((hops->used_hops - 1) * sizeof(u64));
-	hop_shift = *(u64 *)p;
-	offset_mask = (1ull << hop_shift) - 1;
-	addr_mask = ~(offset_mask);
-	*phys_addr = (tmp_phys_addr & addr_mask) |
-					(virt_addr & offset_mask);
+	if ((hops->range_type == HL_VA_RANGE_TYPE_DRAM) &&
+			!is_power_of_2(prop->dram_page_size)) {
+		u32 bit;
+		u64 page_offset_mask;
+		u64 phys_addr_mask;
+
+		bit = __ffs64((u64)prop->dram_page_size);
+		page_offset_mask = ((1ull << bit) - 1);
+		phys_addr_mask = ~page_offset_mask;
+		*phys_addr = (tmp_phys_addr & phys_addr_mask) |
+				(virt_addr & page_offset_mask);
+	} else {
+		/*
+		 * find the correct hop shift field in hl_mmu_properties
+		 * structure in order to determine the right masks
+		 * for the page offset.
+		 */
+		hop0_shift_off = offsetof(struct hl_mmu_properties, hop0_shift);
+		p = (char *)p + hop0_shift_off;
+		p = (char *)p + ((hops->used_hops - 1) * sizeof(u64));
+		hop_shift = *(u64 *)p;
+		offset_mask = (1ull << hop_shift) - 1;
+		addr_mask = ~(offset_mask);
+		*phys_addr = (tmp_phys_addr & addr_mask) |
+				(virt_addr & offset_mask);
+	}
 }
 
 int hl_mmu_va_to_pa(struct hl_ctx *ctx, u64 virt_addr, u64 *phys_addr)