habanalabs: add debugfs support

This patch adds debugfs support to the driver. It allows the user-space to
display information that is contained in the internal structures of the
driver, such as:
- active command submissions
- active user virtual memory mappings
- number of allocated command buffers

It also enables the user to perform reads and writes through Goya's PCI
bars.

Reviewed-by: Mike Rapoport <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Documentation/ABI/testing/debugfs-driver-habanalabs

@@ -0,0 +1,126 @@
+What:           /sys/kernel/debug/habanalabs/hl<n>/addr
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Sets the device address to be used for read or write through
+                PCI bar. The acceptable value is a string that starts with "0x"
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/command_buffers
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Displays a list with information about the currently allocated
+                command buffers
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/command_submission
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Displays a list with information about the currently active
+                command submissions
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/command_submission_jobs
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Displays a list with detailed information about each JOB (CB) of
+                each active command submission
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/data32
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Allows the root user to read or write directly through the
+                device's PCI bar. Writing to this file generates a write
+                transaction while reading from the file generates a read
+                transcation. This custom interface is needed (instead of using
+                the generic Linux user-space PCI mapping) because the DDR bar
+                is very small compared to the DDR memory and only the driver can
+                move the bar before and after the transaction
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/device
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Enables the root user to set the device to specific state.
+                Valid values are "disable", "enable", "suspend", "resume".
+                User can read this property to see the valid values
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/i2c_addr
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Sets I2C device address for I2C transaction that is generated
+                by the device's CPU
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/i2c_bus
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Sets I2C bus address for I2C transaction that is generated by
+                the device's CPU
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/i2c_data
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Triggers an I2C transaction that is generated by the device's
+                CPU. Writing to this file generates a write transaction while
+                reading from the file generates a read transcation
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/i2c_reg
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Sets I2C register id for I2C transaction that is generated by
+                the device's CPU
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/led0
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Sets the state of the first S/W led on the device
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/led1
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Sets the state of the second S/W led on the device
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/led2
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Sets the state of the third S/W led on the device
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/mmu
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Displays the hop values and physical address for a given ASID
+                and virtual address. The user should write the ASID and VA into
+                the file and then read the file to get the result.
+                e.g. to display info about VA 0x1000 for ASID 1 you need to do:
+                echo "1 0x1000" > /sys/kernel/debug/habanalabs/hl0/mmu
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/set_power_state
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Sets the PCI power state. Valid values are "1" for D0 and "2"
+                for D3Hot
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/userptr
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Displays a list with information about the currently user
+                pointers (user virtual addresses) that are pinned and mapped
+                to DMA addresses
+
+What:           /sys/kernel/debug/habanalabs/hl<n>/vm
+Date:           Jan 2019
+KernelVersion:  5.1
+Contact:        [email protected]
+Description:    Displays a list with information about all the active virtual
+                address mappings per ASID

drivers/misc/habanalabs/Makefile

@@ -8,5 +8,7 @@ habanalabs-y := habanalabs_drv.o device.o context.o asid.o habanalabs_ioctl.o \
 		command_buffer.o hw_queue.o irq.o sysfs.o hwmon.o memory.o \
 		command_submission.o mmu.o
 
+habanalabs-$(CONFIG_DEBUG_FS) += debugfs.o
+
 include $(src)/goya/Makefile
 habanalabs-y += $(HL_GOYA_FILES)

drivers/misc/habanalabs/command_buffer.c

@@ -38,6 +38,8 @@ static void cb_release(struct kref *ref)
 	cb = container_of(ref, struct hl_cb, refcount);
 	hdev = cb->hdev;
 
+	hl_debugfs_remove_cb(cb);
+
 	cb_do_release(hdev, cb);
 }
 
@@ -163,6 +165,8 @@ int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
 	*handle = cb->id | HL_MMAP_CB_MASK;
 	*handle <<= PAGE_SHIFT;
 
+	hl_debugfs_add_cb(cb);
+
 	return 0;
 
 release_cb:

drivers/misc/habanalabs/command_submission.c

@@ -149,6 +149,8 @@ static void free_job(struct hl_device *hdev, struct hl_cs_job *job)
 	list_del(&job->cs_node);
 	spin_unlock(&cs->job_lock);
 
+	hl_debugfs_remove_job(hdev, job);
+
 	if (job->ext_queue)
 		cs_put(cs);
 
@@ -212,6 +214,12 @@ static void cs_do_release(struct kref *ref)
 		}
 	}
 
+	/*
+	 * Must be called before hl_ctx_put because inside we use ctx to get
+	 * the device
+	 */
+	hl_debugfs_remove_cs(cs);
+
 	hl_ctx_put(cs->ctx);
 
 	if (cs->timedout)
@@ -480,6 +488,8 @@ static int _hl_cs_ioctl(struct hl_fpriv *hpriv, void __user *chunks,
 
 	*cs_seq = cs->sequence;
 
+	hl_debugfs_add_cs(cs);
+
 	/* Validate ALL the CS chunks before submitting the CS */
 	for (i = 0, parse_cnt = 0 ; i < num_chunks ; i++, parse_cnt++) {
 		struct hl_cs_chunk *chunk = &cs_chunk_array[i];
@@ -528,6 +538,8 @@ static int _hl_cs_ioctl(struct hl_fpriv *hpriv, void __user *chunks,
 		if (job->ext_queue)
 			cs_get(cs);
 
+		hl_debugfs_add_job(hdev, job);
+
 		rc = cs_parser(hpriv, job);
 		if (rc) {
 			dev_err(hdev->dev,