habanalabs: maintain a list of file private data objects

This patch adds a new list to the driver's device structure. The list will
keep the file private data structures that the driver creates when a user
process opens the device.

This change is needed because it is useless to try to count how many FD
are open. Instead, track our own private data structure per open file and
once it is released, remove it from the list. As long as the list is not
empty, it means we have a user that can do something with our device.

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 11 insertions, 13 deletions

diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index 048073590965..0602d62f1127 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -914,6 +914,7 @@ struct hl_debug_params {
  * @ctx_mgr: context manager to handle multiple context for this FD.
  * @cb_mgr: command buffer manager to handle multiple buffers for this FD.
  * @debugfs_list: list of relevant ASIC debugfs.
+ * @dev_node: node in the device list of file private data
  * @refcount: number of related contexts.
  * @restore_phase_mutex: lock for context switch and restore phase.
  */
@@ -925,6 +926,7 @@ struct hl_fpriv {
 	struct hl_ctx_mgr	ctx_mgr;
 	struct hl_cb_mgr	cb_mgr;
 	struct list_head	debugfs_list;
+	struct list_head	dev_node;
 	struct kref		refcount;
 	struct mutex		restore_phase_mutex;
 };
@@ -1178,12 +1180,6 @@ struct hl_device_reset_work {
  * @cpu_accessible_dma_pool: KMD <-> ArmCP shared memory pool.
  * @asid_bitmap: holds used/available ASIDs.
  * @asid_mutex: protects asid_bitmap.
- * @fd_open_cnt_lock: lock for updating fd_open_cnt in hl_device_open. Although
- *                    fd_open_cnt is atomic, we need this lock to serialize
- *                    the open function because the driver currently supports
- *                    only a single process at a time. In addition, we need a
- *                    lock here so we can flush user processes which are opening
- *                    the device while we are trying to hard reset it
  * @send_cpu_message_lock: enforces only one message in KMD <-> ArmCP queue.
  * @debug_lock: protects critical section of setting debug mode for device
  * @asic_prop: ASIC specific immutable properties.
@@ -1199,6 +1195,9 @@ struct hl_device_reset_work {
  * @hl_debugfs: device's debugfs manager.
  * @cb_pool: list of preallocated CBs.
  * @cb_pool_lock: protects the CB pool.
+ * @fpriv_list: list of file private data structures. Each structure is created
+ *              when a user opens the device
+ * @fpriv_list_lock: protects the fpriv_list
  * @compute_ctx: current compute context executing.
  * @dram_used_mem: current DRAM memory consumption.
  * @timeout_jiffies: device CS timeout value.
@@ -1206,10 +1205,9 @@ struct hl_device_reset_work {
  *             value is saved so in case of hard-reset, KMD will restore this
  *             value and update the F/W after the re-initialization
  * @in_reset: is device in reset flow.
- * @curr_pll_profile: current PLL profile.
- * @fd_open_cnt: number of open user processes.
  * @cs_active_cnt: number of active command submissions on this device (active
  *                 means already in H/W queues)
+ * @curr_pll_profile: current PLL profile.
  * @major: habanalabs KMD major.
  * @high_pll: high PLL profile frequency.
  * @soft_reset_cnt: number of soft reset since KMD loading.
@@ -1228,7 +1226,7 @@ struct hl_device_reset_work {
  * @mmu_enable: is MMU enabled.
  * @device_cpu_disabled: is the device CPU disabled (due to timeouts)
  * @dma_mask: the dma mask that was set for this device
- * @in_debug: is device under debug. This, together with fd_open_cnt, enforces
+ * @in_debug: is device under debug. This, together with fpriv_list, enforces
  *            that only a single user is configuring the debug infrastructure.
  */
 struct hl_device {
@@ -1256,8 +1254,6 @@ struct hl_device {
 	struct gen_pool			*cpu_accessible_dma_pool;
 	unsigned long			*asid_bitmap;
 	struct mutex			asid_mutex;
-	/* TODO: remove fd_open_cnt_lock for multiple process support */
-	struct mutex			fd_open_cnt_lock;
 	struct mutex			send_cpu_message_lock;
 	struct mutex			debug_lock;
 	struct asic_fixed_properties	asic_prop;
@@ -1276,15 +1272,17 @@ struct hl_device {
 	struct list_head		cb_pool;
 	spinlock_t			cb_pool_lock;
 
+	struct list_head		fpriv_list;
+	struct mutex			fpriv_list_lock;
+
 	struct hl_ctx			*compute_ctx;
 
 	atomic64_t			dram_used_mem;
 	u64				timeout_jiffies;
 	u64				max_power;
 	atomic_t			in_reset;
-	atomic_t			curr_pll_profile;
-	atomic_t			fd_open_cnt;
 	atomic_t			cs_active_cnt;
+	enum hl_pll_frequency		curr_pll_profile;
 	u32				major;
 	u32				high_pll;
 	u32				soft_reset_cnt;