drm/amd/display: Add control mechanism for FPU utilization

DC invokes DC_FPU_START/END in multiple parts of the code; this can
create a situation where we invoke this FPU operation in a nested way or
exit too early. For avoiding this situation, this commit adds a
mechanism where dc_fpu_begin/end manages the access to
kernel_fpu_begin/end.

Change since V3:
- Rebase

Change since V2:
- Christian: Do not use this_cpu_* between get/put_cpu_ptr().

Change since V1:
- Use a better variable names
- Use get_cpu_ptr and put_cpu_ptr to better balance preemption enable
and disable

Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Anson Jacob <Anson.Jacob@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Hersen Wu <hersenxs.wu@amd.com>
Cc: Aric Cyr <aric.cyr@amd.com>
Cc: Jun Lei <jun.lei@amd.com>
Cc: Dmytro Laktyushkin <dmytro.laktyushkin@amd.com>
Cc: Qingqing Zhuo <qingqing.zhuo@amd.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h

@@ -638,23 +638,26 @@ TRACE_EVENT(amdgpu_refresh_rate_track,
 );
 
 TRACE_EVENT(dcn_fpu,
-	    TP_PROTO(bool begin, const char *function, const int line),
-	    TP_ARGS(begin, function, line),
+	    TP_PROTO(bool begin, const char *function, const int line, const int recursion_depth),
+	    TP_ARGS(begin, function, line, recursion_depth),
 
 	    TP_STRUCT__entry(
 			     __field(bool, begin)
 			     __field(const char *, function)
 			     __field(int, line)
+			     __field(int, recursion_depth)
 	    ),
 	    TP_fast_assign(
 			   __entry->begin = begin;
 			   __entry->function = function;
 			   __entry->line = line;
+			   __entry->recursion_depth = recursion_depth;
 	    ),
-	    TP_printk("%s()+%d: %s",
+	    TP_printk("%s: recursion_depth: %d: %s()+%d:",
+		      __entry->begin ? "begin" : "end",
+		      __entry->recursion_depth,
 		      __entry->function,
-		      __entry->line,
-		      __entry->begin ? "begin" : "end"
+		      __entry->line
 	    )
 );
 

drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c

@@ -33,6 +33,19 @@
 #include <asm/cputable.h>
 #endif
 
+/**
+ * DOC: DC FPU manipulation overview
+ *
+ * DC core uses FPU operations in multiple parts of the code, which requires a
+ * more specialized way to manage these areas' entrance. To fulfill this
+ * requirement, we created some wrapper functions that encapsulate
+ * kernel_fpu_begin/end to better fit our need in the display component. In
+ * summary, in this file, you can find functions related to FPU operation
+ * management.
+ */
+
+static DEFINE_PER_CPU(int, fpu_recursion_depth);
+
 /**
  * dc_fpu_begin - Enables FPU protection
  * @function_name: A string containing the function name for debug purposes
@@ -48,8 +61,12 @@
  */
 void dc_fpu_begin(const char *function_name, const int line)
 {
-	TRACE_DCN_FPU(true, function_name, line);
+	int *pcpu;
+
+	pcpu = get_cpu_ptr(&fpu_recursion_depth);
+	*pcpu += 1;
 
+	if (*pcpu == 1) {
 #if defined(CONFIG_X86)
 		kernel_fpu_begin();
 #elif defined(CONFIG_PPC64)
@@ -64,6 +81,10 @@ void dc_fpu_begin(const char *function_name, const int line)
 			enable_kernel_fp();
 		}
 #endif
+	}
+
+	TRACE_DCN_FPU(true, function_name, line, *pcpu);
+	put_cpu_ptr(&fpu_recursion_depth);
 }
 
 /**
@@ -78,7 +99,11 @@ void dc_fpu_begin(const char *function_name, const int line)
  */
 void dc_fpu_end(const char *function_name, const int line)
 {
-	TRACE_DCN_FPU(false, function_name, line);
+	int *pcpu;
+
+	pcpu = get_cpu_ptr(&fpu_recursion_depth);
+	*pcpu -= 1;
+	if (*pcpu <= 0) {
 #if defined(CONFIG_X86)
 		kernel_fpu_end();
 #elif defined(CONFIG_PPC64)
@@ -93,4 +118,8 @@ void dc_fpu_end(const char *function_name, const int line)
 			preempt_enable();
 		}
 #endif
+	}
+
+	TRACE_DCN_FPU(false, function_name, line, *pcpu);
+	put_cpu_ptr(&fpu_recursion_depth);
 }

drivers/gpu/drm/amd/display/dc/dc_trace.h

@@ -38,5 +38,5 @@
 #define TRACE_DCN_CLOCK_STATE(dcn_clocks) \
 	trace_amdgpu_dm_dc_clocks_state(dcn_clocks)
 
-#define TRACE_DCN_FPU(begin, function, line) \
-	trace_dcn_fpu(begin, function, line)
+#define TRACE_DCN_FPU(begin, function, line, ref_count) \
+	trace_dcn_fpu(begin, function, line, ref_count)