gpu: nvgpu: debugging API update

Update the debugging APIs in nvgpu to be more coherent and less dependent
on Linux kernel APIs and data structures. The old API is maintained for
backwards compatibility but the prints themselves are changed.

The old API now prints stuff like this:

  [   46.376077] nvgpu:              gk20a_channel_suspend:3430 [DBG]  suspend channel 508
  [   46.376242] nvgpu:              gk20a_channel_suspend:3430 [DBG]  suspend channel 509
  [   46.376359] nvgpu:              gk20a_channel_suspend:3430 [DBG]  suspend channel 510
  [   46.376466] nvgpu:              gk20a_channel_suspend:3430 [DBG]  suspend channel 511
  [   46.376604] nvgpu:   gk20a_fifo_update_runlist_locked:3090 [DBG]  runlist_id : 0, switch to new buffer 0x       4003a0000
  [   46.378348] nvgpu:                  gk20a_mm_l2_flush:5259 [DBG]  l2_flush_dirty 0x2
  [   46.378562] nvgpu:                     clk_config_pll:170  [DBG]  low_PL 1(div1), high_PL 2(div2)
  [   46.378684] nvgpu:                     clk_config_pll:170  [DBG]  low_PL 8(div8), high_PL 17(div17)

Each line starts with 'nvgpu:' since this is the nvgpu driver. Then there's
the function name which is is right justified and post-fixed with a line
number. This keeps all statements lined up so long as the function name does
not exceed the length of characters alloted for function names (33 currently).
Lines are also left justified with 4 available spaces since there are currently
no source files with over 9999 lines. The type of message (DBG, WRN, ERR) is
then printed in brackets. Finally there's whatever message is to be printed.

The new API will be largely the same except there will be an additional
print of the GPU that the message has originated from in order to help debug
cases where both an iGPU and dGPU are active. Also the implicit newline
added in the legacy API has been removed. This is inline with essentially
every other print function in the C world. There are numerous places where
'\n' is added despite it not being needed which results in log files being
littered with blank lines. This makes the logs much harder to read.

Bug ...

Change-Id: I7bc87f2dbbaebf6eb6c9de1a629a0e2963e1804c
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1329487
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 130 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/common/linux/log.c b/drivers/gpu/nvgpu/common/linux/log.c
new file mode 100644
index 00000000..9dd965ec
--- /dev/null
+++ b/drivers/gpu/nvgpu/common/linux/log.c
@@ -0,0 +1,130 @@
+/*
+ * Copyright (c) 2017, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+
+#include <nvgpu/log.h>
+
+#include "gk20a/gk20a.h"
+
+/*
+ * Define a length for log buffers. This is the buffer that the 'fmt, ...' part
+ * of __nvgpu_do_log_print() prints into. This buffer lives on the stack so it
+ * needs to not be overly sized since we have limited kernel stack space. But at
+ * the same time we don't want it to be restrictive either.
+ */
+#define LOG_BUFFER_LENGTH       160
+
+/*
+ * Annoying quirk of Linux: this has to be a string literal since the printk()
+ * function and friends use the preprocessor to concatenate stuff to the start
+ * of this string when printing.
+ */
+#define LOG_FMT                 "nvgpu: %s %33s:%-4d [%s]  %s"
+
+u32 nvgpu_dbg_mask = NVGPU_DEFAULT_DBG_MASK;
+
+static const char *log_types[] = {
+        "ERR",
+        "WRN",
+        "DBG"
+};
+
+int nvgpu_log_mask_enabled(struct gk20a *g, u32 log_mask)
+{
+        return !!(g->log_mask & log_mask);
+}
+
+static inline const char *nvgpu_log_name(struct gk20a *g)
+{
+        return dev_name(g->dev);
+}
+
+#ifdef CONFIG_GK20A_TRACE_PRINTK
+static void __nvgpu_trace_printk_log(u32 trace, const char *gpu_name,
+                                     const char *func_name, int line,
+                                     enum nvgpu_log_type type, const char *log)
+{
+        trace_printk(LOG_FMT, gpu_name, func_name, line, type, log);
+}
+#endif
+
+static void __nvgpu_really_print_log(u32 trace, const char *gpu_name,
+                                     const char *func_name, int line,
+                                     enum nvgpu_log_type type, const char *log)
+{
+        const char *name = gpu_name ? gpu_name : "";
+
+#ifdef CONFIG_GK20A_TRACE_PRINTK
+        if (trace)
+                return __nvgpu_trace_printk_log(trace, name, func_name,
+                                                line, type, log);
+#else
+        const char *log_type = log_types[type];
+
+        switch (type) {
+        case DEBUG:
+                /*
+                 * We could use pr_debug() here but we control debug enablement
+                 * separately from the Linux kernel. Perhaps this is a bug in
+                 * nvgpu.
+                 */
+                pr_info(LOG_FMT, name, func_name, line, log_type, log);
+                break;
+        case WARNING:
+                pr_warn(LOG_FMT, name, func_name, line, log_type, log);
+                break;
+        case ERROR:
+                pr_err(LOG_FMT, name, func_name, line, log_type, log);
+                break;
+        }
+#endif
+}
+
+__attribute__((format (printf, 5, 6)))
+void __nvgpu_log_msg(struct gk20a *g, const char *func_name, int line,
+                     enum nvgpu_log_type type, const char *fmt, ...)
+{
+        char log[LOG_BUFFER_LENGTH];
+        va_list args;
+
+        va_start(args, fmt);
+        vsnprintf(log, LOG_BUFFER_LENGTH, fmt, args);
+        va_end(args);
+
+        __nvgpu_really_print_log(0, g ? nvgpu_log_name(g) : "",
+                                 func_name, line, type, log);
+}
+
+__attribute__((format (printf, 5, 6)))
+void __nvgpu_log_dbg(struct gk20a *g, u32 log_mask,
+                     const char *func_name, int line,
+                     const char *fmt, ...)
+{
+        char log[LOG_BUFFER_LENGTH];
+        va_list args;
+
+        if ((log_mask & g->log_mask) == 0)
+                return;
+
+        va_start(args, fmt);
+        vsnprintf(log, LOG_BUFFER_LENGTH, fmt, args);
+        va_end(args);
+
+        __nvgpu_really_print_log(g->log_trace, nvgpu_log_name(g),
+                                 func_name, line, DEBUG, log);
+}