ntb_perf: Return results by reading the run file

Instead of having to watch logs, allow the results to be retrieved
by reading back the run file. This file will return "running" when
the test is running and nothing if no tests have been run yet.
It returns 1 line per thread, and will display an error message if the
corresponding thread returns an error.

With the above change, the pr_info calls that returned the results are
then changed to pr_debug calls.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index db4dc61..05a8705 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -123,6 +123,9 @@
 	int			src_idx;
 	void			*srcs[MAX_SRCS];
 	wait_queue_head_t       *wq;
+	int			status;
+	u64			copied;
+	u64			diff_us;
 };
 
 struct perf_ctx {
@@ -305,7 +308,7 @@
 	}
 
 	if (use_dma) {
-		pr_info("%s: All DMA descriptors submitted\n", current->comm);
+		pr_debug("%s: All DMA descriptors submitted\n", current->comm);
 		while (atomic_read(&pctx->dma_sync) != 0) {
 			if (kthread_should_stop())
 				break;
@@ -317,13 +320,16 @@
 	kdiff = ktime_sub(kstop, kstart);
 	diff_us = ktime_to_us(kdiff);
 
-	pr_info("%s: copied %llu bytes\n", current->comm, copied);
+	pr_debug("%s: copied %llu bytes\n", current->comm, copied);
 
-	pr_info("%s: lasted %llu usecs\n", current->comm, diff_us);
+	pr_debug("%s: lasted %llu usecs\n", current->comm, diff_us);
 
 	perf = div64_u64(copied, diff_us);
 
-	pr_info("%s: MBytes/s: %llu\n", current->comm, perf);
+	pr_debug("%s: MBytes/s: %llu\n", current->comm, perf);
+
+	pctx->copied = copied;
+	pctx->diff_us = diff_us;
 
 	return 0;
 }
@@ -345,7 +351,7 @@
 	int rc, node, i;
 	struct dma_chan *dma_chan = NULL;
 
-	pr_info("kthread %s starting...\n", current->comm);
+	pr_debug("kthread %s starting...\n", current->comm);
 
 	node = dev_to_node(&pdev->dev);
 
@@ -575,19 +581,44 @@
 {
 	struct perf_ctx *perf = filp->private_data;
 	char *buf;
-	ssize_t ret, out_offset;
-	int running;
+	ssize_t ret, out_off = 0;
+	struct pthr_ctx *pctx;
+	int i;
+	u64 rate;
 
 	if (!perf)
 		return 0;
 
-	buf = kmalloc(64, GFP_KERNEL);
+	buf = kmalloc(1024, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	running = mutex_is_locked(&perf->run_mutex);
-	out_offset = snprintf(buf, 64, "%d\n", running);
-	ret = simple_read_from_buffer(ubuf, count, offp, buf, out_offset);
+	if (mutex_is_locked(&perf->run_mutex)) {
+		out_off = snprintf(buf, 64, "running\n");
+		goto read_from_buf;
+	}
+
+	for (i = 0; i < MAX_THREADS; i++) {
+		pctx = &perf->pthr_ctx[i];
+
+		if (pctx->status == -ENODATA)
+			break;
+
+		if (pctx->status) {
+			out_off += snprintf(buf + out_off, 1024 - out_off,
+					    "%d: error %d\n", i,
+					    pctx->status);
+			continue;
+		}
+
+		rate = div64_u64(pctx->copied, pctx->diff_us);
+		out_off += snprintf(buf + out_off, 1024 - out_off,
+			"%d: copied %llu bytes in %llu usecs, %llu MBytes/s\n",
+			i, pctx->copied, pctx->diff_us, rate);
+	}
+
+read_from_buf:
+	ret = simple_read_from_buffer(ubuf, count, offp, buf, out_off);
 	kfree(buf);
 
 	return ret;
@@ -601,12 +632,20 @@
 	for (i = 0; i < MAX_THREADS; i++) {
 		pctx = &perf->pthr_ctx[i];
 		if (pctx->thread) {
-			kthread_stop(pctx->thread);
+			pctx->status = kthread_stop(pctx->thread);
 			pctx->thread = NULL;
 		}
 	}
 }
 
+static void perf_clear_thread_status(struct perf_ctx *perf)
+{
+	int i;
+
+	for (i = 0; i < MAX_THREADS; i++)
+		perf->pthr_ctx[i].status = -ENODATA;
+}
+
 static ssize_t debugfs_run_write(struct file *filp, const char __user *ubuf,
 				 size_t count, loff_t *offp)
 {
@@ -623,6 +662,8 @@
 	if (!mutex_trylock(&perf->run_mutex))
 		return -EBUSY;
 
+	perf_clear_thread_status(perf);
+
 	if (perf->perf_threads > MAX_THREADS) {
 		perf->perf_threads = MAX_THREADS;
 		pr_info("Reset total threads to: %u\n", MAX_THREADS);
@@ -757,6 +798,8 @@
 	if (rc)
 		goto err_ctx;
 
+	perf_clear_thread_status(perf);
+
 	return 0;
 
 err_ctx: