powerpc/perf/vpa-dtl: Handle the writing of perf record when aux wake up is needed

Handle the case when the aux buffer is going to be full and
data needs to be written to the data file. perf_aux_output_begin()
function checks if there is enough space depending on the values of
aux_wakeup and aux_watermark which is part of "struct perf_buffer".
Inorder to maintain where to write to aux buffer, add two fields
to "struct vpa_pmu_buf". Field "threshold" to indicate total possible
DTL entries that can be contained in aux buffer and field "full" to
indicate anytime when buffer is full. In perf_aux_output_end, there
is check to see if wake up is needed based on aux head value.

In vpa_dtl_capture_aux(), check if there is enough space to contain the
DTL data. If not, save the data for available memory and set full to true.
Set head of private aux to zero when buffer is full so that next data
will be copied to beginning of the buffer. The address used for copying
to aux is "aux_copy_buf + buf->head". So once buffer is full, set head
to zero, so that next time it will be written from start of the buffer.

Signed-off-by: Athira Rajeev <[e-mail]>
Tested-by: Tejas Manhas <[e-mail]>
Tested-by: Venkat Rao Bagalkote <[e-mail]>
Signed-off-by: Madhavan Srinivasan <[e-mail]>
Link: https://patch.msgid.link/[e-mail]

arch/powerpc/perf/vpa-dtl.c

···
 	u64     *base;
 	u64     size;
 	u64     head;
+	u64	head_size;
 	/* boot timebase and frequency needs to be saved only at once */
 	int	boottb_freq_saved;
+	u64	threshold;
+	bool	full;
 };
 
 /*
···
 	struct dtl_entry *aux_copy_buf = (struct dtl_entry *)buf->base;
 
 	/*
+	 * check if there is enough space to contain the
+	 * DTL data. If not, save the data for available
+	 * memory and set full to true.
+	 */
+	if (buf->head + *n_entries >= buf->threshold) {
+		*n_entries = buf->threshold - buf->head;
+		buf->full = 1;
+	}
+
+	/*
 	 * Copy to AUX buffer from per-thread address
 	 */
 	memcpy(aux_copy_buf + buf->head, &dtl->buf[index], *n_entries * sizeof(struct dtl_entry));
+
+	if (buf->full) {
+		/*
+		 * Set head of private aux to zero when buffer is full
+		 * so that next data will be copied to beginning of the
+		 * buffer
+		 */
+		buf->head = 0;
+		return;
+	}
 
 	buf->head += *n_entries;
 
···
 	struct vpa_pmu_buf *aux_buf;
 
 	struct vpa_dtl *dtl = &per_cpu(vpa_dtl_cpu, event->cpu);
+	u64 size;
 
 	cur_idx = be64_to_cpu(lppaca_of(event->cpu).dtl_idx);
 	last_idx = dtl->last_idx;
···
 		n_req -= read_size;
 		n_read += read_size;
 		i = 0;
+		if (aux_buf->full) {
+			size = (n_read * sizeof(struct dtl_entry));
+			if ((size +  aux_buf->head_size) > aux_buf->size) {
+				size = aux_buf->size - aux_buf->head_size;
+				perf_aux_output_end(&vpa_ctx->handle, size);
+				aux_buf->head = 0;
+				aux_buf->head_size = 0;
+			} else {
+				aux_buf->head_size += (n_read * sizeof(struct dtl_entry));
+				perf_aux_output_end(&vpa_ctx->handle, n_read * sizeof(struct dtl_entry));
+			}
+			goto out;
+		}
 	}
 
 	/* .. and now the head */
 	vpa_dtl_capture_aux(&n_req, aux_buf, dtl, i);
 
-	/* Move the aux->head to indicate size of data in aux buffer */
-	perf_aux_output_end(&vpa_ctx->handle, (n_req + n_read) * sizeof(struct dtl_entry));
+	size = ((n_req + n_read) * sizeof(struct dtl_entry));
+	if ((size +  aux_buf->head_size) > aux_buf->size) {
+		size = aux_buf->size - aux_buf->head_size;
+		perf_aux_output_end(&vpa_ctx->handle, size);
+		aux_buf->head = 0;
+		aux_buf->head_size = 0;
+	} else {
+		aux_buf->head_size += ((n_req + n_read) * sizeof(struct dtl_entry));
+		/* Move the aux->head to indicate size of data in aux buffer */
+		perf_aux_output_end(&vpa_ctx->handle, (n_req + n_read) * sizeof(struct dtl_entry));
+	}
+out:
+	aux_buf->full = 0;
 }
 
 /*
···
 
 	buf->size = nr_pages << PAGE_SHIFT;
 	buf->head = 0;
+	buf->head_size = 0;
 	buf->boottb_freq_saved = 0;
+	buf->threshold = ((buf->size - 32) / sizeof(struct dtl_entry));
 	return no_free_ptr(buf);
 }