drm/i915/perf: Handle non-power-of-2 reports

Some of the newer OA formats are not powers of 2. For those formats,
adjust the hw_tail accordingly when checking for new reports.

v2: (Ashutosh)
- Switch to OA_TAKEN for diff calculation
- Use OA_BUFFER_SIZE instead of the vma size
- Update comments
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-8-umesh.nerlige.ramappa@intel.com

drivers/gpu/drm/i915/i915_perf.c

@@ -534,6 +534,7 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 	bool pollin;
 	u32 hw_tail;
 	u64 now;
+	u32 partial_report_size;
 
 	/* We have to consider the (unlikely) possibility that read() errors
 	 * could result in an OA buffer reset which might reset the head and
@@ -543,10 +544,15 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 
 	hw_tail = stream->perf->ops.oa_hw_tail_read(stream);
 
-	/* The tail pointer increases in 64 byte increments,
-	 * not in report_size steps...
+	/* The tail pointer increases in 64 byte increments, not in report_size
+	 * steps. Also the report size may not be a power of 2. Compute
+	 * potentially partially landed report in the OA buffer
 	 */
-	hw_tail &= ~(report_size - 1);
+	partial_report_size = OA_TAKEN(hw_tail, stream->oa_buffer.tail);
+	partial_report_size %= report_size;
+
+	/* Subtract partial amount off the tail */
+	hw_tail = gtt_offset + OA_TAKEN(hw_tail, partial_report_size);
 
 	now = ktime_get_mono_fast_ns();
 
@@ -669,6 +675,8 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 {
 	int report_size = stream->oa_buffer.format->size;
 	struct drm_i915_perf_record_header header;
+	int report_size_partial;
+	u8 *oa_buf_end;
 
 	header.type = DRM_I915_PERF_RECORD_SAMPLE;
 	header.pad = 0;
@@ -682,8 +690,20 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 		return -EFAULT;
 	buf += sizeof(header);
 
-	if (copy_to_user(buf, report, report_size))
+	oa_buf_end = stream->oa_buffer.vaddr + OA_BUFFER_SIZE;
+	report_size_partial = oa_buf_end - report;
+
+	if (report_size_partial < report_size) {
+		if (copy_to_user(buf, report, report_size_partial))
+			return -EFAULT;
+		buf += report_size_partial;
+
+		if (copy_to_user(buf, stream->oa_buffer.vaddr,
+				 report_size - report_size_partial))
+			return -EFAULT;
+	} else if (copy_to_user(buf, report, report_size)) {
 		return -EFAULT;
+	}
 
 	(*offset) += header.size;
 
@@ -747,12 +767,11 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	 * An out of bounds or misaligned head or tail pointer implies a driver
 	 * bug since we validate + align the tail pointers we read from the
 	 * hardware and we are in full control of the head pointer which should
-	 * only be incremented by multiples of the report size (notably also
-	 * all a power of two).
+	 * only be incremented by multiples of the report size.
 	 */
 	if (drm_WARN_ONCE(&uncore->i915->drm,
-			  head > OA_BUFFER_SIZE || head % report_size ||
-			  tail > OA_BUFFER_SIZE || tail % report_size,
+			  head > OA_BUFFER_SIZE ||
+			  tail > OA_BUFFER_SIZE,
 			  "Inconsistent OA buffer pointers: head = %u, tail = %u\n",
 			  head, tail))
 		return -EIO;
@@ -766,22 +785,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		u32 ctx_id;
 		u64 reason;
 
-		/*
-		 * All the report sizes factor neatly into the buffer
-		 * size so we never expect to see a report split
-		 * between the beginning and end of the buffer.
-		 *
-		 * Given the initial alignment check a misalignment
-		 * here would imply a driver bug that would result
-		 * in an overrun.
-		 */
-		if (drm_WARN_ON(&uncore->i915->drm,
-				(OA_BUFFER_SIZE - head) < report_size)) {
-			drm_err(&uncore->i915->drm,
-				"Spurious OA head ptr: non-integral report offset\n");
-			break;
-		}
-
 		/*
 		 * The reason field includes flags identifying what
 		 * triggered this specific report (mostly timer