[PATCH V11 08/10] arm64/perf: Add struct brbe_regset helper functions

[Anshuman Khandual]

The primary abstraction level for fetching branch records from BRBE HW has
been changed as 'struct brbe_regset', which contains storage for all three
BRBE registers i.e BRBSRC, BRBTGT, BRBINF. Whether branch record processing
happens in the task sched out path, or in the PMU IRQ handling path, these
registers need to be extracted from the HW. Afterwards both live and stored
sets need to be stitched together to create final branch records set. This
adds required helper functions for such operations.

Cc: Catalin Marinas <catalin.marinas at arm.com>
Cc: Will Deacon <will at kernel.org>
Cc: Mark Rutland <mark.rutland at arm.com>
Cc: linux-arm-kernel at lists.infradead.org
Cc: linux-kernel at vger.kernel.org
Tested-by: James Clark <james.clark at arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual at arm.com>
---
 drivers/perf/arm_brbe.c | 163 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 163 insertions(+)

diff --git a/drivers/perf/arm_brbe.c b/drivers/perf/arm_brbe.c
index 484842d8cf3e..759db681d673 100644
--- a/drivers/perf/arm_brbe.c
+++ b/drivers/perf/arm_brbe.c
@@ -44,6 +44,169 @@ static void select_brbe_bank(int bank)
 	isb();
 }
 
+/*
+ * This scans over BRBE register banks and captures individual branch reocrds
+ * [BRBSRC, BRBTGT, BRBINF] into a pre-allocated 'struct brbe_regset' buffer,
+ * until an invalid one gets encountered. The caller for this function needs
+ * to ensure BRBE is an appropriate state before the records can be captured.
+ */
+static int capture_brbe_regset(struct brbe_hw_attr *brbe_attr, struct brbe_regset *buf)
+{
+	int loop1_idx1, loop1_idx2, loop2_idx1, loop2_idx2;
+	int idx, count;
+
+	loop1_idx1 = BRBE_BANK0_IDX_MIN;
+	if (brbe_attr->brbe_nr <= BRBE_BANK_MAX_ENTRIES) {
+		loop1_idx2 = brbe_attr->brbe_nr - 1;
+		loop2_idx1 = BRBE_BANK1_IDX_MIN;
+		loop2_idx2 = BRBE_BANK0_IDX_MAX;
+	} else {
+		loop1_idx2 = BRBE_BANK0_IDX_MAX;
+		loop2_idx1 = BRBE_BANK1_IDX_MIN;
+		loop2_idx2 = brbe_attr->brbe_nr - 1;
+	}
+
+	select_brbe_bank(BRBE_BANK_IDX_0);
+	for (idx = 0, count = loop1_idx1; count <= loop1_idx2; idx++, count++) {
+		buf[idx].brbinf = get_brbinf_reg(idx);
+		/*
+		 * There are no valid entries anymore on the buffer.
+		 * Abort the branch record processing to save some
+		 * cycles and also reduce the capture/process load
+		 * for the user space as well.
+		 */
+		if (brbe_invalid(buf[idx].brbinf))
+			return idx;
+
+		buf[idx].brbsrc = get_brbsrc_reg(idx);
+		buf[idx].brbtgt = get_brbtgt_reg(idx);
+	}
+
+	select_brbe_bank(BRBE_BANK_IDX_1);
+	for (count = loop2_idx1; count <= loop2_idx2; idx++, count++) {
+		buf[idx].brbinf = get_brbinf_reg(idx);
+		/*
+		 * There are no valid entries anymore on the buffer.
+		 * Abort the branch record processing to save some
+		 * cycles and also reduce the capture/process load
+		 * for the user space as well.
+		 */
+		if (brbe_invalid(buf[idx].brbinf))
+			return idx;
+
+		buf[idx].brbsrc = get_brbsrc_reg(idx);
+		buf[idx].brbtgt = get_brbtgt_reg(idx);
+	}
+	return idx;
+}
+
+static inline void copy_brbe_regset(struct brbe_regset *src, int src_idx,
+				    struct brbe_regset *dst, int dst_idx)
+{
+	dst[dst_idx].brbinf = src[src_idx].brbinf;
+	dst[dst_idx].brbsrc = src[src_idx].brbsrc;
+	dst[dst_idx].brbtgt = src[src_idx].brbtgt;
+}
+
+/*
+ * This function concatenates branch records from stored and live buffer
+ * up to maximum nr_max records and the stored buffer holds the resultant
+ * buffer. The concatenated buffer contains all the branch records from
+ * the live buffer but might contain some from stored buffer considering
+ * the maximum combined length does not exceed 'nr_max'.
+ *
+ *	Stored records	Live records
+ *	------------------------------------------------^
+ *	|	S0	|	L0	|	Newest	|
+ *	---------------------------------		|
+ *	|	S1	|	L1	|		|
+ *	---------------------------------		|
+ *	|	S2	|	L2	|		|
+ *	---------------------------------		|
+ *	|	S3	|	L3	|		|
+ *	---------------------------------		|
+ *	|	S4	|	L4	|		nr_max
+ *	---------------------------------		|
+ *	|		|	L5	|		|
+ *	---------------------------------		|
+ *	|		|	L6	|		|
+ *	---------------------------------		|
+ *	|		|	L7	|		|
+ *	---------------------------------		|
+ *	|		|		|		|
+ *	---------------------------------		|
+ *	|		|		|	Oldest	|
+ *	------------------------------------------------V
+ *
+ *
+ * S0 is the newest in the stored records, where as L7 is the oldest in
+ * the live reocords. Unless the live buffer is detetcted as being full
+ * thus potentially dropping off some older records, L7 and S0 records
+ * are contiguous in time for a user task context. The stitched buffer
+ * here represents maximum possible branch records, contiguous in time.
+ *
+ *	Stored records  Live records
+ *	------------------------------------------------^
+ *	|	L0	|	L0	|	Newest	|
+ *	---------------------------------		|
+ *	|	L0	|	L1	|		|
+ *	---------------------------------		|
+ *	|	L2	|	L2	|		|
+ *	---------------------------------		|
+ *	|	L3	|	L3	|		|
+ *	---------------------------------		|
+ *	|	L4	|	L4	|	      nr_max
+ *	---------------------------------		|
+ *	|	L5	|	L5	|		|
+ *	---------------------------------		|
+ *	|	L6	|	L6	|		|
+ *	---------------------------------		|
+ *	|	L7	|	L7	|		|
+ *	---------------------------------		|
+ *	|	S0	|		|		|
+ *	---------------------------------		|
+ *	|	S1	|		|    Oldest	|
+ *	------------------------------------------------V
+ *	|	S2	| <----|
+ *	-----------------      |
+ *	|	S3	| <----| Dropped off after nr_max
+ *	-----------------      |
+ *	|	S4	| <----|
+ *	-----------------
+ */
+static int stitch_stored_live_entries(struct brbe_regset *stored,
+				      struct brbe_regset *live,
+				      int nr_stored, int nr_live,
+				      int nr_max)
+{
+	int nr_total, nr_excess, nr_last, i;
+
+	nr_total = nr_stored + nr_live;
+	nr_excess = nr_total - nr_max;
+
+	/* Stored branch records in stitched buffer */
+	if (nr_live == nr_max)
+		nr_stored = 0;
+	else if (nr_excess > 0)
+		nr_stored -= nr_excess;
+
+	/* Stitched buffer branch records length */
+	if (nr_total > nr_max)
+		nr_last = nr_max;
+	else
+		nr_last = nr_total;
+
+	/* Move stored branch records */
+	for (i = 0; i < nr_stored; i++)
+		copy_brbe_regset(stored, i, stored, nr_last - nr_stored - 1 + i);
+
+	/* Copy live branch records */
+	for (i = 0; i < nr_live; i++)
+		copy_brbe_regset(live, i, stored, i);
+
+	return nr_last;
+}
+
 /*
  * Generic perf branch filters supported on BRBE
  *
-- 
2.25.1