[PATCH v2 4/6] x86/platform/uv/BAU: Add status mmr location fields to bau_control

[Andrew Banman]

The location of the ERROR and BUSY status bits depends on the descriptor
index, i.e. the CPU, of the message. Since this index does not change,
there is no need to calculate the mmr and index location during message
processing. The less work we do in the hot path the better.

Add stats_mmr and status_index fields to bau_control and compute their
values during initialization. Update uv*_wait_completion to use these
fields rather than receiving the information as parameters.

Signed-off-by: Andrew Banman <abanman@xxxxxxx>
Acked-by: Mike Travis <mike.travis@xxxxxxx>
---
 arch/x86/include/asm/uv/uv_bau.h | 10 +++++++--
 arch/x86/platform/uv/tlb_uv.c    | 46 +++++++++++++++++++---------------------
 2 files changed, 30 insertions(+), 26 deletions(-)

diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 59ae8a7..a02019a 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -600,8 +600,12 @@ struct uvhub_desc {
 	struct socket_desc	socket[2];
 };
 
-/*
- * one per-cpu; to locate the software tables
+/**
+ * struct bau_control
+ * @status_mmr: location of status mrr, determined by uvhub_cpu
+ * @status_index: index of ERR|BUSY bits in status mrr, determined by uvhub_cpu
+ *
+ * Per-cpu control struct containing CPU topology information and BAU tuneables.
  */
 struct bau_control {
 	struct bau_desc		*descriptor_base;
@@ -619,6 +623,8 @@ struct bau_control {
 	int			timeout_tries;
 	int			ipi_attempts;
 	int			conseccompletes;
+	u64			status_mmr;
+	int			status_index;
 	bool			nobau;
 	short			baudisabled;
 	short			cpu;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index e6994fd..13a7055 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -527,11 +527,12 @@ static unsigned long uv1_read_status(unsigned long mmr_offset, int right_shift)
  * return COMPLETE, RETRY(PLUGGED or TIMEOUT) or GIVEUP
  */
 static int uv1_wait_completion(struct bau_desc *bau_desc,
-				unsigned long mmr_offset, int right_shift,
 				struct bau_control *bcp, long try)
 {
 	unsigned long descriptor_status;
 	cycles_t ttm;
+	u64 mmr_offset = bcp->status_mmr;
+	int right_shift = bcp->status_index;
 	struct ptc_stats *stat = bcp->statp;
 
 	descriptor_status = uv1_read_status(mmr_offset, right_shift);
@@ -619,11 +620,12 @@ int handle_uv2_busy(struct bau_control *bcp)
 }
 
 static int uv2_3_wait_completion(struct bau_desc *bau_desc,
-				unsigned long mmr_offset, int right_shift,
 				struct bau_control *bcp, long try)
 {
 	unsigned long descriptor_stat;
 	cycles_t ttm;
+	u64 mmr_offset = bcp->status_mmr;
+	int right_shift = bcp->status_index;
 	int desc = bcp->uvhub_cpu;
 	long busy_reps = 0;
 	struct ptc_stats *stat = bcp->statp;
@@ -684,29 +686,12 @@ static int uv2_3_wait_completion(struct bau_desc *bau_desc,
 	return FLUSH_COMPLETE;
 }
 
-/*
- * There are 2 status registers; each and array[32] of 2 bits. Set up for
- * which register to read and position in that register based on cpu in
- * current hub.
- */
 static int wait_completion(struct bau_desc *bau_desc, struct bau_control *bcp, long try)
 {
-	int right_shift;
-	unsigned long mmr_offset;
-	int desc = bcp->uvhub_cpu;
-
-	if (desc < UV_CPUS_PER_AS) {
-		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
-		right_shift = desc * UV_ACT_STATUS_SIZE;
-	} else {
-		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
-		right_shift = ((desc - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
-	}
-
 	if (bcp->uvhub_version == UV_BAU_V1)
-		return uv1_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try);
+		return uv1_wait_completion(bau_desc, bcp, try);
 	else
-		return uv2_3_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try);
+		return uv2_3_wait_completion(bau_desc, bcp, try);
 }
 
 /*
@@ -2024,8 +2009,7 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
 			struct bau_control **smasterp,
 			struct bau_control **hmasterp)
 {
-	int i;
-	int cpu;
+	int i, cpu, uvhub_cpu;
 	struct bau_control *bcp;
 
 	for (i = 0; i < sdp->num_cpus; i++) {
@@ -2054,7 +2038,21 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
 			return 1;
 		}
 		bcp->uvhub_master = *hmasterp;
-		bcp->uvhub_cpu = uv_cpu_blade_processor_id(cpu);
+		uvhub_cpu = uv_cpu_blade_processor_id(cpu);
+		bcp->uvhub_cpu = uvhub_cpu;
+
+		/*
+		 * The ERROR and BUSY status registers are located pairwise over
+		 * the STATUS_0 and STATUS_1 mmrs; each an array[32] of 2 bits.
+		 */
+		if (uvhub_cpu < UV_CPUS_PER_AS) {
+			bcp->status_mmr = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
+			bcp->status_index = uvhub_cpu * UV_ACT_STATUS_SIZE;
+		} else {
+			bcp->status_mmr = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
+			bcp->status_index = (uvhub_cpu - UV_CPUS_PER_AS)
+						* UV_ACT_STATUS_SIZE;
+		}
 
 		if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
 			pr_emerg("%d cpus per uvhub invalid\n",
-- 
1.8.2.1