Merge branch 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6

* 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6: (35 commits)
  [S390] time: remove unused code
  [S390] zcore: Add prefix registers to dump header
  [S390] correct vdso version string
  [S390] add support for compressed kernels
  [S390] Define new s390 ELF note sections in elf.h
  [S390] codepage conversion of kernel parameter line
  [S390] seq_file: convert drivers/s390/
  [S390] add z9-ec/z10 instruction to kernel disassembler
  [S390] dasd: correct offline processing
  [S390] dasd: fix refcounting.
  [S390] dasd: fix online/offline race
  [S390] use kprobes_built_in() in mm/fault code
  [S390] bug: use relative pointers in bug table entries
  [S390] Cleanup struct _lowcore usage and defines.
  [S390] free_initmem: reduce code duplication
  [S390] Replace ENOTSUPP usage with EOPNOTSUPP
  [S390] spinlock: check virtual cpu running status
  [S390] sysinfo: fix SYSIB 3,2,2 structure
  [S390] add MACHINE_IS_LPAR flag
  [S390] qdio: optimize cache line usage of struct qdio_irq
  ...

1 files changed, 56 insertions, 36 deletions

diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index 44f2f6a97f3..48aa0647432 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -208,18 +208,27 @@ struct qdio_dev_perf_stat {
 	unsigned int eqbs_partial;
 	unsigned int sqbs;
 	unsigned int sqbs_partial;
+} ____cacheline_aligned;
+
+struct qdio_queue_perf_stat {
+	/*
+	 * Sorted into order-2 buckets: 1, 2-3, 4-7, ... 64-127, 128.
+	 * Since max. 127 SBALs are scanned reuse entry for 128 as queue full
+	 * aka 127 SBALs found.
+	 */
+	unsigned int nr_sbals[8];
+	unsigned int nr_sbal_error;
+	unsigned int nr_sbal_nop;
+	unsigned int nr_sbal_total;
 };
 
 struct qdio_input_q {
 	/* input buffer acknowledgement flag */
 	int polling;
-
 	/* first ACK'ed buffer */
 	int ack_start;
-
 	/* how much sbals are acknowledged with qebsm */
 	int ack_count;
-
 	/* last time of noticing incoming data */
 	u64 timestamp;
 };
@@ -227,40 +236,27 @@ struct qdio_input_q {
 struct qdio_output_q {
 	/* PCIs are enabled for the queue */
 	int pci_out_enabled;
-
 	/* IQDIO: output multiple buffers (enhanced SIGA) */
 	int use_enh_siga;
-
 	/* timer to check for more outbound work */
 	struct timer_list timer;
 };
 
+/*
+ * Note on cache alignment: grouped slsb and write mostly data at the beginning
+ * sbal[] is read-only and starts on a new cacheline followed by read mostly.
+ */
 struct qdio_q {
 	struct slsb slsb;
+
 	union {
 		struct qdio_input_q in;
 		struct qdio_output_q out;
 	} u;
 
-	/* queue number */
-	int nr;
-
-	/* bitmask of queue number */
-	int mask;
-
-	/* input or output queue */
-	int is_input_q;
-
-	/* list of thinint input queues */
-	struct list_head entry;
-
-	/* upper-layer program handler */
-	qdio_handler_t (*handler);
-
 	/*
 	 * inbound: next buffer the program should check for
-	 * outbound: next buffer to check for having been processed
-	 * by the card
+	 * outbound: next buffer to check if adapter processed it
 	 */
 	int first_to_check;
 
@@ -273,16 +269,32 @@ struct qdio_q {
 	/* number of buffers in use by the adapter */
 	atomic_t nr_buf_used;
 
-	struct qdio_irq *irq_ptr;
-	struct dentry *debugfs_q;
-	struct tasklet_struct tasklet;
-
 	/* error condition during a data transfer */
 	unsigned int qdio_error;
 
-	struct sl *sl;
-	struct qdio_buffer *sbal[QDIO_MAX_BUFFERS_PER_Q];
+	struct tasklet_struct tasklet;
+	struct qdio_queue_perf_stat q_stats;
+
+	struct qdio_buffer *sbal[QDIO_MAX_BUFFERS_PER_Q] ____cacheline_aligned;
+
+	/* queue number */
+	int nr;
+
+	/* bitmask of queue number */
+	int mask;
+
+	/* input or output queue */
+	int is_input_q;
+
+	/* list of thinint input queues */
+	struct list_head entry;
 
+	/* upper-layer program handler */
+	qdio_handler_t (*handler);
+
+	struct dentry *debugfs_q;
+	struct qdio_irq *irq_ptr;
+	struct sl *sl;
 	/*
 	 * Warning: Leave this member at the end so it won't be cleared in
 	 * qdio_fill_qs. A page is allocated under this pointer and used for
@@ -317,12 +329,8 @@ struct qdio_irq {
 	struct qdio_ssqd_desc ssqd_desc;
 	void (*orig_handler) (struct ccw_device *, unsigned long, struct irb *);
 
-	struct qdio_dev_perf_stat perf_stat;
 	int perf_stat_enabled;
-	/*
-	 * Warning: Leave these members together at the end so they won't be
-	 * cleared in qdio_setup_irq.
-	 */
+
 	struct qdr *qdr;
 	unsigned long chsc_page;
 
@@ -331,6 +339,7 @@ struct qdio_irq {
 
 	debug_info_t *debug_area;
 	struct mutex setup_mutex;
+	struct qdio_dev_perf_stat perf_stat;
 };
 
 /* helper functions */
@@ -341,9 +350,20 @@ struct qdio_irq {
 	(irq->qib.qfmt == QDIO_IQDIO_QFMT || \
 	 css_general_characteristics.aif_osa)
 
-#define qperf(qdev,attr)	qdev->perf_stat.attr
-#define qperf_inc(q,attr)	if (q->irq_ptr->perf_stat_enabled) \
-					q->irq_ptr->perf_stat.attr++
+#define qperf(__qdev, __attr)	((__qdev)->perf_stat.(__attr))
+
+#define qperf_inc(__q, __attr)						\
+({									\
+	struct qdio_irq *qdev = (__q)->irq_ptr;				\
+	if (qdev->perf_stat_enabled)					\
+		(qdev->perf_stat.__attr)++;				\
+})
+
+static inline void account_sbals_error(struct qdio_q *q, int count)
+{
+	q->q_stats.nr_sbal_error += count;
+	q->q_stats.nr_sbal_total += count;
+}
 
 /* the highest iqdio queue is used for multicast */
 static inline int multicast_outbound(struct qdio_q *q)