Merge branch 'x86-uv-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86/uv changes from Ingo Molnar:
 "UV2 BAU productization fixes.

  The BAU (Broadcast Assist Unit) is SGI's fancy out of line way on UV
  hardware to do TLB flushes, instead of the normal APIC IPI methods.
  The commits here fix / work around hangs in their latest hardware
  iteration (UV2).

  My understanding is that the main purpose of the out of line
  signalling channel is to improve scalability: the UV APIC hardware
  glue does not handle broadcasting to many CPUs very well, and this
  matters most for TLB shootdowns.

  [ I don't agree with all aspects of the current approach: in hindsight
    it would have been better to link the BAU at the IPI/APIC driver
    level instead of the TLB shootdown level, where TLB flushes are
    really just one of the uses of broadcast SMP messages.  Doing that
    would improve scalability in some other ways and it would also
    remove a few uglies from the TLB path.  It would also be nice to
    push more is_uv_system() tests into proper x86_init or x86_platform
    callbacks.  Cliff? ]"

* 'x86-uv-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/uv: Work around UV2 BAU hangs
  x86/uv: Implement UV BAU runtime enable and disable control via /proc/sgi_uv/
  x86/uv: Fix the UV BAU destination timeout period

1 files changed, 19 insertions, 9 deletions

diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 6149b476d9d..a06983cdc12 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -140,6 +140,9 @@
 #define IPI_RESET_LIMIT			1
 /* after this # consecutive successes, bump up the throttle if it was lowered */
 #define COMPLETE_THRESHOLD		5
+/* after this # of giveups (fall back to kernel IPI's) disable the use of
+   the BAU for a period of time */
+#define GIVEUP_LIMIT			100
 
 #define UV_LB_SUBNODEID			0x10
 
@@ -166,7 +169,6 @@
 #define FLUSH_RETRY_TIMEOUT		2
 #define FLUSH_GIVEUP			3
 #define FLUSH_COMPLETE			4
-#define FLUSH_RETRY_BUSYBUG		5
 
 /*
  * tuning the action when the numalink network is extremely delayed
@@ -175,7 +177,7 @@
 						   microseconds */
 #define CONGESTED_REPS			10	/* long delays averaged over
 						   this many broadcasts */
-#define CONGESTED_PERIOD		30	/* time for the bau to be
+#define DISABLED_PERIOD			10	/* time for the bau to be
 						   disabled, in seconds */
 /* see msg_type: */
 #define MSG_NOOP			0
@@ -520,6 +522,12 @@ struct ptc_stats {
 	unsigned long	s_uv2_wars;		/* uv2 workaround, perm. busy */
 	unsigned long	s_uv2_wars_hw;		/* uv2 workaround, hiwater */
 	unsigned long	s_uv2_war_waits;	/* uv2 workaround, long waits */
+	unsigned long	s_overipilimit;		/* over the ipi reset limit */
+	unsigned long	s_giveuplimit;		/* disables, over giveup limit*/
+	unsigned long	s_enters;		/* entries to the driver */
+	unsigned long	s_ipifordisabled;	/* fall back to IPI; disabled */
+	unsigned long	s_plugged;		/* plugged by h/w bug*/
+	unsigned long	s_congested;		/* giveup on long wait */
 	/* destination statistics */
 	unsigned long	d_alltlb;		/* times all tlb's on this
 						   cpu were flushed */
@@ -586,8 +594,8 @@ struct bau_control {
 	int			timeout_tries;
 	int			ipi_attempts;
 	int			conseccompletes;
-	int			baudisabled;
-	int			set_bau_off;
+	short			nobau;
+	short			baudisabled;
 	short			cpu;
 	short			osnode;
 	short			uvhub_cpu;
@@ -596,14 +604,16 @@ struct bau_control {
 	short			cpus_in_socket;
 	short			cpus_in_uvhub;
 	short			partition_base_pnode;
-	short			using_desc; /* an index, like uvhub_cpu */
-	unsigned int		inuse_map;
+	short			busy;       /* all were busy (war) */
 	unsigned short		message_number;
 	unsigned short		uvhub_quiesce;
 	short			socket_acknowledge_count[DEST_Q_SIZE];
 	cycles_t		send_message;
+	cycles_t		period_end;
+	cycles_t		period_time;
 	spinlock_t		uvhub_lock;
 	spinlock_t		queue_lock;
+	spinlock_t		disable_lock;
 	/* tunables */
 	int			max_concurr;
 	int			max_concurr_const;
@@ -614,9 +624,9 @@ struct bau_control {
 	int			complete_threshold;
 	int			cong_response_us;
 	int			cong_reps;
-	int			cong_period;
-	unsigned long		clocks_per_100_usec;
-	cycles_t		period_time;
+	cycles_t		disabled_period;
+	int			period_giveups;
+	int			giveup_limit;
 	long			period_requests;
 	struct hub_and_pnode	*thp;
 };