x86/UV: Update UV support for external NMI signals

The current UV NMI handler has not been updated for the changes
in the system NMI handler and the perf operations.  The UV NMI
handler reads an MMR in the UV Hub to check to see if the NMI
event was caused by the external 'system NMI' that the operator
can initiate on the System Mgmt Controller.

The problem arises when the perf tools are running, causing
millions of perf events per second on very large CPU count
systems.  Previously this was okay because the perf NMI handler
ran at a higher priority on the NMI call chain and if the NMI
was a perf event, it would stop calling other NMI handlers
remaining on the NMI call chain.

Now the system NMI handler calls all the handlers on the NMI
call chain including the UV NMI handler.  This causes the UV NMI
handler to read the MMRs at the same millions per second rate.
This can lead to significant performance loss and possible
system failures.  It also can cause thousands of 'Dazed and
Confused' messages being sent to the system console.  This
effectively makes perf tools unusable on UV systems.

To avoid this excessive overhead when perf tools are running,
this code has been optimized to minimize reading of the MMRs as
much as possible, by moving to the NMI_UNKNOWN notifier chain.
This chain is called only when all the users on the standard
NMI_LOCAL call chain have been called and none of them have
claimed this NMI.

There is an exception where the NMI_LOCAL notifier chain is
used.  When the perf tools are in use, it's possible that the UV
NMI was captured by some other NMI handler and then either
ignored or mistakenly processed as a perf event.  We set a
per_cpu ('ping') flag for those CPUs that ignored the initial
NMI, and then send them an IPI NMI signal.  The NMI_LOCAL
handler on each cpu does not need to read the MMR, but instead
checks the in memory flag indicating it was pinged.  There are
two module variables, 'ping_count' indicating how many requested
NMI events occurred, and 'ping_misses' indicating how many stray
NMI events.  These most likely are perf events so it shows the
overhead of the perf NMI interrupts and how many MMR reads were avoided.

This patch also minimizes the reads of the MMRs by having the
first cpu entering the NMI handler on each node set a per HUB
in-memory atomic value.  (Having a per HUB value avoids sending
lock traffic over NumaLink.)  Both types of UV NMIs from the SMI
layer are supported.

Signed-off-by: Mike Travis <travis@sgi.com>
Reviewed-by: Dimitri Sivanich <sivanich@sgi.com>
Reviewed-by: Hedi Berriche <hedi@sgi.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Jason Wessel <jason.wessel@windriver.com>
Link: http://lkml.kernel.org/r/20130923212500.353547733@asylum.americas.sgi.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 55 insertions, 2 deletions

diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 2c32df95bb78..a30836c8ac4d 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -502,8 +502,8 @@ struct uv_blade_info {
 	unsigned short	nr_online_cpus;
 	unsigned short	pnode;
 	short		memory_nid;
-	spinlock_t	nmi_lock;
-	unsigned long	nmi_count;
+	spinlock_t	nmi_lock;	/* obsolete, see uv_hub_nmi */
+	unsigned long	nmi_count;	/* obsolete, see uv_hub_nmi */
 };
 extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
@@ -576,6 +576,59 @@ static inline int uv_num_possible_blades(void)
 	return uv_possible_blades;
 }
 
+/* Per Hub NMI support */
+extern void uv_nmi_setup(void);
+
+/* BMC sets a bit this MMR non-zero before sending an NMI */
+#define UVH_NMI_MMR		UVH_SCRATCH5
+#define UVH_NMI_MMR_CLEAR	UVH_SCRATCH5_ALIAS
+#define UVH_NMI_MMR_SHIFT	63
+#define	UVH_NMI_MMR_TYPE	"SCRATCH5"
+
+/* Newer SMM NMI handler, not present in all systems */
+#define UVH_NMI_MMRX		UVH_EVENT_OCCURRED0
+#define UVH_NMI_MMRX_CLEAR	UVH_EVENT_OCCURRED0_ALIAS
+#define UVH_NMI_MMRX_SHIFT	(is_uv1_hub() ? \
+					UV1H_EVENT_OCCURRED0_EXTIO_INT0_SHFT :\
+					UVXH_EVENT_OCCURRED0_EXTIO_INT0_SHFT)
+#define	UVH_NMI_MMRX_TYPE	"EXTIO_INT0"
+
+/* Non-zero indicates newer SMM NMI handler present */
+#define UVH_NMI_MMRX_SUPPORTED	UVH_EXTIO_INT0_BROADCAST
+
+/* Indicates to BIOS that we want to use the newer SMM NMI handler */
+#define UVH_NMI_MMRX_REQ	UVH_SCRATCH5_ALIAS_2
+#define UVH_NMI_MMRX_REQ_SHIFT	62
+
+struct uv_hub_nmi_s {
+	raw_spinlock_t	nmi_lock;
+	atomic_t	in_nmi;		/* flag this node in UV NMI IRQ */
+	atomic_t	cpu_owner;	/* last locker of this struct */
+	atomic_t	read_mmr_count;	/* count of MMR reads */
+	atomic_t	nmi_count;	/* count of true UV NMIs */
+	unsigned long	nmi_value;	/* last value read from NMI MMR */
+};
+
+struct uv_cpu_nmi_s {
+	struct uv_hub_nmi_s	*hub;
+	atomic_t		state;
+	atomic_t		pinging;
+	int			queries;
+	int			pings;
+};
+
+DECLARE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
+#define uv_cpu_nmi			(__get_cpu_var(__uv_cpu_nmi))
+#define uv_hub_nmi			(uv_cpu_nmi.hub)
+#define uv_cpu_nmi_per(cpu)		(per_cpu(__uv_cpu_nmi, cpu))
+#define uv_hub_nmi_per(cpu)		(uv_cpu_nmi_per(cpu).hub)
+
+/* uv_cpu_nmi_states */
+#define	UV_NMI_STATE_OUT		0
+#define	UV_NMI_STATE_IN			1
+#define	UV_NMI_STATE_DUMP		2
+#define	UV_NMI_STATE_DUMP_DONE		3
+
 /* Update SCIR state */
 static inline void uv_set_scir_bits(unsigned char value)
 {