Merge branches 'sched-urgent-for-linus', 'perf-urgent-for-linus' and...

Merge branches 'sched-urgent-for-linus', 'perf-urgent-for-linus' and 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/accounting, proc: Fix /proc/stat interrupts sum

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  tracepoints/module: Fix disabling tracepoints with taint CRAP or OOT
  x86/kprobes: Add arch/x86/tools/insn_sanity to .gitignore
  x86/kprobes: Fix typo transferred from Intel manual

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, syscall: Need __ARCH_WANT_SYS_IPC for 32 bits
  x86, tsc: Fix SMI induced variation in quick_pit_calibrate()
  x86, opcode: ANDN and Group 17 in x86-opcode-map.txt
  x86/kconfig: Move the ZONE_DMA entry under a menu
  x86/UV2: Add accounting for BAU strong nacks
  x86/UV2: Ack BAU interrupt earlier
  x86/UV2: Remove stale no-resources test for UV2 BAU
  x86/UV2: Work around BAU bug
  x86/UV2: Fix BAU destination timeout initialization
  x86/UV2: Fix new UV2 hardware by using native UV2 broadcast mode
  x86: Get rid of dubious one-bit signed bitfield

arch/x86/.gitignore

 boot/compressed/vmlinux
 tools/test_get_len
+tools/insn_sanity
 

arch/x86/Kconfig

@@ -125,16 +125,6 @@ config HAVE_LATENCYTOP_SUPPORT
 config MMU
 	def_bool y
 
-config ZONE_DMA
-	bool "DMA memory allocation support" if EXPERT
-	default y
-	help
-	  DMA memory allocation support allows devices with less than 32-bit
-	  addressing to allocate within the first 16MB of address space.
-	  Disable if no such devices will be used.
-
-	  If unsure, say Y.
-
 config SBUS
 	bool
 
@@ -255,6 +245,16 @@ source "kernel/Kconfig.freezer"
 
 menu "Processor type and features"
 
+config ZONE_DMA
+	bool "DMA memory allocation support" if EXPERT
+	default y
+	help
+	  DMA memory allocation support allows devices with less than 32-bit
+	  addressing to allocate within the first 16MB of address space.
+	  Disable if no such devices will be used.
+
+	  If unsure, say Y.
+
 source "kernel/time/Kconfig"
 
 config SMP

arch/x86/include/asm/unistd.h

@@ -7,6 +7,7 @@
 #  include <asm/unistd_32.h>
 #  define __ARCH_WANT_IPC_PARSE_VERSION
 #  define __ARCH_WANT_STAT64
+#  define __ARCH_WANT_SYS_IPC
 #  define __ARCH_WANT_SYS_OLD_MMAP
 #  define __ARCH_WANT_SYS_OLD_SELECT
 

arch/x86/include/asm/uv/uv_bau.h

@@ -65,7 +65,7 @@
  * UV2: Bit 19 selects between
  *  (0): 10 microsecond timebase and
  *  (1): 80 microseconds
- *  we're using 655us, similar to UV1: 65 units of 10us
+ *  we're using 560us, similar to UV1: 65 units of 10us
  */
 #define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL)
 #define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (15UL)
@@ -167,6 +167,7 @@
 #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
@@ -235,10 +236,10 @@ struct bau_msg_payload {
 
 
 /*
- * Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * UV1 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
  * see table 4.2.3.0.1 in broacast_assist spec.
  */
-struct bau_msg_header {
+struct uv1_bau_msg_header {
 	unsigned int	dest_subnodeid:6;	/* must be 0x10, for the LB */
 	/* bits 5:0 */
 	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */
@@ -317,20 +318,88 @@ struct bau_msg_header {
 	/* bits 127:107 */
 };
 
+/*
+ * UV2 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * see figure 9-2 of harp_sys.pdf
+ */
+struct uv2_bau_msg_header {
+	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */
+	/* bits 14:0 */				/* in uvhub map */
+	unsigned int	dest_subnodeid:5;	/* must be 0x10, for the LB */
+	/* bits 19:15 */
+	unsigned int	rsvd_1:1;		/* must be zero */
+	/* bit 20 */
+	/* Address bits 59:21 */
+	/* bits 25:2 of address (44:21) are payload */
+	/* these next 24 bits become bytes 12-14 of msg */
+	/* bits 28:21 land in byte 12 */
+	unsigned int	replied_to:1;		/* sent as 0 by the source to
+						   byte 12 */
+	/* bit 21 */
+	unsigned int	msg_type:3;		/* software type of the
+						   message */
+	/* bits 24:22 */
+	unsigned int	canceled:1;		/* message canceled, resource
+						   is to be freed*/
+	/* bit 25 */
+	unsigned int	payload_1:3;		/* not currently used */
+	/* bits 28:26 */
+
+	/* bits 36:29 land in byte 13 */
+	unsigned int	payload_2a:3;		/* not currently used */
+	unsigned int	payload_2b:5;		/* not currently used */
+	/* bits 36:29 */
+
+	/* bits 44:37 land in byte 14 */
+	unsigned int	payload_3:8;		/* not currently used */
+	/* bits 44:37 */
+
+	unsigned int	rsvd_2:7;		/* reserved */
+	/* bits 51:45 */
+	unsigned int	swack_flag:1;		/* software acknowledge flag */
+	/* bit 52 */
+	unsigned int	rsvd_3a:3;		/* must be zero */
+	unsigned int	rsvd_3b:8;		/* must be zero */
+	unsigned int	rsvd_3c:8;		/* must be zero */
+	unsigned int	rsvd_3d:3;		/* must be zero */
+	/* bits 74:53 */
+	unsigned int	fairness:3;		/* usually zero */
+	/* bits 77:75 */
+
+	unsigned int	sequence:16;		/* message sequence number */
+	/* bits 93:78  Suppl_A  */
+	unsigned int	chaining:1;		/* next descriptor is part of
+						   this activation*/
+	/* bit 94 */
+	unsigned int	multilevel:1;		/* multi-level multicast
+						   format */
+	/* bit 95 */
+	unsigned int	rsvd_4:24;		/* ordered / source node /
+						   source subnode / aging
+						   must be zero */
+	/* bits 119:96 */
+	unsigned int	command:8;		/* message type */
+	/* bits 127:120 */
+};
+
 /*
  * The activation descriptor:
  * The format of the message to send, plus all accompanying control
  * Should be 64 bytes
  */
 struct bau_desc {
-	struct pnmask			distribution;
+	struct pnmask				distribution;
 	/*
 	 * message template, consisting of header and payload:
 	 */
-	struct bau_msg_header		header;
-	struct bau_msg_payload		payload;
+	union bau_msg_header {
+		struct uv1_bau_msg_header	uv1_hdr;
+		struct uv2_bau_msg_header	uv2_hdr;
+	} header;
+
+	struct bau_msg_payload			payload;
 };
-/*
+/* UV1:
  *   -payload--    ---------header------
  *   bytes 0-11    bits 41-56  bits 58-81
  *       A           B  (2)      C (3)
@@ -340,6 +409,16 @@ struct bau_desc {
  *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
  *   ------------payload queue-----------
  */
+/* UV2:
+ *   -payload--    ---------header------
+ *   bytes 0-11    bits 70-78  bits 21-44
+ *       A           B  (2)      C (3)
+ *
+ *            A/B/C are moved to:
+ *       A            C          B
+ *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
+ *   ------------payload queue-----------
+ */
 
 /*
  * The payload queue on the destination side is an array of these.
@@ -385,7 +464,6 @@ struct bau_pq_entry {
 struct msg_desc {
 	struct bau_pq_entry	*msg;
 	int			msg_slot;
-	int			swack_slot;
 	struct bau_pq_entry	*queue_first;
 	struct bau_pq_entry	*queue_last;
 };
@@ -405,6 +483,7 @@ struct ptc_stats {
 						   requests */
 	unsigned long	s_stimeout;		/* source side timeouts */
 	unsigned long	s_dtimeout;		/* destination side timeouts */
+	unsigned long	s_strongnacks;		/* number of strong nack's */
 	unsigned long	s_time;			/* time spent in sending side */
 	unsigned long	s_retriesok;		/* successful retries */
 	unsigned long	s_ntargcpu;		/* total number of cpu's
@@ -439,6 +518,9 @@ struct ptc_stats {
 	unsigned long	s_retry_messages;	/* retry broadcasts */
 	unsigned long	s_bau_reenabled;	/* for bau enable/disable */
 	unsigned long	s_bau_disabled;		/* for bau enable/disable */
+	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 */
 	/* destination statistics */
 	unsigned long	d_alltlb;		/* times all tlb's on this
 						   cpu were flushed */
@@ -511,9 +593,12 @@ struct bau_control {
 	short			osnode;
 	short			uvhub_cpu;
 	short			uvhub;
+	short			uvhub_version;
 	short			cpus_in_socket;
 	short			cpus_in_uvhub;
 	short			partition_base_pnode;
+	short			using_desc; /* an index, like uvhub_cpu */
+	unsigned int		inuse_map;
 	unsigned short		message_number;
 	unsigned short		uvhub_quiesce;
 	short			socket_acknowledge_count[DEST_Q_SIZE];
@@ -531,6 +616,7 @@ struct bau_control {
 	int			cong_response_us;
 	int			cong_reps;
 	int			cong_period;
+	unsigned long		clocks_per_100_usec;
 	cycles_t		period_time;
 	long			period_requests;
 	struct hub_and_pnode	*thp;
@@ -591,6 +677,11 @@ static inline void write_mmr_sw_ack(unsigned long mr)
 	uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
 }
 
+static inline void write_gmmr_sw_ack(int pnode, unsigned long mr)
+{
+	write_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
+}
+
 static inline unsigned long read_mmr_sw_ack(void)
 {
 	return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);

arch/x86/kernel/tsc.c

@@ -290,14 +290,15 @@ static inline int pit_verify_msb(unsigned char val)
 static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap)
 {
 	int count;
-	u64 tsc = 0;
+	u64 tsc = 0, prev_tsc = 0;
 
 	for (count = 0; count < 50000; count++) {
 		if (!pit_verify_msb(val))
 			break;
+		prev_tsc = tsc;
 		tsc = get_cycles();
 	}
-	*deltap = get_cycles() - tsc;
+	*deltap = get_cycles() - prev_tsc;
 	*tscp = tsc;
 
 	/*
@@ -311,9 +312,9 @@ static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *de
  * How many MSB values do we want to see? We aim for
  * a maximum error rate of 500ppm (in practice the
  * real error is much smaller), but refuse to spend
- * more than 25ms on it.
+ * more than 50ms on it.
  */
-#define MAX_QUICK_PIT_MS 25
+#define MAX_QUICK_PIT_MS 50
 #define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
 
 static unsigned long quick_pit_calibrate(void)
@@ -383,15 +384,12 @@ static unsigned long quick_pit_calibrate(void)
 	 *
 	 * As a result, we can depend on there not being
 	 * any odd delays anywhere, and the TSC reads are
-	 * reliable (within the error). We also adjust the
-	 * delta to the middle of the error bars, just
-	 * because it looks nicer.
+	 * reliable (within the error).
 	 *
 	 * kHz = ticks / time-in-seconds / 1000;
 	 * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000
 	 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000)
 	 */
-	delta += (long)(d2 - d1)/2;
 	delta *= PIT_TICK_RATE;
 	do_div(delta, i*256*1000);
 	printk("Fast TSC calibration using PIT\n");

arch/x86/lib/x86-opcode-map.txt

@@ -219,7 +219,9 @@ ab: STOS/W/D/Q Yv,rAX
 ac: LODS/B AL,Xb
 ad: LODS/W/D/Q rAX,Xv
 ae: SCAS/B AL,Yb
-af: SCAS/W/D/Q rAX,Xv
+# Note: The May 2011 Intel manual shows Xv for the second parameter of the
+# next instruction but Yv is correct
+af: SCAS/W/D/Q rAX,Yv
 # 0xb0 - 0xbf
 b0: MOV AL/R8L,Ib
 b1: MOV CL/R9L,Ib
@@ -729,8 +731,8 @@ de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
 df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
 f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2)
 f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2)
-f3: ANDN Gy,By,Ey (v)
-f4: Grp17 (1A)
+f2: ANDN Gy,By,Ey (v)
+f3: Grp17 (1A)
 f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
 f6: MULX By,Gy,rDX,Ey (F2),(v)
 f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)

fs/proc/stat.c

@@ -77,6 +77,8 @@ static int show_stat(struct seq_file *p, void *v)
 		steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
 		guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
 		guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
+		sum += kstat_cpu_irqs_sum(i);
+		sum += arch_irq_stat_cpu(i);
 
 		for (j = 0; j < NR_SOFTIRQS; j++) {
 			unsigned int softirq_stat = kstat_softirqs_cpu(j, i);

kernel/tracepoint.c

@@ -634,10 +634,11 @@ static int tracepoint_module_coming(struct module *mod)
 	int ret = 0;
 
 	/*
-	 * We skip modules that tain the kernel, especially those with different
-	 * module header (for forced load), to make sure we don't cause a crash.
+	 * We skip modules that taint the kernel, especially those with different
+	 * module headers (for forced load), to make sure we don't cause a crash.
+	 * Staging and out-of-tree GPL modules are fine.
 	 */
-	if (mod->taints)
+	if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
 		return 0;
 	mutex_lock(&tracepoints_mutex);
 	tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);