Merge branch 'sa11x0-mcp-fixes' into fixes

15 files changed, 441 insertions, 187 deletions

diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index ebafe8aa8956..0c4b76ab4d8e 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -202,7 +202,6 @@ static struct irda_platform_data assabet_irda_data = {
 static struct mcp_plat_data assabet_mcp_data = {
 	.mccr0		= MCCR0_ADM,
 	.sclk_rate	= 11981000,
-	.codec		= "ucb1x00",
 };
 
 static void __init assabet_init(void)
@@ -253,17 +252,6 @@ static void __init assabet_init(void)
 	sa11x0_register_mtd(&assabet_flash_data, assabet_flash_resources,
 			    ARRAY_SIZE(assabet_flash_resources));
 	sa11x0_register_irda(&assabet_irda_data);
-
-	/*
-	 * Setup the PPC unit correctly.
-	 */
-	PPDR &= ~PPC_RXD4;
-	PPDR |= PPC_TXD4 | PPC_SCLK | PPC_SFRM;
-	PSDR |= PPC_RXD4;
-	PSDR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-	PPSR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-
-	ASSABET_BCR_set(ASSABET_BCR_CODEC_RST);
 	sa11x0_register_mcp(&assabet_mcp_data);
 }
 
diff --git a/arch/arm/mach-sa1100/cerf.c b/arch/arm/mach-sa1100/cerf.c
index d12d0f48b1dc..11bb6d0b9be3 100644
--- a/arch/arm/mach-sa1100/cerf.c
+++ b/arch/arm/mach-sa1100/cerf.c
@@ -124,23 +124,12 @@ static void __init cerf_map_io(void)
 static struct mcp_plat_data cerf_mcp_data = {
 	.mccr0		= MCCR0_ADM,
 	.sclk_rate	= 11981000,
-	.codec		= "ucb1x00",
 };
 
 static void __init cerf_init(void)
 {
 	platform_add_devices(cerf_devices, ARRAY_SIZE(cerf_devices));
 	sa11x0_register_mtd(&cerf_flash_data, &cerf_flash_resource, 1);
-
-	/*
-	 * Setup the PPC unit correctly.
-	 */
-	PPDR &= ~PPC_RXD4;
-	PPDR |= PPC_TXD4 | PPC_SCLK | PPC_SFRM;
-	PSDR |= PPC_RXD4;
-	PSDR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-	PPSR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-
 	sa11x0_register_mcp(&cerf_mcp_data);
 }
 
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index cce8763d0839..fd5652118ed1 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -27,7 +27,6 @@
 #include <linux/timer.h>
 #include <linux/gpio.h>
 #include <linux/pda_power.h>
-#include <linux/mfd/ucb1x00.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
@@ -86,15 +85,10 @@ static struct scoop_pcmcia_config collie_pcmcia_config = {
 	.num_devs	= 1,
 };
 
-static struct ucb1x00_plat_data collie_ucb1x00_data = {
-	.gpio_base	= COLLIE_TC35143_GPIO_BASE,
-};
-
 static struct mcp_plat_data collie_mcp_data = {
 	.mccr0		= MCCR0_ADM | MCCR0_ExtClk,
 	.sclk_rate	= 9216000,
-	.codec		= "ucb1x00",
-	.codec_pdata	= &collie_ucb1x00_data,
+	.gpio_base	= COLLIE_TC35143_GPIO_BASE,
 };
 
 /*
@@ -356,16 +350,6 @@ static void __init collie_init(void)
 
 	sa11x0_register_mtd(&collie_flash_data, collie_flash_resources,
 			    ARRAY_SIZE(collie_flash_resources));
-
-	/*
-	 * Setup the PPC unit correctly.
-	 */
-	PPDR &= ~PPC_RXD4;
-	PPDR |= PPC_TXD4 | PPC_SCLK | PPC_SFRM;
-	PSDR |= PPC_RXD4;
-	PSDR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-	PPSR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-
 	sa11x0_register_mcp(&collie_mcp_data);
 
 	sharpsl_save_param();
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index a7c0df6e670c..bb10ee2cb89f 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -217,15 +217,10 @@ static struct platform_device sa11x0uart3_device = {
 static struct resource sa11x0mcp_resources[] = {
 	[0] = {
 		.start	= __PREG(Ser4MCCR0),
-		.end	= __PREG(Ser4MCCR0) + 0x1C - 1,
+		.end	= __PREG(Ser4MCCR0) + 0xffff,
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= __PREG(Ser4MCCR1),
-		.end	= __PREG(Ser4MCCR1) + 0x4 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[2] = {
 		.start	= IRQ_Ser4MCP,
 		.end	= IRQ_Ser4MCP,
 		.flags	= IORESOURCE_IRQ,
diff --git a/arch/arm/mach-sa1100/include/mach/mcp.h b/arch/arm/mach-sa1100/include/mach/mcp.h
index 586cec898b35..ed1a331508a7 100644
--- a/arch/arm/mach-sa1100/include/mach/mcp.h
+++ b/arch/arm/mach-sa1100/include/mach/mcp.h
@@ -17,8 +17,6 @@ struct mcp_plat_data {
 	u32 mccr1;
 	unsigned int sclk_rate;
 	int gpio_base;
-	const char *codec;
-	void *codec_pdata;
 };
 
 #endif
diff --git a/arch/arm/mach-sa1100/lart.c b/arch/arm/mach-sa1100/lart.c
index d117ceab6215..af4e2761f3db 100644
--- a/arch/arm/mach-sa1100/lart.c
+++ b/arch/arm/mach-sa1100/lart.c
@@ -24,20 +24,10 @@
 static struct mcp_plat_data lart_mcp_data = {
 	.mccr0		= MCCR0_ADM,
 	.sclk_rate	= 11981000,
-	.codec		= "ucb1x00",
 };
 
 static void __init lart_init(void)
 {
-	/*
-	 * Setup the PPC unit correctly.
-	 */
-	PPDR &= ~PPC_RXD4;
-	PPDR |= PPC_TXD4 | PPC_SCLK | PPC_SFRM;
-	PSDR |= PPC_RXD4;
-	PSDR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-	PPSR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-
 	sa11x0_register_mcp(&lart_mcp_data);
 }
 
diff --git a/arch/arm/mach-sa1100/shannon.c b/arch/arm/mach-sa1100/shannon.c
index 748d34435b3f..318b2b766a0b 100644
--- a/arch/arm/mach-sa1100/shannon.c
+++ b/arch/arm/mach-sa1100/shannon.c
@@ -55,22 +55,11 @@ static struct resource shannon_flash_resource = {
 static struct mcp_plat_data shannon_mcp_data = {
 	.mccr0		= MCCR0_ADM,
 	.sclk_rate	= 11981000,
-	.codec		= "ucb1x00",
 };
 
 static void __init shannon_init(void)
 {
 	sa11x0_register_mtd(&shannon_flash_data, &shannon_flash_resource, 1);
-
-	/*
-	 * Setup the PPC unit correctly.
-	 */
-	PPDR &= ~PPC_RXD4;
-	PPDR |= PPC_TXD4 | PPC_SCLK | PPC_SFRM;
-	PSDR |= PPC_RXD4;
-	PSDR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-	PPSR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-
 	sa11x0_register_mcp(&shannon_mcp_data);
 }
 
diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c
index 458ececefa58..e17c04d6e324 100644
--- a/arch/arm/mach-sa1100/simpad.c
+++ b/arch/arm/mach-sa1100/simpad.c
@@ -14,7 +14,6 @@
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
-#include <linux/mfd/ucb1x00.h>
 
 #include <asm/irq.h>
 #include <mach/hardware.h>
@@ -188,15 +187,10 @@ static struct resource simpad_flash_resources [] = {
 	}
 };
 
-static struct ucb1x00_plat_data simpad_ucb1x00_data = {
-	.gpio_base	= SIMPAD_UCB1X00_GPIO_BASE,
-};
-
 static struct mcp_plat_data simpad_mcp_data = {
 	.mccr0		= MCCR0_ADM,
 	.sclk_rate	= 11981000,
-	.codec		= "ucb1300",
-	.codec_pdata	= &simpad_ucb1x00_data,
+	.gpio_base	= SIMPAD_UCB1X00_GPIO_BASE,
 };
 
 
@@ -384,16 +378,6 @@ static int __init simpad_init(void)
 
 	sa11x0_register_mtd(&simpad_flash_data, simpad_flash_resources,
 			      ARRAY_SIZE(simpad_flash_resources));
-
-	/*
-	 * Setup the PPC unit correctly.
-	 */
-	PPDR &= ~PPC_RXD4;
-	PPDR |= PPC_TXD4 | PPC_SCLK | PPC_SFRM;
-	PSDR |= PPC_RXD4;
-	PSDR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-	PPSR &= ~(PPC_TXD4 | PPC_SCLK | PPC_SFRM);
-
 	sa11x0_register_mcp(&simpad_mcp_data);
 
 	ret = platform_add_devices(devices, ARRAY_SIZE(devices));
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore
index 028079065af6..7cab8c08e6d1 100644
--- a/arch/x86/.gitignore
+++ b/arch/x86/.gitignore
@@ -1,3 +1,4 @@
 boot/compressed/vmlinux
 tools/test_get_len
+tools/insn_sanity
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6c14ecd851d0..864cc6e6ac8e 100644
--- a/arch/x86/Kconfig
+++ b/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
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index b4a3db7ce140..21f77b89e47a 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/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
 
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 8e862aaf0d90..becf47b81735 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/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 */
@@ -318,19 +319,87 @@ struct bau_msg_header {
 };
 
 /*
+ * 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);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c0dd5b603749..a62c201c97ec 100644
--- a/arch/x86/kernel/tsc.c
+++ b/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 @@ success:
 	 *
 	 * 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");
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 5b83c51c12e0..819137904428 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/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)
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 5b552198f774..9be4cff00a2d 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -157,13 +157,14 @@ static int __init uvhub_to_first_apicid(int uvhub)
  * clear of the Timeout bit (as well) will free the resource. No reply will
  * be sent (the hardware will only do one reply per message).
  */
-static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp)
+static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp,
+						int do_acknowledge)
 {
 	unsigned long dw;
 	struct bau_pq_entry *msg;
 
 	msg = mdp->msg;
-	if (!msg->canceled) {
+	if (!msg->canceled && do_acknowledge) {
 		dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec;
 		write_mmr_sw_ack(dw);
 	}
@@ -212,8 +213,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
 			if (mmr & (msg_res << UV_SW_ACK_NPENDING)) {
 				unsigned long mr;
 				/*
-				 * is the resource timed out?
-				 * make everyone ignore the cancelled message.
+				 * Is the resource timed out?
+				 * Make everyone ignore the cancelled message.
 				 */
 				msg2->canceled = 1;
 				stat->d_canceled++;
@@ -231,8 +232,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
  * Do all the things a cpu should do for a TLB shootdown message.
  * Other cpu's may come here at the same time for this message.
  */
-static void bau_process_message(struct msg_desc *mdp,
-					struct bau_control *bcp)
+static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp,
+						int do_acknowledge)
 {
 	short socket_ack_count = 0;
 	short *sp;
@@ -284,8 +285,9 @@ static void bau_process_message(struct msg_desc *mdp,
 		if (msg_ack_count == bcp->cpus_in_uvhub) {
 			/*
 			 * All cpus in uvhub saw it; reply
+			 * (unless we are in the UV2 workaround)
 			 */
-			reply_to_message(mdp, bcp);
+			reply_to_message(mdp, bcp, do_acknowledge);
 		}
 	}
 
@@ -491,27 +493,138 @@ static int uv1_wait_completion(struct bau_desc *bau_desc,
 /*
  * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register.
  */
-static unsigned long uv2_read_status(unsigned long offset, int rshft, int cpu)
+static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc)
 {
 	unsigned long descriptor_status;
 	unsigned long descriptor_status2;
 
 	descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK);
-	descriptor_status2 = (read_mmr_uv2_status() >> cpu) & 0x1UL;
+	descriptor_status2 = (read_mmr_uv2_status() >> desc) & 0x1UL;
 	descriptor_status = (descriptor_status << 1) | descriptor_status2;
 	return descriptor_status;
 }
 
+/*
+ * Return whether the status of the descriptor that is normally used for this
+ * cpu (the one indexed by its hub-relative cpu number) is busy.
+ * The status of the original 32 descriptors is always reflected in the 64
+ * bits of UVH_LB_BAU_SB_ACTIVATION_STATUS_0.
+ * The bit provided by the activation_status_2 register is irrelevant to
+ * the status if it is only being tested for busy or not busy.
+ */
+int normal_busy(struct bau_control *bcp)
+{
+	int cpu = bcp->uvhub_cpu;
+	int mmr_offset;
+	int right_shift;
+
+	mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
+	right_shift = cpu * UV_ACT_STATUS_SIZE;
+	return (((((read_lmmr(mmr_offset) >> right_shift) &
+				UV_ACT_STATUS_MASK)) << 1) == UV2H_DESC_BUSY);
+}
+
+/*
+ * Entered when a bau descriptor has gone into a permanent busy wait because
+ * of a hardware bug.
+ * Workaround the bug.
+ */
+int handle_uv2_busy(struct bau_control *bcp)
+{
+	int busy_one = bcp->using_desc;
+	int normal = bcp->uvhub_cpu;
+	int selected = -1;
+	int i;
+	unsigned long descriptor_status;
+	unsigned long status;
+	int mmr_offset;
+	struct bau_desc *bau_desc_old;
+	struct bau_desc *bau_desc_new;
+	struct bau_control *hmaster = bcp->uvhub_master;
+	struct ptc_stats *stat = bcp->statp;
+	cycles_t ttm;
+
+	stat->s_uv2_wars++;
+	spin_lock(&hmaster->uvhub_lock);
+	/* try for the original first */
+	if (busy_one != normal) {
+		if (!normal_busy(bcp))
+			selected = normal;
+	}
+	if (selected < 0) {
+		/* can't use the normal, select an alternate */
+		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
+		descriptor_status = read_lmmr(mmr_offset);
+
+		/* scan available descriptors 32-63 */
+		for (i = 0; i < UV_CPUS_PER_AS; i++) {
+			if ((hmaster->inuse_map & (1 << i)) == 0) {
+				status = ((descriptor_status >>
+						(i * UV_ACT_STATUS_SIZE)) &
+						UV_ACT_STATUS_MASK) << 1;
+				if (status != UV2H_DESC_BUSY) {
+					selected = i + UV_CPUS_PER_AS;
+					break;
+				}
+			}
+		}
+	}
+
+	if (busy_one != normal)
+		/* mark the busy alternate as not in-use */
+		hmaster->inuse_map &= ~(1 << (busy_one - UV_CPUS_PER_AS));
+
+	if (selected >= 0) {
+		/* switch to the selected descriptor */
+		if (selected != normal) {
+			/* set the selected alternate as in-use */
+			hmaster->inuse_map |=
+					(1 << (selected - UV_CPUS_PER_AS));
+			if (selected > stat->s_uv2_wars_hw)
+				stat->s_uv2_wars_hw = selected;
+		}
+		bau_desc_old = bcp->descriptor_base;
+		bau_desc_old += (ITEMS_PER_DESC * busy_one);
+		bcp->using_desc = selected;
+		bau_desc_new = bcp->descriptor_base;
+		bau_desc_new += (ITEMS_PER_DESC * selected);
+		*bau_desc_new = *bau_desc_old;
+	} else {
+		/*
+		 * All are busy. Wait for the normal one for this cpu to
+		 * free up.
+		 */
+		stat->s_uv2_war_waits++;
+		spin_unlock(&hmaster->uvhub_lock);
+		ttm = get_cycles();
+		do {
+			cpu_relax();
+		} while (normal_busy(bcp));
+		spin_lock(&hmaster->uvhub_lock);
+		/* switch to the original descriptor */
+		bcp->using_desc = normal;
+		bau_desc_old = bcp->descriptor_base;
+		bau_desc_old += (ITEMS_PER_DESC * bcp->using_desc);
+		bcp->using_desc = (ITEMS_PER_DESC * normal);
+		bau_desc_new = bcp->descriptor_base;
+		bau_desc_new += (ITEMS_PER_DESC * normal);
+		*bau_desc_new = *bau_desc_old; /* copy the entire descriptor */
+	}
+	spin_unlock(&hmaster->uvhub_lock);
+	return FLUSH_RETRY_BUSYBUG;
+}
+
 static int uv2_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;
-	int cpu = bcp->uvhub_cpu;
+	int desc = bcp->using_desc;
+	long busy_reps = 0;
 	struct ptc_stats *stat = bcp->statp;
 
-	descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+	descriptor_stat = uv2_read_status(mmr_offset, right_shift, desc);
 
 	/* spin on the status MMR, waiting for it to go idle */
 	while (descriptor_stat != UV2H_DESC_IDLE) {
@@ -522,32 +635,35 @@ static int uv2_wait_completion(struct bau_desc *bau_desc,
 		 * our message and its state will stay IDLE.
 		 */
 		if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) ||
-		    (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) ||
 		    (descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) {
 			stat->s_stimeout++;
 			return FLUSH_GIVEUP;
+		} else if (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) {
+			stat->s_strongnacks++;
+			bcp->conseccompletes = 0;
+			return FLUSH_GIVEUP;
 		} else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) {
 			stat->s_dtimeout++;
-			ttm = get_cycles();
-			/*
-			 * Our retries may be blocked by all destination
-			 * swack resources being consumed, and a timeout
-			 * pending.  In that case hardware returns the
-			 * ERROR that looks like a destination timeout.
-			 */
-			if (cycles_2_us(ttm - bcp->send_message) < timeout_us) {
-				bcp->conseccompletes = 0;
-				return FLUSH_RETRY_PLUGGED;
-			}
 			bcp->conseccompletes = 0;
 			return FLUSH_RETRY_TIMEOUT;
 		} else {
+			busy_reps++;
+			if (busy_reps > 1000000) {
+				/* not to hammer on the clock */
+				busy_reps = 0;
+				ttm = get_cycles();
+				if ((ttm - bcp->send_message) >
+					(bcp->clocks_per_100_usec)) {
+					return handle_uv2_busy(bcp);
+				}
+			}
 			/*
 			 * descriptor_stat is still BUSY
 			 */
 			cpu_relax();
 		}
-		descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+		descriptor_stat = uv2_read_status(mmr_offset, right_shift,
+									desc);
 	}
 	bcp->conseccompletes++;
 	return FLUSH_COMPLETE;
@@ -563,17 +679,17 @@ static int wait_completion(struct bau_desc *bau_desc,
 {
 	int right_shift;
 	unsigned long mmr_offset;
-	int cpu = bcp->uvhub_cpu;
+	int desc = bcp->using_desc;
 
-	if (cpu < UV_CPUS_PER_AS) {
+	if (desc < UV_CPUS_PER_AS) {
 		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
-		right_shift = cpu * UV_ACT_STATUS_SIZE;
+		right_shift = desc * UV_ACT_STATUS_SIZE;
 	} else {
 		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
-		right_shift = ((cpu - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
+		right_shift = ((desc - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
 	}
 
-	if (is_uv1_hub())
+	if (bcp->uvhub_version == 1)
 		return uv1_wait_completion(bau_desc, mmr_offset, right_shift,
 								bcp, try);
 	else
@@ -752,19 +868,22 @@ static void handle_cmplt(int completion_status, struct bau_desc *bau_desc,
  * Returns 1 if it gives up entirely and the original cpu mask is to be
  * returned to the kernel.
  */
-int uv_flush_send_and_wait(struct bau_desc *bau_desc,
-			struct cpumask *flush_mask, struct bau_control *bcp)
+int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp)
 {
 	int seq_number = 0;
 	int completion_stat = 0;
+	int uv1 = 0;
 	long try = 0;
 	unsigned long index;
 	cycles_t time1;
 	cycles_t time2;
 	struct ptc_stats *stat = bcp->statp;
 	struct bau_control *hmaster = bcp->uvhub_master;
+	struct uv1_bau_msg_header *uv1_hdr = NULL;
+	struct uv2_bau_msg_header *uv2_hdr = NULL;
+	struct bau_desc *bau_desc;
 
-	if (is_uv1_hub())
+	if (bcp->uvhub_version == 1)
 		uv1_throttle(hmaster, stat);
 
 	while (hmaster->uvhub_quiesce)
@@ -772,22 +891,39 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 
 	time1 = get_cycles();
 	do {
-		if (try == 0) {
-			bau_desc->header.msg_type = MSG_REGULAR;
+		bau_desc = bcp->descriptor_base;
+		bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
+		if (bcp->uvhub_version == 1) {
+			uv1 = 1;
+			uv1_hdr = &bau_desc->header.uv1_hdr;
+		} else
+			uv2_hdr = &bau_desc->header.uv2_hdr;
+		if ((try == 0) || (completion_stat == FLUSH_RETRY_BUSYBUG)) {
+			if (uv1)
+				uv1_hdr->msg_type = MSG_REGULAR;
+			else
+				uv2_hdr->msg_type = MSG_REGULAR;
 			seq_number = bcp->message_number++;
 		} else {
-			bau_desc->header.msg_type = MSG_RETRY;
+			if (uv1)
+				uv1_hdr->msg_type = MSG_RETRY;
+			else
+				uv2_hdr->msg_type = MSG_RETRY;
 			stat->s_retry_messages++;
 		}
 
-		bau_desc->header.sequence = seq_number;
-		index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu;
+		if (uv1)
+			uv1_hdr->sequence = seq_number;
+		else
+			uv2_hdr->sequence = seq_number;
+		index = (1UL << AS_PUSH_SHIFT) | bcp->using_desc;
 		bcp->send_message = get_cycles();
 
 		write_mmr_activation(index);
 
 		try++;
 		completion_stat = wait_completion(bau_desc, bcp, try);
+		/* UV2: wait_completion() may change the bcp->using_desc */
 
 		handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat);
 
@@ -798,6 +934,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 		}
 		cpu_relax();
 	} while ((completion_stat == FLUSH_RETRY_PLUGGED) ||
+		 (completion_stat == FLUSH_RETRY_BUSYBUG) ||
 		 (completion_stat == FLUSH_RETRY_TIMEOUT));
 
 	time2 = get_cycles();
@@ -812,6 +949,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 	record_send_stats(time1, time2, bcp, stat, completion_stat, try);
 
 	if (completion_stat == FLUSH_GIVEUP)
+		/* FLUSH_GIVEUP will fall back to using IPI's for tlb flush */
 		return 1;
 	return 0;
 }
@@ -967,7 +1105,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 		stat->s_ntargself++;
 
 	bau_desc = bcp->descriptor_base;
-	bau_desc += ITEMS_PER_DESC * bcp->uvhub_cpu;
+	bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
 	bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
 	if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes))
 		return NULL;
@@ -980,13 +1118,86 @@ const str