Merge branch 'for_2.6.40/pm-cleanup' of ssh://master.kernel.org/pub/scm/linux/kernel/git/khilman/linux-omap-pm into omap-for-linus

Makefile

@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 39
-EXTRAVERSION = -rc7
+EXTRAVERSION =
 NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*

arch/alpha/include/asm/unistd.h

@@ -452,10 +452,14 @@
 #define __NR_fanotify_init		494
 #define __NR_fanotify_mark		495
 #define __NR_prlimit64			496
+#define __NR_name_to_handle_at		497
+#define __NR_open_by_handle_at		498
+#define __NR_clock_adjtime		499
+#define __NR_syncfs			500
 
 #ifdef __KERNEL__
 
-#define NR_SYSCALLS			497
+#define NR_SYSCALLS			501
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR

arch/alpha/kernel/systbls.S

@@ -498,23 +498,27 @@ sys_call_table:
 	.quad sys_ni_syscall			/* sys_timerfd */
 	.quad sys_eventfd
 	.quad sys_recvmmsg
-	.quad sys_fallocate				/* 480 */
+	.quad sys_fallocate			/* 480 */
 	.quad sys_timerfd_create
 	.quad sys_timerfd_settime
 	.quad sys_timerfd_gettime
 	.quad sys_signalfd4
-	.quad sys_eventfd2				/* 485 */
+	.quad sys_eventfd2			/* 485 */
 	.quad sys_epoll_create1
 	.quad sys_dup3
 	.quad sys_pipe2
 	.quad sys_inotify_init1
-	.quad sys_preadv				/* 490 */
+	.quad sys_preadv			/* 490 */
 	.quad sys_pwritev
 	.quad sys_rt_tgsigqueueinfo
 	.quad sys_perf_event_open
 	.quad sys_fanotify_init
-	.quad sys_fanotify_mark				/* 495 */
+	.quad sys_fanotify_mark			/* 495 */
 	.quad sys_prlimit64
+	.quad sys_name_to_handle_at
+	.quad sys_open_by_handle_at
+	.quad sys_clock_adjtime
+	.quad sys_syncfs			/* 500 */
 
 	.size sys_call_table, . - sys_call_table
 	.type sys_call_table, @object

arch/alpha/kernel/time.c

@@ -375,8 +375,7 @@ static struct clocksource clocksource_rpcc = {
 
 static inline void register_rpcc_clocksource(long cycle_freq)
 {
-	clocksource_calc_mult_shift(&clocksource_rpcc, cycle_freq, 4);
+	clocksource_register_hz(&clocksource_rpcc, cycle_freq);
-	clocksource_register(&clocksource_rpcc);
 }
 #else /* !CONFIG_SMP */
 static inline void register_rpcc_clocksource(long cycle_freq)

arch/arm/mach-omap2/board-3430sdp.c

@@ -59,24 +59,6 @@
 
 #define TWL4030_MSECURE_GPIO 22
 
-/* FIXME: These values need to be updated based on more profiling on 3430sdp*/
-static struct cpuidle_params omap3_cpuidle_params_table[] = {
-	/* C1 */
-	{1, 2, 2, 5},
-	/* C2 */
-	{1, 10, 10, 30},
-	/* C3 */
-	{1, 50, 50, 300},
-	/* C4 */
-	{1, 1500, 1800, 4000},
-	/* C5 */
-	{1, 2500, 7500, 12000},
-	/* C6 */
-	{1, 3000, 8500, 15000},
-	/* C7 */
-	{1, 10000, 30000, 300000},
-};
-
 static uint32_t board_keymap[] = {
 	KEY(0, 0, KEY_LEFT),
 	KEY(0, 1, KEY_RIGHT),
@@ -800,7 +782,6 @@ static void __init omap_3430sdp_init(void)
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
 	omap_board_config = sdp3430_config;
 	omap_board_config_size = ARRAY_SIZE(sdp3430_config);
-	omap3_pm_init_cpuidle(omap3_cpuidle_params_table);
 	omap3430_i2c_init();
 	omap_display_init(&sdp3430_dss_data);
 	if (omap_rev() > OMAP3430_REV_ES1_0)

arch/arm/mach-omap2/board-rx51.c

@@ -58,21 +58,25 @@ static struct platform_device leds_gpio = {
 	},
 };
 
+/*
+ * cpuidle C-states definition override from the default values.
+ * The 'exit_latency' field is the sum of sleep and wake-up latencies.
+ */
 static struct cpuidle_params rx51_cpuidle_params[] = {
 	/* C1 */
-	{1, 110, 162, 5},
+	{110 + 162, 5 , 1},
 	/* C2 */
-	{1, 106, 180, 309},
+	{106 + 180, 309, 1},
 	/* C3 */
-	{0, 107, 410, 46057},
+	{107 + 410, 46057, 0},
 	/* C4 */
-	{0, 121, 3374, 46057},
+	{121 + 3374, 46057, 0},
 	/* C5 */
-	{1, 855, 1146, 46057},
+	{855 + 1146, 46057, 1},
 	/* C6 */
-	{0, 7580, 4134, 484329},
+	{7580 + 4134, 484329, 0},
 	/* C7 */
-	{1, 7505, 15274, 484329},
+	{7505 + 15274, 484329, 1},
 };
 
 static struct omap_lcd_config rx51_lcd_config = {

arch/arm/mach-omap2/cpuidle34xx.c

@@ -36,36 +36,6 @@
 
 #ifdef CONFIG_CPU_IDLE
 
-#define OMAP3_MAX_STATES 7
-#define OMAP3_STATE_C1 0 /* C1 - MPU WFI + Core active */
-#define OMAP3_STATE_C2 1 /* C2 - MPU WFI + Core inactive */
-#define OMAP3_STATE_C3 2 /* C3 - MPU CSWR + Core inactive */
-#define OMAP3_STATE_C4 3 /* C4 - MPU OFF + Core iactive */
-#define OMAP3_STATE_C5 4 /* C5 - MPU RET + Core RET */
-#define OMAP3_STATE_C6 5 /* C6 - MPU OFF + Core RET */
-#define OMAP3_STATE_C7 6 /* C7 - MPU OFF + Core OFF */
-
-#define OMAP3_STATE_MAX OMAP3_STATE_C7
-
-#define CPUIDLE_FLAG_CHECK_BM	0x10000	/* use omap3_enter_idle_bm() */
-
-struct omap3_processor_cx {
-	u8 valid;
-	u8 type;
-	u32 sleep_latency;
-	u32 wakeup_latency;
-	u32 mpu_state;
-	u32 core_state;
-	u32 threshold;
-	u32 flags;
-	const char *desc;
-};
-
-struct omap3_processor_cx omap3_power_states[OMAP3_MAX_STATES];
-struct omap3_processor_cx current_cx_state;
-struct powerdomain *mpu_pd, *core_pd, *per_pd;
-struct powerdomain *cam_pd;
-
 /*
  * The latencies/thresholds for various C states have
  * to be configured from the respective board files.
@@ -75,27 +45,31 @@ struct powerdomain *cam_pd;
  */
 static struct cpuidle_params cpuidle_params_table[] = {
 	/* C1 */
-	{1, 2, 2, 5},
+	{2 + 2, 5, 1},
 	/* C2 */
-	{1, 10, 10, 30},
+	{10 + 10, 30, 1},
 	/* C3 */
-	{1, 50, 50, 300},
+	{50 + 50, 300, 1},
 	/* C4 */
-	{1, 1500, 1800, 4000},
+	{1500 + 1800, 4000, 1},
 	/* C5 */
-	{1, 2500, 7500, 12000},
+	{2500 + 7500, 12000, 1},
 	/* C6 */
-	{1, 3000, 8500, 15000},
+	{3000 + 8500, 15000, 1},
 	/* C7 */
-	{1, 10000, 30000, 300000},
+	{10000 + 30000, 300000, 1},
 };
+#define OMAP3_NUM_STATES ARRAY_SIZE(cpuidle_params_table)
 
-static int omap3_idle_bm_check(void)
+/* Mach specific information to be recorded in the C-state driver_data */
-{
+struct omap3_idle_statedata {
-	if (!omap3_can_sleep())
+	u32 mpu_state;
-		return 1;
+	u32 core_state;
-	return 0;
+	u8 valid;
-}
+};
+struct omap3_idle_statedata omap3_idle_data[OMAP3_NUM_STATES];
+
+struct powerdomain *mpu_pd, *core_pd, *per_pd, *cam_pd;
 
 static int _cpuidle_allow_idle(struct powerdomain *pwrdm,
 				struct clockdomain *clkdm)
@@ -122,12 +96,10 @@ static int _cpuidle_deny_idle(struct powerdomain *pwrdm,
 static int omap3_enter_idle(struct cpuidle_device *dev,
 			struct cpuidle_state *state)
 {
-	struct omap3_processor_cx *cx = cpuidle_get_statedata(state);
+	struct omap3_idle_statedata *cx = cpuidle_get_statedata(state);
 	struct timespec ts_preidle, ts_postidle, ts_idle;
 	u32 mpu_state = cx->mpu_state, core_state = cx->core_state;
 
-	current_cx_state = *cx;
-
 	/* Used to keep track of the total time in idle */
 	getnstimeofday(&ts_preidle);
 
@@ -140,7 +112,8 @@ static int omap3_enter_idle(struct cpuidle_device *dev,
 	if (omap_irq_pending() || need_resched())
 		goto return_sleep_time;
 
-	if (cx->type == OMAP3_STATE_C1) {
+	/* Deny idle for C1 */
+	if (state == &dev->states[0]) {
 		pwrdm_for_each_clkdm(mpu_pd, _cpuidle_deny_idle);
 		pwrdm_for_each_clkdm(core_pd, _cpuidle_deny_idle);
 	}
@@ -148,7 +121,8 @@ static int omap3_enter_idle(struct cpuidle_device *dev,
 	/* Execute ARM wfi */
 	omap_sram_idle();
 
-	if (cx->type == OMAP3_STATE_C1) {
+	/* Re-allow idle for C1 */
+	if (state == &dev->states[0]) {
 		pwrdm_for_each_clkdm(mpu_pd, _cpuidle_allow_idle);
 		pwrdm_for_each_clkdm(core_pd, _cpuidle_allow_idle);
 	}
@@ -164,41 +138,53 @@ return_sleep_time:
 }
 
 /**
- * next_valid_state - Find next valid c-state
+ * next_valid_state - Find next valid C-state
  * @dev: cpuidle device
- * @state: Currently selected c-state
+ * @state: Currently selected C-state
  *
  * If the current state is valid, it is returned back to the caller.
  * Else, this function searches for a lower c-state which is still
- * valid (as defined in omap3_power_states[]).
+ * valid.
+ *
+ * A state is valid if the 'valid' field is enabled and
+ * if it satisfies the enable_off_mode condition.
  */
 static struct cpuidle_state *next_valid_state(struct cpuidle_device *dev,
-						struct cpuidle_state *curr)
+					      struct cpuidle_state *curr)
 {
 	struct cpuidle_state *next = NULL;
-	struct omap3_processor_cx *cx;
+	struct omap3_idle_statedata *cx = cpuidle_get_statedata(curr);
+	u32 mpu_deepest_state = PWRDM_POWER_RET;
+	u32 core_deepest_state = PWRDM_POWER_RET;
 
-	cx = (struct omap3_processor_cx *)cpuidle_get_statedata(curr);
+	if (enable_off_mode) {
+		mpu_deepest_state = PWRDM_POWER_OFF;
+		/*
+		 * Erratum i583: valable for ES rev < Es1.2 on 3630.
+		 * CORE OFF mode is not supported in a stable form, restrict
+		 * instead the CORE state to RET.
+		 */
+		if (!IS_PM34XX_ERRATUM(PM_SDRC_WAKEUP_ERRATUM_i583))
+			core_deepest_state = PWRDM_POWER_OFF;
+	}
 
 	/* Check if current state is valid */
-	if (cx->valid) {
+	if ((cx->valid) &&
+	    (cx->mpu_state >= mpu_deepest_state) &&
+	    (cx->core_state >= core_deepest_state)) {
 		return curr;
 	} else {
-		u8 idx = OMAP3_STATE_MAX;
+		int idx = OMAP3_NUM_STATES - 1;
 
-		/*
+		/* Reach the current state starting at highest C-state */
-		 * Reach the current state starting at highest C-state
+		for (; idx >= 0; idx--) {
-		 */
-		for (; idx >= OMAP3_STATE_C1; idx--) {
 			if (&dev->states[idx] == curr) {
 				next = &dev->states[idx];
 				break;
 			}
 		}
 
-		/*
+		/* Should never hit this condition */
-		 * Should never hit this condition.
-		 */
 		WARN_ON(next == NULL);
 
 		/*
@@ -206,17 +192,17 @@ static struct cpuidle_state *next_valid_state(struct cpuidle_device *dev,
 		 * Start search from the next (lower) state.
 		 */
 		idx--;
-		for (; idx >= OMAP3_STATE_C1; idx--) {
+		for (; idx >= 0; idx--) {
-			struct omap3_processor_cx *cx;
-
 			cx = cpuidle_get_statedata(&dev->states[idx]);
-			if (cx->valid) {
+			if ((cx->valid) &&
+			    (cx->mpu_state >= mpu_deepest_state) &&
+			    (cx->core_state >= core_deepest_state)) {
 				next = &dev->states[idx];
 				break;
 			}
 		}
 		/*
-		 * C1 and C2 are always valid.
+		 * C1 is always valid.
 		 * So, no need to check for 'next==NULL' outside this loop.
 		 */
 	}
@@ -229,36 +215,22 @@ static struct cpuidle_state *next_valid_state(struct cpuidle_device *dev,
  * @dev: cpuidle device
  * @state: The target state to be programmed
  *
- * Used for C states with CPUIDLE_FLAG_CHECK_BM flag set. This
+ * This function checks for any pending activity and then programs
- * function checks for any pending activity and then programs the
+ * the device to the specified or a safer state.
- * device to the specified or a safer state.
  */
 static int omap3_enter_idle_bm(struct cpuidle_device *dev,
 			       struct cpuidle_state *state)
 {
-	struct cpuidle_state *new_state = next_valid_state(dev, state);
+	struct cpuidle_state *new_state;
-	u32 core_next_state, per_next_state = 0, per_saved_state = 0;
+	u32 core_next_state, per_next_state = 0, per_saved_state = 0, cam_state;
-	u32 cam_state;
+	struct omap3_idle_statedata *cx;
-	struct omap3_processor_cx *cx;
 	int ret;
 
-	if ((state->flags & CPUIDLE_FLAG_CHECK_BM) && omap3_idle_bm_check()) {
+	if (!omap3_can_sleep()) {
-		BUG_ON(!dev->safe_state);
 		new_state = dev->safe_state;
 		goto select_state;
 	}
 
-	cx = cpuidle_get_statedata(state);
-	core_next_state = cx->core_state;
-
-	/*
-	 * FIXME: we currently manage device-specific idle states
-	 *        for PER and CORE in combination with CPU-specific
-	 *        idle states.  This is wrong, and device-specific
-	 *        idle management needs to be separated out into 
-	 *        its own code.
-	 */
-
 	/*
 	 * Prevent idle completely if CAM is active.
 	 * CAM does not have wakeup capability in OMAP3.
@@ -269,10 +241,20 @@ static int omap3_enter_idle_bm(struct cpuidle_device *dev,
 		goto select_state;
 	}
 
+	/*
+	 * FIXME: we currently manage device-specific idle states
+	 *        for PER and CORE in combination with CPU-specific
+	 *        idle states.  This is wrong, and device-specific
+	 *        idle management needs to be separated out into
+	 *        its own code.
+	 */
+
 	/*
 	 * Prevent PER off if CORE is not in retention or off as this
 	 * would disable PER wakeups completely.
 	 */
+	cx = cpuidle_get_statedata(state);
+	core_next_state = cx->core_state;
 	per_next_state = per_saved_state = pwrdm_read_next_pwrst(per_pd);
 	if ((per_next_state == PWRDM_POWER_OFF) &&
 	    (core_next_state > PWRDM_POWER_RET))
@@ -282,6 +264,8 @@ static int omap3_enter_idle_bm(struct cpuidle_device *dev,
 	if (per_next_state != per_saved_state)
 		pwrdm_set_next_pwrst(per_pd, per_next_state);
 
+	new_state = next_valid_state(dev, state);
+
 select_state:
 	dev->last_state = new_state;
 	ret = omap3_enter_idle(dev, new_state);
@@ -295,31 +279,6 @@ select_state:
 
 DEFINE_PER_CPU(struct cpuidle_device, omap3_idle_dev);
 
-/**
- * omap3_cpuidle_update_states() - Update the cpuidle states
- * @mpu_deepest_state:	Enable states up to and including this for mpu domain
- * @core_deepest_state:	Enable states up to and including this for core domain
- *
- * This goes through the list of states available and enables and disables the
- * validity of C states based on deepest state that can be achieved for the
- * variable domain
- */
-void omap3_cpuidle_update_states(u32 mpu_deepest_state, u32 core_deepest_state)
-{
-	int i;
-
-	for (i = OMAP3_STATE_C1; i < OMAP3_MAX_STATES; i++) {
-		struct omap3_processor_cx *cx = &omap3_power_states[i];
-
-		if ((cx->mpu_state >= mpu_deepest_state) &&
-		    (cx->core_state >= core_deepest_state)) {
-			cx->valid = 1;
-		} else {
-			cx->valid = 0;
-		}
-	}
-}
-
 void omap3_pm_init_cpuidle(struct cpuidle_params *cpuidle_board_params)
 {
 	int i;
@@ -327,212 +286,109 @@ void omap3_pm_init_cpuidle(struct cpuidle_params *cpuidle_board_params)
 	if (!cpuidle_board_params)
 		return;
 
-	for (i = OMAP3_STATE_C1; i < OMAP3_MAX_STATES; i++) {
+	for (i = 0; i < OMAP3_NUM_STATES; i++) {
-		cpuidle_params_table[i].valid =
+		cpuidle_params_table[i].valid =	cpuidle_board_params[i].valid;
-			cpuidle_board_params[i].valid;
+		cpuidle_params_table[i].exit_latency =
-		cpuidle_params_table[i].sleep_latency =
+			cpuidle_board_params[i].exit_latency;
-			cpuidle_board_params[i].sleep_latency;
+		cpuidle_params_table[i].target_residency =
-		cpuidle_params_table[i].wake_latency =
+			cpuidle_board_params[i].target_residency;
-			cpuidle_board_params[i].wake_latency;
-		cpuidle_params_table[i].threshold =
-			cpuidle_board_params[i].threshold;
 	}
 	return;
 }
 
-/* omap3_init_power_states - Initialises the OMAP3 specific C states.
- *
- * Below is the desciption of each C state.
- * 	C1 . MPU WFI + Core active
- *	C2 . MPU WFI + Core inactive
- *	C3 . MPU CSWR + Core inactive
- *	C4 . MPU OFF + Core inactive
- *	C5 . MPU CSWR + Core CSWR
- *	C6 . MPU OFF + Core CSWR
- *	C7 . MPU OFF + Core OFF
- */
-void omap_init_power_states(void)
-{
-	/* C1 . MPU WFI + Core active */
-	omap3_power_states[OMAP3_STATE_C1].valid =
-			cpuidle_params_table[OMAP3_STATE_C1].valid;
-	omap3_power_states[OMAP3_STATE_C1].type = OMAP3_STATE_C1;
-	omap3_power_states[OMAP3_STATE_C1].sleep_latency =
-			cpuidle_params_table[OMAP3_STATE_C1].sleep_latency;
-	omap3_power_states[OMAP3_STATE_C1].wakeup_latency =
-			cpuidle_params_table[OMAP3_STATE_C1].wake_latency;
-	omap3_power_states[OMAP3_STATE_C1].threshold =
-			cpuidle_params_table[OMAP3_STATE_C1].threshold;
-	omap3_power_states[OMAP3_STATE_C1].mpu_state = PWRDM_POWER_ON;
-	omap3_power_states[OMAP3_STATE_C1].core_state = PWRDM_POWER_ON;
-	omap3_power_states[OMAP3_STATE_C1].flags = CPUIDLE_FLAG_TIME_VALID;
-	omap3_power_states[OMAP3_STATE_C1].desc = "MPU ON + CORE ON";
-
-	/* C2 . MPU WFI + Core inactive */
-	omap3_power_states[OMAP3_STATE_C2].valid =
-			cpuidle_params_table[OMAP3_STATE_C2].valid;
-	omap3_power_states[OMAP3_STATE_C2].type = OMAP3_STATE_C2;
-	omap3_power_states[OMAP3_STATE_C2].sleep_latency =
-			cpuidle_params_table[OMAP3_STATE_C2].sleep_latency;
-	omap3_power_states[OMAP3_STATE_C2].wakeup_latency =
-			cpuidle_params_table[OMAP3_STATE_C2].wake_latency;
-	omap3_power_states[OMAP3_STATE_C2].threshold =
-			cpuidle_params_table[OMAP3_STATE_C2].threshold;
-	omap3_power_states[OMAP3_STATE_C2].mpu_state = PWRDM_POWER_ON;
-	omap3_power_states[OMAP3_STATE_C2].core_state = PWRDM_POWER_ON;
-	omap3_power_states[OMAP3_STATE_C2].flags = CPUIDLE_FLAG_TIME_VALID |
-				CPUIDLE_FLAG_CHECK_BM;
-	omap3_power_states[OMAP3_STATE_C2].desc = "MPU ON + CORE ON";
-
-	/* C3 . MPU CSWR + Core inactive */
-	omap3_power_states[OMAP3_STATE_C3].valid =
-			cpuidle_params_table[OMAP3_STATE_C3].valid;
-	omap3_power_states[OMAP3_STATE_C3].type = OMAP3_STATE_C3;
-	omap3_power_states[OMAP3_STATE_C3].sleep_latency =
-			cpuidle_params_table[OMAP3_STATE_C3].sleep_latency;
-	omap3_power_states[OMAP3_STATE_C3].wakeup_latency =
-			cpuidle_params_table[OMAP3_STATE_C3].wake_latency;
-	omap3_power_states[OMAP3_STATE_C3].threshold =
-			cpuidle_params_table[OMAP3_STATE_C3].threshold;
-	omap3_power_states[OMAP3_STATE_C3].mpu_state = PWRDM_POWER_RET;
-	omap3_power_states[OMAP3_STATE_C3].core_state = PWRDM_POWER_ON;
-	omap3_power_states[OMAP3_STATE_C3].flags = CPUIDLE_FLAG_TIME_VALID |
-				CPUIDLE_FLAG_CHECK_BM;
-	omap3_power_states[OMAP3_STATE_C3].desc = "MPU RET + CORE ON";
-
-	/* C4 . MPU OFF + Core inactive */
-	omap3_power_states[OMAP3_STATE_C4].valid =
-			cpuidle_params_table[OMAP3_STATE_C4].valid;
-	omap3_power_states[OMAP3_STATE_C4].type = OMAP3_STATE_C4;
-	omap3_power_states[OMAP3_STATE_C4].sleep_latency =
-			cpuidle_params_table[OMAP3_STATE_C4].sleep_latency;
-	omap3_power_states[OMAP3_STATE_C4].wakeup_latency =
-			cpuidle_params_table[OMAP3_STATE_C4].wake_latency;
-	omap3_power_states[OMAP3_STATE_C4].threshold =
-			cpuidle_params_table[OMAP3_STATE_C4].threshold;
-	omap3_power_states[OMAP3_STATE_C4].mpu_state = PWRDM_POWER_OFF;
-	omap3_power_states[OMAP3_STATE_C4].core_state = PWRDM_POWER_ON;
-	omap3_power_states[OMAP3_STATE_C4].flags = CPUIDLE_FLAG_TIME_VALID |
-				CPUIDLE_FLAG_CHECK_BM;
-	omap3_power_states[OMAP3_STATE_C4].desc = "MPU OFF + CORE ON";
-
-	/* C5 . MPU CSWR + Core CSWR*/
-	omap3_power_states[OMAP3_STATE_C5].valid =
-			cpuidle_params_table[OMAP3_STATE_C5].valid;
-	omap3_power_states[OMAP3_STATE_C5].type = OMAP3_STATE_C5;
-	omap3_power_states[OMAP3_STATE_C5].sleep_latency =
-			cpuidle_params_table[OMAP3_STATE_C5].sleep_latency;
-	omap3_power_states[OMAP3_STATE_C5].wakeup_latency =
-			cpuidle_params_table[OMAP3_STATE_C5].wake_latency;
-	omap3_power_states[OMAP3_STATE_C5].threshold =
-			cpuidle_params_table[OMAP3_STATE_C5].threshold;
-	omap3_power_states[OMAP3_STATE_C5].mpu_state = PWRDM_POWER_RET;
-	omap3_power_states[OMAP3_STATE_C5].core_state = PWRDM_POWER_RET;
-	omap3_power_states[OMAP3_STATE_C5].flags = CPUIDLE_FLAG_TIME_VALID |
-				CPUIDLE_FLAG_CHECK_BM;
-	omap3_power_states[OMAP3_STATE_C5].desc = "MPU RET + CORE RET";
-
-	/* C6 . MPU OFF + Core CSWR */
-	omap3_power_states[OMAP3_STATE_C6].valid =
-			cpuidle_params_table[OMAP3_STATE_C6].valid;
-	omap3_power_states[OMAP3_STATE_C6].type = OMAP3_STATE_C6;
-	omap3_power_states[OMAP3_STATE_C6].sleep_latency =
-			cpuidle_params_table[OMAP3_STATE_C6].sleep_latency;
-	omap3_power_states[OMAP3_STATE_C6].wakeup_latency =
-			cpuidle_params_table[OMAP3_STATE_C6].wake_latency;
-	omap3_power_states[OMAP3_STATE_C6].threshold =
-			cpuidle_params_table[OMAP3_STATE_C6].threshold;
-	omap3_power_states[OMAP3_STATE_C6].mpu_state = PWRDM_POWER_OFF;
-	omap3_power_states[OMAP3_STATE_C6].core_state = PWRDM_POWER_RET;
-	omap3_power_states[OMAP3_STATE_C6].flags = CPUIDLE_FLAG_TIME_VALID |
-				CPUIDLE_FLAG_CHECK_BM;
-	omap3_power_states[OMAP3_STATE_C6].desc = "MPU OFF + CORE RET";
-
-	/* C7 . MPU OFF + Core OFF */
-	omap3_power_states[OMAP3_STATE_C7].valid =
-			cpuidle_params_table[OMAP3_STATE_C7].valid;
-	omap3_power_states[OMAP3_STATE_C7].type = OMAP3_STATE_C7;
-	omap3_power_states[OMAP3_STATE_C7].sleep_latency =
-			cpuidle_params_table[OMAP3_STATE_C7].sleep_latency;
-	omap3_power_states[OMAP3_STATE_C7].wakeup_latency =
-			cpuidle_params_table[OMAP3_STATE_C7].wake_latency;
-	omap3_power_states[OMAP3_STATE_C7].threshold =
-			cpuidle_params_table[OMAP3_STATE_C7].threshold;
-	omap3_power_states[OMAP3_STATE_C7].mpu_state = PWRDM_POWER_OFF;
-	omap3_power_states[OMAP3_STATE_C7].core_state = PWRDM_POWER_OFF;
-	omap3_power_states[OMAP3_STATE_C7].flags = CPUIDLE_FLAG_TIME_VALID |
-				CPUIDLE_FLAG_CHECK_BM;
-	omap3_power_states[OMAP3_STATE_C7].desc = "MPU OFF + CORE OFF";
-
-	/*
-	 * Erratum i583: implementation for ES rev < Es1.2 on 3630. We cannot
-	 * enable OFF mode in a stable form for previous revisions.
-	 * we disable C7 state as a result.
-	 */
-	if (IS_PM34XX_ERRATUM(PM_SDRC_WAKEUP_ERRATUM_i583)) {
-		omap3_power_states[OMAP3_STATE_C7].valid = 0;
-		cpuidle_params_table[OMAP3_STATE_C7].valid = 0;
-		pr_warn("%s: core off state C7 disabled due to i583\n",
-				__func__);
-	}
-}
-
 struct cpuidle_driver omap3_idle_driver = {
 	.name = 	"omap3_idle",
 	.owner = 	THIS_MODULE,
 };
 
+/* Helper to fill the C-state common data and register the driver_data */
+static inline struct omap3_idle_statedata *_fill_cstate(
+					struct cpuidle_device *dev,
+					int idx, const char *descr)
+{
+	struct omap3_idle_statedata *cx = &omap3_idle_data[idx];
+	struct cpuidle_state *state = &dev->states[idx];
+
+	state->exit_latency	= cpuidle_params_table[idx].exit_latency;
+	state->target_residency	= cpuidle_params_table[idx].target_residency;
+	state->flags		= CPUIDLE_FLAG_TIME_VALID;
+	state->enter		= omap3_enter_idle_bm;
+	cx->valid		= cpuidle_params_table[idx].valid;
+	sprintf(state->name, "C%d", idx + 1);
+	strncpy(state->desc, descr, CPUIDLE_DESC_LEN);
+	cpuidle_set_statedata(state, cx);
+
+	return cx;
+}
+
 /**
  * omap3_idle_init - Init routine for OMAP3 idle
  *
- * Registers the OMAP3 specific cpuidle driver with the cpuidle
+ * Registers the OMAP3 specific cpuidle driver to the cpuidle
  * framework with the valid set of states.
  */
 int __init omap3_idle_init(void)
 {
-	int i, count = 0;
-	struct omap3_processor_cx *cx;
-	struct cpuidle_state *state;
 	struct cpuidle_device *dev;
+	struct omap3_idle_statedata *cx;
 
 	mpu_pd = pwrdm_lookup("mpu_pwrdm");
 	core_pd = pwrdm_lookup("core_pwrdm");
 	per_pd = pwrdm_lookup("per_pwrdm");
 	cam_pd = pwrdm_lookup("cam_pwrdm");
 
-	omap_init_power_states();
 	cpuidle_register_driver(&omap3_idle_driver);
-
 	dev = &per_cpu(omap3_idle_dev, smp_processor_id());
 
-	for (i = OMAP3_STATE_C1; i < OMAP3_MAX_STATES; i++) {
+	/* C1 . MPU WFI + Core active */
-		cx = &omap3_power_states[i];
+	cx = _fill_cstate(dev, 0, "MPU ON + CORE ON");
-		state = &dev->states[count];
+	(&dev->states[0])->enter = omap3_enter_idle;
+	dev->safe_state = &dev->states[0];
+	cx->valid = 1;	/* C1 is always valid */
+	cx->mpu_state = PWRDM_POWER_ON;
+	cx->core_state = PWRDM_POWER_ON;
 
-		if (!cx->valid)
+	/* C2 . MPU WFI + Core inactive */
-			continue;
+	cx = _fill_cstate(dev, 1, "MPU ON + CORE ON");
-		cpuidle_set_statedata(state, cx);
+	cx->mpu_state = PWRDM_POWER_ON;
-		state->exit_latency = cx->sleep_latency + cx->wakeup_latency;
+	cx->core_state = PWRDM_POWER_ON;
-		state->target_residency = cx->threshold;
+
-		state->flags = cx->flags;
+	/* C3 . MPU CSWR + Core inactive */
-		state->enter = (state->flags & CPUIDLE_FLAG_CHECK_BM) ?
+	cx = _fill_cstate(dev, 2, "MPU RET + CORE ON");
-			omap3_enter_idle_bm : omap3_enter_idle;
+	cx->mpu_state = PWRDM_POWER_RET;
-		if (cx->type == OMAP3_STATE_C1)
+	cx->core_state = PWRDM_POWER_ON;
-			dev->safe_state = state;
+
-		sprintf(state->name, "C%d", count+1);
+	/* C4 . MPU OFF + Core inactive */
-		strncpy(state->desc, cx->desc, CPUIDLE_DESC_LEN);
+	cx = _fill_cstate(dev, 3, "MPU OFF + CORE ON");
-		count++;
+	cx->mpu_state = PWRDM_POWER_OFF;
+	cx->core_state = PWRDM_POWER_ON;
+
+	/* C5 . MPU RET + Core RET */
+	cx = _fill_cstate(dev, 4, "MPU RET + CORE RET");
+	cx->mpu_state = PWRDM_POWER_RET;
+	cx->core_state = PWRDM_POWER_RET;
+
+	/* C6 . MPU OFF + Core RET */
+	cx = _fill_cstate(dev, 5, "MPU OFF + CORE RET");
+	cx->mpu_state = PWRDM_POWER_OFF;
+	cx->core_state = PWRDM_POWER_RET;
+
+	/* C7 . MPU OFF + Core OFF */
+	cx = _fill_cstate(dev, 6, "MPU OFF + CORE OFF");
+	/*
+	 * Erratum i583: implementation for ES rev < Es1.2 on 3630. We cannot
+	 * enable OFF mode in a stable form for previous revisions.
+	 * We disable C7 state as a result.
+	 */
+	if (IS_PM34XX_ERRATUM(PM_SDRC_WAKEUP_ERRATUM_i583)) {
+		cx->valid = 0;
+		pr_warn("%s: core off state C7 disabled due to i583\n",
+			__func__);
 	}
+	cx->mpu_state = PWRDM_POWER_OFF;
+	cx->core_state = PWRDM_POWER_OFF;
 
-	if (!count)
+	dev->state_count = OMAP3_NUM_STATES;
-		return -EINVAL;
-	dev->state_count = count;
-
-	if (enable_off_mode)
-		omap3_cpuidle_update_states(PWRDM_POWER_OFF, PWRDM_POWER_OFF);
-	else
-		omap3_cpuidle_update_states(PWRDM_POWER_RET, PWRDM_POWER_RET);
-
 	if (cpuidle_register_device(dev)) {
 		printk(KERN_ERR "%s: CPUidle register device failed\n",
 		       __func__);

arch/arm/mach-omap2/pm.h

@@ -36,11 +36,16 @@ static inline int omap4_opp_init(void)
 }
 #endif
 
+/*
+ * cpuidle mach specific parameters
+ *
+ * The board code can override the default C-states definition using
+ * omap3_pm_init_cpuidle
+ */
 struct cpuidle_params {
-	u8  valid;
+	u32 exit_latency;	/* exit_latency = sleep + wake-up latencies */
-	u32 sleep_latency;
+	u32 target_residency;
-	u32 wake_latency;
+	u8 valid;		/* validates the C-state */
-	u32 threshold;
 };
 
 #if defined(CONFIG_PM) && defined(CONFIG_CPU_IDLE)
@@ -73,10 +78,6 @@ extern u32 sleep_while_idle;
 #define sleep_while_idle 0
 #endif
 
-#if defined(CONFIG_CPU_IDLE)
-extern void omap3_cpuidle_update_states(u32, u32);
-#endif
-
 #if defined(CONFIG_PM_DEBUG) && defined(CONFIG_DEBUG_FS)
 extern void pm_dbg_update_time(struct powerdomain *pwrdm, int prev);
 extern int pm_dbg_regset_save(int reg_set);

arch/arm/mach-omap2/pm34xx.c

@@ -779,18 +779,6 @@ void omap3_pm_off_mode_enable(int enable)
 	else
 		state = PWRDM_POWER_RET;
 
-#ifdef CONFIG_CPU_IDLE
-	/*
-	 * Erratum i583: implementation for ES rev < Es1.2 on 3630. We cannot
-	 * enable OFF mode in a stable form for previous revisions, restrict
-	 * instead to RET
-	 */
-	if (IS_PM34XX_ERRATUM(PM_SDRC_WAKEUP_ERRATUM_i583))
-		omap3_cpuidle_update_states(state, PWRDM_POWER_RET);
-	else
-		omap3_cpuidle_update_states(state, state);
-#endif
-
 	list_for_each_entry(pwrst, &pwrst_list, node) {
 		if (IS_PM34XX_ERRATUM(PM_SDRC_WAKEUP_ERRATUM_i583) &&
 				pwrst->pwrdm == core_pwrdm &&
@@ -895,8 +883,6 @@ static int __init omap3_pm_init(void)
 
 	pm_errata_configure();
 
-	printk(KERN_ERR "Power Management for TI OMAP3.\n");
-
 	/* XXX prcm_setup_regs needs to be before enabling hw
 	 * supervised mode for powerdomains */
 	prcm_setup_regs();

arch/mips/ar7/gpio.c

@@ -325,9 +325,7 @@ int __init ar7_gpio_init(void)
 		size = 0x1f;
 	}
 
-	gpch->regs = ioremap_nocache(AR7_REGS_GPIO,
+	gpch->regs = ioremap_nocache(AR7_REGS_GPIO, size);
-					AR7_REGS_GPIO + 0x10);
-
 	if (!gpch->regs) {
 		printk(KERN_ERR "%s: failed to ioremap regs\n",
 					gpch->chip.label);

arch/mips/include/asm/dma-mapping.h

@@ -5,7 +5,9 @@
 #include <asm/cache.h>
 #include <asm-generic/dma-coherent.h>
 
+#ifndef CONFIG_SGI_IP27	/* Kludge to fix 2.6.39 build for IP27 */
 #include <dma-coherence.h>
+#endif
 
 extern struct dma_map_ops *mips_dma_map_ops;
 

arch/mips/kernel/traps.c

@@ -374,7 +374,8 @@ void __noreturn die(const char *str, struct pt_regs *regs)
 	unsigned long dvpret = dvpe();
 #endif /* CONFIG_MIPS_MT_SMTC */
 
-	notify_die(DIE_OOPS, str, regs, 0, regs_to_trapnr(regs), SIGSEGV);
+	if (notify_die(DIE_OOPS, str, regs, 0, regs_to_trapnr(regs), SIGSEGV) == NOTIFY_STOP)
+		sig = 0;
 
 	console_verbose();
 	spin_lock_irq(&die_lock);
@@ -383,9 +384,6 @@ void __noreturn die(const char *str, struct pt_regs *regs)
 	mips_mt_regdump(dvpret);
 #endif /* CONFIG_MIPS_MT_SMTC */
 
-	if (notify_die(DIE_OOPS, str, regs, 0, regs_to_trapnr(regs), SIGSEGV) == NOTIFY_STOP)
-		sig = 0;
-
 	printk("%s[#%d]:\n", str, ++die_counter);
 	show_registers(regs);
 	add_taint(TAINT_DIE);

arch/mips/rb532/gpio.c

@@ -185,7 +185,7 @@ int __init rb532_gpio_init(void)
 	struct resource *r;
 
 	r = rb532_gpio_reg0_res;
-	rb532_gpio_chip->regbase = ioremap_nocache(r->start, r->end - r->start);
+	rb532_gpio_chip->regbase = ioremap_nocache(r->start, resource_size(r));
 
 	if (!rb532_gpio_chip->regbase) {
 		printk(KERN_ERR "rb532: cannot remap GPIO register 0\n");

arch/powerpc/platforms/83xx/suspend.c

@@ -318,17 +318,20 @@ static const struct platform_suspend_ops mpc83xx_suspend_ops = {
 	.end = mpc83xx_suspend_end,
 };
 
+static struct of_device_id pmc_match[];
 static int pmc_probe(struct platform_device *ofdev)
 {
+	const struct of_device_id *match;
 	struct device_node *np = ofdev->dev.of_node;
 	struct resource res;
 	struct pmc_type *type;
 	int ret = 0;
 
-	if (!ofdev->dev.of_match)
+	match = of_match_device(pmc_match, &ofdev->dev);
+	if (!match)
 		return -EINVAL;
 
-	type = ofdev->dev.of_match->data;
+	type = match->data;
 
 	if (!of_device_is_available(np))
 		return -ENODEV;

arch/powerpc/sysdev/fsl_msi.c

@@ -304,8 +304,10 @@ static int __devinit fsl_msi_setup_hwirq(struct fsl_msi *msi,
 	return 0;
 }
 
+static const struct of_device_id fsl_of_msi_ids[];
 static int __devinit fsl_of_msi_probe(struct platform_device *dev)
 {
+	const struct of_device_id *match;
 	struct fsl_msi *msi;
 	struct resource res;
 	int err, i, j, irq_index, count;
@@ -316,9 +318,10 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev)
 	u32 offset;
 	static const u32 all_avail[] = { 0, NR_MSI_IRQS };
 
-	if (!dev->dev.of_match)
+	match = of_match_device(fsl_of_msi_ids, &dev->dev);
+	if (!match)
 		return -EINVAL;
-	features = dev->dev.of_match->data;
+	features = match->data;
 
 	printk(KERN_DEBUG "Setting up Freescale MSI support\n");
 

arch/sparc/kernel/apc.c

@@ -165,7 +165,7 @@ static int __devinit apc_probe(struct platform_device *op)
 	return 0;
 }
 
-static struct of_device_id __initdata apc_match[] = {
+static struct of_device_id apc_match[] = {
 	{
 		.name = APC_OBPNAME,
 	},

arch/sparc/kernel/pci_sabre.c

@@ -452,8 +452,10 @@ static void __devinit sabre_pbm_init(struct pci_pbm_info *pbm,
 	sabre_scan_bus(pbm, &op->dev);
 }
 
+static const struct of_device_id sabre_match[];
 static int __devinit sabre_probe(struct platform_device *op)
 {
+	const struct of_device_id *match;
 	const struct linux_prom64_registers *pr_regs;
 	struct device_node *dp = op->dev.of_node;
 	struct pci_pbm_info *pbm;
@@ -463,7 +465,8 @@ static int __devinit sabre_probe(struct platform_device *op)
 	const u32 *vdma;
 	u64 clear_irq;
 
-	hummingbird_p = op->dev.of_match && (op->dev.of_match->data != NULL);
+	match = of_match_device(sabre_match, &op->dev);
+	hummingbird_p = match && (match->data != NULL);
 	if (!hummingbird_p) {
 		struct device_node *cpu_dp;
 

arch/sparc/kernel/pci_schizo.c

@@ -1458,11 +1458,15 @@ out_err:
 	return err;
 }
 
+static const struct of_device_id schizo_match[];
 static int __devinit schizo_probe(struct platform_device *op)
 {
-	if (!op->dev.of_match)
+	const struct of_device_id *match;
+
+	match = of_match_device(schizo_match, &op->dev);
+	if (!match)
 		return -EINVAL;
-	return __schizo_init(op, (unsigned long) op->dev.of_match->data);
+	return __schizo_init(op, (unsigned long)match->data);
 }
 
 /* The ordering of this table is very important.  Some Tomatillo

arch/sparc/kernel/pmc.c

@@ -69,7 +69,7 @@ static int __devinit pmc_probe(struct platform_device *op)
 	return 0;
 }
 
-static struct of_device_id __initdata pmc_match[] = {
+static struct of_device_id pmc_match[] = {
 	{
 		.name = PMC_OBPNAME,
 	},

arch/sparc/kernel/smp_32.c

@@ -53,6 +53,7 @@ cpumask_t smp_commenced_mask = CPU_MASK_NONE;
 void __cpuinit smp_store_cpu_info(int id)
 {
 	int cpu_node;
+	int mid;
 
 	cpu_data(id).udelay_val = loops_per_jiffy;
 
@@ -60,10 +61,13 @@ void __cpuinit smp_store_cpu_info(int id)
 	cpu_data(id).clock_tick = prom_getintdefault(cpu_node,
 						     "clock-frequency", 0);
 	cpu_data(id).prom_node = cpu_node;
-	cpu_data(id).mid = cpu_get_hwmid(cpu_node);
+	mid = cpu_get_hwmid(cpu_node);
 
-	if (cpu_data(id).mid < 0)
+	if (mid < 0) {
-		panic("No MID found for CPU%d at node 0x%08d", id, cpu_node);
+		printk(KERN_NOTICE "No MID found for CPU%d at node 0x%08d", id, cpu_node);
+		mid = 0;
+	}
+	cpu_data(id).mid = mid;
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)

arch/sparc/kernel/time_32.c

@@ -168,7 +168,7 @@ static int __devinit clock_probe(struct platform_device *op)
 	return 0;
 }
 
-static struct of_device_id __initdata clock_match[] = {
+static struct of_device_id clock_match[] = {
 	{
 		.name = "eeprom",
 	},

arch/sparc/lib/checksum_32.S

@@ -289,10 +289,16 @@ cc_end_cruft:
 
 	/* Also, handle the alignment code out of band. */
 cc_dword_align:
-	cmp	%g1, 6
+	cmp	%g1, 16
-	bl,a	ccte
+	bge	1f
+	 srl	%g1, 1, %o3
+2:	cmp	%o3, 0
+	be,a	ccte
 	 andcc	%g1, 0xf, %o3
-	andcc	%o0, 0x1, %g0
+	andcc	%o3, %o0, %g0	! Check %o0 only (%o1 has the same last 2 bits)
+	be,a	2b
+	 srl	%o3, 1, %o3
+1:	andcc	%o0, 0x1, %g0
 	bne	ccslow
 	 andcc	%o0, 0x2, %g0
 	be	1f

arch/um/os-Linux/util.c

@@ -5,6 +5,7 @@
 
 #include <stdio.h>
 #include <stdlib.h>
+#include <unistd.h>
 #include <errno.h>
 #include <signal.h>
 #include <string.h>
@@ -75,6 +76,26 @@ void setup_hostinfo(char *buf, int len)
 		 host.release, host.version, host.machine);
 }
 
+/*
+ * We cannot use glibc's abort(). It makes use of tgkill() which
+ * has no effect within UML's kernel threads.
+ * After that glibc would execute an invalid instruction to kill
+ * the calling process and UML crashes with SIGSEGV.
+ */
+static inline void __attribute__ ((noreturn)) uml_abort(void)
+{
+	sigset_t sig;
+
+	fflush(NULL);
+
+	if (!sigemptyset(&sig) && !sigaddset(&sig, SIGABRT))
+		sigprocmask(SIG_UNBLOCK, &sig, 0);
+
+	for (;;)
+		if (kill(getpid(), SIGABRT) < 0)
+			exit(127);
+}
+
 void os_dump_core(void)
 {
 	int pid;
@@ -116,5 +137,5 @@ void os_dump_core(void)
 	while ((pid = waitpid(-1, NULL, WNOHANG | __WALL)) > 0)
 		os_kill_ptraced_process(pid, 0);
 
-	abort();
+	uml_abort();
 }

arch/x86/include/asm/apicdef.h

@@ -78,6 +78,7 @@
 #define		APIC_DEST_LOGICAL	0x00800
 #define		APIC_DEST_PHYSICAL	0x00000
 #define		APIC_DM_FIXED		0x00000
+#define		APIC_DM_FIXED_MASK	0x00700
 #define		APIC_DM_LOWEST		0x00100
 #define		APIC_DM_SMI		0x00200
 #define		APIC_DM_REMRD		0x00300

arch/x86/include/asm/pgtable_types.h

@@ -299,6 +299,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 /* Install a pte for a particular vaddr in kernel space. */
 void set_pte_vaddr(unsigned long vaddr, pte_t pte);
 
+extern void native_pagetable_reserve(u64 start, u64 end);
 #ifdef CONFIG_X86_32
 extern void native_pagetable_setup_start(pgd_t *base);
 extern void native_pagetable_setup_done(pgd_t *base);

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

@@ -94,6 +94,8 @@
 /* after this # consecutive successes, bump up the throttle if it was lowered */
 #define COMPLETE_THRESHOLD 5
 
+#define UV_LB_SUBNODEID 0x10
+
 /*
  * number of entries in the destination side payload queue
  */
@@ -124,7 +126,7 @@
  * The distribution specification (32 bytes) is interpreted as a 256-bit
  * distribution vector. Adjacent bits correspond to consecutive even numbered
  * nodeIDs. The result of adding the index of a given bit to the 15-bit
- * 'base_dest_nodeid' field of the header corresponds to the
+ * 'base_dest_nasid' field of the header corresponds to the
  * destination nodeID associated with that specified bit.
  */
 struct bau_target_uvhubmask {
@@ -176,7 +178,7 @@ struct bau_msg_payload {
 struct bau_msg_header {
 	unsigned int dest_subnodeid:6;	/* must be 0x10, for the LB */
 	/* bits 5:0 */
-	unsigned int base_dest_nodeid:15; /* nasid of the */
+	unsigned int base_dest_nasid:15; /* nasid of the */
 	/* bits 20:6 */			  /* first bit in uvhub map */
 	unsigned int command:8;	/* message type */
 	/* bits 28:21 */
@@ -378,6 +380,10 @@ struct ptc_stats {
 	unsigned long d_rcanceled; /* number of messages canceled by resets */
 };
 
+struct hub_and_pnode {
+	short uvhub;
+	short pnode;
+};
 /*
  * one per-cpu; to locate the software tables
  */
@@ -399,10 +405,12 @@ struct bau_control {
 	int baudisabled;
 	int set_bau_off;
 	short cpu;
+	short osnode;
 	short uvhub_cpu;
 	short uvhub;
 	short cpus_in_socket;
 	short cpus_in_uvhub;
+	short partition_base_pnode;
 	unsigned short message_number;
 	unsigned short uvhub_quiesce;
 	short socket_acknowledge_count[DEST_Q_SIZE];
@@ -422,15 +430,16 @@ struct bau_control {
 	int congested_period;
 	cycles_t period_time;
 	long period_requests;
+	struct hub_and_pnode *target_hub_and_pnode;
 };
 
 static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp)
 {
 	return constant_test_bit(uvhub, &dstp->bits[0]);
 }
-static inline void bau_uvhub_set(int uvhub, struct bau_target_uvhubmask *dstp)
+static inline void bau_uvhub_set(int pnode, struct bau_target_uvhubmask *dstp)
 {
-	__set_bit(uvhub, &dstp->bits[0]);
+	__set_bit(pnode, &dstp->bits[0]);
 }
 static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp,
 				    int nbits)

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

@@ -398,6 +398,8 @@ struct uv_blade_info {
 	unsigned short	nr_online_cpus;
 	unsigned short	pnode;
 	short		memory_nid;
+	spinlock_t	nmi_lock;
+	unsigned long	nmi_count;
 };
 extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;

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

@@ -5,7 +5,7 @@
  *
  * SGI UV MMR definitions
  *
- * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2011 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef _ASM_X86_UV_UV_MMRS_H
@@ -1099,5 +1099,19 @@ union uvh_rtc1_int_config_u {
     } s;
 };
 
+/* ========================================================================= */
+/*                               UVH_SCRATCH5                                */
+/* ========================================================================= */
+#define UVH_SCRATCH5 0x2d0200UL
+#define UVH_SCRATCH5_32 0x00778
+
+#define UVH_SCRATCH5_SCRATCH5_SHFT 0
+#define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL
+union uvh_scratch5_u {
+    unsigned long	v;
+    struct uvh_scratch5_s {
+	unsigned long	scratch5 : 64;  /* RW, W1CS */
+    } s;
+};
 
 #endif /* __ASM_UV_MMRS_X86_H__ */

arch/x86/include/asm/x86_init.h

@@ -67,6 +67,17 @@ struct x86_init_oem {
 	void (*banner)(void);
 };
 
+/**
+ * struct x86_init_mapping - platform specific initial kernel pagetable setup
+ * @pagetable_reserve:	reserve a range of addresses for kernel pagetable usage
+ *
+ * For more details on the purpose of this hook, look in
+ * init_memory_mapping and the commit that added it.
+ */
+struct x86_init_mapping {
+	void (*pagetable_reserve)(u64 start, u64 end);
+};
+
 /**
  * struct x86_init_paging - platform specific paging functions
  * @pagetable_setup_start:	platform specific pre paging_init() call
@@ -123,6 +134,7 @@ struct x86_init_ops {
 	struct x86_init_mpparse		mpparse;
 	struct x86_init_irqs		irqs;
 	struct x86_init_oem		oem;
+	struct x86_init_mapping		mapping;
 	struct x86_init_paging		paging;
 	struct x86_init_timers		timers;
 	struct x86_init_iommu		iommu;

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -37,6 +37,13 @@
 #include <asm/smp.h>
 #include <asm/x86_init.h>
 #include <asm/emergency-restart.h>
+#include <asm/nmi.h>
+
+/* BMC sets a bit this MMR non-zero before sending an NMI */
+#define UVH_NMI_MMR				UVH_SCRATCH5
+#define UVH_NMI_MMR_CLEAR			(UVH_NMI_MMR + 8)
+#define UV_NMI_PENDING_MASK			(1UL << 63)
+DEFINE_PER_CPU(unsigned long, cpu_last_nmi_count);
 
 DEFINE_PER_CPU(int, x2apic_extra_bits);
 
@@ -642,18 +649,46 @@ void __cpuinit uv_cpu_init(void)
  */
 int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 {
+	unsigned long real_uv_nmi;
+	int bid;
+
 	if (reason != DIE_NMIUNKNOWN)
 		return NOTIFY_OK;
 
 	if (in_crash_kexec)
 		/* do nothing if entering the crash kernel */
 		return NOTIFY_OK;
+
 	/*
-	 * Use a lock so only one cpu prints at a time
+	 * Each blade has an MMR that indicates when an NMI has been sent
-	 * to prevent intermixed output.
+	 * to cpus on the blade. If an NMI is detected, atomically
+	 * clear the MMR and update a per-blade NMI count used to
+	 * cause each cpu on the blade to notice a new NMI.
+	 */
+	bid = uv_numa_blade_id();
+	real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
+
+	if (unlikely(real_uv_nmi)) {
+		spin_lock(&uv_blade_info[bid].nmi_lock);
+		real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
+		if (real_uv_nmi) {
+			uv_blade_info[bid].nmi_count++;
+			uv_write_local_mmr(UVH_NMI_MMR_CLEAR, UV_NMI_PENDING_MASK);
+		}
+		spin_unlock(&uv_blade_info[bid].nmi_lock);
+	}
+
+	if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count))
+		return NOTIFY_DONE;
+
+	__get_cpu_var(cpu_last_nmi_count) = uv_blade_info[bid].nmi_count;
+
+	/*
+	 * Use a lock so only one cpu prints at a time.
+	 * This prevents intermixed output.
 	 */
 	spin_lock(&uv_nmi_lock);
-	pr_info("NMI stack dump cpu %u:\n", smp_processor_id());
+	pr_info("UV NMI stack dump cpu %u:\n", smp_processor_id());
 	dump_stack();
 	spin_unlock(&uv_nmi_lock);
 
@@ -661,7 +696,8 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 }
 
 static struct notifier_block uv_dump_stack_nmi_nb = {
-	.notifier_call	= uv_handle_nmi
+	.notifier_call	= uv_handle_nmi,
+	.priority = NMI_LOCAL_LOW_PRIOR - 1,
 };
 
 void uv_register_nmi_notifier(void)
@@ -720,8 +756,9 @@ void __init uv_system_init(void)
 	printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
 
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
-	uv_blade_info = kmalloc(bytes, GFP_KERNEL);
+	uv_blade_info = kzalloc(bytes, GFP_KERNEL);
 	BUG_ON(!uv_blade_info);
+
 	for (blade = 0; blade < uv_num_possible_blades(); blade++)
 		uv_blade_info[blade].memory_nid = -1;
 
@@ -747,6 +784,7 @@ void __init uv_system_init(void)
 			uv_blade_info[blade].pnode = pnode;
 			uv_blade_info[blade].nr_possible_cpus = 0;
 			uv_blade_info[blade].nr_online_cpus = 0;
+			spin_lock_init(&uv_blade_info[blade].nmi_lock);
 			max_pnode = max(pnode, max_pnode);
 			blade++;
 		}

arch/x86/kernel/cpu/amd.c

@@ -613,7 +613,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 #endif
 
 	/* As a rule processors have APIC timer running in deep C states */
-	if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400))
+	if (c->x86 > 0xf && !cpu_has_amd_erratum(amd_erratum_400))
 		set_cpu_cap(c, X86_FEATURE_ARAT);
 
 	/*
@@ -698,7 +698,7 @@ cpu_dev_register(amd_cpu_dev);
  */
 
 const int amd_erratum_400[] =
-	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0x0f, 0x4, 0x2, 0xff, 0xf),
+	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
 			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
 EXPORT_SYMBOL_GPL(amd_erratum_400);
 

arch/x86/kernel/cpu/mcheck/mce_amd.c

@@ -509,6 +509,7 @@ recurse:
 out_free:
 	if (b) {
 		kobject_put(&b->kobj);
+		list_del(&b->miscj);
 		kfree(b);
 	}
 	return err;

arch/x86/kernel/cpu/mcheck/therm_throt.c

@@ -446,18 +446,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 	 */
 	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
 
+	h = lvtthmr_init;
 	/*
 	 * The initial value of thermal LVT entries on all APs always reads
 	 * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
 	 * sequence to them and LVT registers are reset to 0s except for
 	 * the mask bits which are set to 1s when APs receive INIT IPI.
-	 * Always restore the value that BIOS has programmed on AP based on
+	 * If BIOS takes over the thermal interrupt and sets its interrupt
-	 * BSP's info we saved since BIOS is always setting the same value
+	 * delivery mode to SMI (not fixed), it restores the value that the
-	 * for all threads/cores
+	 * BIOS has programmed on AP based on BSP's info we saved since BIOS
+	 * is always setting the same value for all threads/cores.
 	 */
-	apic_write(APIC_LVTTHMR, lvtthmr_init);
+	if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED)
+		apic_write(APIC_LVTTHMR, lvtthmr_init);
 
-	h = lvtthmr_init;
 
 	if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
 		printk(KERN_DEBUG

arch/x86/kernel/kprobes.c

@@ -1183,12 +1183,13 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
 					 struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long flags;
 
 	/* This is possible if op is under delayed unoptimizing */
 	if (kprobe_disabled(&op->kp))
 		return;
 
-	preempt_disable();
+	local_irq_save(flags);
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(&op->kp);
 	} else {
@@ -1207,7 +1208,7 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
 		opt_pre_handler(&op->kp, regs);
 		__this_cpu_write(current_kprobe, NULL);
 	}
-	preempt_enable_no_resched();
+	local_irq_restore(flags);
 }
 
 static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)

arch/x86/kernel/x86_init.c

@@ -61,6 +61,10 @@ struct x86_init_ops x86_init __initdata = {
 		.banner			= default_banner,
 	},
 
+	.mapping = {
+		.pagetable_reserve		= native_pagetable_reserve,
+	},
+
 	.paging = {
 		.pagetable_setup_start	= native_pagetable_setup_start,
 		.pagetable_setup_done	= native_pagetable_setup_done,

arch/x86/mm/init.c

@@ -81,6 +81,11 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 		end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
 }
 
+void __init native_pagetable_reserve(u64 start, u64 end)
+{
+	memblock_x86_reserve_range(start, end, "PGTABLE");
+}
+
 struct map_range {
 	unsigned long start;
 	unsigned long end;
@@ -272,9 +277,24 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 
 	__flush_tlb_all();
 
+	/*
+	 * Reserve the kernel pagetable pages we used (pgt_buf_start -
+	 * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
+	 * so that they can be reused for other purposes.
+	 *
+	 * On native it just means calling memblock_x86_reserve_range, on Xen it
+	 * also means marking RW the pagetable pages that we allocated before
+	 * but that haven't been used.
+	 *
+	 * In fact on xen we mark RO the whole range pgt_buf_start -
+	 * pgt_buf_top, because we have to make sure that when
+	 * init_memory_mapping reaches the pagetable pages area, it maps
+	 * RO all the pagetable pages, including the ones that are beyond
+	 * pgt_buf_end at that time.
+	 */
 	if (!after_bootmem && pgt_buf_end > pgt_buf_start)
-		memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT,
+		x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
-				 pgt_buf_end << PAGE_SHIFT, "PGTABLE");
+				PFN_PHYS(pgt_buf_end));
 
 	if (!after_bootmem)
 		early_memtest(start, end);

arch/x86/platform/uv/tlb_uv.c

@@ -699,16 +699,17 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 					  struct mm_struct *mm,
 					  unsigned long va, unsigned int cpu)
 {
-	int tcpu;
-	int uvhub;
 	int locals = 0;
 	int remotes = 0;
 	int hubs = 0;
+	int tcpu;
+	int tpnode;
 	struct bau_desc *bau_desc;
 	struct cpumask *flush_mask;
 	struct ptc_stats *stat;
 	struct bau_control *bcp;
 	struct bau_control *tbcp;
+	struct hub_and_pnode *hpp;
 
 	/* kernel was booted 'nobau' */
 	if (nobau)
@@ -750,11 +751,18 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 	bau_desc += UV_ITEMS_PER_DESCRIPTOR * bcp->uvhub_cpu;
 	bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
 
-	/* cpu statistics */
 	for_each_cpu(tcpu, flush_mask) {
-		uvhub = uv_cpu_to_blade_id(tcpu);
+		/*
-		bau_uvhub_set(uvhub, &bau_desc->distribution);
+		 * The distribution vector is a bit map of pnodes, relative
-		if (uvhub == bcp->uvhub)
+		 * to the partition base pnode (and the partition base nasid
+		 * in the header).
+		 * Translate cpu to pnode and hub using an array stored
+		 * in local memory.
+		 */
+		hpp = &bcp->socket_master->target_hub_and_pnode[tcpu];
+		tpnode = hpp->pnode - bcp->partition_base_pnode;
+		bau_uvhub_set(tpnode, &bau_desc->distribution);
+		if (hpp->uvhub == bcp->uvhub)
 			locals++;
 		else
 			remotes++;
@@ -855,7 +863,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
  * an interrupt, but causes an error message to be returned to
  * the sender.
  */
-static void uv_enable_timeouts(void)
+static void __init uv_enable_timeouts(void)
 {
 	int uvhub;
 	int nuvhubs;
@@ -1326,10 +1334,10 @@ static int __init uv_ptc_init(void)
 }
 
 /*
- * initialize the sending side's sending buffers
+ * Initialize the sending side's sending buffers.
  */
 static void
-uv_activation_descriptor_init(int node, int pnode)
+uv_activation_descriptor_init(int node, int pnode, int base_pnode)
 {
 	int i;
 	int cpu;
@@ -1352,11 +1360,11 @@ uv_activation_descriptor_init(int node, int pnode)
 	n = pa >> uv_nshift;
 	m = pa & uv_mmask;
 
+	/* the 14-bit pnode */
 	uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE,
 			      (n << UV_DESC_BASE_PNODE_SHIFT | m));
-
 	/*
-	 * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
+	 * Initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
 	 * cpu even though we only use the first one; one descriptor can
 	 * describe a broadcast to 256 uv hubs.
 	 */
@@ -1365,12 +1373,13 @@ uv_activation_descriptor_init(int node, int pnode)
 		memset(bd2, 0, sizeof(struct bau_desc));
 		bd2->header.sw_ack_flag = 1;
 		/*
-		 * base_dest_nodeid is the nasid of the first uvhub
+		 * The base_dest_nasid set in the message header is the nasid
-		 * in the partition. The bit map will indicate uvhub numbers,
+		 * of the first uvhub in the partition. The bit map will
-		 * which are 0-N in a partition. Pnodes are unique system-wide.
+		 * indicate destination pnode numbers relative to that base.
+		 * They may not be consecutive if nasid striding is being used.
 		 */
-		bd2->header.base_dest_nodeid = UV_PNODE_TO_NASID(uv_partition_base_pnode);
+		bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode);
-		bd2->header.dest_subnodeid = 0x10; /* the LB */
+		bd2->header.dest_subnodeid = UV_LB_SUBNODEID;
 		bd2->header.command = UV_NET_ENDPOINT_INTD;
 		bd2->header.int_both = 1;
 		/*
@@ -1442,7 +1451,7 @@ uv_payload_queue_init(int node, int pnode)
 /*
  * Initialization of each UV hub's structures
  */
-static void __init uv_init_uvhub(int uvhub, int vector)
+static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode)
 {
 	int node;
 	int pnode;
@@ -1450,11 +1459,11 @@ static void __init uv_init_uvhub(int uvhub, int vector)
 
 	node = uvhub_to_first_node(uvhub);
 	pnode = uv_blade_to_pnode(uvhub);
-	uv_activation_descriptor_init(node, pnode);
+	uv_activation_descriptor_init(node, pnode, base_pnode);
 	uv_payload_queue_init(node, pnode);
 	/*
-	 * the below initialization can't be in firmware because the
+	 * The below initialization can't be in firmware because the
-	 * messaging IRQ will be determined by the OS
+	 * messaging IRQ will be determined by the OS.
 	 */
 	apicid = uvhub_to_first_apicid(uvhub) | uv_apicid_hibits;
 	uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
@@ -1491,10 +1500,11 @@ calculate_destination_timeout(void)
 /*
  * initialize the bau_control structure for each cpu
  */
-static int __init uv_init_per_cpu(int nuvhubs)
+static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode)
 {
 	int i;
 	int cpu;
+	int tcpu;
 	int pnode;
 	int uvhub;
 	int have_hmaster;
@@ -1528,6 +1538,15 @@ static int __init uv_init_per_cpu(int nuvhubs)
 		bcp = &per_cpu(bau_control, cpu);
 		memset(bcp, 0, sizeof(struct bau_control));
 		pnode = uv_cpu_hub_info(cpu)->pnode;
+		if ((pnode - base_part_pnode) >= UV_DISTRIBUTION_SIZE) {
+			printk(KERN_EMERG
+				"cpu %d pnode %d-%d beyond %d; BAU disabled\n",
+				cpu, pnode, base_part_pnode,
+				UV_DISTRIBUTION_SIZE);
+			return 1;
+		}
+		bcp->osnode = cpu_to_node(cpu);
+		bcp->partition_base_pnode = uv_partition_base_pnode;
 		uvhub = uv_cpu_hub_info(cpu)->numa_blade_id;
 		*(uvhub_mask + (uvhub/8)) |= (1 << (uvhub%8));
 		bdp = &uvhub_descs[uvhub];
@@ -1536,7 +1555,7 @@ static int __init uv_init_per_cpu(int nuvhubs)
 		bdp->pnode = pnode;
 		/* kludge: 'assuming' one node per socket, and assuming that
 		   disabling a socket just leaves a gap in node numbers */
-		socket = (cpu_to_node(cpu) & 1);
+		socket = bcp->osnode & 1;
 		bdp->socket_mask |= (1 << socket);
 		sdp = &bdp->socket[socket];
 		sdp->cpu_number[sdp->num_cpus] = cpu;
@@ -1585,6 +1604,20 @@ static int __init uv_init_per_cpu(int nuvhubs)
 nextsocket:
 			socket++;
 			socket_mask = (socket_mask >> 1);
+			/* each socket gets a local array of pnodes/hubs */
+			bcp = smaster;
+			bcp->target_hub_and_pnode = kmalloc_node(
+				sizeof(struct hub_and_pnode) *
+				num_possible_cpus(), GFP_KERNEL, bcp->osnode);
+			memset(bcp->target_hub_and_pnode, 0,
+				sizeof(struct hub_and_pnode) *
+				num_possible_cpus());
+			for_each_present_cpu(tcpu) {
+				bcp->target_hub_and_pnode[tcpu].pnode =
+					uv_cpu_hub_info(tcpu)->pnode;
+				bcp->target_hub_and_pnode[tcpu].uvhub =
+					uv_cpu_hub_info(tcpu)->numa_blade_id;
+			}
 		}
 	}
 	kfree(uvhub_descs);
@@ -1637,21 +1670,22 @@ static int __init uv_bau_init(void)
 	spin_lock_init(&disable_lock);
 	congested_cycles = microsec_2_cycles(congested_response_us);
 
-	if (uv_init_per_cpu(nuvhubs)) {
+	uv_partition_base_pnode = 0x7fffffff;
+	for (uvhub = 0; uvhub < nuvhubs; uvhub++) {
+		if (uv_blade_nr_possible_cpus(uvhub) &&
+			(uv_blade_to_pnode(uvhub) < uv_partition_base_pnode))
+			uv_partition_base_pnode = uv_blade_to_pnode(uvhub);
+	}
+
+	if (uv_init_per_cpu(nuvhubs, uv_partition_base_pnode)) {
 		nobau = 1;
 		return 0;
 	}
 
-	uv_partition_base_pnode = 0x7fffffff;
-	for (uvhub = 0; uvhub < nuvhubs; uvhub++)
-		if (uv_blade_nr_possible_cpus(uvhub) &&
-			(uv_blade_to_pnode(uvhub) < uv_partition_base_pnode))
-			uv_partition_base_pnode = uv_blade_to_pnode(uvhub);
-
 	vector = UV_BAU_MESSAGE;
 	for_each_possible_blade(uvhub)
 		if (uv_blade_nr_possible_cpus(uvhub))
-			uv_init_uvhub(uvhub, vector);
+			uv_init_uvhub(uvhub, vector, uv_partition_base_pnode);
 
 	uv_enable_timeouts();
 	alloc_intr_gate(vector, uv_bau_message_intr1);

arch/x86/xen/mmu.c

@@ -1275,6 +1275,20 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 }
 
+static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
+{
+	/* reserve the range used */
+	native_pagetable_reserve(start, end);
+
+	/* set as RW the rest */
+	printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
+			PFN_PHYS(pgt_buf_top));
+	while (end < PFN_PHYS(pgt_buf_top)) {
+		make_lowmem_page_readwrite(__va(end));
+		end += PAGE_SIZE;
+	}
+}
+
 static void xen_post_allocator_init(void);
 
 static __init void xen_pagetable_setup_done(pgd_t *base)
@@ -1463,119 +1477,6 @@ static int xen_pgd_alloc(struct mm_struct *mm)
 	return ret;
 }
 
-#ifdef CONFIG_X86_64
-static __initdata u64 __last_pgt_set_rw = 0;
-static __initdata u64 __pgt_buf_start = 0;
-static __initdata u64 __pgt_buf_end = 0;
-static __initdata u64 __pgt_buf_top = 0;
-/*
- * As a consequence of the commit:
- * 
- * commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e
- * Author: Yinghai Lu <yinghai@kernel.org>
- * Date:   Fri Dec 17 16:58:28 2010 -0800
- * 
- *     x86-64, mm: Put early page table high
- * 
- * at some point init_memory_mapping is going to reach the pagetable pages
- * area and map those pages too (mapping them as normal memory that falls
- * in the range of addresses passed to init_memory_mapping as argument).
- * Some of those pages are already pagetable pages (they are in the range
- * pgt_buf_start-pgt_buf_end) therefore they are going to be mapped RO and
- * everything is fine.
- * Some of these pages are not pagetable pages yet (they fall in the range
- * pgt_buf_end-pgt_buf_top; for example the page at pgt_buf_end) so they
- * are going to be mapped RW.  When these pages become pagetable pages and
- * are hooked into the pagetable, xen will find that the guest has already
- * a RW mapping of them somewhere and fail the operation.
- * The reason Xen requires pagetables to be RO is that the hypervisor needs
- * to verify that the pagetables are valid before using them. The validation
- * operations are called "pinning".
- * 
- * In order to fix the issue we mark all the pages in the entire range
- * pgt_buf_start-pgt_buf_top as RO, however when the pagetable allocation
- * is completed only the range pgt_buf_start-pgt_buf_end is reserved by
- * init_memory_mapping. Hence the kernel is going to crash as soon as one
- * of the pages in the range pgt_buf_end-pgt_buf_top is reused (b/c those
- * ranges are RO).
- * 
- * For this reason, 'mark_rw_past_pgt' is introduced which is called _after_
- * the init_memory_mapping has completed (in a perfect world we would
- * call this function from init_memory_mapping, but lets ignore that).
- * 
- * Because we are called _after_ init_memory_mapping the pgt_buf_[start,
- * end,top] have all changed to new values (b/c init_memory_mapping
- * is called and setting up another new page-table). Hence, the first time
- * we enter this function, we save away the pgt_buf_start value and update
- * the pgt_buf_[end,top].
- * 
- * When we detect that the "old" pgt_buf_start through pgt_buf_end
- * PFNs have been reserved (so memblock_x86_reserve_range has been called),
- * we immediately set out to RW the "old" pgt_buf_end through pgt_buf_top.
- * 
- * And then we update those "old" pgt_buf_[end|top] with the new ones
- * so that we can redo this on the next pagetable.
- */
-static __init void mark_rw_past_pgt(void) {
-
-	if (pgt_buf_end > pgt_buf_start) {
-		u64 addr, size;
-
-		/* Save it away. */
-		if (!__pgt_buf_start) {
-			__pgt_buf_start = pgt_buf_start;
-			__pgt_buf_end = pgt_buf_end;
-			__pgt_buf_top = pgt_buf_top;
-			return;
-		}
-		/* If we get the range that starts at __pgt_buf_end that means
-		 * the range is reserved, and that in 'init_memory_mapping'
-		 * the 'memblock_x86_reserve_range' has been called with the
-		 * outdated __pgt_buf_start, __pgt_buf_end (the "new"
-		 * pgt_buf_[start|end|top] refer now to a new pagetable.
-		 * Note: we are called _after_ the pgt_buf_[..] have been
-		 * updated.*/
-
-		addr = memblock_x86_find_in_range_size(PFN_PHYS(__pgt_buf_start),
-						       &size, PAGE_SIZE);
-
-		/* Still not reserved, meaning 'memblock_x86_reserve_range'
-		 * hasn't been called yet. Update the _end and _top.*/
-		if (addr == PFN_PHYS(__pgt_buf_start)) {
-			__pgt_buf_end = pgt_buf_end;
-			__pgt_buf_top = pgt_buf_top;
-			return;
-		}
-
-		/* OK, the area is reserved, meaning it is time for us to
-		 * set RW for the old end->top PFNs. */
-
-		/* ..unless we had already done this. */
-		if (__pgt_buf_end == __last_pgt_set_rw)
-			return;
-
-		addr = PFN_PHYS(__pgt_buf_end);
-		
-		/* set as RW the rest */
-		printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n",
-			PFN_PHYS(__pgt_buf_end), PFN_PHYS(__pgt_buf_top));
-		
-		while (addr < PFN_PHYS(__pgt_buf_top)) {
-			make_lowmem_page_readwrite(__va(addr));
-			addr += PAGE_SIZE;
-		}
-		/* And update everything so that we are ready for the next
-		 * pagetable (the one created for regions past 4GB) */
-		__last_pgt_set_rw = __pgt_buf_end;
-		__pgt_buf_start = pgt_buf_start;
-		__pgt_buf_end = pgt_buf_end;
-		__pgt_buf_top = pgt_buf_top;
-	}
-	return;
-}
-#else
-static __init void mark_rw_past_pgt(void) { }
-#endif
 static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 #ifdef CONFIG_X86_64
@@ -1601,14 +1502,6 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
 
-	/*
-	 * A bit of optimization. We do not need to call the workaround
-	 * when xen_set_pte_init is called with a PTE with 0 as PFN.
-	 * That is b/c the pagetable at that point are just being populated
-	 * with empty values and we can save some cycles by not calling
-	 * the 'memblock' code.*/
-	if (pfn)
-		mark_rw_past_pgt();
 	/*
 	 * If the new pfn is within the range of the newly allocated
 	 * kernel pagetable, and it isn't being mapped into an
@@ -2118,8 +2011,6 @@ __init void xen_ident_map_ISA(void)
 
 static __init void xen_post_allocator_init(void)
 {
-	mark_rw_past_pgt();
-
 #ifdef CONFIG_XEN_DEBUG
 	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
 #endif
@@ -2228,6 +2119,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 void __init xen_init_mmu_ops(void)
 {
+	x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
 	x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
 	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
 	pv_mmu_ops = xen_mmu_ops;

block/blk-cgroup.c

@@ -114,6 +114,13 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 }
 EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
 
+struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk)
+{
+	return container_of(task_subsys_state(tsk, blkio_subsys_id),
+			    struct blkio_cgroup, css);
+}
+EXPORT_SYMBOL_GPL(task_blkio_cgroup);
+
 static inline void
 blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
 {

block/blk-cgroup.h

@@ -291,6 +291,7 @@ static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
 #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
 extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
+extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk);
 extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 	struct blkio_group *blkg, void *key, dev_t dev,
 	enum blkio_policy_id plid);
@@ -314,6 +315,8 @@ void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
 struct cgroup;
 static inline struct blkio_cgroup *
 cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
+static inline struct blkio_cgroup *
+task_blkio_cgroup(struct task_struct *tsk) { return NULL; }
 
 static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 		struct blkio_group *blkg, void *key, dev_t dev,

block/blk-core.c

@@ -316,8 +316,10 @@ EXPORT_SYMBOL(__blk_run_queue);
  */
 void blk_run_queue_async(struct request_queue *q)
 {
-	if (likely(!blk_queue_stopped(q)))
+	if (likely(!blk_queue_stopped(q))) {
+		__cancel_delayed_work(&q->delay_work);
 		queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
+	}
 }
 EXPORT_SYMBOL(blk_run_queue_async);
 

block/blk-throttle.c

@@ -160,9 +160,8 @@ static void throtl_put_tg(struct throtl_grp *tg)
 }
 
 static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
-			struct cgroup *cgroup)
+			struct blkio_cgroup *blkcg)
 {
-	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
 	struct throtl_grp *tg = NULL;
 	void *key = td;
 	struct backing_dev_info *bdi = &td->queue->backing_dev_info;
@@ -229,12 +228,12 @@ done:
 
 static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 {
-	struct cgroup *cgroup;
 	struct throtl_grp *tg = NULL;
+	struct blkio_cgroup *blkcg;
 
 	rcu_read_lock();
-	cgroup = task_cgroup(current, blkio_subsys_id);
+	blkcg = task_blkio_cgroup(current);
-	tg = throtl_find_alloc_tg(td, cgroup);
+	tg = throtl_find_alloc_tg(td, blkcg);
 	if (!tg)
 		tg = &td->root_tg;
 	rcu_read_unlock();

block/cfq-iosched.c

@@ -1014,10 +1014,9 @@ void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
 	cfqg->needs_update = true;
 }
 
-static struct cfq_group *
+static struct cfq_group * cfq_find_alloc_cfqg(struct cfq_data *cfqd,
-cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
+		struct blkio_cgroup *blkcg, int create)
 {
-	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
 	struct cfq_group *cfqg = NULL;
 	void *key = cfqd;
 	int i, j;
@@ -1079,12 +1078,12 @@ done:
  */
 static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
 {
-	struct cgroup *cgroup;
+	struct blkio_cgroup *blkcg;
 	struct cfq_group *cfqg = NULL;
 
 	rcu_read_lock();
-	cgroup = task_cgroup(current, blkio_subsys_id);
+	blkcg = task_blkio_cgroup(current);
-	cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create);
+	cfqg = cfq_find_alloc_cfqg(cfqd, blkcg, create);
 	if (!cfqg && create)
 		cfqg = &cfqd->root_group;
 	rcu_read_unlock();

drivers/ata/libahci.c

@@ -561,27 +561,6 @@ void ahci_start_engine(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
 	u32 tmp;
-	u8 status;
-
-	status = readl(port_mmio + PORT_TFDATA) & 0xFF;
-
-	/*
-	 * At end of section 10.1 of AHCI spec (rev 1.3), it states
-	 * Software shall not set PxCMD.ST to 1 until it is determined
-	 * that a functoinal device is present on the port as determined by
-	 * PxTFD.STS.BSY=0, PxTFD.STS.DRQ=0 and PxSSTS.DET=3h
-	 *
-	 * Even though most AHCI host controllers work without this check,
-	 * specific controller will fail under this condition
-	 */
-	if (status & (ATA_BUSY | ATA_DRQ))
-		return;
-	else {
-		ahci_scr_read(&ap->link, SCR_STATUS, &tmp);
-
-		if ((tmp & 0xf) != 0x3)
-			return;
-	}
 
 	/* start DMA */
 	tmp = readl(port_mmio + PORT_CMD);

drivers/ata/libata-eh.c

@@ -3316,7 +3316,7 @@ static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 	struct ata_eh_context *ehc = &link->eh_context;
 	struct ata_device *dev, *link_dev = NULL, *lpm_dev = NULL;
 	enum ata_lpm_policy old_policy = link->lpm_policy;
-	bool no_dipm = ap->flags & ATA_FLAG_NO_DIPM;
+	bool no_dipm = link->ap->flags & ATA_FLAG_NO_DIPM;
 	unsigned int hints = ATA_LPM_EMPTY | ATA_LPM_HIPM;
 	unsigned int err_mask;
 	int rc;

drivers/atm/fore200e.c

@@ -2643,16 +2643,19 @@ fore200e_init(struct fore200e* fore200e, struct device *parent)
 }
 
 #ifdef CONFIG_SBUS
+static const struct of_device_id fore200e_sba_match[];
 static int __devinit fore200e_sba_probe(struct platform_device *op)
 {
+	const struct of_device_id *match;
 	const struct fore200e_bus *bus;
 	struct fore200e *fore200e;
 	static int index = 0;
 	int err;
 
-	if (!op->dev.of_match)
+	match = of_match_device(fore200e_sba_match, &op->dev);
+	if (!match)
 		return -EINVAL;
-	bus = op->dev.of_match->data;
+	bus = match->data;
 
 	fore200e = kzalloc(sizeof(struct fore200e), GFP_KERNEL);
 	if (!fore200e)

drivers/block/DAC960.c

@@ -2547,7 +2547,6 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller)
 	disk->major = MajorNumber;
 	disk->first_minor = n << DAC960_MaxPartitionsBits;
 	disk->fops = &DAC960_BlockDeviceOperations;
-	disk->events = DISK_EVENT_MEDIA_CHANGE;
    }
   /*
     Indicate the Block Device Registration completed successfully,

drivers/block/amiflop.c

@@ -1736,7 +1736,6 @@ static int __init fd_probe_drives(void)
 		disk->major = FLOPPY_MAJOR;
 		disk->first_minor = drive;
 		disk->fops = &floppy_fops;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
 		sprintf(disk->disk_name, "fd%d", drive);
 		disk->private_data = &unit[drive];
 		set_capacity(disk, 880*2);

drivers/block/ataflop.c

@@ -1964,7 +1964,6 @@ static int __init atari_floppy_init (void)
 		unit[i].disk->first_minor = i;
 		sprintf(unit[i].disk->disk_name, "fd%d", i);
 		unit[i].disk->fops = &floppy_fops;
-		unit[i].disk->events = DISK_EVENT_MEDIA_CHANGE;
 		unit[i].disk->private_data = &unit[i];
 		unit[i].disk->queue = blk_init_queue(do_fd_request,
 					&ataflop_lock);

drivers/block/floppy.c

@@ -4205,7 +4205,6 @@ static int __init floppy_init(void)
 		disks[dr]->major = FLOPPY_MAJOR;
 		disks[dr]->first_minor = TOMINOR(dr);
 		disks[dr]->fops = &floppy_fops;
-		disks[dr]->events = DISK_EVENT_MEDIA_CHANGE;
 		sprintf(disks[dr]->disk_name, "fd%d", dr);
 
 		init_timer(&motor_off_timer[dr]);

drivers/block/paride/pcd.c

@@ -320,7 +320,6 @@ static void pcd_init_units(void)
 		disk->first_minor = unit;
 		strcpy(disk->disk_name, cd->name);	/* umm... */
 		disk->fops = &pcd_bdops;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
 	}
 }
 

drivers/block/paride/pd.c

@@ -837,7 +837,6 @@ static void pd_probe_drive(struct pd_unit *disk)
 	p->fops = &pd_fops;
 	p->major = major;
 	p->first_minor = (disk - pd) << PD_BITS;
-	p->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->gd = p;
 	p->private_data = disk;
 	p->queue = pd_queue;

drivers/block/paride/pf.c

@@ -294,7 +294,6 @@ static void __init pf_init_units(void)
 		disk->first_minor = unit;
 		strcpy(disk->disk_name, pf->name);
 		disk->fops = &pf_fops;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
 		if (!(*drives[unit])[D_PRT])
 			pf_drive_count++;
 	}

drivers/block/rbd.c

@@ -92,6 +92,8 @@ struct rbd_client {
 	struct list_head	node;
 };
 
+struct rbd_req_coll;
+
 /*
  * a single io request
  */
@@ -100,6 +102,24 @@ struct rbd_request {
 	struct bio		*bio;		/* cloned bio */
 	struct page		**pages;	/* list of used pages */
 	u64			len;
+	int			coll_index;
+	struct rbd_req_coll	*coll;
+};
+
+struct rbd_req_status {
+	int done;
+	int rc;
+	u64 bytes;
+};
+
+/*
+ * a collection of requests
+ */
+struct rbd_req_coll {
+	int			total;
+	int			num_done;
+	struct kref		kref;
+	struct rbd_req_status	status[0];
 };
 
 struct rbd_snap {
@@ -416,6 +436,17 @@ static void rbd_put_client(struct rbd_device *rbd_dev)
 	rbd_dev->client = NULL;
 }
 
+/*
+ * Destroy requests collection
+ */
+static void rbd_coll_release(struct kref *kref)
+{
+	struct rbd_req_coll *coll =
+		container_of(kref, struct rbd_req_coll, kref);
+
+	dout("rbd_coll_release %p\n", coll);
+	kfree(coll);
+}
 
 /*
  * Create a new header structure, translate header format from the on-disk
@@ -590,6 +621,14 @@ static u64 rbd_get_segment(struct rbd_image_header *header,
 	return len;
 }
 
+static int rbd_get_num_segments(struct rbd_image_header *header,
+				u64 ofs, u64 len)
+{
+	u64 start_seg = ofs >> header->obj_order;
+	u64 end_seg = (ofs + len - 1) >> header->obj_order;
+	return end_seg - start_seg + 1;
+}
+
 /*
  * bio helpers
  */
@@ -735,6 +774,50 @@ static void rbd_destroy_ops(struct ceph_osd_req_op *ops)
 	kfree(ops);
 }
 
+static void rbd_coll_end_req_index(struct request *rq,
+				   struct rbd_req_coll *coll,
+				   int index,
+				   int ret, u64 len)
+{
+	struct request_queue *q;
+	int min, max, i;
+
+	dout("rbd_coll_end_req_index %p index %d ret %d len %lld\n",
+	     coll, index, ret, len);
+
+	if (!rq)
+		return;
+
+	if (!coll) {
+		blk_end_request(rq, ret, len);
+		return;
+	}
+
+	q = rq->q;
+
+	spin_lock_irq(q->queue_lock);
+	coll->status[index].done = 1;
+	coll->status[index].rc = ret;
+	coll->status[index].bytes = len;
+	max = min = coll->num_done;
+	while (max < coll->total && coll->status[max].done)
+		max++;
+
+	for (i = min; i<max; i++) {
+		__blk_end_request(rq, coll->status[i].rc,
+				  coll->status[i].bytes);
+		coll->num_done++;
+		kref_put(&coll->kref, rbd_coll_release);
+	}
+	spin_unlock_irq(q->queue_lock);
+}
+
+static void rbd_coll_end_req(struct rbd_request *req,
+			     int ret, u64 len)
+{
+	rbd_coll_end_req_index(req->rq, req->coll, req->coll_index, ret, len);
+}
+
 /*
  * Send ceph osd request
  */
@@ -749,6 +832,8 @@ static int rbd_do_request(struct request *rq,
 			  int flags,
 			  struct ceph_osd_req_op *ops,
 			  int num_reply,
+			  struct rbd_req_coll *coll,
+			  int coll_index,
 			  void (*rbd_cb)(struct ceph_osd_request *req,
 					 struct ceph_msg *msg),
 			  struct ceph_osd_request **linger_req,
@@ -763,12 +848,20 @@ static int rbd_do_request(struct request *rq,
 	struct ceph_osd_request_head *reqhead;
 	struct rbd_image_header *header = &dev->header;
 
-	ret = -ENOMEM;
 	req_data = kzalloc(sizeof(*req_data), GFP_NOIO);
-	if (!req_data)
+	if (!req_data) {
-		goto done;
+		if (coll)
+			rbd_coll_end_req_index(rq, coll, coll_index,
+					       -ENOMEM, len);
+		return -ENOMEM;
+	}
 
-	dout("rbd_do_request len=%lld ofs=%lld\n", len, ofs);
+	if (coll) {
+		req_data->coll = coll;
+		req_data->coll_index = coll_index;
+	}
+
+	dout("rbd_do_request obj=%s ofs=%lld len=%lld\n", obj, len, ofs);
 
 	down_read(&header->snap_rwsem);
 
@@ -828,7 +921,8 @@ static int rbd_do_request(struct request *rq,
 		ret = ceph_osdc_wait_request(&dev->client->osdc, req);
 		if (ver)
 			*ver = le64_to_cpu(req->r_reassert_version.version);
-		dout("reassert_ver=%lld\n", le64_to_cpu(req->r_reassert_version.version));
+		dout("reassert_ver=%lld\n",
+		     le64_to_cpu(req->r_reassert_version.version));
 		ceph_osdc_put_request(req);
 	}
 	return ret;
@@ -837,10 +931,8 @@ done_err:
 	bio_chain_put(req_data->bio);
 	ceph_osdc_put_request(req);
 done_pages:
+	rbd_coll_end_req(req_data, ret, len);
 	kfree(req_data);
-done:
-	if (rq)
-		blk_end_request(rq, ret, len);
 	return ret;
 }
 
@@ -874,7 +966,7 @@ static void rbd_req_cb(struct ceph_osd_request *req, struct ceph_msg *msg)
 		bytes = req_data->len;
 	}
 
-	blk_end_request(req_data->rq, rc, bytes);
+	rbd_coll_end_req(req_data, rc, bytes);
 
 	if (req_data->bio)
 		bio_chain_put(req_data->bio);
@@ -934,6 +1026,7 @@ static int rbd_req_sync_op(struct rbd_device *dev,
 			  flags,
 			  ops,
 			  2,
+			  NULL, 0,
 			  NULL,
 			  linger_req, ver);
 	if (ret < 0)
@@ -959,7 +1052,9 @@ static int rbd_do_op(struct request *rq,
 		     u64 snapid,
 		     int opcode, int flags, int num_reply,
 		     u64 ofs, u64 len,
-		     struct bio *bio)
+		     struct bio *bio,
+		     struct rbd_req_coll *coll,
+		     int coll_index)
 {
 	char *seg_name;
 	u64 seg_ofs;
@@ -995,7 +1090,10 @@ static int rbd_do_op(struct request *rq,
 			     flags,
 			     ops,
 			     num_reply,
+			     coll, coll_index,
 			     rbd_req_cb, 0, NULL);
+
+	rbd_destroy_ops(ops);
 done:
 	kfree(seg_name);
 	return ret;
@@ -1008,13 +1106,15 @@ static int rbd_req_write(struct request *rq,
 			 struct rbd_device *rbd_dev,
 			 struct ceph_snap_context *snapc,
 			 u64 ofs, u64 len,
-			 struct bio *bio)
+			 struct bio *bio,
+			 struct rbd_req_coll *coll,
+			 int coll_index)
 {
 	return rbd_do_op(rq, rbd_dev, snapc, CEPH_NOSNAP,
 			 CEPH_OSD_OP_WRITE,
 			 CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
 			 2,
-			 ofs, len, bio);
+			 ofs, len, bio, coll, coll_index);
 }
 
 /*
@@ -1024,14 +1124,16 @@ static int rbd_req_read(struct request *rq,
 			 struct rbd_device *rbd_dev,
 			 u64 snapid,
 			 u64 ofs, u64 len,
-			 struct bio *bio)
+			 struct bio *bio,
+			 struct rbd_req_coll *coll,
+			 int coll_index)
 {
 	return rbd_do_op(rq, rbd_dev, NULL,
 			 (snapid ? snapid : CEPH_NOSNAP),
 			 CEPH_OSD_OP_READ,
 			 CEPH_OSD_FLAG_READ,
 			 2,
-			 ofs, len, bio);
+			 ofs, len, bio, coll, coll_index);
 }
 
 /*
@@ -1063,7 +1165,9 @@ static int rbd_req_sync_notify_ack(struct rbd_device *dev,
 {
 	struct ceph_osd_req_op *ops;
 	struct page **pages = NULL;
-	int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_NOTIFY_ACK, 0);
+	int ret;
+
+	ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_NOTIFY_ACK, 0);
 	if (ret < 0)
 		return ret;
 
@@ -1077,6 +1181,7 @@ static int rbd_req_sync_notify_ack(struct rbd_device *dev,
 			  CEPH_OSD_FLAG_READ,
 			  ops,
 			  1,
+			  NULL, 0,
 			  rbd_simple_req_cb, 0, NULL);
 
 	rbd_destroy_ops(ops);
@@ -1274,6 +1379,20 @@ static int rbd_req_sync_exec(struct rbd_device *dev,
 	return ret;
 }
 
+static struct rbd_req_coll *rbd_alloc_coll(int num_reqs)
+{
+	struct rbd_req_coll *coll =
+			kzalloc(sizeof(struct rbd_req_coll) +
+			        sizeof(struct rbd_req_status) * num_reqs,
+				GFP_ATOMIC);
+
+	if (!coll)
+		return NULL;
+	coll->total = num_reqs;
+	kref_init(&coll->kref);
+	return coll;
+}
+
 /*
  * block device queue callback
  */
@@ -1291,6 +1410,8 @@ static void rbd_rq_fn(struct request_queue *q)
 		bool do_write;
 		int size, op_size = 0;
 		u64 ofs;
+		int num_segs, cur_seg = 0;
+		struct rbd_req_coll *coll;
 
 		/* peek at request from block layer */
 		if (!rq)
@@ -1321,6 +1442,14 @@ static void rbd_rq_fn(struct request_queue *q)
 		     do_write ? "write" : "read",
 		     size, blk_rq_pos(rq) * 512ULL);
 
+		num_segs = rbd_get_num_segments(&rbd_dev->header, ofs, size);
+		coll = rbd_alloc_coll(num_segs);
+		if (!coll) {
+			spin_lock_irq(q->queue_lock);
+			__blk_end_request_all(rq, -ENOMEM);
+			goto next;
+		}
+
 		do {
 			/* a bio clone to be passed down to OSD req */
 			dout("rq->bio->bi_vcnt=%d\n", rq->bio->bi_vcnt);
@@ -1328,35 +1457,41 @@ static void rbd_rq_fn(struct request_queue *q)
 						  rbd_dev->header.block_name,
 						  ofs, size,
 						  NULL, NULL);
+			kref_get(&coll->kref);
 			bio = bio_chain_clone(&rq_bio, &next_bio, &bp,
 					      op_size, GFP_ATOMIC);
 			if (!bio) {
-				spin_lock_irq(q->queue_lock);
+				rbd_coll_end_req_index(rq, coll, cur_seg,
-				__blk_end_request_all(rq, -ENOMEM);
+						       -ENOMEM, op_size);
-				goto next;
+				goto next_seg;
 			}
 
+
 			/* init OSD command: write or read */
 			if (do_write)
 				rbd_req_write(rq, rbd_dev,
 					      rbd_dev->header.snapc,
 					      ofs,
-					      op_size, bio);
+					      op_size, bio,
+					      coll, cur_seg);
 			else
 				rbd_req_read(rq, rbd_dev,
 					     cur_snap_id(rbd_dev),
 					     ofs,
-					     op_size, bio);
+					     op_size, bio,
+					     coll, cur_seg);
 
+next_seg:
 			size -= op_size;
 			ofs += op_size;
 
+			cur_seg++;
 			rq_bio = next_bio;
 		} while (size > 0);
+		kref_put(&coll->kref, rbd_coll_release);
 
 		if (bp)
 			bio_pair_release(bp);
-
 		spin_lock_irq(q->queue_lock);
 next:
 		rq = blk_fetch_request(q);

drivers/block/swim.c

@@ -858,7 +858,6 @@ static int __devinit swim_floppy_init(struct swim_priv *swd)
 		swd->unit[drive].disk->first_minor = drive;
 		sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive);
 		swd->unit[drive].disk->fops = &floppy_fops;
-		swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE;
 		swd->unit[drive].disk->private_data = &swd->unit[drive];
 		swd->unit[drive].disk->queue = swd->queue;
 		set_capacity(swd->unit[drive].disk, 2880);

drivers/block/swim3.c

@@ -1163,7 +1163,6 @@ static int __devinit swim3_attach(struct macio_dev *mdev, const struct of_device
 	disk->major = FLOPPY_MAJOR;
 	disk->first_minor = i;
 	disk->fops = &floppy_fops;
-	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->private_data = &floppy_states[i];
 	disk->queue = swim3_queue;
 	disk->flags |= GENHD_FL_REMOVABLE;

drivers/block/ub.c

@@ -2334,7 +2334,6 @@ static int ub_probe_lun(struct ub_dev *sc, int lnum)
 	disk->major = UB_MAJOR;
 	disk->first_minor = lun->id * UB_PARTS_PER_LUN;
 	disk->fops = &ub_bd_fops;
-	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->private_data = lun;
 	disk->driverfs_dev = &sc->intf->dev;
 

drivers/block/xsysace.c

@@ -1005,7 +1005,6 @@ static int __devinit ace_setup(struct ace_device *ace)
 	ace->gd->major = ace_major;
 	ace->gd->first_minor = ace->id * ACE_NUM_MINORS;
 	ace->gd->fops = &ace_fops;
-	ace->gd->events = DISK_EVENT_MEDIA_CHANGE;
 	ace->gd->queue = ace->queue;
 	ace->gd->private_data = ace;
 	snprintf(ace->gd->disk_name, 32, "xs%c", ace->id + 'a');

drivers/cdrom/cdrom.c

@@ -986,6 +986,9 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t
 
 	cdinfo(CD_OPEN, "entering cdrom_open\n"); 
 
+	/* open is event synchronization point, check events first */
+	check_disk_change(bdev);
+
 	/* if this was a O_NONBLOCK open and we should honor the flags,
 	 * do a quick open without drive/disc integrity checks. */
 	cdi->use_count++;
@@ -1012,9 +1015,6 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t
 
 	cdinfo(CD_OPEN, "Use count for \"/dev/%s\" now %d\n",
 			cdi->name, cdi->use_count);
-	/* Do this on open.  Don't wait for mount, because they might
-	    not be mounting, but opening with O_NONBLOCK */
-	check_disk_change(bdev);
 	return 0;
 err_release:
 	if (CDROM_CAN(CDC_LOCK) && cdi->options & CDO_LOCK) {

drivers/cdrom/gdrom.c

@@ -803,7 +803,6 @@ static int __devinit probe_gdrom(struct platform_device *devptr)
 		goto probe_fail_cdrom_register;
 	}
 	gd.disk->fops = &gdrom_bdops;
-	gd.disk->events = DISK_EVENT_MEDIA_CHANGE;
 	/* latch on to the interrupt */
 	err = gdrom_set_interrupt_handlers();
 	if (err)

drivers/cdrom/viocd.c

@@ -626,7 +626,6 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	gendisk->queue = q;
 	gendisk->fops = &viocd_fops;
 	gendisk->flags = GENHD_FL_CD|GENHD_FL_REMOVABLE;
-	gendisk->events = DISK_EVENT_MEDIA_CHANGE;
 	set_capacity(gendisk, 0);
 	gendisk->private_data = d;
 	d->viocd_disk = gendisk;

drivers/char/hw_random/n2-drv.c

@@ -619,15 +619,18 @@ static void __devinit n2rng_driver_version(void)
 		pr_info("%s", version);
 }
 
+static const struct of_device_id n2rng_match[];
 static int __devinit n2rng_probe(struct platform_device *op)
 {
+	const struct of_device_id *match;
 	int victoria_falls;
 	int err = -ENOMEM;
 	struct n2rng *np;
 
-	if (!op->dev.of_match)
+	match = of_match_device(n2rng_match, &op->dev);
+	if (!match)
 		return -EINVAL;
-	victoria_falls = (op->dev.of_match->data != NULL);
+	victoria_falls = (match->data != NULL);
 
 	n2rng_driver_version();
 	np = kzalloc(sizeof(*np), GFP_KERNEL);

drivers/char/ipmi/ipmi_si_intf.c

@@ -2554,9 +2554,11 @@ static struct pci_driver ipmi_pci_driver = {
 };
 #endif /* CONFIG_PCI */
 
+static struct of_device_id ipmi_match[];
 static int __devinit ipmi_probe(struct platform_device *dev)
 {
 #ifdef CONFIG_OF
+	const struct of_device_id *match;
 	struct smi_info *info;
 	struct resource resource;
 	const __be32 *regsize, *regspacing, *regshift;
@@ -2566,7 +2568,8 @@ static int __devinit ipmi_probe(struct platform_device *dev)
 
 	dev_info(&dev->dev, "probing via device tree\n");
 
-	if (!dev->dev.of_match)
+	match = of_match_device(ipmi_match, &dev->dev);
+	if (!match)
 		return -EINVAL;
 
 	ret = of_address_to_resource(np, 0, &resource);
@@ -2601,7 +2604,7 @@ static int __devinit ipmi_probe(struct platform_device *dev)
 		return -ENOMEM;
 	}
 
-	info->si_type		= (enum si_type) dev->dev.of_match->data;
+	info->si_type		= (enum si_type) match->data;
 	info->addr_source	= SI_DEVICETREE;
 	info->irq_setup		= std_irq_setup;
 

drivers/char/xilinx_hwicap/xilinx_hwicap.c

@@ -715,13 +715,13 @@ static int __devexit hwicap_remove(struct device *dev)
 }
 
 #ifdef CONFIG_OF
-static int __devinit hwicap_of_probe(struct platform_device *op)
+static int __devinit hwicap_of_probe(struct platform_device *op,
+				     const struct hwicap_driver_config *config)
 {
 	struct resource res;
 	const unsigned int *id;
 	const char *family;
 	int rc;
-	const struct hwicap_driver_config *config = op->dev.of_match->data;
 	const struct config_registers *regs;
 
 
@@ -751,20 +751,24 @@ static int __devinit hwicap_of_probe(struct platform_device *op)
 			regs);
 }
 #else
-static inline int hwicap_of_probe(struct platform_device *op)
+static inline int hwicap_of_probe(struct platform_device *op,
+				  const struct hwicap_driver_config *config)
 {
 	return -EINVAL;
 }
 #endif /* CONFIG_OF */
 
+static const struct of_device_id __devinitconst hwicap_of_match[];
 static int __devinit hwicap_drv_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *match;
 	struct resource *res;
 	const struct config_registers *regs;
 	const char *family;
 
-	if (pdev->dev.of_match)
+	match = of_match_device(hwicap_of_match, &pdev->dev);
-		return hwicap_of_probe(pdev);
+	if (match)
+		return hwicap_of_probe(pdev, match->data);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)

drivers/edac/ppc4xx_edac.c

@@ -1019,7 +1019,7 @@ ppc4xx_edac_mc_init(struct mem_ctl_info *mci,
 	struct ppc4xx_edac_pdata *pdata = NULL;
 	const struct device_node *np = op->dev.of_node;
 
-	if (op->dev.of_match == NULL)
+	if (of_match_device(ppc4xx_edac_match, &op->dev) == NULL)
 		return -EINVAL;
 
 	/* Initial driver pointers and private data */

drivers/gpu/drm/drm_fb_helper.c

@@ -1516,17 +1516,33 @@ bool drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper, int bpp_sel)
 }
 EXPORT_SYMBOL(drm_fb_helper_initial_config);
 
-bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper)
+/**
+ * drm_fb_helper_hotplug_event - respond to a hotplug notification by
+ *                               probing all the outputs attached to the fb.
+ * @fb_helper: the drm_fb_helper
+ *
+ * LOCKING:
+ * Called at runtime, must take mode config lock.
+ *
+ * Scan the connectors attached to the fb_helper and try to put together a
+ * setup after *notification of a change in output configuration.
+ *
+ * RETURNS:
+ * 0 on success and a non-zero error code otherwise.
+ */
+int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper)
 {
+	struct drm_device *dev = fb_helper->dev;
 	int count = 0;
 	u32 max_width, max_height, bpp_sel;
 	bool bound = false, crtcs_bound = false;
 	struct drm_crtc *crtc;
 
 	if (!fb_helper->fb)
-		return false;
+		return 0;
 
-	list_for_each_entry(crtc, &fb_helper->dev->mode_config.crtc_list, head) {
+	mutex_lock(&dev->mode_config.mutex);
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		if (crtc->fb)
 			crtcs_bound = true;
 		if (crtc->fb == fb_helper->fb)
@@ -1535,7 +1551,8 @@ bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper)
 
 	if (!bound && crtcs_bound) {
 		fb_helper->delayed_hotplug = true;
-		return false;
+		mutex_unlock(&dev->mode_config.mutex);
+		return 0;
 	}
 	DRM_DEBUG_KMS("\n");
 
@@ -1546,6 +1563,7 @@ bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper)
 	count = drm_fb_helper_probe_connector_modes(fb_helper, max_width,
 						    max_height);
 	drm_setup_crtcs(fb_helper);
+	mutex_unlock(&dev->mode_config.mutex);
 
 	return drm_fb_helper_single_fb_probe(fb_helper, bpp_sel);
 }

drivers/gpu/drm/i915/i915_drv.c

@@ -49,7 +49,7 @@ module_param_named(panel_ignore_lid, i915_panel_ignore_lid, int, 0600);
 unsigned int i915_powersave = 1;
 module_param_named(powersave, i915_powersave, int, 0600);
 
-unsigned int i915_semaphores = 1;
+unsigned int i915_semaphores = 0;
 module_param_named(semaphores, i915_semaphores, int, 0600);
 
 unsigned int i915_enable_rc6 = 0;

drivers/gpu/drm/i915/intel_display.c

@@ -5154,6 +5154,8 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc,
 
 	I915_WRITE(DSPCNTR(plane), dspcntr);
 	POSTING_READ(DSPCNTR(plane));
+	if (!HAS_PCH_SPLIT(dev))
+		intel_enable_plane(dev_priv, plane, pipe);
 
 	ret = intel_pipe_set_base(crtc, x, y, old_fb);
 

drivers/gpu/drm/radeon/evergreen.c

@@ -1780,7 +1780,10 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 
 
 	mc_shared_chmap = RREG32(MC_SHARED_CHMAP);
-	mc_arb_ramcfg = RREG32(MC_ARB_RAMCFG);
+	if (rdev->flags & RADEON_IS_IGP)
+		mc_arb_ramcfg = RREG32(FUS_MC_ARB_RAMCFG);
+	else
+		mc_arb_ramcfg = RREG32(MC_ARB_RAMCFG);
 
 	switch (rdev->config.evergreen.max_tile_pipes) {
 	case 1:

drivers/gpu/drm/radeon/evergreend.h

@@ -200,6 +200,7 @@
 #define		BURSTLENGTH_SHIFT				9
 #define		BURSTLENGTH_MASK				0x00000200
 #define		CHANSIZE_OVERRIDE				(1 << 11)
+#define	FUS_MC_ARB_RAMCFG				0x2768
 #define	MC_VM_AGP_TOP					0x2028
 #define	MC_VM_AGP_BOT					0x202C
 #define	MC_VM_AGP_BASE					0x2030

drivers/gpu/drm/radeon/radeon_atombios.c

@@ -1574,9 +1574,17 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct
 			ATOM_FAKE_EDID_PATCH_RECORD *fake_edid_record;
 			ATOM_PANEL_RESOLUTION_PATCH_RECORD *panel_res_record;
 			bool bad_record = false;
-			u8 *record = (u8 *)(mode_info->atom_context->bios +
+			u8 *record;
-					    data_offset +
+
-					    le16_to_cpu(lvds_info->info.usModePatchTableOffset));
+			if ((frev == 1) && (crev < 2))
+				/* absolute */
+				record = (u8 *)(mode_info->atom_context->bios +
+						le16_to_cpu(lvds_info->info.usModePatchTableOffset));
+			else
+				/* relative */
+				record = (u8 *)(mode_info->atom_context->bios +
+						data_offset +
+						le16_to_cpu(lvds_info->info.usModePatchTableOffset));
 			while (*record != ATOM_RECORD_END_TYPE) {
 				switch (*record) {
 				case LCD_MODE_PATCH_RECORD_MODE_TYPE:

drivers/gpu/drm/radeon/reg_srcs/cayman

@@ -33,6 +33,7 @@ cayman 0x9400
 0x00008E48 SQ_EX_ALLOC_TABLE_SLOTS
 0x00009100 SPI_CONFIG_CNTL
 0x0000913C SPI_CONFIG_CNTL_1
+0x00009508 TA_CNTL_AUX
 0x00009830 DB_DEBUG
 0x00009834 DB_DEBUG2
 0x00009838 DB_DEBUG3

drivers/gpu/drm/radeon/reg_srcs/evergreen

@@ -46,6 +46,7 @@ evergreen 0x9400
 0x00008E48 SQ_EX_ALLOC_TABLE_SLOTS
 0x00009100 SPI_CONFIG_CNTL
 0x0000913C SPI_CONFIG_CNTL_1
+0x00009508 TA_CNTL_AUX
 0x00009700 VC_CNTL
 0x00009714 VC_ENHANCE
 0x00009830 DB_DEBUG

drivers/gpu/vga/vga_switcheroo.c

@@ -219,9 +219,6 @@ static int vga_switchto_stage1(struct vga_switcheroo_client *new_client)
 	int i;
 	struct vga_switcheroo_client *active = NULL;
 
-	if (new_client->active == true)
-		return 0;
-
 	for (i = 0; i < VGA_SWITCHEROO_MAX_CLIENTS; i++) {
 		if (vgasr_priv.clients[i].active == true) {
 			active = &vgasr_priv.clients[i];
@@ -372,6 +369,9 @@ vga_switcheroo_debugfs_write(struct file *filp, const char __user *ubuf,
 		goto out;
 	}
 
+	if (client->active == true)
+		goto out;
+
 	/* okay we want a switch - test if devices are willing to switch */
 	can_switch = true;
 	for (i = 0; i < VGA_SWITCHEROO_MAX_CLIENTS; i++) {

drivers/i2c/busses/i2c-mpc.c

@@ -560,15 +560,18 @@ static struct i2c_adapter mpc_ops = {
 	.timeout = HZ,
 };
 
+static const struct of_device_id mpc_i2c_of_match[];
 static int __devinit fsl_i2c_probe(struct platform_device *op)
 {
+	const struct of_device_id *match;
 	struct mpc_i2c *i2c;
 	const u32 *prop;
 	u32 clock = MPC_I2C_CLOCK_LEGACY;
 	int result = 0;
 	int plen;
 
-	if (!op->dev.of_match)
+	match = of_match_device(mpc_i2c_of_match, &op->dev);
+	if (!match)
 		return -EINVAL;
 
 	i2c = kzalloc(sizeof(*i2c), GFP_KERNEL);
@@ -605,8 +608,8 @@ static int __devinit fsl_i2c_probe(struct platform_device *op)
 			clock = *prop;
 	}
 
-	if (op->dev.of_match->data) {
+	if (match->data) {
-		struct mpc_i2c_data *data = op->dev.of_match->data;
+		struct mpc_i2c_data *data = match->data;
 		data->setup(op->dev.of_node, i2c, clock, data->prescaler);
 	} else {
 		/* Backwards compatibility */

drivers/i2c/busses/i2c-pnx.c

@@ -65,7 +65,7 @@ static inline void i2c_pnx_arm_timer(struct i2c_pnx_algo_data *alg_data)
 		jiffies, expires);
 
 	timer->expires = jiffies + expires;
-	timer->data = (unsigned long)&alg_data;
+	timer->data = (unsigned long)alg_data;
 
 	add_timer(timer);
 }

drivers/input/touchscreen/ads7846.c

@@ -281,17 +281,24 @@ struct ser_req {
 	u8			command;
 	u8			ref_off;
 	u16			scratch;
-	__be16			sample;
 	struct spi_message	msg;
 	struct spi_transfer	xfer[6];
+	/*
+	 * DMA (thus cache coherency maintenance) requires the
+	 * transfer buffers to live in their own cache lines.
+	 */
+	__be16 sample ____cacheline_aligned;
 };
 
 struct ads7845_ser_req {
 	u8			command[3];
-	u8			pwrdown[3];
-	u8			sample[3];
 	struct spi_message	msg;
 	struct spi_transfer	xfer[2];
+	/*
+	 * DMA (thus cache coherency maintenance) requires the
+	 * transfer buffers to live in their own cache lines.
+	 */
+	u8 sample[3] ____cacheline_aligned;
 };
 
 static int ads7846_read12_ser(struct device *dev, unsigned command)

drivers/leds/leds-lm3530.c

@@ -349,6 +349,7 @@ static const struct i2c_device_id lm3530_id[] = {
 	{LM3530_NAME, 0},
 	{}
 };
+MODULE_DEVICE_TABLE(i2c, lm3530_id);
 
 static struct i2c_driver lm3530_i2c_driver = {
 	.probe = lm3530_probe,

drivers/media/video/cx88/cx88-input.c

@@ -524,7 +524,7 @@ void cx88_ir_irq(struct cx88_core *core)
 	for (todo = 32; todo > 0; todo -= bits) {
 		ev.pulse = samples & 0x80000000 ? false : true;
 		bits = min(todo, 32U - fls(ev.pulse ? samples : ~samples));
-		ev.duration = (bits * NSEC_PER_SEC) / (1000 * ir_samplerate);
+		ev.duration = (bits * (NSEC_PER_SEC / 1000)) / ir_samplerate;
 		ir_raw_event_store_with_filter(ir->dev, &ev);
 		samples <<= bits;
 	}

drivers/media/video/soc_camera.c

@@ -136,11 +136,50 @@ unsigned long soc_camera_apply_sensor_flags(struct soc_camera_link *icl,
 }
 EXPORT_SYMBOL(soc_camera_apply_sensor_flags);
 
+#define pixfmtstr(x) (x) & 0xff, ((x) >> 8) & 0xff, ((x) >> 16) & 0xff, \
+	((x) >> 24) & 0xff
+
+static int soc_camera_try_fmt(struct soc_camera_device *icd,
+			      struct v4l2_format *f)
+{
+	struct soc_camera_host *ici = to_soc_camera_host(icd->dev.parent);
+	struct v4l2_pix_format *pix = &f->fmt.pix;
+	int ret;
+
+	dev_dbg(&icd->dev, "TRY_FMT(%c%c%c%c, %ux%u)\n",
+		pixfmtstr(pix->pixelformat), pix->width, pix->height);
+
+	pix->bytesperline = 0;
+	pix->sizeimage = 0;
+
+	ret = ici->ops->try_fmt(icd, f);
+	if (ret < 0)
+		return ret;
+
+	if (!pix->sizeimage) {
+		if (!pix->bytesperline) {
+			const struct soc_camera_format_xlate *xlate;
+
+			xlate = soc_camera_xlate_by_fourcc(icd, pix->pixelformat);
+			if (!xlate)
+				return -EINVAL;
+
+			ret = soc_mbus_bytes_per_line(pix->width,
+						      xlate->host_fmt);
+			if (ret > 0)
+				pix->bytesperline = ret;
+		}
+		if (pix->bytesperline)
+			pix->sizeimage = pix->bytesperline * pix->height;
+	}
+
+	return 0;
+}
+
 static int soc_camera_try_fmt_vid_cap(struct file *file, void *priv,
 				      struct v4l2_format *f)
 {
 	struct soc_camera_device *icd = file->private_data;
-	struct soc_camera_host *ici = to_soc_camera_host(icd->dev.parent);
 
 	WARN_ON(priv != file->private_data);
 
@@ -149,7 +188,7 @@ static int soc_camera_try_fmt_vid_cap(struct file *file, void *priv,
 		return -EINVAL;
 
 	/* limit format to hardware capabilities */
-	return ici->ops->try_fmt(icd, f);
+	return soc_camera_try_fmt(icd, f);
 }
 
 static int soc_camera_enum_input(struct file *file, void *priv,
@@ -362,9 +401,6 @@ static void soc_camera_free_user_formats(struct soc_camera_device *icd)
 	icd->user_formats = NULL;
 }
 
-#define pixfmtstr(x) (x) & 0xff, ((x) >> 8) & 0xff, ((x) >> 16) & 0xff, \
-	((x) >> 24) & 0xff
-
 /* Called with .vb_lock held, or from the first open(2), see comment there */
 static int soc_camera_set_fmt(struct soc_camera_device *icd,
 			      struct v4l2_format *f)
@@ -377,7 +413,7 @@ static int soc_camera_set_fmt(struct soc_camera_device *icd,
 		pixfmtstr(pix->pixelformat), pix->width, pix->height);
 
 	/* We always call try_fmt() before set_fmt() or set_crop() */
-	ret = ici->ops->try_fmt(icd, f);
+	ret = soc_camera_try_fmt(icd, f);
 	if (ret < 0)
 		return ret;
 

drivers/media/video/v4l2-device.c

@@ -155,8 +155,10 @@ int v4l2_device_register_subdev(struct v4l2_device *v4l2_dev,
 	sd->v4l2_dev = v4l2_dev;
 	if (sd->internal_ops && sd->internal_ops->registered) {
 		err = sd->internal_ops->registered(sd);
-		if (err)
+		if (err) {
+			module_put(sd->owner);
 			return err;
+		}
 	}
 
 	/* This just returns 0 if either of the two args is NULL */
@@ -164,6 +166,7 @@ int v4l2_device_register_subdev(struct v4l2_device *v4l2_dev,
 	if (err) {
 		if (sd->internal_ops && sd->internal_ops->unregistered)
 			sd->internal_ops->unregistered(sd);
+		module_put(sd->owner);
 		return err;
 	}
 

drivers/media/video/v4l2-subdev.c

@@ -155,25 +155,25 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 
 	switch (cmd) {
 	case VIDIOC_QUERYCTRL:
-		return v4l2_subdev_queryctrl(sd, arg);
+		return v4l2_queryctrl(sd->ctrl_handler, arg);
 
 	case VIDIOC_QUERYMENU:
-		return v4l2_subdev_querymenu(sd, arg);
+		return v4l2_querymenu(sd->ctrl_handler, arg);
 
 	case VIDIOC_G_CTRL:
-		return v4l2_subdev_g_ctrl(sd, arg);
+		return v4l2_g_ctrl(sd->ctrl_handler, arg);
 
 	case VIDIOC_S_CTRL:
-		return v4l2_subdev_s_ctrl(sd, arg);
+		return v4l2_s_ctrl(sd->ctrl_handler, arg);
 
 	case VIDIOC_G_EXT_CTRLS:
-		return v4l2_subdev_g_ext_ctrls(sd, arg);
+		return v4l2_g_ext_ctrls(sd->ctrl_handler, arg);
 
 	case VIDIOC_S_EXT_CTRLS:
-		return v4l2_subdev_s_ext_ctrls(sd, arg);
+		return v4l2_s_ext_ctrls(sd->ctrl_handler, arg);
 
 	case VIDIOC_TRY_EXT_CTRLS:
-		return v4l2_subdev_try_ext_ctrls(sd, arg);
+		return v4l2_try_ext_ctrls(sd->ctrl_handler, arg);
 
 	case VIDIOC_DQEVENT:
 		if (!(sd->flags & V4L2_SUBDEV_FL_HAS_EVENTS))

drivers/message/i2o/i2o_block.c

@@ -1000,7 +1000,6 @@ static struct i2o_block_device *i2o_block_device_alloc(void)
 	gd->major = I2O_MAJOR;
 	gd->queue = queue;
 	gd->fops = &i2o_block_fops;
-	gd->events = DISK_EVENT_MEDIA_CHANGE;
 	gd->private_data = dev;
 
 	dev->gd = gd;

drivers/mmc/core/host.c

@@ -94,7 +94,7 @@ static void mmc_host_clk_gate_delayed(struct mmc_host *host)
 		spin_unlock_irqrestore(&host->clk_lock, flags);
 		return;
 	}
-	mmc_claim_host(host);
+	mutex_lock(&host->clk_gate_mutex);
 	spin_lock_irqsave(&host->clk_lock, flags);
 	if (!host->clk_requests) {
 		spin_unlock_irqrestore(&host->clk_lock, flags);
@@ -104,7 +104,7 @@ static void mmc_host_clk_gate_delayed(struct mmc_host *host)
 		pr_debug("%s: gated MCI clock\n", mmc_hostname(host));
 	}
 	spin_unlock_irqrestore(&host->clk_lock, flags);
-	mmc_release_host(host);
+	mutex_unlock(&host->clk_gate_mutex);
 }
 
 /*
@@ -130,7 +130,7 @@ void mmc_host_clk_ungate(struct mmc_host *host)
 {
 	unsigned long flags;
 
-	mmc_claim_host(host);
+	mutex_lock(&host->clk_gate_mutex);
 	spin_lock_irqsave(&host->clk_lock, flags);
 	if (host->clk_gated) {
 		spin_unlock_irqrestore(&host->clk_lock, flags);
@@ -140,7 +140,7 @@ void mmc_host_clk_ungate(struct mmc_host *host)
 	}
 	host->clk_requests++;
 	spin_unlock_irqrestore(&host->clk_lock, flags);
-	mmc_release_host(host);
+	mutex_unlock(&host->clk_gate_mutex);
 }
 
 /**
@@ -215,6 +215,7 @@ static inline void mmc_host_clk_init(struct mmc_host *host)
 	host->clk_gated = false;
 	INIT_WORK(&host->clk_gate_work, mmc_host_clk_gate_work);
 	spin_lock_init(&host->clk_lock);
+	mutex_init(&host->clk_gate_mutex);
 }
 
 /**

drivers/mmc/host/sdhci-of-core.c

@@ -124,8 +124,10 @@ static bool __devinit sdhci_of_wp_inverted(struct device_node *np)
 #endif
 }
 
+static const struct of_device_id sdhci_of_match[];
 static int __devinit sdhci_of_probe(struct platform_device *ofdev)
 {
+	const struct of_device_id *match;
 	struct device_node *np = ofdev->dev.of_node;
 	struct sdhci_of_data *sdhci_of_data;
 	struct sdhci_host *host;
@@ -134,9 +136,10 @@ static int __devinit sdhci_of_probe(struct platform_device *ofdev)
 	int size;
 	int ret;
 
-	if (!ofdev->dev.of_match)
+	match = of_match_device(sdhci_of_match, &ofdev->dev);
+	if (!match)
 		return -EINVAL;
-	sdhci_of_data = ofdev->dev.of_match->data;
+	sdhci_of_data = match->data;
 
 	if (!of_device_is_available(np))
 		return -ENODEV;

drivers/mtd/maps/physmap_of.c

@@ -214,11 +214,13 @@ static void __devinit of_free_probes(const char **probes)
 }
 #endif
 
+static struct of_device_id of_flash_match[];
 static int __devinit of_flash_probe(struct platform_device *dev)
 {
 #ifdef CONFIG_MTD_PARTITIONS
 	const char **part_probe_types;
 #endif
+	const struct of_device_id *match;
 	struct device_node *dp = dev->dev.of_node;
 	struct resource res;
 	struct of_flash *info;
@@ -232,9 +234,10 @@ static int __devinit of_flash_probe(struct platform_device *dev)
 	struct mtd_info **mtd_list = NULL;
 	resource_size_t res_size;
 
-	if (!dev->dev.of_match)
+	match = of_match_device(of_flash_match, &dev->dev);
+	if (!match)
 		return -EINVAL;
-	probe_type = dev->dev.of_match->data;
+	probe_type = match->data;
 
 	reg_tuple_size = (of_n_addr_cells(dp) + of_n_size_cells(dp)) * sizeof(u32);
 

drivers/net/Makefile

@@ -144,7 +144,7 @@ obj-$(CONFIG_NE3210) += ne3210.o 8390.o
 obj-$(CONFIG_SB1250_MAC) += sb1250-mac.o
 obj-$(CONFIG_B44) += b44.o
 obj-$(CONFIG_FORCEDETH) += forcedeth.o
-obj-$(CONFIG_NE_H8300) += ne-h8300.o 8390.o
+obj-$(CONFIG_NE_H8300) += ne-h8300.o
 obj-$(CONFIG_AX88796) += ax88796.o
 obj-$(CONFIG_BCM63XX_ENET) += bcm63xx_enet.o
 obj-$(CONFIG_FTMAC100) += ftmac100.o
@@ -219,7 +219,7 @@ obj-$(CONFIG_SC92031) += sc92031.o
 obj-$(CONFIG_LP486E) += lp486e.o
 
 obj-$(CONFIG_ETH16I) += eth16i.o
-obj-$(CONFIG_ZORRO8390) += zorro8390.o 8390.o
+obj-$(CONFIG_ZORRO8390) += zorro8390.o
 obj-$(CONFIG_HPLANCE) += hplance.o 7990.o
 obj-$(CONFIG_MVME147_NET) += mvme147.o 7990.o
 obj-$(CONFIG_EQUALIZER) += eql.o
@@ -231,7 +231,7 @@ obj-$(CONFIG_SGI_IOC3_ETH) += ioc3-eth.o
 obj-$(CONFIG_DECLANCE) += declance.o
 obj-$(CONFIG_ATARILANCE) += atarilance.o
 obj-$(CONFIG_A2065) += a2065.o
-obj-$(CONFIG_HYDRA) += hydra.o 8390.o
+obj-$(CONFIG_HYDRA) += hydra.o
 obj-$(CONFIG_ARIADNE) += ariadne.o
 obj-$(CONFIG_CS89x0) += cs89x0.o
 obj-$(CONFIG_MACSONIC) += macsonic.o

drivers/net/bonding/bond_3ad.h

@@ -39,7 +39,7 @@
 
 typedef struct mac_addr {
 	u8 mac_addr_value[ETH_ALEN];
-} mac_addr_t;
+} __packed mac_addr_t;
 
 enum {
 	BOND_AD_STABLE = 0,
@@ -134,12 +134,12 @@ typedef struct lacpdu {
 	u8 tlv_type_terminator;	     // = terminator
 	u8 terminator_length;	     // = 0
 	u8 reserved_50[50];	     // = 0
-} lacpdu_t;
+} __packed lacpdu_t;
 
 typedef struct lacpdu_header {
 	struct ethhdr hdr;
 	struct lacpdu lacpdu;
-} lacpdu_header_t;
+} __packed lacpdu_header_t;
 
 // Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard)
 typedef struct bond_marker {
@@ -155,12 +155,12 @@ typedef struct bond_marker {
 	u8 tlv_type_terminator;	     //  = 0x00
 	u8 terminator_length;	     //  = 0x00
 	u8 reserved_90[90];	     //  = 0
-} bond_marker_t;
+} __packed bond_marker_t;
 
 typedef struct bond_marker_header {
 	struct ethhdr hdr;
 	struct bond_marker marker;
-} bond_marker_header_t;
+} __packed bond_marker_header_t;
 
 #pragma pack()
 

drivers/net/can/mscan/mpc5xxx_can.c

@@ -247,8 +247,10 @@ static u32 __devinit mpc512x_can_get_clock(struct platform_device *ofdev,
 }
 #endif /* CONFIG_PPC_MPC512x */
 
+static struct of_device_id mpc5xxx_can_table[];
 static int __devinit mpc5xxx_can_probe(struct platform_device *ofdev)
 {
+	const struct of_device_id *match;
 	struct mpc5xxx_can_data *data;
 	struct device_node *np = ofdev->dev.of_node;
 	struct net_device *dev;
@@ -258,9 +260,10 @@ static int __devinit mpc5xxx_can_probe(struct platform_device *ofdev)
 	int irq, mscan_clksrc = 0;
 	int err = -ENOMEM;
 
-	if (!ofdev->dev.of_match)
+	match = of_match_device(mpc5xxx_can_table, &ofdev->dev);
+	if (!match)
 		return -EINVAL;
-	data = (struct mpc5xxx_can_data *)ofdev->dev.of_match->data;
+	data = match->data;
 
 	base = of_iomap(np, 0);
 	if (!base) {

drivers/net/ehea/ehea_main.c

@@ -2688,9 +2688,6 @@ static int ehea_open(struct net_device *dev)
 		netif_start_queue(dev);
 	}
 
-	init_waitqueue_head(&port->swqe_avail_wq);
-	init_waitqueue_head(&port->restart_wq);
-
 	mutex_unlock(&port->port_lock);
 
 	return ret;
@@ -3276,6 +3273,9 @@ struct ehea_port *ehea_setup_single_port(struct ehea_adapter *adapter,
 
 	INIT_WORK(&port->reset_task, ehea_reset_port);
 
+	init_waitqueue_head(&port->swqe_avail_wq);
+	init_waitqueue_head(&port->restart_wq);
+
 	ret = register_netdev(dev);
 	if (ret) {
 		pr_err("register_netdev failed. ret=%d\n", ret);

drivers/net/fs_enet/fs_enet-main.c

@@ -998,8 +998,10 @@ static const struct net_device_ops fs_enet_netdev_ops = {
 #endif
 };
 
+static struct of_device_id fs_enet_match[];
 static int __devinit fs_enet_probe(struct platform_device *ofdev)
 {
+	const struct of_device_id *match;
 	struct net_device *ndev;
 	struct fs_enet_private *fep;
 	struct fs_platform_info *fpi;
@@ -1007,14 +1009,15 @@ static int __devinit fs_enet_probe(struct platform_device *ofdev)
 	const u8 *mac_addr;
 	int privsize, len, ret = -ENODEV;
 
-	if (!ofdev->dev.of_match)
+	match = of_match_device(fs_enet_match, &ofdev->dev);
+	if (!match)
 		return -EINVAL;
 
 	fpi = kzalloc(sizeof(*fpi), GFP_KERNEL);
 	if (!fpi)
 		return -ENOMEM;
 
-	if (!IS_FEC(ofdev->dev.of_match)) {
+	if (!IS_FEC(match)) {
 		data = of_get_property(ofdev->dev.of_node, "fsl,cpm-command", &len);
 		if (!data || len != 4)
 			goto out_free_fpi;
@@ -1049,7 +1052,7 @@ static int __devinit fs_enet_probe(struct platform_device *ofdev)
 	fep->dev = &ofdev->dev;
 	fep->ndev = ndev;
 	fep->fpi = fpi;
-	fep->ops = ofdev->dev.of_match->data;
+	fep->ops = match->data;
 
 	ret = fep->ops->setup_data(ndev);
 	if (ret)

drivers/net/fs_enet/mii-fec.c

@@ -101,17 +101,20 @@ static int fs_enet_fec_mii_reset(struct mii_bus *bus)
 	return 0;
 }
 
+static struct of_device_id fs_enet_mdio_fec_match[];
 static int __devinit fs_enet_mdio_probe(struct platform_device *ofdev)
 {
+	const struct of_device_id *match;
 	struct resource res;
 	struct mii_bus *new_bus;
 	struct fec_info *fec;
 	int (*get_bus_freq)(struct device_node *);
 	int ret = -ENOMEM, clock, speed;
 
-	if (!ofdev->dev.of_match)
+	match = of_match_device(fs_enet_mdio_fec_match, &ofdev->dev);
+	if (!match)
 		return -EINVAL;
-	get_bus_freq = ofdev->dev.of_match->data;
+	get_bus_freq = match->data;
 
 	new_bus = mdiobus_alloc();
 	if (!new_bus)

drivers/net/hydra.c

@@ -98,15 +98,15 @@ static const struct net_device_ops hydra_netdev_ops = {
 	.ndo_open		= hydra_open,
 	.ndo_stop		= hydra_close,
 
-	.ndo_start_xmit		= ei_start_xmit,
+	.ndo_start_xmit		= __ei_start_xmit,
-	.ndo_tx_timeout		= ei_tx_timeout,
+	.ndo_tx_timeout		= __ei_tx_timeout,
-	.ndo_get_stats		= ei_get_stats,
+	.ndo_get_stats		= __ei_get_stats,
-	.ndo_set_multicast_list = ei_set_multicast_list,
+	.ndo_set_multicast_list = __ei_set_multicast_list,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_set_mac_address 	= eth_mac_addr,
+	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_change_mtu		= eth_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= ei_poll,
+	.ndo_poll_controller	= __ei_poll,
 #endif
 };
 
@@ -125,7 +125,7 @@ static int __devinit hydra_init(struct zorro_dev *z)
 	0x10, 0x12, 0x14, 0x16, 0x18, 0x1a, 0x1c, 0x1e,
     };
 
-    dev = alloc_ei_netdev();
+    dev = ____alloc_ei_netdev(0);
     if (!dev)
 	return -ENOMEM;
 

drivers/net/ne-h8300.c

@@ -167,7 +167,7 @@ static void cleanup_card(struct net_device *dev)
 #ifndef MODULE
 struct net_device * __init ne_probe(int unit)
 {
-	struct net_device *dev = alloc_ei_netdev();
+	struct net_device *dev = ____alloc_ei_netdev(0);
 	int err;
 
 	if (!dev)
@@ -197,15 +197,15 @@ static const struct net_device_ops ne_netdev_ops = {
 	.ndo_open		= ne_open,
 	.ndo_stop		= ne_close,
 
-	.ndo_start_xmit		= ei_start_xmit,
+	.ndo_start_xmit		= __ei_start_xmit,
-	.ndo_tx_timeout		= ei_tx_timeout,
+	.ndo_tx_timeout		= __ei_tx_timeout,
-	.ndo_get_stats		= ei_get_stats,
+	.ndo_get_stats		= __ei_get_stats,
-	.ndo_set_multicast_list = ei_set_multicast_list,
+	.ndo_set_multicast_list = __ei_set_multicast_list,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_set_mac_address 	= eth_mac_addr,
+	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_change_mtu		= eth_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= ei_poll,
+	.ndo_poll_controller	= __ei_poll,
 #endif
 };
 
@@ -637,7 +637,7 @@ int init_module(void)
 	int err;
 
 	for (this_dev = 0; this_dev < MAX_NE_CARDS; this_dev++) {
-		struct net_device *dev = alloc_ei_netdev();
+		struct net_device *dev = ____alloc_ei_netdev(0);
 		if (!dev)
 			break;
 		if (io[this_dev]) {

drivers/net/sfc/mcdi.c

@@ -50,6 +50,20 @@ static inline struct efx_mcdi_iface *efx_mcdi(struct efx_nic *efx)
 	return &nic_data->mcdi;
 }
 
+static inline void
+efx_mcdi_readd(struct efx_nic *efx, efx_dword_t *value, unsigned reg)
+{
+	struct siena_nic_data *nic_data = efx->nic_data;
+	value->u32[0] = (__force __le32)__raw_readl(nic_data->mcdi_smem + reg);
+}
+
+static inline void
+efx_mcdi_writed(struct efx_nic *efx, const efx_dword_t *value, unsigned reg)
+{
+	struct siena_nic_data *nic_data = efx->nic_data;
+	__raw_writel((__force u32)value->u32[0], nic_data->mcdi_smem + reg);
+}
+
 void efx_mcdi_init(struct efx_nic *efx)
 {
 	struct efx_mcdi_iface *mcdi;
@@ -70,8 +84,8 @@ static void efx_mcdi_copyin(struct efx_nic *efx, unsigned cmd,
 			    const u8 *inbuf, size_t inlen)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
-	unsigned pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
+	unsigned pdu = MCDI_PDU(efx);
-	unsigned doorbell = FR_CZ_MC_TREG_SMEM + MCDI_DOORBELL(efx);
+	unsigned doorbell = MCDI_DOORBELL(efx);
 	unsigned int i;
 	efx_dword_t hdr;
 	u32 xflags, seqno;
@@ -92,30 +106,28 @@ static void efx_mcdi_copyin(struct efx_nic *efx, unsigned cmd,
 			     MCDI_HEADER_SEQ, seqno,
 			     MCDI_HEADER_XFLAGS, xflags);
 
-	efx_writed(efx, &hdr, pdu);
+	efx_mcdi_writed(efx, &hdr, pdu);
 
-	for (i = 0; i < inlen; i += 4) {
+	for (i = 0; i < inlen; i += 4)
-		_efx_writed(efx, *((__le32 *)(inbuf + i)), pdu + 4 + i);
+		efx_mcdi_writed(efx, (const efx_dword_t *)(inbuf + i),
-		/* use wmb() within loop to inhibit write combining */
+				pdu + 4 + i);
-		wmb();
-	}
 
 	/* ring the doorbell with a distinctive value */
-	_efx_writed(efx, (__force __le32) 0x45789abc, doorbell);
+	EFX_POPULATE_DWORD_1(hdr, EFX_DWORD_0, 0x45789abc);
-	wmb();
+	efx_mcdi_writed(efx, &hdr, doorbell);
 }
 
 static void efx_mcdi_copyout(struct efx_nic *efx, u8 *outbuf, size_t outlen)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
-	unsigned int pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
+	unsigned int pdu = MCDI_PDU(efx);
 	int i;
 
 	BUG_ON(atomic_read(&mcdi->state) == MCDI_STATE_QUIESCENT);
 	BUG_ON(outlen & 3 || outlen >= 0x100);
 
 	for (i = 0; i < outlen; i += 4)
-		*((__le32 *)(outbuf + i)) = _efx_readd(efx, pdu + 4 + i);
+		efx_mcdi_readd(efx, (efx_dword_t *)(outbuf + i), pdu + 4 + i);
 }
 
 static int efx_mcdi_poll(struct efx_nic *efx)
@@ -123,7 +135,7 @@ static int efx_mcdi_poll(struct efx_nic *efx)
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
 	unsigned int time, finish;
 	unsigned int respseq, respcmd, error;
-	unsigned int pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
+	unsigned int pdu = MCDI_PDU(efx);
 	unsigned int rc, spins;
 	efx_dword_t reg;
 
@@ -149,8 +161,7 @@ static int efx_mcdi_poll(struct efx_nic *efx)
 
 		time = get_seconds();
 
-		rmb();
+		efx_mcdi_readd(efx, &reg, pdu);
-		efx_readd(efx, &reg, pdu);
 
 		/* All 1's indicates that shared memory is in reset (and is
 		 * not a valid header). Wait for it to come out reset before
@@ -177,7 +188,7 @@ static int efx_mcdi_poll(struct efx_nic *efx)
 			  respseq, mcdi->seqno);
 		rc = EIO;
 	} else if (error) {
-		efx_readd(efx, &reg, pdu + 4);
+		efx_mcdi_readd(efx, &reg, pdu + 4);
 		switch (EFX_DWORD_FIELD(reg, EFX_DWORD_0)) {
 #define TRANSLATE_ERROR(name)					\
 		case MC_CMD_ERR_ ## name:			\
@@ -211,21 +222,21 @@ out:
 /* Test and clear MC-rebooted flag for this port/function */
 int efx_mcdi_poll_reboot(struct efx_nic *efx)
 {
-	unsigned int addr = FR_CZ_MC_TREG_SMEM + MCDI_REBOOT_FLAG(efx);
+	unsigned int addr = MCDI_REBOOT_FLAG(efx);
 	efx_dword_t reg;
 	uint32_t value;
 
 	if (efx_nic_rev(efx) < EFX_REV_SIENA_A0)
 		return false;
 
-	efx_readd(efx, &reg, addr);
+	efx_mcdi_readd(efx, &reg, addr);
 	value = EFX_DWORD_FIELD(reg, EFX_DWORD_0);
 
 	if (value == 0)
 		return 0;
 
 	EFX_ZERO_DWORD(reg);
-	efx_writed(efx, &reg, addr);
+	efx_mcdi_writed(efx, &reg, addr);
 
 	if (value == MC_STATUS_DWORD_ASSERT)
 		return -EINTR;

drivers/net/sfc/nic.c

@@ -1937,6 +1937,13 @@ void efx_nic_get_regs(struct efx_nic *efx, void *buf)
 
 		size = min_t(size_t, table->step, 16);
 
+		if (table->offset >= efx->type->mem_map_size) {
+			/* No longer mapped; return dummy data */
+			memcpy(buf, "\xde\xc0\xad\xde", 4);
+			buf += table->rows * size;
+			continue;
+		}
+
 		for (i = 0; i < table->rows; i++) {
 			switch (table->step) {
 			case 4: /* 32-bit register or SRAM */

drivers/net/sfc/nic.h

@@ -143,10 +143,12 @@ static inline struct falcon_board *falcon_board(struct efx_nic *efx)
 /**
  * struct siena_nic_data - Siena NIC state
  * @mcdi: Management-Controller-to-Driver Interface
+ * @mcdi_smem: MCDI shared memory mapping. The mapping is always uncacheable.
  * @wol_filter_id: Wake-on-LAN packet filter id
  */
 struct siena_nic_data {
 	struct efx_mcdi_iface mcdi;
+	void __iomem *mcdi_smem;
 	int wol_filter_id;
 };
 

drivers/net/sfc/siena.c

@@ -220,12 +220,26 @@ static int siena_probe_nic(struct efx_nic *efx)
 	efx_reado(efx, &reg, FR_AZ_CS_DEBUG);
 	efx->net_dev->dev_id = EFX_OWORD_FIELD(reg, FRF_CZ_CS_PORT_NUM) - 1;
 
+	/* Initialise MCDI */
+	nic_data->mcdi_smem = ioremap_nocache(efx->membase_phys +
+					      FR_CZ_MC_TREG_SMEM,
+					      FR_CZ_MC_TREG_SMEM_STEP *
+					      FR_CZ_MC_TREG_SMEM_ROWS);
+	if (!nic_data->mcdi_smem) {
+		netif_err(efx, probe, efx->net_dev,
+			  "could not map MCDI at %llx+%x\n",
+			  (unsigned long long)efx->membase_phys +
+			  FR_CZ_MC_TREG_SMEM,
+			  FR_CZ_MC_TREG_SMEM_STEP * FR_CZ_MC_TREG_SMEM_ROWS);
+		rc = -ENOMEM;
+		goto fail1;
+	}
 	efx_mcdi_init(efx);
 
 	/* Recover from a failed assertion before probing */
 	rc = efx_mcdi_handle_assertion(efx);
 	if (rc)
-		goto fail1;
+		goto fail2;
 
 	/* Let the BMC know that the driver is now in charge of link and
 	 * filter settings. We must do this before we reset the NIC */
@@ -280,6 +294,7 @@ fail4:
 fail3:
 	efx_mcdi_drv_attach(efx, false, NULL);
 fail2:
+	iounmap(nic_data->mcdi_smem);
 fail1:
 	kfree(efx->nic_data);
 	return rc;
@@ -359,6 +374,8 @@ static int siena_init_nic(struct efx_nic *efx)
 
 static void siena_remove_nic(struct efx_nic *efx)
 {
+	struct siena_nic_data *nic_data = efx->nic_data;
+
 	efx_nic_free_buffer(efx, &efx->irq_status);
 
 	siena_reset_hw(efx, RESET_TYPE_ALL);
@@ -368,7 +385,8 @@ static void siena_remove_nic(struct efx_nic *efx)
 		efx_mcdi_drv_attach(efx, false, NULL);
 
 	/* Tear down the private nic state */
-	kfree(efx->nic_data);
+	iounmap(nic_data->mcdi_smem);
+	kfree(nic_data);
 	efx->nic_data = NULL;
 }
 
@@ -606,8 +624,7 @@ struct efx_nic_type siena_a0_nic_type = {
 	.default_mac_ops = &efx_mcdi_mac_operations,
 
 	.revision = EFX_REV_SIENA_A0,
-	.mem_map_size = (FR_CZ_MC_TREG_SMEM +
+	.mem_map_size = FR_CZ_MC_TREG_SMEM, /* MC_TREG_SMEM mapped separately */
-			 FR_CZ_MC_TREG_SMEM_STEP * FR_CZ_MC_TREG_SMEM_ROWS),
 	.txd_ptr_tbl_base = FR_BZ_TX_DESC_PTR_TBL,
 	.rxd_ptr_tbl_base = FR_BZ_RX_DESC_PTR_TBL,
 	.buf_tbl_base = FR_BZ_BUF_FULL_TBL,

drivers/net/sunhme.c

@@ -3237,15 +3237,18 @@ static void happy_meal_pci_exit(void)
 #endif
 
 #ifdef CONFIG_SBUS
+static const struct of_device_id hme_sbus_match[];
 static int __devinit hme_sbus_probe(struct platform_device *op)
 {
+	const struct of_device_id *match;
 	struct device_node *dp = op->dev.of_node;
 	const char *model = of_get_property(dp, "model", NULL);
 	int is_qfe;
 
-	if (!op->dev.of_match)
+	match = of_match_device(hme_sbus_match, &op->dev);
+	if (!match)
 		return -EINVAL;
-	is_qfe = (op->dev.of_match->data != NULL);
+	is_qfe = (match->data != NULL);
 
 	if (!is_qfe && model && !strcmp(model, "SUNW,sbus-qfe"))
 		is_qfe = 1;

drivers/net/vmxnet3/vmxnet3_ethtool.c

@@ -311,6 +311,9 @@ vmxnet3_set_flags(struct net_device *netdev, u32 data)
 		/* toggle the LRO feature*/
 		netdev->features ^= NETIF_F_LRO;
 
+		/* Update private LRO flag */
+		adapter->lro = lro_requested;
+
 		/* update harware LRO capability accordingly */
 		if (lro_requested)
 			adapter->shared->devRead.misc.uptFeatures |=