Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (119 commits)
  MIPS: Delete unused function add_temporary_entry.
  MIPS: Set default pci cache line size.
  MIPS: Flush huge TLB
  MIPS: Octeon: Remove SYS_SUPPORTS_HIGHMEM.
  MIPS: Octeon: Add support for OCTEON II PCIe
  MIPS: Octeon: Update PCI Latency timer and enable more error reporting.
  MIPS: Alchemy: Update cpu-feature-overrides
  MIPS: Alchemy: db1200: Improve PB1200 detection.
  MIPS: Alchemy: merge Au1000 and Au1300-style IRQ controller code.
  MIPS: Alchemy: chain IRQ controllers to MIPS IRQ controller
  MIPS: Alchemy: irq: register pm at irq init time
  MIPS: Alchemy: Touchscreen support on DB1100
  MIPS: Alchemy: Hook up IrDA on DB1000/DB1100
  net/irda: convert au1k_ir to platform driver.
  MIPS: Alchemy: remove unused board headers
  MTD: nand: make au1550nd.c a platform_driver
  MIPS: Netlogic: Mark Netlogic chips as SMT capable
  MIPS: Netlogic: Add support for XLP 3XX cores
  MIPS: Netlogic: Merge some of XLR/XLP wakup code
  MIPS: Netlogic: Add default XLP config.
  ...

Fix up trivial conflicts in arch/mips/kernel/{perf_event_mipsxx.c,
traps.c} and drivers/tty/serial/Makefile

18 files changed, 1046 insertions, 154 deletions

diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 1a966183e35..0c6877ea900 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -55,9 +55,11 @@ obj-$(CONFIG_CPU_TX49XX)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_VR41XX)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= octeon_switch.o
 obj-$(CONFIG_CPU_XLR)		+= r4k_fpu.o r4k_switch.o
+obj-$(CONFIG_CPU_XLP)		+= r4k_fpu.o r4k_switch.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP_UP)		+= smp-up.o
+obj-$(CONFIG_CPU_BMIPS)		+= smp-bmips.o bmips_vec.o
 
 obj-$(CONFIG_MIPS_MT)		+= mips-mt.o
 obj-$(CONFIG_MIPS_MT_FPAFF)	+= mips-mt-fpaff.o
diff --git a/arch/mips/kernel/bmips_vec.S b/arch/mips/kernel/bmips_vec.S
new file mode 100644
index 00000000000..e908e81330b
--- /dev/null
+++ b/arch/mips/kernel/bmips_vec.S
@@ -0,0 +1,255 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2011 by Kevin Cernekee (cernekee@gmail.com)
+ *
+ * Reset/NMI/re-entry vectors for BMIPS processors
+ */
+
+#include <linux/init.h>
+
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/cacheops.h>
+#include <asm/regdef.h>
+#include <asm/mipsregs.h>
+#include <asm/stackframe.h>
+#include <asm/addrspace.h>
+#include <asm/hazards.h>
+#include <asm/bmips.h>
+
+	.macro	BARRIER
+	.set	mips32
+	_ssnop
+	_ssnop
+	_ssnop
+	.set	mips0
+	.endm
+
+	__CPUINIT
+
+/***********************************************************************
+ * Alternate CPU1 startup vector for BMIPS4350
+ *
+ * On some systems the bootloader has already started CPU1 and configured
+ * it to resume execution at 0x8000_0200 (!BEV IV vector) when it is
+ * triggered by the SW1 interrupt.  If that is the case we try to move
+ * it to a more convenient place: BMIPS_WARM_RESTART_VEC @ 0x8000_0380.
+ ***********************************************************************/
+
+LEAF(bmips_smp_movevec)
+	la	k0, 1f
+	li	k1, CKSEG1
+	or	k0, k1
+	jr	k0
+
+1:
+	/* clear IV, pending IPIs */
+	mtc0	zero, CP0_CAUSE
+
+	/* re-enable IRQs to wait for SW1 */
+	li	k0, ST0_IE | ST0_BEV | STATUSF_IP1
+	mtc0	k0, CP0_STATUS
+
+	/* set up CPU1 CBR; move BASE to 0xa000_0000 */
+	li	k0, 0xff400000
+	mtc0	k0, $22, 6
+	li	k1, CKSEG1 | BMIPS_RELO_VECTOR_CONTROL_1
+	or	k0, k1
+	li	k1, 0xa0080000
+	sw	k1, 0(k0)
+
+	/* wait here for SW1 interrupt from bmips_boot_secondary() */
+	wait
+
+	la	k0, bmips_reset_nmi_vec
+	li	k1, CKSEG1
+	or	k0, k1
+	jr	k0
+END(bmips_smp_movevec)
+
+/***********************************************************************
+ * Reset/NMI vector
+ * For BMIPS processors that can relocate their exception vectors, this
+ * entire function gets copied to 0x8000_0000.
+ ***********************************************************************/
+
+NESTED(bmips_reset_nmi_vec, PT_SIZE, sp)
+	.set	push
+	.set	noat
+	.align	4
+
+#ifdef CONFIG_SMP
+	/* if the NMI bit is clear, assume this is a CPU1 reset instead */
+	li	k1, (1 << 19)
+	mfc0	k0, CP0_STATUS
+	and	k0, k1
+	beqz	k0, bmips_smp_entry
+
+#if defined(CONFIG_CPU_BMIPS5000)
+	/* if we're not on core 0, this must be the SMP boot signal */
+	li	k1, (3 << 25)
+	mfc0	k0, $22
+	and	k0, k1
+	bnez	k0, bmips_smp_entry
+#endif
+#endif /* CONFIG_SMP */
+
+	/* nope, it's just a regular NMI */
+	SAVE_ALL
+	move	a0, sp
+
+	/* clear EXL, ERL, BEV so that TLB refills still work */
+	mfc0	k0, CP0_STATUS
+	li	k1, ST0_ERL | ST0_EXL | ST0_BEV | ST0_IE
+	or	k0, k1
+	xor	k0, k1
+	mtc0	k0, CP0_STATUS
+	BARRIER
+
+	/* jump to the NMI handler function */
+	la	k0, nmi_handler
+	jr	k0
+
+	RESTORE_ALL
+	.set	mips3
+	eret
+
+/***********************************************************************
+ * CPU1 reset vector (used for the initial boot only)
+ * This is still part of bmips_reset_nmi_vec().
+ ***********************************************************************/
+
+#ifdef CONFIG_SMP
+
+bmips_smp_entry:
+
+	/* set up CP0 STATUS; enable FPU */
+	li	k0, 0x30000000
+	mtc0	k0, CP0_STATUS
+	BARRIER
+
+	/* set local CP0 CONFIG to make kseg0 cacheable, write-back */
+	mfc0	k0, CP0_CONFIG
+	ori	k0, 0x07
+	xori	k0, 0x04
+	mtc0	k0, CP0_CONFIG
+
+#if defined(CONFIG_CPU_BMIPS4350) || defined(CONFIG_CPU_BMIPS4380)
+	/* initialize CPU1's local I-cache */
+	li	k0, 0x80000000
+	li	k1, 0x80010000
+	mtc0	zero, $28
+	mtc0	zero, $28, 1
+	BARRIER
+
+1:	cache	Index_Store_Tag_I, 0(k0)
+	addiu	k0, 16
+	bne	k0, k1, 1b
+#elif defined(CONFIG_CPU_BMIPS5000)
+	/* set exception vector base */
+	la	k0, ebase
+	lw	k0, 0(k0)
+	mtc0	k0, $15, 1
+	BARRIER
+#endif
+
+	/* jump back to kseg0 in case we need to remap the kseg1 area */
+	la	k0, 1f
+	jr	k0
+1:
+	la	k0, bmips_enable_xks01
+	jalr	k0
+
+	/* use temporary stack to set up upper memory TLB */
+	li	sp, BMIPS_WARM_RESTART_VEC
+	la	k0, plat_wired_tlb_setup
+	jalr	k0
+
+	/* switch to permanent stack and continue booting */
+
+	.global	bmips_secondary_reentry
+bmips_secondary_reentry:
+	la	k0, bmips_smp_boot_sp
+	lw	sp, 0(k0)
+	la	k0, bmips_smp_boot_gp
+	lw	gp, 0(k0)
+	la	k0, start_secondary
+	jr	k0
+
+#endif /* CONFIG_SMP */
+
+	.align	4
+	.global	bmips_reset_nmi_vec_end
+bmips_reset_nmi_vec_end:
+
+END(bmips_reset_nmi_vec)
+
+	.set	pop
+	.previous
+
+/***********************************************************************
+ * CPU1 warm restart vector (used for second and subsequent boots).
+ * Also used for S2 standby recovery (PM).
+ * This entire function gets copied to (BMIPS_WARM_RESTART_VEC)
+ ***********************************************************************/
+
+LEAF(bmips_smp_int_vec)
+
+	.align	4
+	mfc0	k0, CP0_STATUS
+	ori	k0, 0x01
+	xori	k0, 0x01
+	mtc0	k0, CP0_STATUS
+	eret
+
+	.align	4
+	.global	bmips_smp_int_vec_end
+bmips_smp_int_vec_end:
+
+END(bmips_smp_int_vec)
+
+/***********************************************************************
+ * XKS01 support
+ * Certain CPUs support extending kseg0 to 1024MB.
+ ***********************************************************************/
+
+	__CPUINIT
+
+LEAF(bmips_enable_xks01)
+
+#if defined(CONFIG_XKS01)
+
+#if defined(CONFIG_CPU_BMIPS4380)
+	mfc0	t0, $22, 3
+	li	t1, 0x1ff0
+	li	t2, (1 << 12) | (1 << 9)
+	or	t0, t1
+	xor	t0, t1
+	or	t0, t2
+	mtc0	t0, $22, 3
+	BARRIER
+#elif defined(CONFIG_CPU_BMIPS5000)
+	mfc0	t0, $22, 5
+	li	t1, 0x01ff
+	li	t2, (1 << 8) | (1 << 5)
+	or	t0, t1
+	xor	t0, t1
+	or	t0, t2
+	mtc0	t0, $22, 5
+	BARRIER
+#else
+
+#error Missing XKS01 setup
+
+#endif
+
+#endif /* defined(CONFIG_XKS01) */
+
+	jr	ra
+
+END(bmips_enable_xks01)
+
+	.previous
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 32103cc2a25..4d735d0e58f 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
+#include <linux/module.h>
 #include <asm/branch.h>
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>
@@ -17,28 +18,22 @@
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 
-/*
- * Compute the return address and do emulate branch simulation, if required.
+/**
+ * __compute_return_epc_for_insn - Computes the return address and do emulate
+ *				    branch simulation, if required.
+ *
+ * @regs:	Pointer to pt_regs
+ * @insn:	branch instruction to decode
+ * @returns:	-EFAULT on error and forces SIGBUS, and on success
+ *		returns 0 or BRANCH_LIKELY_TAKEN as appropriate after
+ *		evaluating the branch.
  */
-int __compute_return_epc(struct pt_regs *regs)
+int __compute_return_epc_for_insn(struct pt_regs *regs,
+				   union mips_instruction insn)
 {
-	unsigned int __user *addr;
 	unsigned int bit, fcr31, dspcontrol;
-	long epc;
-	union mips_instruction insn;
-
-	epc = regs->cp0_epc;
-	if (epc & 3)
-		goto unaligned;
-
-	/*
-	 * Read the instruction
-	 */
-	addr = (unsigned int __user *) epc;
-	if (__get_user(insn.word, addr)) {
-		force_sig(SIGSEGV, current);
-		return -EFAULT;
-	}
+	long epc = regs->cp0_epc;
+	int ret = 0;
 
 	switch (insn.i_format.opcode) {
 	/*
@@ -64,18 +59,22 @@ int __compute_return_epc(struct pt_regs *regs)
 		switch (insn.i_format.rt) {
 	 	case bltz_op:
 		case bltzl_op:
-			if ((long)regs->regs[insn.i_format.rs] < 0)
+			if ((long)regs->regs[insn.i_format.rs] < 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
-			else
+				if (insn.i_format.rt == bltzl_op)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
 				epc += 8;
 			regs->cp0_epc = epc;
 			break;
 
 		case bgez_op:
 		case bgezl_op:
-			if ((long)regs->regs[insn.i_format.rs] >= 0)
+			if ((long)regs->regs[insn.i_format.rs] >= 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
-			else
+				if (insn.i_format.rt == bgezl_op)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
 				epc += 8;
 			regs->cp0_epc = epc;
 			break;
@@ -83,9 +82,11 @@ int __compute_return_epc(struct pt_regs *regs)
 		case bltzal_op:
 		case bltzall_op:
 			regs->regs[31] = epc + 8;
-			if ((long)regs->regs[insn.i_format.rs] < 0)
+			if ((long)regs->regs[insn.i_format.rs] < 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
-			else
+				if (insn.i_format.rt == bltzall_op)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
 				epc += 8;
 			regs->cp0_epc = epc;
 			break;
@@ -93,12 +94,15 @@ int __compute_return_epc(struct pt_regs *regs)
 		case bgezal_op:
 		case bgezall_op:
 			regs->regs[31] = epc + 8;
-			if ((long)regs->regs[insn.i_format.rs] >= 0)
+			if ((long)regs->regs[insn.i_format.rs] >= 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
-			else
+				if (insn.i_format.rt == bgezall_op)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
 				epc += 8;
 			regs->cp0_epc = epc;
 			break;
+
 		case bposge32_op:
 			if (!cpu_has_dsp)
 				goto sigill;
@@ -133,9 +137,11 @@ int __compute_return_epc(struct pt_regs *regs)
 	case beq_op:
 	case beql_op:
 		if (regs->regs[insn.i_format.rs] ==
-		    regs->regs[insn.i_format.rt])
+		    regs->regs[insn.i_format.rt]) {
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
-		else
+			if (insn.i_format.rt == beql_op)
+				ret = BRANCH_LIKELY_TAKEN;
+		} else
 			epc += 8;
 		regs->cp0_epc = epc;
 		break;
@@ -143,9 +149,11 @@ int __compute_return_epc(struct pt_regs *regs)
 	case bne_op:
 	case bnel_op:
 		if (regs->regs[insn.i_format.rs] !=
-		    regs->regs[insn.i_format.rt])
+		    regs->regs[insn.i_format.rt]) {
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
-		else
+			if (insn.i_format.rt == bnel_op)
+				ret = BRANCH_LIKELY_TAKEN;
+		} else
 			epc += 8;
 		regs->cp0_epc = epc;
 		break;
@@ -153,9 +161,11 @@ int __compute_return_epc(struct pt_regs *regs)
 	case blez_op: /* not really i_format */
 	case blezl_op:
 		/* rt field assumed to be zero */
-		if ((long)regs->regs[insn.i_format.rs] <= 0)
+		if ((long)regs->regs[insn.i_format.rs] <= 0) {
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
-		else
+			if (insn.i_format.rt == bnel_op)
+				ret = BRANCH_LIKELY_TAKEN;
+		} else
 			epc += 8;
 		regs->cp0_epc = epc;
 		break;
@@ -163,9 +173,11 @@ int __compute_return_epc(struct pt_regs *regs)
 	case bgtz_op:
 	case bgtzl_op:
 		/* rt field assumed to be zero */
-		if ((long)regs->regs[insn.i_format.rs] > 0)
+		if ((long)regs->regs[insn.i_format.rs] > 0) {
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
-		else
+			if (insn.i_format.rt == bnel_op)
+				ret = BRANCH_LIKELY_TAKEN;
+		} else
 			epc += 8;
 		regs->cp0_epc = epc;
 		break;
@@ -187,18 +199,22 @@ int __compute_return_epc(struct pt_regs *regs)
 		switch (insn.i_format.rt & 3) {
 		case 0:	/* bc1f */
 		case 2:	/* bc1fl */
-			if (~fcr31 & (1 << bit))
+			if (~fcr31 & (1 << bit)) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
-			else
+				if (insn.i_format.rt == 2)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
 				epc += 8;
 			regs->cp0_epc = epc;
 			break;
 
 		case 1:	/* bc1t */
 		case 3:	/* bc1tl */
-			if (fcr31 & (1 << bit))
+			if (fcr31 & (1 << bit)) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
-			else
+				if (insn.i_format.rt == 3)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
 				epc += 8;
 			regs->cp0_epc = epc;
 			break;
@@ -239,15 +255,39 @@ int __compute_return_epc(struct pt_regs *regs)
 #endif
 	}
 
-	return 0;
+	return ret;
 
-unaligned:
-	printk("%s: unaligned epc - sending SIGBUS.\n", current->comm);
+sigill:
+	printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm);
 	force_sig(SIGBUS, current);
 	return -EFAULT;
+}
+EXPORT_SYMBOL_GPL(__compute_return_epc_for_insn);
 
-sigill:
-	printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm);
+int __compute_return_epc(struct pt_regs *regs)
+{
+	unsigned int __user *addr;
+	long epc;
+	union mips_instruction insn;
+
+	epc = regs->cp0_epc;
+	if (epc & 3)
+		goto unaligned;
+
+	/*
+	 * Read the instruction
+	 */
+	addr = (unsigned int __user *) epc;
+	if (__get_user(insn.word, addr)) {
+		force_sig(SIGSEGV, current);
+		return -EFAULT;
+	}
+
+	return __compute_return_epc_for_insn(regs, insn);
+
+unaligned:
+	printk("%s: unaligned epc - sending SIGBUS.\n", current->comm);
 	force_sig(SIGBUS, current);
 	return -EFAULT;
+
 }
diff --git a/arch/mips/kernel/cevt-bcm1480.c b/arch/mips/kernel/cevt-bcm1480.c
index 36c3898b76d..69bbfae183b 100644
--- a/arch/mips/kernel/cevt-bcm1480.c
+++ b/arch/mips/kernel/cevt-bcm1480.c
@@ -145,7 +145,7 @@ void __cpuinit sb1480_clockevent_init(void)
 	bcm1480_unmask_irq(cpu, irq);
 
 	action->handler	= sibyte_counter_handler;
-	action->flags	= IRQF_DISABLED | IRQF_PERCPU | IRQF_TIMER;
+	action->flags	= IRQF_PERCPU | IRQF_TIMER;
 	action->name	= name;
 	action->dev_id	= cd;
 
diff --git a/arch/mips/kernel/cevt-ds1287.c b/arch/mips/kernel/cevt-ds1287.c
index 939157e397b..ed648cb5a69 100644
--- a/arch/mips/kernel/cevt-ds1287.c
+++ b/arch/mips/kernel/cevt-ds1287.c
@@ -108,7 +108,7 @@ static irqreturn_t ds1287_interrupt(int irq, void *dev_id)
 
 static struct irqaction ds1287_irqaction = {
 	.handler	= ds1287_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_PERCPU | IRQF_TIMER,
+	.flags		= IRQF_PERCPU | IRQF_TIMER,
 	.name		= "ds1287",
 };
 
diff --git a/arch/mips/kernel/cevt-gt641xx.c b/arch/mips/kernel/cevt-gt641xx.c
index 339f3639b90..831b47585b7 100644
--- a/arch/mips/kernel/cevt-gt641xx.c
+++ b/arch/mips/kernel/cevt-gt641xx.c
@@ -114,7 +114,7 @@ static irqreturn_t gt641xx_timer0_interrupt(int irq, void *dev_id)
 
 static struct irqaction gt641xx_timer0_irqaction = {
 	.handler	= gt641xx_timer0_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_PERCPU | IRQF_TIMER,
+	.flags		= IRQF_PERCPU | IRQF_TIMER,
 	.name		= "gt641xx_timer0",
 };
 
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index e2d8e199be3..51095dd9599 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -84,7 +84,7 @@ out:
 
 struct irqaction c0_compare_irqaction = {
 	.handler = c0_compare_interrupt,
-	.flags = IRQF_DISABLED | IRQF_PERCPU | IRQF_TIMER,
+	.flags = IRQF_PERCPU | IRQF_TIMER,
 	.name = "timer",
 };
 
diff --git a/arch/mips/kernel/cevt-sb1250.c b/arch/mips/kernel/cevt-sb1250.c
index 590c54f28a8..e73439fd685 100644
--- a/arch/mips/kernel/cevt-sb1250.c
+++ b/arch/mips/kernel/cevt-sb1250.c
@@ -144,7 +144,7 @@ void __cpuinit sb1250_clockevent_init(void)
 	sb1250_unmask_irq(cpu, irq);
 
 	action->handler	= sibyte_counter_handler;
-	action->flags	= IRQF_DISABLED | IRQF_PERCPU | IRQF_TIMER;
+	action->flags	= IRQF_PERCPU | IRQF_TIMER;
 	action->name	= name;
 	action->dev_id	= cd;
 
diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c
index f0ab92a1b05..e5c30b1d086 100644
--- a/arch/mips/kernel/cevt-txx9.c
+++ b/arch/mips/kernel/cevt-txx9.c
@@ -146,7 +146,7 @@ static irqreturn_t txx9tmr_interrupt(int irq, void *dev_id)
 
 static struct irqaction txx9tmr_irq = {
 	.handler	= txx9tmr_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_PERCPU | IRQF_TIMER,
+	.flags		= IRQF_PERCPU | IRQF_TIMER,
 	.name		= "txx9tmr",
 	.dev_id		= &txx9_clock_event_device,
 };
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index c7d3cf1ce46..0bab464b8e3 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -191,6 +191,8 @@ void __init check_wait(void)
 	case CPU_CAVIUM_OCTEON_PLUS:
 	case CPU_CAVIUM_OCTEON2:
 	case CPU_JZRISC:
+	case CPU_XLR:
+	case CPU_XLP:
 		cpu_wait = r4k_wait;
 		break;
 
@@ -1014,6 +1016,13 @@ static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu)
 {
 	decode_configs(c);
 
+	if ((c->processor_id & 0xff00) == PRID_IMP_NETLOGIC_AU13XX) {
+		c->cputype = CPU_ALCHEMY;
+		__cpu_name[cpu] = "Au1300";
+		/* following stuff is not for Alchemy */
+		return;
+	}
+
 	c->options = (MIPS_CPU_TLB       |
 			MIPS_CPU_4KEX    |
 			MIPS_CPU_COUNTER |
@@ -1023,6 +1032,12 @@ static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu)
 			MIPS_CPU_LLSC);
 
 	switch (c->processor_id & 0xff00) {
+	case PRID_IMP_NETLOGIC_XLP8XX:
+	case PRID_IMP_NETLOGIC_XLP3XX:
+		c->cputype = CPU_XLP;
+		__cpu_name[cpu] = "Netlogic XLP";
+		break;
+
 	case PRID_IMP_NETLOGIC_XLR732:
 	case PRID_IMP_NETLOGIC_XLR716:
 	case PRID_IMP_NETLOGIC_XLR532:
@@ -1053,14 +1068,21 @@ static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu)
 		break;
 
 	default:
-		printk(KERN_INFO "Unknown Netlogic chip id [%02x]!\n",
+		pr_info("Unknown Netlogic chip id [%02x]!\n",
 		       c->processor_id);
 		c->cputype = CPU_XLR;
 		break;
 	}
 
-	c->isa_level = MIPS_CPU_ISA_M64R1;
-	c->tlbsize = ((read_c0_config1() >> 25) & 0x3f) + 1;
+	if (c->cputype == CPU_XLP) {
+		c->isa_level = MIPS_CPU_ISA_M64R2;
+		c->options |= (MIPS_CPU_FPU | MIPS_CPU_ULRI | MIPS_CPU_MCHECK);
+		/* This will be updated again after all threads are woken up */
+		c->tlbsize = ((read_c0_config6() >> 16) & 0xffff) + 1;
+	} else {
+		c->isa_level = MIPS_CPU_ISA_M64R1;
+		c->tlbsize = ((read_c0_config1() >> 25) & 0x3f) + 1;
+	}
 }
 
 #ifdef CONFIG_64BIT
diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c
index 7047bff35ea..c5bc344fc74 100644
--- a/arch/mips/kernel/i8253.c
+++ b/arch/mips/kernel/i8253.c
@@ -19,7 +19,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction irq0  = {
 	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER,
+	.flags = IRQF_NOBALANCING | IRQF_TIMER,
 	.name = "timer"
 };
 
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index ee28683fc2a..158467da9bc 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -25,10 +25,12 @@
 
 #include <linux/kprobes.h>
 #include <linux/preempt.h>
+#include <linux/uaccess.h>
 #include <linux/kdebug.h>
 #include <linux/slab.h>
 
 #include <asm/ptrace.h>
+#include <asm/branch.h>
 #include <asm/break.h>
 #include <asm/inst.h>
 
@@ -112,17 +114,49 @@ insn_ok:
 	return 0;
 }
 
+/*
+ * insn_has_ll_or_sc function checks whether instruction is ll or sc
+ * one; putting breakpoint on top of atomic ll/sc pair is bad idea;
+ * so we need to prevent it and refuse kprobes insertion for such
+ * instructions; cannot do much about breakpoint in the middle of
+ * ll/sc pair; it is upto user to avoid those places
+ */
+static int __kprobes insn_has_ll_or_sc(union mips_instruction insn)
+{
+	int ret = 0;
+
+	switch (insn.i_format.opcode) {
+	case ll_op:
+	case lld_op:
+	case sc_op:
+	case scd_op:
+		ret = 1;
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
 	union mips_instruction insn;
 	union mips_instruction prev_insn;
 	int ret = 0;
 
-	prev_insn = p->addr[-1];
 	insn = p->addr[0];
 
-	if (insn_has_delayslot(insn) || insn_has_delayslot(prev_insn)) {
-		pr_notice("Kprobes for branch and jump instructions are not supported\n");
+	if (insn_has_ll_or_sc(insn)) {
+		pr_notice("Kprobes for ll and sc instructions are not"
+			  "supported\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if ((probe_kernel_read(&prev_insn, p->addr - 1,
+				sizeof(mips_instruction)) == 0) &&
+				insn_has_delayslot(prev_insn)) {
+		pr_notice("Kprobes for branch delayslot are not supported\n");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -138,9 +172,20 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	 * In the kprobe->ainsn.insn[] array we store the original
 	 * instruction at index zero and a break trap instruction at
 	 * index one.
+	 *
+	 * On MIPS arch if the instruction at probed address is a
+	 * branch instruction, we need to execute the instruction at
+	 * Branch Delayslot (BD) at the time of probe hit. As MIPS also
+	 * doesn't have single stepping support, the BD instruction can
+	 * not be executed in-line and it would be executed on SSOL slot
+	 * using a normal breakpoint instruction in the next slot.
+	 * So, read the instruction and save it for later execution.
 	 */
+	if (insn_has_delayslot(insn))
+		memcpy(&p->ainsn.insn[0], p->addr + 1, sizeof(kprobe_opcode_t));
+	else
+		memcpy(&p->ainsn.insn[0], p->addr, sizeof(kprobe_opcode_t));
 
-	memcpy(&p->ainsn.insn[0], p->addr, sizeof(kprobe_opcode_t));
 	p->ainsn.insn[1] = breakpoint2_insn;
 	p->opcode = *p->addr;
 
@@ -191,16 +236,96 @@ static void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 	kcb->kprobe_saved_epc = regs->cp0_epc;
 }
 
-static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
+/**
+ * evaluate_branch_instrucion -
+ *
+ * Evaluate the branch instruction at probed address during probe hit. The
+ * result of evaluation would be the updated epc. The insturction in delayslot
+ * would actually be single stepped using a normal breakpoint) on SSOL slot.
+ *
+ * The result is also saved in the kprobe control block for later use,
+ * in case we need to execute the delayslot instruction. The latter will be
+ * false for NOP instruction in dealyslot and the branch-likely instructions
+ * when the branch is taken. And for those cases we set a flag as
+ * SKIP_DELAYSLOT in the kprobe control block
+ */
+static int evaluate_branch_instruction(struct kprobe *p, struct pt_regs *regs,
+					struct kprobe_ctlblk *kcb)
 {
+	union mips_instruction insn = p->opcode;
+	long epc;
+	int ret = 0;
+
+	epc = regs->cp0_epc;
+	if (epc & 3)
+		goto unaligned;
+
+	if (p->ainsn.insn->word == 0)
+		kcb->flags |= SKIP_DELAYSLOT;
+	else
+		kcb->flags &= ~SKIP_DELAYSLOT;
+
+	ret = __compute_return_epc_for_insn(regs, insn);
+	if (ret < 0)
+		return ret;
+
+	if (ret == BRANCH_LIKELY_TAKEN)
+		kcb->flags |= SKIP_DELAYSLOT;
+
+	kcb->target_epc = regs->cp0_epc;
+
+	return 0;
+
+unaligned:
+	pr_notice("%s: unaligned epc - sending SIGBUS.\n", current->comm);
+	force_sig(SIGBUS, current);
+	return -EFAULT;
+
+}
+
+static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs,
+						struct kprobe_ctlblk *kcb)
+{
+	int ret = 0;
+
 	regs->cp0_status &= ~ST0_IE;
 
 	/* single step inline if the instruction is a break */
 	if (p->opcode.word == breakpoint_insn.word ||
 	    p->opcode.word == breakpoint2_insn.word)
 		regs->cp0_epc = (unsigned long)p->addr;
-	else
-		regs->cp0_epc = (unsigned long)&p->ainsn.insn[0];
+	else if (insn_has_delayslot(p->opcode)) {
+		ret = evaluate_branch_instruction(p, regs, kcb);
+		if (ret < 0) {
+			pr_notice("Kprobes: Error in evaluating branch\n");
+			return;
+		}
+	}
+	regs->cp0_epc = (unsigned long)&p->ainsn.insn[0];
+}
+
+/*
+ * Called after single-stepping.  p->addr is the address of the
+ * instruction whose first byte has been replaced by the "break 0"
+ * instruction.  To avoid the SMP problems that can occur when we
+ * temporarily put back the original opcode to single-step, we
+ * single-stepped a copy of the instruction.  The address of this
+ * copy is p->ainsn.insn.
+ *
+ * This function prepares to return from the post-single-step
+ * breakpoint trap. In case of branch instructions, the target
+ * epc to be restored.
+ */
+static void __kprobes resume_execution(struct kprobe *p,
+				       struct pt_regs *regs,
+				       struct kprobe_ctlblk *kcb)
+{
+	if (insn_has_delayslot(p->opcode))
+		regs->cp0_epc = kcb->target_epc;
+	else {
+		unsigned long orig_epc = kcb->kprobe_saved_epc;
+		regs->cp0_epc = orig_epc + 4;
+	}
 }
 
 static int __kprobes kprobe_handler(struct pt_regs *regs)
@@ -239,8 +364,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			save_previous_kprobe(kcb);
 			set_current_kprobe(p, regs, kcb);
 			kprobes_inc_nmissed_count(p);
-			prepare_singlestep(p, regs);
+			prepare_singlestep(p, regs, kcb);
 			kcb->kprobe_status = KPROBE_REENTER;
+			if (kcb->flags & SKIP_DELAYSLOT) {
+				resume_execution(p, regs, kcb);
+				restore_previous_kprobe(kcb);
+				preempt_enable_no_resched();
+			}
 			return 1;
 		} else {
 			if (addr->word != breakpoint_insn.word) {
@@ -284,8 +414,16 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	}
 
 ss_probe:
-	prepare_singlestep(p, regs);
-	kcb->kprobe_status = KPROBE_HIT_SS;
+	prepare_singlestep(p, regs, kcb);
+	if (kcb->flags & SKIP_DELAYSLOT) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		if (p->post_handler)
+			p->post_handler(p, regs, 0);
+		resume_execution(p, regs, kcb);
+		preempt_enable_no_resched();
+	} else
+		kcb->kprobe_status = KPROBE_HIT_SS;
+
 	return 1;
 
 no_kprobe:
@@ -294,25 +432,6 @@ no_kprobe:
 
 }
 
-/*
- * Called after single-stepping.  p->addr is the address of the
- * instruction whose first byte has been replaced by the "break 0"
- * instruction.  To avoid the SMP problems that can occur when we
- * temporarily put back the original opcode to single-step, we
- * single-stepped a copy of the instruction.  The address of this
- * copy is p->ainsn.insn.
- *
- * This function prepares to return from the post-single-step
- * breakpoint trap.
- */
-static void __kprobes resume_execution(struct kprobe *p,
-				       struct pt_regs *regs,
-				       struct kprobe_ctlblk *kcb)
-{
-	unsigned long orig_epc = kcb->kprobe_saved_epc;
-	regs->cp0_epc = orig_epc + 4;
-}
-
 static inline int post_kprobe_handler(struct pt_regs *regs)
 {
 	struct kprobe *cur = kprobe_running();
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 315fc0b250f..e3b897acfbc 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -621,11 +621,6 @@ static int mipspmu_event_init(struct perf_event *event)
 		return -ENODEV;
 
 	if (!atomic_inc_not_zero(&active_events)) {
-		if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
-			atomic_dec(&active_events);
-			return -EINVAL;
-		}
-
 		mutex_lock(&pmu_reserve_mutex);
 		if (atomic_read(&active_events) == 0)
 			err = mipspmu_get_irq();
@@ -638,11 +633,7 @@ static int mipspmu_event_init(struct perf_event *event)
 	if (err)
 		return err;
 
-	err = __hw_perf_event_init(event);
-	if (err)
-		hw_perf_event_destroy(event);
-
-	return err;
+	return __hw_perf_event_init(event);
 }
 
 static struct pmu pmu = {
@@ -712,18 +703,6 @@ static const struct mips_perf_event *mipspmu_map_cache_event(u64 config)
 
 }
 
-static int validate_event(struct cpu_hw_events *cpuc,
-	       struct perf_event *event)
-{
-	struct hw_perf_event fake_hwc = event->hw;
-
-	/* Allow mixed event group. So return 1 to pass validation. */
-	if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
-		return 1;
-
-	return mipsxx_pmu_alloc_counter(cpuc, &fake_hwc) >= 0;
-}
-
 static int validate_group(struct perf_event *event)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
@@ -731,15 +710,15 @@ static int validate_group(struct perf_event *event)
 
 	memset(&fake_cpuc, 0, sizeof(fake_cpuc));
 
-	if (!validate_event(&fake_cpuc, leader))
+	if (mipsxx_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0)
 		return -EINVAL;
 
 	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
-		if (!validate_event(&fake_cpuc, sibling))
+		if (mipsxx_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0)
 			return -EINVAL;
 	}
 
-	if (!validate_event(&fake_cpuc, event))
+	if (mipsxx_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0)
 		return -EINVAL;
 
 	return 0;
@@ -1279,13 +1258,14 @@ static int __hw_perf_event_init(struct perf_event *event)
 	}
 
 	err = 0;
-	if (event->group_leader != event) {
+	if (event->group_leader != event)
 		err = validate_group(event);
-		if (err)
-			return -EINVAL;
-	}
 
 	event->destroy = hw_perf_event_destroy;
+
+	if (err)
+		event->destroy(event);
+
 	return err;
 }
 
@@ -1380,20 +1360,10 @@ static irqreturn_t mipsxx_pmu_handle_irq(int irq, void *dev)
 }
 
 /* 24K */
-#define IS_UNSUPPORTED_24K_EVENT(r, b)					\
-	((b) == 12 || (r) == 151 || (r) == 152 || (b) == 26 ||		\
-	 (b) == 27 || (r) == 28 || (r) == 158 || (b) == 31 ||		\
-	 (b) == 32 || (b) == 34 || (b) == 36 || (r) == 168 ||		\
-	 (r) == 172 || (b) == 47 || ((b) >= 56 && (b) <= 63) ||		\
-	 ((b) >= 68 && (b) <= 127))
 #define IS_BOTH_COUNTERS_24K_EVENT(b)					\
 	((b) == 0 || (b) == 1 || (b) == 11)
 
 /* 34K */
-#define IS_UNSUPPORTED_34K_EVENT(r, b)					\
-	((b) == 12 || (r) == 27 || (r) == 158 || (b) == 36 ||		\
-	 (b) == 38 || (r) == 175 || ((b) >= 56 && (b) <= 63) ||		\
-	 ((b) >= 68 && (b) <= 127))
 #define IS_BOTH_COUNTERS_34K_EVENT(b)					\
 	((b) == 0 || (b) == 1 || (b) == 11)
 #ifdef CONFIG_MIPS_MT_SMP
@@ -1406,20 +1376,10 @@ static irqreturn_t mipsxx_pmu_handle_irq(int irq, void *dev)
 #endif
 
 /* 74K */
-#define IS_UNSUPPORTED_74K_EVENT(r, b)					\
-	((r) == 5 || ((r) >= 135 && (r) <= 137) ||			\
-	 ((b) >= 10 && (b) <= 12) || (b) == 22 || (b) == 27 ||		\
-	 (b) == 33 || (b) == 34 || ((b) >= 47 && (b) <= 49) ||		\
-	 (r) == 178 || (b) == 55 || (b) == 57 || (b) == 60 ||		\
-	 (b) == 61 || (r) == 62 || (r) == 191 ||			\
-	 ((b) >= 64 && (b) <= 127))
 #define IS_BOTH_COUNTERS_74K_EVENT(b)					\
 	((b) == 0 || (b) == 1)
 
 /* 1004K */
-#define IS_UNSUPPORTED_1004K_EVENT(r, b)				\
-	((b) == 12 || (r) == 27 || (r) == 158 || (b) == 38 ||		\
-	 (r) == 175 || (b) == 63 || ((b) >= 68 && (b) <= 127))
 #define IS_BOTH_COUNTERS_1004K_EVENT(b)					\
 	((b) == 0 || (b) == 1 || (b) == 11)
 #ifdef CONFIG_MIPS_MT_SMP
@@ -1445,11 +1405,10 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config)
 	unsigned int raw_id = config & 0xff;
 	unsigned int base_id = raw_id & 0x7f;
 
+	raw_event.event_id = base_id;
+
 	switch (current_cpu_type()) {
 	case CPU_24K:
-		if (IS_UNSUPPORTED_24K_EVENT(raw_id, base_id))
-			return ERR_PTR(-EOPNOTSUPP);
-		raw_event.event_id = base_id;
 		if (IS_BOTH_COUNTERS_24K_EVENT(base_id))
 			raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD;
 		else
@@ -1464,9 +1423,6 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config)
 #endif
 		break;
 	case CPU_34K:
-		if (IS_UNSUPPORTED_34K_EVENT(raw_id, base_id))
-			return ERR_PTR(-EOPNOTSUPP);
-		raw_event.event_id = base_id;
 		if (IS_BOTH_COUNTERS_34K_EVENT(base_id))
 			raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD;
 		else
@@ -1482,9 +1438,6 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config)
 #endif
 		break;
 	case CPU_74K:
-		if (IS_UNSUPPORTED_74K_EVENT(raw_id, base_id))
-			return ERR_PTR(-EOPNOTSUPP);
-		raw_event.event_id = base_id;
 		if (IS_BOTH_COUNTERS_74K_EVENT(base_id))
 			raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD;
 		else
@@ -1495,9 +1448,6 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config)
 #endif
 		break;
 	case CPU_1004K:
-		if (IS_UNSUPPORTED_1004K_EVENT(raw_id, base_id))
-			return ERR_PTR(-EOPNOTSUPP);
-		raw_event.event_id = base_id;
 		if (IS_BOTH_COUNTERS_1004K_EVENT(base_id))
 			raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD;
 		else
diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c
index 933166f44a6..a9d801dec6b 100644
--- a/arch/mips/kernel/rtlx.c
+++ b/arch/mips/kernel/rtlx.c
@@ -473,7 +473,6 @@ static const struct file_operations rtlx_fops = {
 
 static struct irqaction rtlx_irq = {
 	.handler	= rtlx_interrupt,
-	.flags		= IRQF_DISABLED,
 	.name		= "RTLX",
 };
 
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index b1cb8f87d7b..058e964e730 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -122,6 +122,9 @@ static void __init print_memory_map(void)
 		case BOOT_MEM_RAM:
 			printk(KERN_CONT "(usable)\n");
 			break;
+		case BOOT_MEM_INIT_RAM:
+			printk(KERN_CONT "(usable after init)\n");
+			break;
 		case BOOT_MEM_ROM_DATA:
 			printk(KERN_CONT "(ROM data)\n");
 			break;
@@ -362,15 +365,24 @@ static void __init bootmem_init(void)
 	for (i = 0; i < boot_mem_map.nr_map; i++) {
 		unsigned long start, end, size;
 
+		start = PFN_UP(boot_mem_map.map[i].addr);
+		end   = PFN_DOWN(boot_mem_map.map[i].addr
+				    + boot_mem_map.map[i].size);
+
 		/*
 		 * Reserve usable memory.
 		 */
-		if (boot_mem_map.map[i].type != BOOT_MEM_RAM)
+		switch (boot_mem_map.map[i].type) {
+		case BOOT_MEM_RAM:
+			break;
+		case BOOT_MEM_INIT_RAM:
+			memory_present(0, start, end);
 			continue;
+		default:
+			/* Not usable memory */
+			continue;
+		}
 
-		start = PFN_UP(boot_mem_map.map[i].addr);
-		end   = PFN_DOWN(boot_mem_map.map[i].addr
-				    + boot_mem_map.map[i].size);
 		/*
 		 * We are rounding up the start address of usable memory
 		 * and at the end of the usable range downwards.
@@ -456,11 +468,33 @@ early_param("mem", early_parse_mem);
 
 static void __init arch_mem_init(char **cmdline_p)
 {
+	phys_t init_mem, init_end, init_size;
+
 	extern void plat_mem_setup(void);
 
 	/* call board setup routine */
 	plat_mem_setup();
 
+	init_mem = PFN_UP(__pa_symbol(&__init_begin)) << PAGE_SHIFT;
+	init_end = PFN_DOWN(__pa_symbol(&__init_end)) << PAGE_SHIFT;
+	init_size = init_end - init_mem;
+	if (init_size) {
+		/* Make sure it is in the boot_mem_map */
+		int i, found;
+		found = 0;
+		for (i = 0; i < boot_mem_map.nr_map; i++) {
+			if (init_mem >= boot_mem_map.map[i].addr &&
+			    init_mem < (boot_mem_map.map[i].addr +
+					boot_mem_map.map[i].size)) {
+				found = 1;
+				break;
+			}
+		}
+		if (!found)
+			add_memory_region(init_mem, init_size,
+					  BOOT_MEM_INIT_RAM);
+	}
+
 	pr_info("Determined physical RAM map:\n");
 	print_memory_map();
 
@@ -524,6 +558,7 @@ static void __init resource_init(void)
 		res = alloc_bootmem(sizeof(struct resource));
 		switch (boot_mem_map.map[i].type) {
 		case BOOT_MEM_RAM:
+		case BOOT_MEM_INIT_RAM:
 		case BOOT_MEM_ROM_DATA:
 			res->name = "System RAM";
 			break;
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
new file mode 100644
index 00000000000..58fe71afd87
--- /dev/null
+++ b/arch/mips/kernel/smp-bmips.c
@@ -0,0 +1,458 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2011 by Kevin Cernekee (cernekee@gmail.com)
+ *
+ * SMP support for BMIPS
+ */
+
+#include <linux/version.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/reboot.h>
+#include <linux/io.h>
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/bug.h>
+#include <linux/kernel.h>
+
+#include <asm/time.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/bootinfo.h>
+#include <asm/pmon.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/mipsregs.h>
+#include <asm/bmips.h>
+#include <asm/traps.h>
+#include <asm/barrier.h>
+
+static int __maybe_unused max_cpus = 1;
+
+/* these may be configured by the platform code */
+int bmips_smp_enabled = 1;
+int bmips_cpu_offset;
+cpumask_t bmips_booted_mask;
+
+#ifdef CONFIG_SMP
+
+/* initial $sp, $gp - used by arch/mips/kernel/bmips_vec.S */
+unsigned long bmips_smp_boot_sp;
+unsigned long bmips_smp_boot_gp;
+
+static void bmips_send_ipi_single(int cpu, unsigned int action);
+static irqreturn_t bmips_ipi_interrupt(int irq, void *dev_id);
+
+/* SW interrupts 0,1 are used for interprocessor signaling */
+#define IPI0_IRQ			(MIPS_CPU_IRQ_BASE + 0)
+#define IPI1_IRQ			(MIPS_CPU_IRQ_BASE + 1)
+
+#define CPUNUM(cpu, shift)		(((cpu) + bmips_cpu_offset) << (shift))
+#define ACTION_CLR_IPI(cpu, ipi)	(0x2000 | CPUNUM(cpu, 9) | ((ipi) << 8))
+#define ACTION_SET_IPI(cpu, ipi)	(0x3000 | CPUNUM(cpu, 9) | ((ipi) << 8))
+#define ACTION_BOOT_THREAD(cpu)		(0x08 | CPUNUM(cpu, 0))
+
+static void __init bmips_smp_setup(void)
+{
+	int i;
+
+#if defined(CONFIG_CPU_BMIPS4350) || defined(CONFIG_CPU_BMIPS4380)
+	/* arbitration priority */
+	clear_c0_brcm_cmt_ctrl(0x30);
+
+	/* NBK and weak order flags */
+	set_c0_brcm_config_0(0x30000);
+
+	/*
+	 * MIPS interrupts 0,1 (SW INT 0,1) cross over to the other thread
+	 * MIPS interrupt 2 (HW INT 0) is the CPU0 L1 controller output
+	 * MIPS interrupt 3 (HW INT 1) is the CPU1 L1 controller output
+	 */
+	change_c0_brcm_cmt_intr(0xf8018000,
+		(0x02 << 27) | (0x03 << 15));
+
+	/* single core, 2 threads (2 pipelines) */
+	max_cpus = 2;
+#elif defined(CONFIG_CPU_BMIPS5000)
+	/* enable raceless SW interrupts */
+	set_c0_brcm_config(0x03 << 22);
+
+	/* route HW interrupt 0 to CPU0, HW interrupt 1 to CPU1 */
+	change_c0_brcm_mode(0x1f << 27, 0x02 << 27);
+
+	/* N cores, 2 threads per core */
+	max_cpus = (((read_c0_brcm_config() >> 6) & 0x03) + 1) << 1;
+
+	/* clear any pending SW interrupts */
+	for (i = 0; i < max_cpus; i++) {
+		write_c0_brcm_action(ACTION_CLR_IPI(i, 0));
+		write_c0_brcm_action(ACTION_CLR_IPI(i, 1));
+	}
+#endif
+
+	if (!bmips_smp_enabled)
+		max_cpus = 1;
+
+	/* this can be overridden by the BSP */
+	if (!board_ebase_setup)
+		board_ebase_setup = &bmips_ebase_setup;
+
+	for (i = 0; i < max_cpus; i++) {
+		__cpu_number_map[i] = 1;
+		__cpu_logical_map[i] = 1;
+		set_cpu_possible(i, 1);
+		set_cpu_present(i, 1);
+	}
+}
+
+/*
+ * IPI IRQ setup - runs on CPU0
+ */
+static void bmips_prepare_cpus(unsigned int max_cpus)
+{
+	if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
+			"smp_ipi0", NULL))
+		panic("Can't request IPI0 interrupt\n");
+	if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
+			"smp_ipi1", NULL))
+		panic("Can't request IPI1 interrupt\n");
+}
+
+/*
+ * Tell the hardware to boot CPUx - runs on CPU0
+ */
+static void bmips_boot_secondary(int cpu, struct task_struct *idle)
+{
+	bmips_smp_boot_sp = __KSTK_TOS(idle);
+	bmips_smp_boot_gp = (unsigned long)task_thread_info(idle);
+	mb();
+
+	/*
+	 * Initial boot sequence for secondary CPU:
+	 *   bmips_reset_nmi_vec @ a000_0000 ->
+	 *   bmips_smp_entry ->
+	 *   plat_wired_tlb_setup (cached function call; optional) ->
+	 *   start_secondary (cached jump)
+	 *
+	 * Warm restart sequence:
+	 *   play_dead WAIT loop ->
+	 *   bmips_smp_int_vec @ BMIPS_WARM_RESTART_VEC ->
+	 *   eret to play_dead ->
+	 *   bmips_secondary_reentry ->
+	 *   start_secondary
+	 */
+
+	pr_info("SMP: Booting CPU%d...\n", cpu);
+
+	if (cpumask_test_cpu(cpu, &bmips_booted_mask))
+		bmips_send_ipi_single(cpu, 0);
+	else {
+#if defined(CONFIG_CPU_BMIPS4350) || defined(CONFIG_CPU_BMIPS4380)
+		set_c0_brcm_cmt_ctrl(0x01);
+#elif defined(CONFIG_CPU_BMIPS5000)
+		if (cpu & 0x01)
+			write_c0_brcm_action(ACTION_BOOT_THREAD(cpu));
+		else {
+			/*
+			 * core N thread 0 was already booted; just
+			 * pulse the NMI line
+			 */
+			bmips_write_zscm_reg(0x210, 0xc0000000);
+			udelay(10);
+			bmips_write_zscm_reg(0x210, 0x00);
+		}
+#endif
+		cpumask_set_cpu(cpu, &bmips_booted_mask);
+	}
+}
+
+/*
+ * Early setup - runs on secondary CPU after cache probe
+ */
+static void bmips_init_secondary(void)
+{
+	/* move NMI vector to kseg0, in case XKS01 is enabled */
+
+#if defined(CONFIG_CPU_BMIPS4350) || defined(CONFIG_CPU_BMIPS4380)
+	void __iomem *cbr = BMIPS_GET_CBR();
+	unsigned long old_vec;
+
+	old_vec = __raw_readl(cbr + BMIPS_RELO_VECTOR_CONTROL_1);
+	__raw_writel(old_vec & ~0x20000000, cbr + BMIPS_RELO_VECTOR_CONTROL_1);
+
+	clear_c0_cause(smp_processor_id() ? C_SW1 : C_SW0);
+#elif defined(CONFIG_CPU_BMIPS5000)
+	write_c0_brcm_bootvec(read_c0_brcm_bootvec() &
+		(smp_processor_id() & 0x01 ? ~0x20000000 : ~0x2000));
+
+	write_c0_brcm_action(ACTION_CLR_IPI(smp_processor_id(), 0));
+#endif
+
+	/* make sure there won't be a timer interrupt for a little while */
+	write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ);
+
+	irq_enable_hazard();
+	set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ1 | IE_IRQ5 | ST0_IE);
+	irq_enable_hazard();
+}
+
+/*
+ * Late setup - runs on secondary CPU before entering the idle loop
+ */
+static void bmips_smp_finish(void)
+{
+	pr_info("SMP: CPU%d is running\n", smp_processor_id());
+}
+
+/*
+ * Runs on CPU0 after all CPUs have been booted
+ */
+static void bmips_cpus_done(void)
+{
+}
+
+#if defined(CONFIG_CPU_BMIPS5000)
+
+/*
+ * BMIPS5000 raceless IPIs
+ *
+ * Each CPU has two inbound SW IRQs which are independent of all other CPUs.
+ * IPI0 is used for SMP_RESCHEDULE_YOURSELF
+ * IPI1 is used for SMP_CALL_FUNCTION
+ */
+
+static void bmips_send_ipi_single(int cpu, unsigned int action)
+{
+	write_c0_brcm_action(ACTION_SET_IPI(cpu, action == SMP_CALL_FUNCTION));
+}
+
+static irqreturn_t bmips_ipi_interrupt(int irq, void *dev_id)
+{
+	int action = irq - IPI0_IRQ;
+
+	write_c0_brcm_action(ACTION_CLR_IPI(smp_processor_id(), action));
+
+	if (action == 0)
+		scheduler_ipi();
+	else
+		smp_call_function_interrupt();
+
+	return IRQ_HANDLED;
+}
+
+#else
+
+/*
+ * BMIPS43xx racey IPIs
+ *
+ * We use one inbound SW IRQ for each CPU.
+ *
+ * A spinlock must be held in order to keep CPUx from accidentally clearing
+ * an incoming IPI when it writes CP0 CAUSE to raise an IPI on CPUy.  The
+ * same spinlock is used to protect the action masks.
+ */
+
+static DEFINE_SPINLOCK(ipi_lock);
+static DEFINE_PER_CPU(int, ipi_action_mask);
+
+static void bmips_send_ipi_single(int cpu, unsigned int action)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ipi_lock, flags);
+	set_c0_cause(cpu ? C_SW1 : C_SW0);
+	per_cpu(ipi_action_mask, cpu) |= action;
+	irq_enable_hazard();
+	spin_unlock_irqrestore(&ipi_lock, flags);
+}
+
+static irqreturn_t bmips_ipi_interrupt(int irq, void *dev_id)
+{
+	unsigned long flags;
+	int action, cpu = irq - IPI0_IRQ;
+
+	spin_lock_irqsave(&ipi_lock, flags);
+	action = __get_cpu_var(ipi_action_mask);
+	per_cpu(ipi_action_mask, cpu) = 0;
+	clear_c0_cause(cpu ? C_SW1 : C_SW0);
+	spin_unlock_irqrestore(&ipi_lock, flags);
+
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
+	if (action & SMP_CALL_FUNCTION)
+		smp_call_function_interrupt();
+
+	return IRQ_HANDLED;
+}
+
+#endif /* BMIPS type */
+
+static void bmips_send_ipi_mask(const struct cpumask *mask,
+	unsigned int action)
+{
+	unsigned int i;
+
+	for_each_cpu(i, mask)
+		bmips_send_ipi_single(i, action);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static int bmips_cpu_disable(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	if (cpu == 0)
+		return -EBUSY;
+
+	pr_info("SMP: CPU%d is offline\n", cpu);
+
+	cpu_clear(cpu, cpu_online_map);
+	cpu_clear(cpu, cpu_callin_map);
+
+	local_flush_tlb_all();
+	local_flush_icache_range(0, ~0);
+
+	return 0;
+}
+
+static void bmips_cpu_die(unsigned int cpu)
+{
+}
+
+void __ref play_dead(void)
+{
+	idle_task_exit();
+
+	/* flush data cache */
+	_dma_cache_wback_inv(0, ~0);
+
+	/*
+	 * Wakeup is on SW0 or SW1; disable everything else
+	 * Use BEV !IV (BMIPS_WARM_RESTART_VEC) to avoid the regular Linux
+	 * IRQ handlers; this clears ST0_IE and returns immediately.
+	 */
+	clear_c0_cause(CAUSEF_IV | C_SW0 | C_SW1);
+	change_c0_status(IE_IRQ5 | IE_IRQ1 | IE_SW0 | IE_SW1 | ST0_IE | ST0_BEV,
+		IE_SW0 | IE_SW1 | ST0_IE | ST0_BEV);
+	irq_disable_hazard();
+
+	/*
+	 * wait for SW interrupt from bmips_boot_secondary(), then jump
+	 * back to start_secondary()
+	 */
+	__asm__ __volatile__(
+	"	wait\n"
+	"	j	bmips_secondary_reentry\n"
+	: : : "memory");
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+struct plat_smp_ops bmips_smp_ops = {
+	.smp_setup		= bmips_smp_setup,
+	.prepare_cpus		= bmips_prepare_cpus,
+	.boot_secondary		= bmips_boot_secondary,
+	.smp_finish		= bmips_smp_finish,
+	.init_secondary		= bmips_init_secondary,
+	.cpus_done		= bmips_cpus_done,
+	.send_ipi_single	= bmips_send_ipi_single,
+	.send_ipi_mask		= bmips_send_ipi_mask,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable		= bmips_cpu_disable,
+	.cpu_die		= bmips_cpu_die,
+#endif
+};
+
+#endif /* CONFIG_SMP */
+
+/***********************************************************************
+ * BMIPS vector relocation
+ * This is primarily used for SMP boot, but it is applicable to some
+ * UP BMIPS systems as well.
+ ***********************************************************************/
+
+static void __cpuinit bmips_wr_vec(unsigned long dst, char *start, char *end)
+{
+	memcpy((void *)dst, start, end - start);
+	dma_cache_wback((unsigned long)start, end - start);
+	local_flush_icache_range(dst, dst + (end - start));
+	instruction_hazard();
+}
+
+static inline void __cpuinit bmips_nmi_handler_setup(void)
+{
+	bmips_wr_vec(BMIPS_NMI_RESET_VEC, &bmips_reset_nmi_vec,
+		&bmips_reset_nmi_vec_end);
+	bmips_wr_vec(BMIPS_WARM_RESTART_VEC, &bmips_smp_int_vec,
+		&bmips_smp_int_vec_end);
+}
+
+void __cpuinit bmips_ebase_setup(void)
+{
+	unsigned long new_ebase = ebase;
+	void __iomem __maybe_unused *cbr;
+
+	BUG_ON(ebase != CKSEG0);
+
+#if defined(CONFIG_CPU_BMIPS4350)
+	/*
+	 * BMIPS4350 cannot relocate the normal vectors, but it
+	 * can relocate the BEV=1 vectors.  So CPU1 starts up at
+	 * the relocated BEV=1, IV=0 general exception vector @
+	 * 0xa000_0380.
+	 *
+	 * set_uncached_handler() is used here because:
+	 *  - CPU1 will run this from uncached space
+	 *  - None of the cacheflush functions are set up yet
+	 */
+	set_uncached_handler(BMIPS_WARM_RESTART_VEC - CKSEG0,
+		&bmips_smp_int_vec, 0x80);
+	__sync();
+	return;
+#elif defined(CONFIG_CPU_BMIPS4380)
+	/*
+	 * 0x8000_0000: reset/NMI (initially in kseg1)
+	 * 0x8000_0400: normal vectors
+	 */
+	new_ebase = 0x80000400;
+	cbr = BMIPS_GET_CBR();
+	__raw_writel(0x80080800, cbr + BMIPS_RELO_VECTOR_CONTROL_0);
+	__raw_writel(0xa0080800, cbr + BMIPS_RELO_VECTOR_CONTROL_1);
+#elif defined(CONFIG_CPU_BMIPS5000)
+	/*
+	 * 0x8000_0000: reset/NMI (initially in kseg1)
+	 * 0x8000_1000: normal vectors
+	 */
+	new_ebase = 0x80001000;
+	write_c0_brcm_bootvec(0xa0088008);
+	write_c0_ebase(new_ebase);
+	if (max_cpus > 2)
+		bmips_write_zscm_reg(0xa0, 0xa008a008);
+#else
+	return;
+#endif
+	board_nmi_handler_setup = &bmips_nmi_handler_setup;
+	ebase = new_ebase;
+}
+
+asmlinkage void __weak plat_wired_tlb_setup(void)
+{
+	/*
+	 * Called when starting/restarting a secondary CPU.
+	 * Kernel stacks and other important data might only be accessible
+	 * once the wired entries are present.
+	 */
+}
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index f0895e70e28..0a42ff3ff6a 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -559,7 +559,7 @@ void smtc_prepare_cpus(int cpus)
 
 	pipi = kmalloc(nipi *sizeof(struct smtc_ipi), GFP_KERNEL);
 	if (pipi == NULL)
-		panic("kmalloc of IPI message buffers failed\n");
+		panic("kmalloc of IPI message buffers failed");
 	else
 		printk("IPI buffer pool of %d buffers\n", nipi);
 	for (i = 0; i < nipi; i++) {
@@ -813,7 +813,7 @@ void smtc_send_ipi(int cpu, int type, unsigned int action)
 	if (pipi == NULL) {
 		bust_spinlocks(1);
 		mips_mt_regdump(dvpe());
-		panic("IPI Msg. Buffers Depleted\n");
+		panic("IPI Msg. Buffers Depleted");
 	}
 	pipi->type = type;
 	pipi->arg = (void *)action;
@@ -1130,7 +1130,7 @@ static void ipi_irq_dispatch(void)
 
 static struct irqaction irq_ipi = {
 	.handler	= ipi_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_PERCPU,
+	.flags		= IRQF_PERCPU,
 	.name		= "SMTC_IPI"
 };
 
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index bbddb86c1fa..cc4a3f120f5 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -91,6 +91,7 @@ int (*board_be_handler)(struct pt_regs *regs, int is_fixup);
 void (*board_nmi_handler_setup)(void);
 void (*board_ejtag_handler_setup)(void);
 void (*board_bind_eic_interrupt)(int irq, int regset);
+void (*board_ebase_setup)(void);
 
 
 static void show_raw_backtrace(unsigned long reg29)
@@ -400,7 +401,7 @@ void __noreturn die(const char *str, struct pt_regs *regs)
 		panic("Fatal exception in interrupt");
 
 	if (panic_on_oops) {
-		printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n");
+		printk(KERN_EMERG "Fatal exception: panic in 5 seconds");
 		ssleep(5);
 		panic("Fatal exception");
 	}
@@ -1150,7 +1151,7 @@ asmlinkage void do_mt(struct pt_regs *regs)
 asmlinkage void do_dsp(struct pt_regs *regs)
 {
 	if (cpu_has_dsp)
-		panic("Unexpected DSP exception\n");
+		panic("Unexpected DSP exception");
 
 	force_sig(SIGILL, current);
 }
@@ -1339,9 +1340,18 @@ void ejtag_exception_handler(struct pt_regs *regs)
 
 /*
  * NMI exception handler.
+ * No lock; only written during early bootup by CPU 0.
  */
+static RAW_NOTIFIER_HEAD(nmi_chain);
+
+int register_nmi_notifier(struct notifier_block *nb)
+{
+	return raw_notifier_chain_register(&nmi_chain, nb);
+}
+
 void __noreturn nmi_exception_handler(struct pt_regs *regs)
 {
+	raw_notifier_call_chain(&nmi_chain, 0, regs);
 	bust_spinlocks(1);
 	printk("NMI taken!!!!\n");
 	die("NMI", regs);
@@ -1682,6 +1692,8 @@ void __init trap_init(void)
 			ebase += (read_c0_ebase() & 0x3ffff000);
 	}
 
+	if (board_ebase_setup)
+		board_ebase_setup();
 	per_cpu_trap_init();
 
 	/*