From d0f0f63ac1374c13b7862b48bd7d6514913dbcad Mon Sep 17 00:00:00 2001
From: Ralf Baechle <ralf@linux-mips.org>
Date: Wed, 17 Dec 2014 14:06:00 +0100
Subject: MIPS: Rewrite csum_fold to plain C.

This isn't only short and easier to read and fully portable but also
shrinks a Malta kernel's by 160 bytes.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/checksum.h | 22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 3418c51e1151..ac0f55cc6e78 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -103,22 +103,16 @@ __wsum csum_partial_copy_nocheck(const void *src, void *dst,
 /*
  *	Fold a partial checksum without adding pseudo headers
  */
-static inline __sum16 csum_fold(__wsum sum)
+static inline __sum16 csum_fold(__wsum csum)
 {
-	__asm__(
-	"	.set	push		# csum_fold\n"
-	"	.set	noat		\n"
-	"	sll	$1, %0, 16	\n"
-	"	addu	%0, $1		\n"
-	"	sltu	$1, %0, $1	\n"
-	"	srl	%0, %0, 16	\n"
-	"	addu	%0, $1		\n"
-	"	xori	%0, 0xffff	\n"
-	"	.set	pop"
-	: "=r" (sum)
-	: "0" (sum));
+	u32 sum = (__force u32)csum;;
+
+	sum += (sum << 16);
+	csum = (sum < csum);
+	sum >>= 16;
+	sum += csum;
 
-	return (__force __sum16)sum;
+	return (__force __sum16)~sum;
 }
 
 /*
-- 
cgit v1.2.3


From b4b5015a1c1450e008ccd414c760f4ef907a461b Mon Sep 17 00:00:00 2001
From: Ralf Baechle <ralf@linux-mips.org>
Date: Wed, 17 Dec 2014 23:03:46 +0100
Subject: MIPS: Use <asm-generic/checksum.h>

Right now the MIPS <asm/checksum.h> still overrides all functions.  This
will change in the future.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/checksum.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index ac0f55cc6e78..64ae32c082d1 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -99,6 +99,7 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
  */
 __wsum csum_partial_copy_nocheck(const void *src, void *dst,
 				       int len, __wsum sum);
+#define csum_partial_copy_nocheck csum_partial_copy_nocheck
 
 /*
  *	Fold a partial checksum without adding pseudo headers
@@ -114,6 +115,7 @@ static inline __sum16 csum_fold(__wsum csum)
 
 	return (__force __sum16)~sum;
 }
+#define csum_fold csum_fold
 
 /*
  *	This is a version of ip_compute_csum() optimized for IP headers,
@@ -152,6 +154,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 
 	return csum_fold(csum);
 }
+#define ip_fast_csum ip_fast_csum
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr,
 	__be32 daddr, unsigned short len, unsigned short proto,
@@ -194,6 +197,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr,
 
 	return sum;
 }
+#define csum_tcpudp_nofold csum_tcpudp_nofold
 
 /*
  * computes the checksum of the TCP/UDP pseudo-header
@@ -206,6 +210,7 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
+#define csum_tcpudp_magic csum_tcpudp_magic
 
 /*
  * this routine is used for miscellaneous IP-like checksums, mainly
@@ -281,4 +286,6 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	return csum_fold(sum);
 }
 
+#include <asm-generic/checksum.h>
+
 #endif /* _ASM_CHECKSUM_H */
-- 
cgit v1.2.3


From 2f26c48824ece86ccc6e8d5889fbf338ebfc67e5 Mon Sep 17 00:00:00 2001
From: Ralf Baechle <ralf@linux-mips.org>
Date: Wed, 17 Dec 2014 23:05:10 +0100
Subject: MIPS: Use generic csum_tcpudp_magic for MIPS.

Its implementation is identical to MIPS.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/checksum.h | 13 -------------
 1 file changed, 13 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 64ae32c082d1..5996252680c6 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -199,19 +199,6 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr,
 }
 #define csum_tcpudp_nofold csum_tcpudp_nofold
 
-/*
- * computes the checksum of the TCP/UDP pseudo-header
- * returns a 16-bit checksum, already complemented
- */
-static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
-{
-	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
-}
-#define csum_tcpudp_magic csum_tcpudp_magic
-
 /*
  * this routine is used for miscellaneous IP-like checksums, mainly
  * in icmp.c
-- 
cgit v1.2.3


From bb03006ec93cb286ec0fab344e2a14d591d0bc4c Mon Sep 17 00:00:00 2001
From: Ralf Baechle <ralf@linux-mips.org>
Date: Fri, 2 Jan 2015 15:59:06 +0100
Subject: MIPS: ARC: Use __noreturn instead of open coded attributes in
 declarations.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/sgialib.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/sgialib.h b/arch/mips/include/asm/sgialib.h
index 753275accd18..40dc9839f63c 100644
--- a/arch/mips/include/asm/sgialib.h
+++ b/arch/mips/include/asm/sgialib.h
@@ -11,6 +11,7 @@
 #ifndef _ASM_SGIALIB_H
 #define _ASM_SGIALIB_H
 
+#include <linux/compiler.h>
 #include <asm/sgiarcs.h>
 
 extern struct linux_romvec *romvec;
@@ -70,8 +71,8 @@ extern LONG ArcRead(ULONG fd, PVOID buf, ULONG num, PULONG cnt);
 extern LONG ArcWrite(ULONG fd, PVOID buf, ULONG num, PULONG cnt);
 
 /* Misc. routines. */
-extern VOID ArcReboot(VOID) __attribute__((noreturn));
-extern VOID ArcEnterInteractiveMode(VOID) __attribute__((noreturn));
+extern VOID ArcReboot(VOID) __noreturn;
+extern VOID ArcEnterInteractiveMode(VOID) __noreturn;
 extern VOID ArcFlushAllCaches(VOID);
 extern DISPLAY_STATUS *ArcGetDisplayStatus(ULONG FileID);
 
-- 
cgit v1.2.3


From e9503246a2c72dbdfce38668936faf8e52198bdb Mon Sep 17 00:00:00 2001
From: Ralf Baechle <ralf@linux-mips.org>
Date: Fri, 2 Jan 2015 16:00:58 +0100
Subject: MIPS: ARC: Add declarations for a few missing ARC firmware functions.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/sgialib.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/sgialib.h b/arch/mips/include/asm/sgialib.h
index 40dc9839f63c..195db5045ae5 100644
--- a/arch/mips/include/asm/sgialib.h
+++ b/arch/mips/include/asm/sgialib.h
@@ -71,6 +71,9 @@ extern LONG ArcRead(ULONG fd, PVOID buf, ULONG num, PULONG cnt);
 extern LONG ArcWrite(ULONG fd, PVOID buf, ULONG num, PULONG cnt);
 
 /* Misc. routines. */
+extern VOID ArcHalt(VOID) __noreturn;
+extern VOID ArcPowerDown(VOID) __noreturn;
+extern VOID ArcRestart(VOID) __noreturn;
 extern VOID ArcReboot(VOID) __noreturn;
 extern VOID ArcEnterInteractiveMode(VOID) __noreturn;
 extern VOID ArcFlushAllCaches(VOID);
-- 
cgit v1.2.3


From 250215ccf6def938f7b4f037185b8277eb54bcda Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 12 Jan 2015 21:19:13 +0100
Subject: MIPS: Remove unused dt_setup_arch()

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/8928/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/prom.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/prom.h b/arch/mips/include/asm/prom.h
index eaa26270a5e5..8ebc2aa5f3e1 100644
--- a/arch/mips/include/asm/prom.h
+++ b/arch/mips/include/asm/prom.h
@@ -24,13 +24,6 @@ struct boot_param_header;
 extern void __dt_setup_arch(void *bph);
 extern int __dt_register_buses(const char *bus0, const char *bus1);
 
-#define dt_setup_arch(sym)						\
-({									\
-	extern char __dtb_##sym##_begin[];				\
-									\
-	__dt_setup_arch(__dtb_##sym##_begin);				\
-})
-
 #else /* CONFIG_OF */
 static inline void device_tree_init(void) { }
 #endif /* CONFIG_OF */
-- 
cgit v1.2.3


From 9791554b45a2acc28247f66a5fd5bbc212a6b8c8 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@imgtec.com>
Date: Thu, 8 Jan 2015 12:17:37 +0000
Subject: MIPS,prctl: add PR_[GS]ET_FP_MODE prctl options for MIPS

Userland code may be built using an ABI which permits linking to objects
that have more restrictive floating point requirements. For example,
userland code may be built to target the O32 FPXX ABI. Such code may be
linked with other FPXX code, or code built for either one of the more
restrictive FP32 or FP64. When linking with more restrictive code, the
overall requirement of the process becomes that of the more restrictive
code. The kernel has no way to know in advance which mode the process
will need to be executed in, and indeed it may need to change during
execution. The dynamic loader is the only code which will know the
overall required mode, and so it needs to have a means to instruct the
kernel to switch the FP mode of the process.

This patch introduces 2 new options to the prctl syscall which provide
such a capability. The FP mode of the process is represented as a
simple bitmask combining a number of mode bits mirroring those present
in the hardware. Userland can either retrieve the current FP mode of
the process:

  mode = prctl(PR_GET_FP_MODE);

or modify the current FP mode of the process:

  err = prctl(PR_SET_FP_MODE, new_mode);

Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: Markos Chandras <markos.chandras@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/8899/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/mmu.h         |  3 ++
 arch/mips/include/asm/mmu_context.h |  2 +
 arch/mips/include/asm/processor.h   | 11 +++++
 arch/mips/kernel/process.c          | 92 +++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/traps.c            | 19 ++++++++
 include/uapi/linux/prctl.h          |  5 ++
 kernel/sys.c                        | 12 +++++
 7 files changed, 144 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/mmu.h b/arch/mips/include/asm/mmu.h
index c436138945a8..1afa1f986df8 100644
--- a/arch/mips/include/asm/mmu.h
+++ b/arch/mips/include/asm/mmu.h
@@ -1,9 +1,12 @@
 #ifndef __ASM_MMU_H
 #define __ASM_MMU_H
 
+#include <linux/atomic.h>
+
 typedef struct {
 	unsigned long asid[NR_CPUS];
 	void *vdso;
+	atomic_t fp_mode_switching;
 } mm_context_t;
 
 #endif /* __ASM_MMU_H */
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index 2f82568a3ee4..87f11072f557 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -132,6 +132,8 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	for_each_possible_cpu(i)
 		cpu_context(i, mm) = 0;
 
+	atomic_set(&mm->context.fp_mode_switching, 0);
+
 	return 0;
 }
 
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index f1df4cb4a286..9daa38608cd8 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -399,4 +399,15 @@ unsigned long get_wchan(struct task_struct *p);
 
 #endif
 
+/*
+ * Functions & macros implementing the PR_GET_FP_MODE & PR_SET_FP_MODE options
+ * to the prctl syscall.
+ */
+extern int mips_get_process_fp_mode(struct task_struct *task);
+extern int mips_set_process_fp_mode(struct task_struct *task,
+				    unsigned int value);
+
+#define GET_FP_MODE(task)		mips_get_process_fp_mode(task)
+#define SET_FP_MODE(task,value)		mips_set_process_fp_mode(task, value)
+
 #endif /* _ASM_PROCESSOR_H */
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index eb76434828e8..4677b4c67da6 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -25,6 +25,7 @@
 #include <linux/completion.h>
 #include <linux/kallsyms.h>
 #include <linux/random.h>
+#include <linux/prctl.h>
 
 #include <asm/asm.h>
 #include <asm/bootinfo.h>
@@ -550,3 +551,94 @@ void arch_trigger_all_cpu_backtrace(bool include_self)
 {
 	smp_call_function(arch_dump_stack, NULL, 1);
 }
+
+int mips_get_process_fp_mode(struct task_struct *task)
+{
+	int value = 0;
+
+	if (!test_tsk_thread_flag(task, TIF_32BIT_FPREGS))
+		value |= PR_FP_MODE_FR;
+	if (test_tsk_thread_flag(task, TIF_HYBRID_FPREGS))
+		value |= PR_FP_MODE_FRE;
+
+	return value;
+}
+
+int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
+{
+	const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE;
+	unsigned long switch_count;
+	struct task_struct *t;
+
+	/* Check the value is valid */
+	if (value & ~known_bits)
+		return -EOPNOTSUPP;
+
+	/* Avoid inadvertently triggering emulation */
+	if ((value & PR_FP_MODE_FR) && cpu_has_fpu &&
+	    !(current_cpu_data.fpu_id & MIPS_FPIR_F64))
+		return -EOPNOTSUPP;
+	if ((value & PR_FP_MODE_FRE) && cpu_has_fpu && !cpu_has_fre)
+		return -EOPNOTSUPP;
+
+	/* Save FP & vector context, then disable FPU & MSA */
+	if (task->signal == current->signal)
+		lose_fpu(1);
+
+	/* Prevent any threads from obtaining live FP context */
+	atomic_set(&task->mm->context.fp_mode_switching, 1);
+	smp_mb__after_atomic();
+
+	/*
+	 * If there are multiple online CPUs then wait until all threads whose
+	 * FP mode is about to change have been context switched. This approach
+	 * allows us to only worry about whether an FP mode switch is in
+	 * progress when FP is first used in a tasks time slice. Pretty much all
+	 * of the mode switch overhead can thus be confined to cases where mode
+	 * switches are actually occuring. That is, to here. However for the
+	 * thread performing the mode switch it may take a while...
+	 */
+	if (num_online_cpus() > 1) {
+		spin_lock_irq(&task->sighand->siglock);
+
+		for_each_thread(task, t) {
+			if (t == current)
+				continue;
+
+			switch_count = t->nvcsw + t->nivcsw;
+
+			do {
+				spin_unlock_irq(&task->sighand->siglock);
+				cond_resched();
+				spin_lock_irq(&task->sighand->siglock);
+			} while ((t->nvcsw + t->nivcsw) == switch_count);
+		}
+
+		spin_unlock_irq(&task->sighand->siglock);
+	}
+
+	/*
+	 * There are now no threads of the process with live FP context, so it
+	 * is safe to proceed with the FP mode switch.
+	 */
+	for_each_thread(task, t) {
+		/* Update desired FP register width */
+		if (value & PR_FP_MODE_FR) {
+			clear_tsk_thread_flag(t, TIF_32BIT_FPREGS);
+		} else {
+			set_tsk_thread_flag(t, TIF_32BIT_FPREGS);
+			clear_tsk_thread_flag(t, TIF_MSA_CTX_LIVE);
+		}
+
+		/* Update desired FP single layout */
+		if (value & PR_FP_MODE_FRE)
+			set_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
+		else
+			clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
+	}
+
+	/* Allow threads to use FP again */
+	atomic_set(&task->mm->context.fp_mode_switching, 0);
+
+	return 0;
+}
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index ad3d2031c327..d5fbfb51b9da 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1134,10 +1134,29 @@ static int default_cu2_call(struct notifier_block *nfb, unsigned long action,
 	return NOTIFY_OK;
 }
 
+static int wait_on_fp_mode_switch(atomic_t *p)
+{
+	/*
+	 * The FP mode for this task is currently being switched. That may
+	 * involve modifications to the format of this tasks FP context which
+	 * make it unsafe to proceed with execution for the moment. Instead,
+	 * schedule some other task.
+	 */
+	schedule();
+	return 0;
+}
+
 static int enable_restore_fp_context(int msa)
 {
 	int err, was_fpu_owner, prior_msa;
 
+	/*
+	 * If an FP mode switch is currently underway, wait for it to
+	 * complete before proceeding.
+	 */
+	wait_on_atomic_t(&current->mm->context.fp_mode_switching,
+			 wait_on_fp_mode_switch, TASK_KILLABLE);
+
 	if (!used_math()) {
 		/* First time FP context user. */
 		preempt_disable();
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 89f63503f903..31891d9535e2 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -185,4 +185,9 @@ struct prctl_mm_map {
 #define PR_MPX_ENABLE_MANAGEMENT  43
 #define PR_MPX_DISABLE_MANAGEMENT 44
 
+#define PR_SET_FP_MODE		45
+#define PR_GET_FP_MODE		46
+# define PR_FP_MODE_FR		(1 << 0)	/* 64b FP registers */
+# define PR_FP_MODE_FRE		(1 << 1)	/* 32b compatibility */
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index a8c9f5a7dda6..08b16bbdcdf0 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -97,6 +97,12 @@
 #ifndef MPX_DISABLE_MANAGEMENT
 # define MPX_DISABLE_MANAGEMENT(a)	(-EINVAL)
 #endif
+#ifndef GET_FP_MODE
+# define GET_FP_MODE(a)		(-EINVAL)
+#endif
+#ifndef SET_FP_MODE
+# define SET_FP_MODE(a,b)	(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for
@@ -2215,6 +2221,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_MPX_DISABLE_MANAGEMENT:
 		error = MPX_DISABLE_MANAGEMENT(me);
 		break;
+	case PR_SET_FP_MODE:
+		error = SET_FP_MODE(me, arg2);
+		break;
+	case PR_GET_FP_MODE:
+		error = GET_FP_MODE(me);
+		break;
 	default:
 		error = -EINVAL;
 		break;
-- 
cgit v1.2.3


From 461d1597ffad7a826f8aaa63ab0727c37b632e34 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Mon, 26 Jan 2015 09:40:34 +0000
Subject: MIPS: asm: pgtable: Add c0 hazards on HTW start/stop sequences

When we use htw_{start,stop}() outside of htw_reset(), we need
to ensure that c0 changes have been propagated properly before
we attempt to continue with subsequence memory operations.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Cc: <stable@vger.kernel.org> # 3.17+
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/9114/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/pgtable.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 62a6ba383d4f..45d7fd5e1466 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -99,16 +99,20 @@ extern void paging_init(void);
 
 #define htw_stop()							\
 do {									\
-	if (cpu_has_htw)						\
+	if (cpu_has_htw) {						\
 		write_c0_pwctl(read_c0_pwctl() &			\
 			       ~(1 << MIPS_PWCTL_PWEN_SHIFT));		\
+		back_to_back_c0_hazard();				\
+	}								\
 } while(0)
 
 #define htw_start()							\
 do {									\
-	if (cpu_has_htw)						\
+	if (cpu_has_htw) {						\
 		write_c0_pwctl(read_c0_pwctl() |			\
 			       (1 << MIPS_PWCTL_PWEN_SHIFT));		\
+		back_to_back_c0_hazard();				\
+	}								\
 } while(0)
 
 
@@ -116,9 +120,7 @@ do {									\
 do {									\
 	if (cpu_has_htw) {						\
 		htw_stop();						\
-		back_to_back_c0_hazard();				\
 		htw_start();						\
-		back_to_back_c0_hazard();				\
 	}								\
 } while(0)
 
-- 
cgit v1.2.3


From fde3538a8a711aedf1173ecb2d45aed868f51c97 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Mon, 26 Jan 2015 09:40:36 +0000
Subject: MIPS: asm: pgtable: Prevent HTW race when updating PTEs

Whenever we modify a page table entry, we need to ensure that the HTW
will not fetch a stable entry. And for that to happen we need to ensure
that HTW is stopped before we modify the said entry otherwise the HTW
may already be in the process of reading that entry and fetching the
old information. As a result of which, we replace the htw_reset() calls
with htw_{stop,start} in more appropriate places. This also removes the
remaining users of htw_reset() and as a result we drop that macro

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Cc: <stable@vger.kernel.org> # 3.17+
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/9116/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/pgtable.h | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 45d7fd5e1466..3aa982b50a10 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -116,14 +116,6 @@ do {									\
 } while(0)
 
 
-#define htw_reset()							\
-do {									\
-	if (cpu_has_htw) {						\
-		htw_stop();						\
-		htw_start();						\
-	}								\
-} while(0)
-
 extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 	pte_t pteval);
 
@@ -155,12 +147,13 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 {
 	pte_t null = __pte(0);
 
+	htw_stop();
 	/* Preserve global status for the pair */
 	if (ptep_buddy(ptep)->pte_low & _PAGE_GLOBAL)
 		null.pte_low = null.pte_high = _PAGE_GLOBAL;
 
 	set_pte_at(mm, addr, ptep, null);
-	htw_reset();
+	htw_start();
 }
 #else
 
@@ -190,6 +183,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
+	htw_stop();
 #if !defined(CONFIG_CPU_R3000) && !defined(CONFIG_CPU_TX39XX)
 	/* Preserve global status for the pair */
 	if (pte_val(*ptep_buddy(ptep)) & _PAGE_GLOBAL)
@@ -197,7 +191,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 	else
 #endif
 		set_pte_at(mm, addr, ptep, __pte(0));
-	htw_reset();
+	htw_start();
 }
 #endif
 
-- 
cgit v1.2.3


From ed4cbc81addbc076b016c5b979fd1a02f0897f0a Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Mon, 26 Jan 2015 13:04:33 +0000
Subject: MIPS: HTW: Prevent accidental HTW start due to nested htw_{start,
 stop}

activate_mm() and switch_mm() call get_new_mmu_context() which in turn
can enable the HTW before the entryhi is changed with the new ASID.
Since the latter will enable the HTW in local_flush_tlb_all(),
then there is a small timing window where the HTW is running with the
new ASID but with an old pgd since the TLBMISS_HANDLER_SETUP_PGD
hasn't assigned a new one yet. In order to prevent that, we introduce a
simple htw counter to avoid starting HTW accidentally due to nested
htw_{start,stop}() sequences. Moreover, since various IPI calls can
enforce TLB flushing operations on a different core, such an operation
may interrupt another htw_{stop,start} in progress leading inconsistent
updates of the htw_seq variable. In order to avoid that, we disable the
interrupts whenever we update that variable.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Cc: <stable@vger.kernel.org> # 3.17+
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/9118/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/cpu-info.h    |  5 +++++
 arch/mips/include/asm/mmu_context.h |  7 ++++++-
 arch/mips/include/asm/pgtable.h     | 24 ++++++++++++++++++------
 arch/mips/kernel/cpu-probe.c        |  4 +++-
 4 files changed, 32 insertions(+), 8 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h
index a6c9ccb33c5c..c3f4f2d2e108 100644
--- a/arch/mips/include/asm/cpu-info.h
+++ b/arch/mips/include/asm/cpu-info.h
@@ -84,6 +84,11 @@ struct cpuinfo_mips {
 	 * (shifted by _CACHE_SHIFT)
 	 */
 	unsigned int		writecombine;
+	/*
+	 * Simple counter to prevent enabling HTW in nested
+	 * htw_start/htw_stop calls
+	 */
+	unsigned int		htw_seq;
 } __attribute__((aligned(SMP_CACHE_BYTES)));
 
 extern struct cpuinfo_mips cpu_data[];
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index 87f11072f557..45914b59824c 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -25,7 +25,6 @@ do {									\
 	if (cpu_has_htw) {						\
 		write_c0_pwbase(pgd);					\
 		back_to_back_c0_hazard();				\
-		htw_reset();						\
 	}								\
 } while (0)
 
@@ -144,6 +143,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	unsigned long flags;
 	local_irq_save(flags);
 
+	htw_stop();
 	/* Check if our ASID is of an older version and thus invalid */
 	if ((cpu_context(cpu, next) ^ asid_cache(cpu)) & ASID_VERSION_MASK)
 		get_new_mmu_context(next, cpu);
@@ -156,6 +156,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 */
 	cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	cpumask_set_cpu(cpu, mm_cpumask(next));
+	htw_start();
 
 	local_irq_restore(flags);
 }
@@ -182,6 +183,7 @@ activate_mm(struct mm_struct *prev, struct mm_struct *next)
 
 	local_irq_save(flags);
 
+	htw_stop();
 	/* Unconditionally get a new ASID.  */
 	get_new_mmu_context(next, cpu);
 
@@ -191,6 +193,7 @@ activate_mm(struct mm_struct *prev, struct mm_struct *next)
 	/* mark mmu ownership change */
 	cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	cpumask_set_cpu(cpu, mm_cpumask(next));
+	htw_start();
 
 	local_irq_restore(flags);
 }
@@ -205,6 +208,7 @@ drop_mmu_context(struct mm_struct *mm, unsigned cpu)
 	unsigned long flags;
 
 	local_irq_save(flags);
+	htw_stop();
 
 	if (cpumask_test_cpu(cpu, mm_cpumask(mm)))  {
 		get_new_mmu_context(mm, cpu);
@@ -213,6 +217,7 @@ drop_mmu_context(struct mm_struct *mm, unsigned cpu)
 		/* will get a new context next time */
 		cpu_context(cpu, mm) = 0;
 	}
+	htw_start();
 	local_irq_restore(flags);
 }
 
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 3aa982b50a10..845016d1cdbd 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -99,19 +99,31 @@ extern void paging_init(void);
 
 #define htw_stop()							\
 do {									\
+	unsigned long flags;						\
+									\
 	if (cpu_has_htw) {						\
-		write_c0_pwctl(read_c0_pwctl() &			\
-			       ~(1 << MIPS_PWCTL_PWEN_SHIFT));		\
-		back_to_back_c0_hazard();				\
+		local_irq_save(flags);					\
+		if(!raw_current_cpu_data.htw_seq++) {			\
+			write_c0_pwctl(read_c0_pwctl() &		\
+				       ~(1 << MIPS_PWCTL_PWEN_SHIFT));	\
+			back_to_back_c0_hazard();			\
+		}							\
+		local_irq_restore(flags);				\
 	}								\
 } while(0)
 
 #define htw_start()							\
 do {									\
+	unsigned long flags;						\
+									\
 	if (cpu_has_htw) {						\
-		write_c0_pwctl(read_c0_pwctl() |			\
-			       (1 << MIPS_PWCTL_PWEN_SHIFT));		\
-		back_to_back_c0_hazard();				\
+		local_irq_save(flags);					\
+		if (!--raw_current_cpu_data.htw_seq) {			\
+			write_c0_pwctl(read_c0_pwctl() |		\
+				       (1 << MIPS_PWCTL_PWEN_SHIFT));	\
+			back_to_back_c0_hazard();			\
+		}							\
+		local_irq_restore(flags);				\
 	}								\
 } while(0)
 
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 5342674842f5..228ae864c92e 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -424,8 +424,10 @@ static inline unsigned int decode_config3(struct cpuinfo_mips *c)
 	if (config3 & MIPS_CONF3_MSA)
 		c->ases |= MIPS_ASE_MSA;
 	/* Only tested on 32-bit cores */
-	if ((config3 & MIPS_CONF3_PW) && config_enabled(CONFIG_32BIT))
+	if ((config3 & MIPS_CONF3_PW) && config_enabled(CONFIG_32BIT)) {
+		c->htw_seq = 0;
 		c->options |= MIPS_CPU_HTW;
+	}
 
 	return config3 & MIPS_CONF_M;
 }
-- 
cgit v1.2.3


From aca5721e9524de0306ba914e678365fcb704c60c Mon Sep 17 00:00:00 2001
From: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Date: Mon, 27 Oct 2014 10:12:23 +0000
Subject: MIPS: Add generic QEMU PRid and cpu type identifiers

Latest versions of QEMU added support for mips32r6-generic and
mips64r6-generic cpu types so add related definitions in preparation
of MIPS R6 support. This is also used for QEMU R2 generic cpus.

Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/cpu.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 33866fce4d63..0b74bbf976e4 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -93,6 +93,7 @@
  * These are the PRID's for when 23:16 == PRID_COMP_MIPS
  */
 
+#define PRID_IMP_QEMU_GENERIC	0x0000
 #define PRID_IMP_4KC		0x8000
 #define PRID_IMP_5KC		0x8100
 #define PRID_IMP_20KC		0x8200
@@ -312,6 +313,8 @@ enum cpu_type_enum {
 	CPU_LOONGSON3, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS,
 	CPU_CAVIUM_OCTEON2, CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP,
 
+	CPU_QEMU_GENERIC,
+
 	CPU_LAST
 };
 
-- 
cgit v1.2.3


From 4695089f03929c8cfa58470faf6e1e041bfb285a Mon Sep 17 00:00:00 2001
From: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Date: Mon, 24 Nov 2014 12:59:01 +0000
Subject: MIPS: Add cases for CPU_QEMU_GENERIC

Add a CPU_QEMU_GENERIC case to various switch statements.

Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/cpu-type.h | 7 +++++++
 arch/mips/kernel/idle.c          | 1 +
 arch/mips/kernel/spram.c         | 1 +
 arch/mips/kernel/traps.c         | 1 +
 arch/mips/mm/c-r4k.c             | 1 +
 arch/mips/mm/sc-mips.c           | 1 +
 arch/mips/mm/tlbex.c             | 1 +
 7 files changed, 13 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index b4e2bd87df50..8245875f8b33 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -54,6 +54,13 @@ static inline int __pure __get_cpu_type(const int cpu_type)
 	case CPU_M5150:
 #endif
 
+#if defined(CONFIG_SYS_HAS_CPU_MIPS32_R2) || \
+    defined(CONFIG_SYS_HAS_CPU_MIPS32_R6) || \
+    defined(CONFIG_SYS_HAS_CPU_MIPS64_R2) || \
+    defined(CONFIG_SYS_HAS_CPU_MIPS64_R6)
+	case CPU_QEMU_GENERIC:
+#endif
+
 #ifdef CONFIG_SYS_HAS_CPU_MIPS64_R1
 	case CPU_5KC:
 	case CPU_5KE:
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 0b9082b6b683..368c88b7eb6c 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -186,6 +186,7 @@ void __init check_wait(void)
 	case CPU_PROAPTIV:
 	case CPU_P5600:
 	case CPU_M5150:
+	case CPU_QEMU_GENERIC:
 		cpu_wait = r4k_wait;
 		if (read_c0_config7() & MIPS_CONF7_WII)
 			cpu_wait = r4k_wait_irqoff;
diff --git a/arch/mips/kernel/spram.c b/arch/mips/kernel/spram.c
index 67f2495def1c..d1168d7c31e8 100644
--- a/arch/mips/kernel/spram.c
+++ b/arch/mips/kernel/spram.c
@@ -208,6 +208,7 @@ void spram_config(void)
 	case CPU_INTERAPTIV:
 	case CPU_PROAPTIV:
 	case CPU_P5600:
+	case CPU_QEMU_GENERIC:
 		config0 = read_c0_config();
 		/* FIXME: addresses are Malta specific */
 		if (config0 & (1<<24)) {
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index d5fbfb51b9da..461653ea28c8 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1559,6 +1559,7 @@ static inline void parity_protection_init(void)
 	case CPU_INTERAPTIV:
 	case CPU_PROAPTIV:
 	case CPU_P5600:
+	case CPU_QEMU_GENERIC:
 		{
 #define ERRCTL_PE	0x80000000
 #define ERRCTL_L2P	0x00800000
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index dd261df005c2..b806deb29e63 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1255,6 +1255,7 @@ static void probe_pcache(void)
 	case CPU_P5600:
 	case CPU_PROAPTIV:
 	case CPU_M5150:
+	case CPU_QEMU_GENERIC:
 		if (!(read_c0_config7() & MIPS_CONF7_IAR) &&
 		    (c->icache.waysize > PAGE_SIZE))
 			c->icache.flags |= MIPS_CACHE_ALIASES;
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 99eb8fabab60..fd9b5d45e91b 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -81,6 +81,7 @@ static inline int mips_sc_is_activated(struct cpuinfo_mips *c)
 	case CPU_PROAPTIV:
 	case CPU_P5600:
 	case CPU_BMIPS5000:
+	case CPU_QEMU_GENERIC:
 		if (config2 & (1 << 12))
 			return 0;
 	}
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 3978a3d81366..ff8d99ce3b9b 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -514,6 +514,7 @@ static void build_tlb_write_entry(u32 **p, struct uasm_label **l,
 		case CPU_PROAPTIV:
 		case CPU_P5600:
 		case CPU_M5150:
+		case CPU_QEMU_GENERIC:
 			break;
 
 		default:
-- 
cgit v1.2.3


From be5136988e25ae0dc8379fcb937efc63d87aba9e Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Tue, 18 Nov 2014 15:02:32 +0000
Subject: MIPS: asm: compiler: Add new macros to set ISA and arch asm
 annotations

There are certain places where the code uses .set mips32 or .set mips64
or .set arch=r4000. In preparation of MIPS R6 support, and in order to
use as less #ifdefs as possible, we define new macros to set similar
annotations for MIPS R6.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/compiler.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/compiler.h b/arch/mips/include/asm/compiler.h
index c73815e0123a..10b642f55eb7 100644
--- a/arch/mips/include/asm/compiler.h
+++ b/arch/mips/include/asm/compiler.h
@@ -24,4 +24,17 @@
 #error "microMIPS compilation unsupported with GCC older than 4.9"
 #endif
 
+#ifdef CONFIG_CPU_MIPSR6
+#define MIPS_ISA_LEVEL "mips64r6"
+#define MIPS_ISA_ARCH_LEVEL MIPS_ISA_LEVEL
+#define MIPS_ISA_LEVEL_RAW mips64r6
+#define MIPS_ISA_ARCH_LEVEL_RAW MIPS_ISA_LEVEL_RAW
+#else
+/* MIPS64 is a superset of MIPS32 */
+#define MIPS_ISA_LEVEL "mips64r2"
+#define MIPS_ISA_ARCH_LEVEL "arch=r4000"
+#define MIPS_ISA_LEVEL_RAW mips64r2
+#define MIPS_ISA_ARCH_LEVEL_RAW MIPS_ISA_LEVEL_RAW
+#endif /* CONFIG_CPU_MIPSR6 */
+
 #endif /* _ASM_COMPILER_H */
-- 
cgit v1.2.3


From b840a82c549d4126b5c4958673de3f472206e23e Mon Sep 17 00:00:00 2001
From: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Date: Mon, 27 Oct 2014 11:23:34 +0000
Subject: MIPS: asm: module: define MODULE_PROC_FAMILY for MIPS R6

Define the MODULE_PROC_FAMILY for the MIPS R6 ISA.

Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/module.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h
index 800fe578dc99..0aaf9a01ea50 100644
--- a/arch/mips/include/asm/module.h
+++ b/arch/mips/include/asm/module.h
@@ -88,10 +88,14 @@ search_module_dbetables(unsigned long addr)
 #define MODULE_PROC_FAMILY "MIPS32_R1 "
 #elif defined CONFIG_CPU_MIPS32_R2
 #define MODULE_PROC_FAMILY "MIPS32_R2 "
+#elif defined CONFIG_CPU_MIPS32_R6
+#define MODULE_PROC_FAMILY "MIPS32_R6 "
 #elif defined CONFIG_CPU_MIPS64_R1
 #define MODULE_PROC_FAMILY "MIPS64_R1 "
 #elif defined CONFIG_CPU_MIPS64_R2
 #define MODULE_PROC_FAMILY "MIPS64_R2 "
+#elif defined CONFIG_CPU_MIPS64_R6
+#define MODULE_PROC_FAMILY "MIPS64_R6 "
 #elif defined CONFIG_CPU_R3000
 #define MODULE_PROC_FAMILY "R3000 "
 #elif defined CONFIG_CPU_TX39XX
-- 
cgit v1.2.3


From 6a0e9865b9003ba2bb1c3135dd99185946fa7159 Mon Sep 17 00:00:00 2001
From: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Date: Mon, 27 Oct 2014 11:37:47 +0000
Subject: MIPS: asm: stackframe: Do not preserve the HI/LO registers on MIPS R6

The HI/LO registers have been removed from MIPS R6. Instructions
such as MULT and DIV have been replaced with a new pair of
instructions for the HI/LO operations for example:

MULT -> MUL, MUH
DIV -> DIV, MOD

So we avoid preserving the pre-R6 HI/LO registers in MIPS R6

Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/stackframe.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index b188c797565c..28d6d9364bd1 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -40,7 +40,7 @@
 		LONG_S	v1, PT_HI(sp)
 		mflhxu	v1
 		LONG_S	v1, PT_ACX(sp)
-#else
+#elif !defined(CONFIG_CPU_MIPSR6)
 		mfhi	v1
 #endif
 #ifdef CONFIG_32BIT
@@ -50,7 +50,7 @@
 		LONG_S	$10, PT_R10(sp)
 		LONG_S	$11, PT_R11(sp)
 		LONG_S	$12, PT_R12(sp)
-#ifndef CONFIG_CPU_HAS_SMARTMIPS
+#if !defined(CONFIG_CPU_HAS_SMARTMIPS) && !defined(CONFIG_CPU_MIPSR6)
 		LONG_S	v1, PT_HI(sp)
 		mflo	v1
 #endif
@@ -58,7 +58,7 @@
 		LONG_S	$14, PT_R14(sp)
 		LONG_S	$15, PT_R15(sp)
 		LONG_S	$24, PT_R24(sp)
-#ifndef CONFIG_CPU_HAS_SMARTMIPS
+#if !defined(CONFIG_CPU_HAS_SMARTMIPS) && !defined(CONFIG_CPU_MIPSR6)
 		LONG_S	v1, PT_LO(sp)
 #endif
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
@@ -226,7 +226,7 @@
 		mtlhx	$24
 		LONG_L	$24, PT_LO(sp)
 		mtlhx	$24
-#else
+#elif !defined(CONFIG_CPU_MIPSR6)
 		LONG_L	$24, PT_LO(sp)
 		mtlo	$24
 		LONG_L	$24, PT_HI(sp)
-- 
cgit v1.2.3


From 226da55f48651c59ae5dc6a46cb4183105e7f17d Mon Sep 17 00:00:00 2001
From: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Date: Wed, 5 Nov 2014 12:56:40 +0000
Subject: MIPS: asm: asmmacro: Add MIPS R6 support to the simple EI/DI variants

EI/DI instructions are available in MIPS R6 so add the needed
definitions.

Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/asmmacro.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 6caf8766b80f..b6540cfcc97b 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -19,7 +19,7 @@
 #include <asm/asmmacro-64.h>
 #endif
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	.macro	local_irq_enable reg=t0
 	ei
 	irq_enable_hazard
-- 
cgit v1.2.3


From 98a833c1fa4de0695830f77b2d13fd86693da298 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Wed, 5 Nov 2014 14:17:52 +0000
Subject: MIPS: asm: asmmacro: Replace "add" instructions with "addu"

The "add" instruction is actually a macro in binutils and depending on
the size of the immediate it can expand to an "addi" instruction.
However, the "addi" instruction traps on overflows which is not
something we want on address calculation.

Link: http://www.linux-mips.org/archives/linux-mips/2015-01/msg00121.html
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: Maciej W. Rozycki <macro@linux-mips.org>
Cc: <stable@vger.kernel.org> # v3.15+
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/asmmacro.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index b6540cfcc97b..0af29ce84e0b 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -304,7 +304,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	add	$1, \base, \off
+	addu	$1, \base, \off
 	.word	LDD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -313,7 +313,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	add	$1, \base, \off
+	addu	$1, \base, \off
 	.word	STD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
-- 
cgit v1.2.3


From 4e0748f5beb92a14f6be4716938cbf27177ecd07 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 13 Nov 2014 11:25:27 +0000
Subject: MIPS: Use generic checksum functions for MIPS R6

The following instructions have been removed from MIPS R6

ulw, ulh, swl, lwr, lwl, swr.

However, all of them are used in the MIPS specific checksum implementation.
As a result of which, we will use the generic checksum on MIPS R6

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/Kconfig                | 5 +++++
 arch/mips/include/asm/Kbuild     | 1 +
 arch/mips/include/asm/checksum.h | 5 +++++
 arch/mips/kernel/mips_ksyms.c    | 2 ++
 arch/mips/lib/Makefile           | 1 +
 5 files changed, 14 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c01e1d4e0db3..0a8508b4803d 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1034,6 +1034,9 @@ config MIPS_MACHINE
 config NO_IOPORT_MAP
 	def_bool n
 
+config GENERIC_CSUM
+	bool
+
 config GENERIC_ISA_DMA
 	bool
 	select ZONE_DMA if GENERIC_ISA_DMA_SUPPORT_BROKEN=n
@@ -1312,6 +1315,7 @@ config CPU_MIPS32_R6
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
+	select GENERIC_CSUM
 	select HAVE_KVM
 	select MIPS_O32_FP64_SUPPORT
 	help
@@ -1363,6 +1367,7 @@ config CPU_MIPS64_R6
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
+	select GENERIC_CSUM
 	help
 	  Choose this option to build a kernel for release 6 or later of the
 	  MIPS64 architecture.  New MIPS processors, starting with the Warrior
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 200efeac4181..526539cbc99f 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1,4 +1,5 @@
 # MIPS headers
+generic-(CONFIG_GENERIC_CSUM) += checksum.h
 generic-y += cputime.h
 generic-y += current.h
 generic-y += dma-contiguous.h
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 5996252680c6..5c585c5c1c3e 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -12,6 +12,10 @@
 #ifndef _ASM_CHECKSUM_H
 #define _ASM_CHECKSUM_H
 
+#ifdef CONFIG_GENERIC_CSUM
+#include <asm-generic/checksum.h>
+#else
+
 #include <linux/in6.h>
 
 #include <asm/uaccess.h>
@@ -274,5 +278,6 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 }
 
 #include <asm-generic/checksum.h>
+#endif /* CONFIG_GENERIC_CSUM */
 
 #endif /* _ASM_CHECKSUM_H */
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index 17eaf0cf760c..ac66c30c8cd6 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -67,11 +67,13 @@ EXPORT_SYMBOL(__strnlen_kernel_asm);
 EXPORT_SYMBOL(__strnlen_user_nocheck_asm);
 EXPORT_SYMBOL(__strnlen_user_asm);
 
+#ifndef CONFIG_CPU_MIPSR6
 EXPORT_SYMBOL(csum_partial);
 EXPORT_SYMBOL(csum_partial_copy_nocheck);
 EXPORT_SYMBOL(__csum_partial_copy_kernel);
 EXPORT_SYMBOL(__csum_partial_copy_to_user);
 EXPORT_SYMBOL(__csum_partial_copy_from_user);
+#endif
 
 EXPORT_SYMBOL(invalid_pte_table);
 #ifdef CONFIG_FUNCTION_TRACER
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index eeddc58802e1..1e9e900cd3c3 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -8,6 +8,7 @@ lib-y	+= bitops.o csum_partial.o delay.o memcpy.o memset.o \
 
 obj-y			+= iomap.o
 obj-$(CONFIG_PCI)	+= iomap-pci.o
+lib-$(CONFIG_GENERIC_CSUM)	:= $(filter-out csum_partial.o, $(lib-y))
 
 obj-$(CONFIG_CPU_GENERIC_DUMP_TLB) += dump_tlb.o
 obj-$(CONFIG_CPU_R3000)		+= r3k_dump_tlb.o
-- 
cgit v1.2.3


From 34c56fc1c167facc375d927687df0a3891d164ac Mon Sep 17 00:00:00 2001
From: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Date: Thu, 13 Nov 2014 11:49:21 +0000
Subject: MIPS: asm: cpu: Add MIPSR6 ISA definitions

Add MIPS R6 to the ISA definitions

Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/cpu-features.h | 19 +++++++++++++++----
 arch/mips/include/asm/cpu.h          |  7 +++++--
 2 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 2897cfafcaf0..799dc6db7847 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -189,12 +189,18 @@
 #ifndef cpu_has_mips32r2
 # define cpu_has_mips32r2	(cpu_data[0].isa_level & MIPS_CPU_ISA_M32R2)
 #endif
+#ifndef cpu_has_mips32r6
+# define cpu_has_mips32r6	(cpu_data[0].isa_level & MIPS_CPU_ISA_M32R6)
+#endif
 #ifndef cpu_has_mips64r1
 # define cpu_has_mips64r1	(cpu_data[0].isa_level & MIPS_CPU_ISA_M64R1)
 #endif
 #ifndef cpu_has_mips64r2
 # define cpu_has_mips64r2	(cpu_data[0].isa_level & MIPS_CPU_ISA_M64R2)
 #endif
+#ifndef cpu_has_mips64r6
+# define cpu_has_mips64r6	(cpu_data[0].isa_level & MIPS_CPU_ISA_M64R6)
+#endif
 
 /*
  * Shortcuts ...
@@ -210,15 +216,20 @@
 
 #define cpu_has_mips_4_5_r2	(cpu_has_mips_4_5 | cpu_has_mips_r2)
 
-#define cpu_has_mips32	(cpu_has_mips32r1 | cpu_has_mips32r2)
-#define cpu_has_mips64	(cpu_has_mips64r1 | cpu_has_mips64r2)
+#define cpu_has_mips32	(cpu_has_mips32r1 | cpu_has_mips32r2 | cpu_has_mips32r6)
+#define cpu_has_mips64	(cpu_has_mips64r1 | cpu_has_mips64r2 | cpu_has_mips64r6)
 #define cpu_has_mips_r1 (cpu_has_mips32r1 | cpu_has_mips64r1)
 #define cpu_has_mips_r2 (cpu_has_mips32r2 | cpu_has_mips64r2)
+#define cpu_has_mips_r6	(cpu_has_mips32r6 | cpu_has_mips64r6)
 #define cpu_has_mips_r	(cpu_has_mips32r1 | cpu_has_mips32r2 | \
-			 cpu_has_mips64r1 | cpu_has_mips64r2)
+			 cpu_has_mips32r6 | cpu_has_mips64r1 | \
+			 cpu_has_mips64r2 | cpu_has_mips64r6)
+
+/* MIPSR2 and MIPSR6 have a lot of similarities */
+#define cpu_has_mips_r2_r6	(cpu_has_mips_r2 | cpu_has_mips_r6)
 
 #ifndef cpu_has_mips_r2_exec_hazard
-#define cpu_has_mips_r2_exec_hazard cpu_has_mips_r2
+#define cpu_has_mips_r2_exec_hazard (cpu_has_mips_r2 | cpu_has_mips_r6)
 #endif
 
 /*
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 0b74bbf976e4..f604523aec3d 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -332,11 +332,14 @@ enum cpu_type_enum {
 #define MIPS_CPU_ISA_M32R2	0x00000020
 #define MIPS_CPU_ISA_M64R1	0x00000040
 #define MIPS_CPU_ISA_M64R2	0x00000080
+#define MIPS_CPU_ISA_M32R6	0x00000100
+#define MIPS_CPU_ISA_M64R6	0x00000200
 
 #define MIPS_CPU_ISA_32BIT (MIPS_CPU_ISA_II | MIPS_CPU_ISA_M32R1 | \
-	MIPS_CPU_ISA_M32R2)
+	MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M32R6)
 #define MIPS_CPU_ISA_64BIT (MIPS_CPU_ISA_III | MIPS_CPU_ISA_IV | \
-	MIPS_CPU_ISA_V | MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)
+	MIPS_CPU_ISA_V | MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2 | \
+	MIPS_CPU_ISA_M64R6)
 
 /*
  * CPU Option encodings
-- 
cgit v1.2.3


From f52fca9713c223b8e90ab00eea46d494789f1d77 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 13 Nov 2014 11:52:22 +0000
Subject: MIPS: asm: hazards: Add MIPSR6 definitions

Add the MIPSR6 related definitions to MIPS hazards

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/hazards.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/hazards.h b/arch/mips/include/asm/hazards.h
index e3ee92d4dbe7..4087b47ad1cb 100644
--- a/arch/mips/include/asm/hazards.h
+++ b/arch/mips/include/asm/hazards.h
@@ -11,6 +11,7 @@
 #define _ASM_HAZARDS_H
 
 #include <linux/stringify.h>
+#include <asm/compiler.h>
 
 #define ___ssnop							\
 	sll	$0, $0, 1
@@ -21,7 +22,7 @@
 /*
  * TLB hazards
  */
-#if defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_CPU_CAVIUM_OCTEON)
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) && !defined(CONFIG_CPU_CAVIUM_OCTEON)
 
 /*
  * MIPSR2 defines ehb for hazard avoidance
@@ -58,7 +59,7 @@ do {									\
 	unsigned long tmp;						\
 									\
 	__asm__ __volatile__(						\
-	"	.set	mips64r2				\n"	\
+	"	.set "MIPS_ISA_LEVEL"				\n"	\
 	"	dla	%0, 1f					\n"	\
 	"	jr.hb	%0					\n"	\
 	"	.set	mips0					\n"	\
@@ -132,7 +133,7 @@ do {									\
 
 #define instruction_hazard()						\
 do {									\
-	if (cpu_has_mips_r2)						\
+	if (cpu_has_mips_r2_r6)						\
 		__instruction_hazard();					\
 } while (0)
 
@@ -240,7 +241,7 @@ do {									\
 
 #define __disable_fpu_hazard
 
-#elif defined(CONFIG_CPU_MIPSR2)
+#elif defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 
 #define __enable_fpu_hazard						\
 	___ehb
-- 
cgit v1.2.3


From 8716a7635665008291d3f19dd5d36a858ed1561b Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 13 Nov 2014 11:54:31 +0000
Subject: MIPS: asm: irqflags: Add MIPS R6 related definitions

Add the MIPS R6 related definitions to the IRQ related macros

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/irqflags.h | 7 ++++---
 arch/mips/lib/mips-atomic.c      | 2 +-
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h
index 0fa5fdcd1f01..d60cc68fa31e 100644
--- a/arch/mips/include/asm/irqflags.h
+++ b/arch/mips/include/asm/irqflags.h
@@ -15,9 +15,10 @@
 
 #include <linux/compiler.h>
 #include <linux/stringify.h>
+#include <asm/compiler.h>
 #include <asm/hazards.h>
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined (CONFIG_CPU_MIPSR6)
 
 static inline void arch_local_irq_disable(void)
 {
@@ -118,7 +119,7 @@ void arch_local_irq_disable(void);
 unsigned long arch_local_irq_save(void);
 void arch_local_irq_restore(unsigned long flags);
 void __arch_local_irq_restore(unsigned long flags);
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 
 static inline void arch_local_irq_enable(void)
 {
@@ -126,7 +127,7 @@ static inline void arch_local_irq_enable(void)
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
-#if   defined(CONFIG_CPU_MIPSR2)
+#if   defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	"	ei							\n"
 #else
 	"	mfc0	$1,$12						\n"
diff --git a/arch/mips/lib/mips-atomic.c b/arch/mips/lib/mips-atomic.c
index be777d9a3f85..272af8ac2425 100644
--- a/arch/mips/lib/mips-atomic.c
+++ b/arch/mips/lib/mips-atomic.c
@@ -15,7 +15,7 @@
 #include <linux/export.h>
 #include <linux/stringify.h>
 
-#ifndef CONFIG_CPU_MIPSR2
+#if !defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_CPU_MIPSR6)
 
 /*
  * For cli() we have to insert nops to make sure that the new value
-- 
cgit v1.2.3


From 934c79231c1b3a88ed1ef8f1473fb26849ae501c Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 13 Nov 2014 13:25:51 +0000
Subject: MIPS: asm: r4kcache: Add MIPS R6 cache unroll functions

MIPS R6 changed the 'cache' instruction opcode and reduced the
offset field to 8 bits. This means we now have to adjust the
base register every 256 bytes and as a result of which we can
no longer use the previous cache functions.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/r4kcache.h | 150 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 148 insertions(+), 2 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index e293a8d89a6d..1b22d2da88a1 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -14,6 +14,7 @@
 
 #include <asm/asm.h>
 #include <asm/cacheops.h>
+#include <asm/compiler.h>
 #include <asm/cpu-features.h>
 #include <asm/cpu-type.h>
 #include <asm/mipsmtregs.h>
@@ -39,7 +40,7 @@ extern void (*r4k_blast_icache)(void);
 	__asm__ __volatile__(						\
 	"	.set	push					\n"	\
 	"	.set	noreorder				\n"	\
-	"	.set	arch=r4000				\n"	\
+	"	.set "MIPS_ISA_ARCH_LEVEL"			\n"	\
 	"	cache	%0, %1					\n"	\
 	"	.set	pop					\n"	\
 	:								\
@@ -147,7 +148,7 @@ static inline void flush_scache_line(unsigned long addr)
 	__asm__ __volatile__(					\
 	"	.set	push			\n"		\
 	"	.set	noreorder		\n"		\
-	"	.set	arch=r4000		\n"		\
+	"	.set "MIPS_ISA_ARCH_LEVEL"	\n"		\
 	"1:	cache	%0, (%1)		\n"		\
 	"2:	.set	pop			\n"		\
 	"	.section __ex_table,\"a\"	\n"		\
@@ -218,6 +219,7 @@ static inline void invalidate_tcache_page(unsigned long addr)
 	cache_op(Page_Invalidate_T, addr);
 }
 
+#ifndef CONFIG_CPU_MIPSR6
 #define cache16_unroll32(base,op)					\
 	__asm__ __volatile__(						\
 	"	.set push					\n"	\
@@ -322,6 +324,150 @@ static inline void invalidate_tcache_page(unsigned long addr)
 		: "r" (base),						\
 		  "i" (op));
 
+#else
+/*
+ * MIPS R6 changed the cache opcode and moved to a 8-bit offset field.
+ * This means we now need to increment the base register before we flush
+ * more cache lines
+ */
+#define cache16_unroll32(base,op)				\
+	__asm__ __volatile__(					\
+	"	.set push\n"					\
+	"	.set noreorder\n"				\
+	"	.set mips64r6\n"				\
+	"	.set noat\n"					\
+	"	cache %1, 0x000(%0); cache %1, 0x010(%0)\n"	\
+	"	cache %1, 0x020(%0); cache %1, 0x030(%0)\n"	\
+	"	cache %1, 0x040(%0); cache %1, 0x050(%0)\n"	\
+	"	cache %1, 0x060(%0); cache %1, 0x070(%0)\n"	\
+	"	cache %1, 0x080(%0); cache %1, 0x090(%0)\n"	\
+	"	cache %1, 0x0a0(%0); cache %1, 0x0b0(%0)\n"	\
+	"	cache %1, 0x0c0(%0); cache %1, 0x0d0(%0)\n"	\
+	"	cache %1, 0x0e0(%0); cache %1, 0x0f0(%0)\n"	\
+	"	addiu $1, $0, 0x100			\n"	\
+	"	cache %1, 0x000($1); cache %1, 0x010($1)\n"	\
+	"	cache %1, 0x020($1); cache %1, 0x030($1)\n"	\
+	"	cache %1, 0x040($1); cache %1, 0x050($1)\n"	\
+	"	cache %1, 0x060($1); cache %1, 0x070($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x090($1)\n"	\
+	"	cache %1, 0x0a0($1); cache %1, 0x0b0($1)\n"	\
+	"	cache %1, 0x0c0($1); cache %1, 0x0d0($1)\n"	\
+	"	cache %1, 0x0e0($1); cache %1, 0x0f0($1)\n"	\
+	"	.set pop\n"					\
+		:						\
+		: "r" (base),					\
+		  "i" (op));
+
+#define cache32_unroll32(base,op)				\
+	__asm__ __volatile__(					\
+	"	.set push\n"					\
+	"	.set noreorder\n"				\
+	"	.set mips64r6\n"				\
+	"	.set noat\n"					\
+	"	cache %1, 0x000(%0); cache %1, 0x020(%0)\n"	\
+	"	cache %1, 0x040(%0); cache %1, 0x060(%0)\n"	\
+	"	cache %1, 0x080(%0); cache %1, 0x0a0(%0)\n"	\
+	"	cache %1, 0x0c0(%0); cache %1, 0x0e0(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x020($1)\n"	\
+	"	cache %1, 0x040($1); cache %1, 0x060($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0a0($1)\n"	\
+	"	cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n"	\
+	"	addiu $1, $1, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x020($1)\n"	\
+	"	cache %1, 0x040($1); cache %1, 0x060($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0a0($1)\n"	\
+	"	cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n"	\
+	"	addiu $1, $1, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x020($1)\n"	\
+	"	cache %1, 0x040($1); cache %1, 0x060($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0a0($1)\n"	\
+	"	cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n"	\
+	"	.set pop\n"					\
+		:						\
+		: "r" (base),					\
+		  "i" (op));
+
+#define cache64_unroll32(base,op)				\
+	__asm__ __volatile__(					\
+	"	.set push\n"					\
+	"	.set noreorder\n"				\
+	"	.set mips64r6\n"				\
+	"	.set noat\n"					\
+	"	cache %1, 0x000(%0); cache %1, 0x040(%0)\n"	\
+	"	cache %1, 0x080(%0); cache %1, 0x0c0(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	.set pop\n"					\
+		:						\
+		: "r" (base),					\
+		  "i" (op));
+
+#define cache128_unroll32(base,op)				\
+	__asm__ __volatile__(					\
+	"	.set push\n"					\
+	"	.set noreorder\n"				\
+	"	.set mips64r6\n"				\
+	"	.set noat\n"					\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	.set pop\n"					\
+		:						\
+		: "r" (base),					\
+		  "i" (op));
+#endif /* CONFIG_CPU_MIPSR6 */
+
 /*
  * Perform the cache operation specified by op using a user mode virtual
  * address while in kernel mode.
-- 
cgit v1.2.3


From a7e07b1ae550303c6611f4d3b054a4f9c2bc8a9e Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 13 Nov 2014 13:32:03 +0000
Subject: MIPS: asm: spram: Add new symbol for MIPS scratch pad storage

MIPS R6, just like MIPS R2, have scratch pad storage, so add a new
symbol which is selected by MIPS R2 and R6.

Link: http://www.linux-mips.org/archives/linux-mips/2015-01/msg00389.html
Cc: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/Kconfig             | 5 +++++
 arch/mips/include/asm/spram.h | 4 ++--
 arch/mips/kernel/Makefile     | 2 +-
 3 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 0a8508b4803d..883eb3aacedf 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1150,6 +1150,9 @@ config SOC_PNX8335
 	bool
 	select SOC_PNX833X
 
+config MIPS_SPRAM
+	bool
+
 config SWAP_IO_SPACE
 	bool
 
@@ -1821,10 +1824,12 @@ config CPU_MIPSR1
 config CPU_MIPSR2
 	bool
 	default y if CPU_MIPS32_R2 || CPU_MIPS64_R2 || CPU_CAVIUM_OCTEON
+	select MIPS_SPRAM
 
 config CPU_MIPSR6
 	bool
 	default y if CPU_MIPS32_R6 || CPU_MIPS64_R6
+	select MIPS_SPRAM
 
 config EVA
 	bool
diff --git a/arch/mips/include/asm/spram.h b/arch/mips/include/asm/spram.h
index 0b89006e4907..0f90d88e464d 100644
--- a/arch/mips/include/asm/spram.h
+++ b/arch/mips/include/asm/spram.h
@@ -1,10 +1,10 @@
 #ifndef _MIPS_SPRAM_H
 #define _MIPS_SPRAM_H
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_MIPS_SPRAM)
 extern __init void spram_config(void);
 #else
 static inline void spram_config(void) { };
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_MIPS_SPRAM */
 
 #endif /* _MIPS_SPRAM_H */
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 92987d1bbe5f..de1e65366f02 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -52,7 +52,7 @@ obj-$(CONFIG_MIPS_MT_SMP)	+= smp-mt.o
 obj-$(CONFIG_MIPS_CMP)		+= smp-cmp.o
 obj-$(CONFIG_MIPS_CPS)		+= smp-cps.o cps-vec.o
 obj-$(CONFIG_MIPS_GIC_IPI)	+= smp-gic.o
-obj-$(CONFIG_CPU_MIPSR2)	+= spram.o
+obj-$(CONFIG_MIPS_SPRAM)	+= spram.o
 
 obj-$(CONFIG_MIPS_VPE_LOADER)	+= vpe.o
 obj-$(CONFIG_MIPS_VPE_LOADER_CMP) += vpe-cmp.o
-- 
cgit v1.2.3


From 94bfb75ace81f7b09860400ba02ed1607a2e0e27 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Mon, 26 Jan 2015 12:44:11 +0000
Subject: MIPS: asm: Rename GCC_OFF12_ASM to GCC_OFF_SMALL_ASM

The GCC_OFF12_ASM macro is used for 12-bit immediate constrains
but we will also use it for 9-bit constrains on MIPS R6 so we
rename it to something more appropriate.

Cc: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/atomic.h                     | 30 +++++++-------
 arch/mips/include/asm/bitops.h                     | 34 +++++++--------
 arch/mips/include/asm/cmpxchg.h                    | 24 +++++------
 arch/mips/include/asm/compiler.h                   |  4 +-
 arch/mips/include/asm/edac.h                       |  4 +-
 arch/mips/include/asm/futex.h                      | 16 ++++----
 .../include/asm/mach-pmcs-msp71xx/msp_regops.h     | 24 +++++------
 arch/mips/include/asm/octeon/cvmx-cmd-queue.h      |  2 +-
 arch/mips/include/asm/spinlock.h                   | 48 +++++++++++-----------
 9 files changed, 93 insertions(+), 93 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 857da84cfc92..3a44c2f17e53 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -54,7 +54,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 		"	sc	%0, %1					\n"   \
 		"	beqzl	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (v->counter)	      \
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
 	} else if (kernel_uses_llsc) {					      \
 		int temp;						      \
@@ -66,7 +66,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 			"	" #asm_op " %0, %2			\n"   \
 			"	sc	%0, %1				\n"   \
 			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (v->counter)      \
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
 			: "Ir" (i));					      \
 		} while (unlikely(!temp));				      \
 	} else {							      \
@@ -97,7 +97,7 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
-		  "+" GCC_OFF12_ASM() (v->counter)			      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
 	} else if (kernel_uses_llsc) {					      \
 		int temp;						      \
@@ -110,7 +110,7 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
 			"	sc	%0, %2				\n"   \
 			"	.set	mips0				\n"   \
 			: "=&r" (result), "=&r" (temp),			      \
-			  "+" GCC_OFF12_ASM() (v->counter)		      \
+			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
 			: "Ir" (i));					      \
 		} while (unlikely(!result));				      \
 									      \
@@ -171,8 +171,8 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF12_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF12_ASM() (v->counter)
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)
+		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		int temp;
@@ -190,7 +190,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF12_ASM() (v->counter)
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "Ir" (i));
 	} else {
 		unsigned long flags;
@@ -333,7 +333,7 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 		"	scd	%0, %1					\n"   \
 		"	beqzl	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (v->counter)	      \
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
 	} else if (kernel_uses_llsc) {					      \
 		long temp;						      \
@@ -345,7 +345,7 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 			"	" #asm_op " %0, %2			\n"   \
 			"	scd	%0, %1				\n"   \
 			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (v->counter)      \
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
 			: "Ir" (i));					      \
 		} while (unlikely(!temp));				      \
 	} else {							      \
@@ -376,7 +376,7 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
-		  "+" GCC_OFF12_ASM() (v->counter)			      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
 	} else if (kernel_uses_llsc) {					      \
 		long temp;						      \
@@ -389,8 +389,8 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
 			"	scd	%0, %2				\n"   \
 			"	.set	mips0				\n"   \
 			: "=&r" (result), "=&r" (temp),			      \
-			  "=" GCC_OFF12_ASM() (v->counter)		      \
-			: "Ir" (i), GCC_OFF12_ASM() (v->counter)	      \
+			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
+			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
 			: "memory");					      \
 		} while (unlikely(!result));				      \
 									      \
@@ -452,8 +452,8 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-		  "=" GCC_OFF12_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF12_ASM() (v->counter)
+		  "=" GCC_OFF_SMALL_ASM() (v->counter)
+		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		long temp;
@@ -471,7 +471,7 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF12_ASM() (v->counter)
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "Ir" (i));
 	} else {
 		unsigned long flags;
diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index 6663bcca9d0c..6cc1f539c79a 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -79,8 +79,8 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 		"	" __SC	"%0, %1					\n"
 		"	beqzl	%0, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "=" GCC_OFF12_ASM() (*m)
-		: "ir" (1UL << bit), GCC_OFF12_ASM() (*m));
+		: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*m)
+		: "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m));
 #ifdef CONFIG_CPU_MIPSR2
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
 		do {
@@ -88,7 +88,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 			"	" __LL "%0, %1		# set_bit	\n"
 			"	" __INS "%0, %3, %2, 1			\n"
 			"	" __SC "%0, %1				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (bit), "r" (~0));
 		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 */
@@ -100,7 +100,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 			"	or	%0, %2				\n"
 			"	" __SC	"%0, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (1UL << bit));
 		} while (unlikely(!temp));
 	} else
@@ -131,7 +131,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 		"	" __SC "%0, %1					\n"
 		"	beqzl	%0, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 		: "ir" (~(1UL << bit)));
 #ifdef CONFIG_CPU_MIPSR2
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
@@ -140,7 +140,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 			"	" __LL "%0, %1		# clear_bit	\n"
 			"	" __INS "%0, $0, %2, 1			\n"
 			"	" __SC "%0, %1				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (bit));
 		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 */
@@ -152,7 +152,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 			"	and	%0, %2				\n"
 			"	" __SC "%0, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (~(1UL << bit)));
 		} while (unlikely(!temp));
 	} else
@@ -197,7 +197,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 		"	" __SC	"%0, %1				\n"
 		"	beqzl	%0, 1b				\n"
 		"	.set	mips0				\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 		: "ir" (1UL << bit));
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
@@ -210,7 +210,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 			"	xor	%0, %2				\n"
 			"	" __SC	"%0, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (1UL << bit));
 		} while (unlikely(!temp));
 	} else
@@ -245,7 +245,7 @@ static inline int test_and_set_bit(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
 		: "memory");
 	} else if (kernel_uses_llsc) {
@@ -259,7 +259,7 @@ static inline int test_and_set_bit(unsigned long nr,
 			"	or	%2, %0, %3			\n"
 			"	" __SC	"%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
 			: "memory");
 		} while (unlikely(!res));
@@ -313,7 +313,7 @@ static inline int test_and_set_bit_lock(unsigned long nr,
 			"	or	%2, %0, %3			\n"
 			"	" __SC	"%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
 			: "memory");
 		} while (unlikely(!res));
@@ -355,7 +355,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
 		: "memory");
 #ifdef CONFIG_CPU_MIPSR2
@@ -369,7 +369,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 			"	" __EXT "%2, %0, %3, 1			\n"
 			"	" __INS "%0, $0, %3, 1			\n"
 			"	" __SC	"%0, %1				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "ir" (bit)
 			: "memory");
 		} while (unlikely(!temp));
@@ -386,7 +386,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 			"	xor	%2, %3				\n"
 			"	" __SC	"%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
 			: "memory");
 		} while (unlikely(!res));
@@ -428,7 +428,7 @@ static inline int test_and_change_bit(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
 		: "memory");
 	} else if (kernel_uses_llsc) {
@@ -442,7 +442,7 @@ static inline int test_and_change_bit(unsigned long nr,
 			"	xor	%2, %0, %3			\n"
 			"	" __SC	"\t%2, %1			\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
 			: "memory");
 		} while (unlikely(!res));
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 28b1edf19501..68baa0cf521a 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -31,8 +31,8 @@ static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
 		"	sc	%2, %1					\n"
 		"	beqzl	%2, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (retval), "=" GCC_OFF12_ASM() (*m), "=&r" (dummy)
-		: GCC_OFF12_ASM() (*m), "Jr" (val)
+		: "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy)
+		: GCC_OFF_SMALL_ASM() (*m), "Jr" (val)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		unsigned long dummy;
@@ -46,9 +46,9 @@ static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
 			"	.set	arch=r4000			\n"
 			"	sc	%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (retval), "=" GCC_OFF12_ASM() (*m),
+			: "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m),
 			  "=&r" (dummy)
-			: GCC_OFF12_ASM() (*m), "Jr" (val)
+			: GCC_OFF_SMALL_ASM() (*m), "Jr" (val)
 			: "memory");
 		} while (unlikely(!dummy));
 	} else {
@@ -82,8 +82,8 @@ static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val)
 		"	scd	%2, %1					\n"
 		"	beqzl	%2, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (retval), "=" GCC_OFF12_ASM() (*m), "=&r" (dummy)
-		: GCC_OFF12_ASM() (*m), "Jr" (val)
+		: "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy)
+		: GCC_OFF_SMALL_ASM() (*m), "Jr" (val)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		unsigned long dummy;
@@ -95,9 +95,9 @@ static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val)
 			"	move	%2, %z4				\n"
 			"	scd	%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (retval), "=" GCC_OFF12_ASM() (*m),
+			: "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m),
 			  "=&r" (dummy)
-			: GCC_OFF12_ASM() (*m), "Jr" (val)
+			: GCC_OFF_SMALL_ASM() (*m), "Jr" (val)
 			: "memory");
 		} while (unlikely(!dummy));
 	} else {
@@ -158,8 +158,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 		"	beqzl	$1, 1b				\n"	\
 		"2:						\n"	\
 		"	.set	pop				\n"	\
-		: "=&r" (__ret), "=" GCC_OFF12_ASM() (*m)		\
-		: GCC_OFF12_ASM() (*m), "Jr" (old), "Jr" (new)		\
+		: "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m)		\
+		: GCC_OFF_SMALL_ASM() (*m), "Jr" (old), "Jr" (new)		\
 		: "memory");						\
 	} else if (kernel_uses_llsc) {					\
 		__asm__ __volatile__(					\
@@ -175,8 +175,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 		"	beqz	$1, 1b				\n"	\
 		"	.set	pop				\n"	\
 		"2:						\n"	\
-		: "=&r" (__ret), "=" GCC_OFF12_ASM() (*m)		\
-		: GCC_OFF12_ASM() (*m), "Jr" (old), "Jr" (new)		\
+		: "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m)		\
+		: GCC_OFF_SMALL_ASM() (*m), "Jr" (old), "Jr" (new)		\
 		: "memory");						\
 	} else {							\
 		unsigned long __flags;					\
diff --git a/arch/mips/include/asm/compiler.h b/arch/mips/include/asm/compiler.h
index 10b642f55eb7..34ad65a7801f 100644
--- a/arch/mips/include/asm/compiler.h
+++ b/arch/mips/include/asm/compiler.h
@@ -17,9 +17,9 @@
 #endif
 
 #ifndef CONFIG_CPU_MICROMIPS
-#define GCC_OFF12_ASM() "R"
+#define GCC_OFF_SMALL_ASM() "R"
 #elif __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 9)
-#define GCC_OFF12_ASM() "ZC"
+#define GCC_OFF_SMALL_ASM() "ZC"
 #else
 #error "microMIPS compilation unsupported with GCC older than 4.9"
 #endif
diff --git a/arch/mips/include/asm/edac.h b/arch/mips/include/asm/edac.h
index ae6fedcb0060..94105d3f58f4 100644
--- a/arch/mips/include/asm/edac.h
+++ b/arch/mips/include/asm/edac.h
@@ -26,8 +26,8 @@ static inline void atomic_scrub(void *va, u32 size)
 		"	sc	%0, %1					\n"
 		"	beqz	%0, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "=" GCC_OFF12_ASM() (*virt_addr)
-		: GCC_OFF12_ASM() (*virt_addr));
+		: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*virt_addr)
+		: GCC_OFF_SMALL_ASM() (*virt_addr));
 
 		virt_addr++;
 	}
diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index ef9987a61d88..f666c0608c11 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -45,8 +45,8 @@
 		"	"__UA_ADDR "\t2b, 4b			\n"	\
 		"	.previous				\n"	\
 		: "=r" (ret), "=&r" (oldval),				\
-		  "=" GCC_OFF12_ASM() (*uaddr)				\
-		: "0" (0), GCC_OFF12_ASM() (*uaddr), "Jr" (oparg),	\
+		  "=" GCC_OFF_SMALL_ASM() (*uaddr)				\
+		: "0" (0), GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oparg),	\
 		  "i" (-EFAULT)						\
 		: "memory");						\
 	} else if (cpu_has_llsc) {					\
@@ -74,8 +74,8 @@
 		"	"__UA_ADDR "\t2b, 4b			\n"	\
 		"	.previous				\n"	\
 		: "=r" (ret), "=&r" (oldval),				\
-		  "=" GCC_OFF12_ASM() (*uaddr)				\
-		: "0" (0), GCC_OFF12_ASM() (*uaddr), "Jr" (oparg),	\
+		  "=" GCC_OFF_SMALL_ASM() (*uaddr)				\
+		: "0" (0), GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oparg),	\
 		  "i" (-EFAULT)						\
 		: "memory");						\
 	} else								\
@@ -174,8 +174,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		"	"__UA_ADDR "\t1b, 4b				\n"
 		"	"__UA_ADDR "\t2b, 4b				\n"
 		"	.previous					\n"
-		: "+r" (ret), "=&r" (val), "=" GCC_OFF12_ASM() (*uaddr)
-		: GCC_OFF12_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
+		: "+r" (ret), "=&r" (val), "=" GCC_OFF_SMALL_ASM() (*uaddr)
+		: GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
 		  "i" (-EFAULT)
 		: "memory");
 	} else if (cpu_has_llsc) {
@@ -203,8 +203,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		"	"__UA_ADDR "\t1b, 4b				\n"
 		"	"__UA_ADDR "\t2b, 4b				\n"
 		"	.previous					\n"
-		: "+r" (ret), "=&r" (val), "=" GCC_OFF12_ASM() (*uaddr)
-		: GCC_OFF12_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
+		: "+r" (ret), "=&r" (val), "=" GCC_OFF_SMALL_ASM() (*uaddr)
+		: GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
 		  "i" (-EFAULT)
 		: "memory");
 	} else
diff --git a/arch/mips/include/asm/mach-pmcs-msp71xx/msp_regops.h b/arch/mips/include/asm/mach-pmcs-msp71xx/msp_regops.h
index 2e54b4bff5cf..90dbe43c8d27 100644
--- a/arch/mips/include/asm/mach-pmcs-msp71xx/msp_regops.h
+++ b/arch/mips/include/asm/mach-pmcs-msp71xx/msp_regops.h
@@ -85,8 +85,8 @@ static inline void set_value_reg32(volatile u32 *const addr,
 	"	"__beqz"%0, 1b				\n"
 	"	nop					\n"
 	"	.set	pop				\n"
-	: "=&r" (temp), "=" GCC_OFF12_ASM() (*addr)
-	: "ir" (~mask), "ir" (value), GCC_OFF12_ASM() (*addr));
+	: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*addr)
+	: "ir" (~mask), "ir" (value), GCC_OFF_SMALL_ASM() (*addr));
 }
 
 /*
@@ -106,8 +106,8 @@ static inline void set_reg32(volatile u32 *const addr,
 	"	"__beqz"%0, 1b				\n"
 	"	nop					\n"
 	"	.set	pop				\n"
-	: "=&r" (temp), "=" GCC_OFF12_ASM() (*addr)
-	: "ir" (mask), GCC_OFF12_ASM() (*addr));
+	: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*addr)
+	: "ir" (mask), GCC_OFF_SMALL_ASM() (*addr));
 }
 
 /*
@@ -127,8 +127,8 @@ static inline void clear_reg32(volatile u32 *const addr,
 	"	"__beqz"%0, 1b				\n"
 	"	nop					\n"
 	"	.set	pop				\n"
-	: "=&r" (temp), "=" GCC_OFF12_ASM() (*addr)
-	: "ir" (~mask), GCC_OFF12_ASM() (*addr));
+	: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*addr)
+	: "ir" (~mask), GCC_OFF_SMALL_ASM() (*addr));
 }
 
 /*
@@ -148,8 +148,8 @@ static inline void toggle_reg32(volatile u32 *const addr,
 	"	"__beqz"%0, 1b				\n"
 	"	nop					\n"
 	"	.set	pop				\n"
-	: "=&r" (temp), "=" GCC_OFF12_ASM() (*addr)
-	: "ir" (mask), GCC_OFF12_ASM() (*addr));
+	: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*addr)
+	: "ir" (mask), GCC_OFF_SMALL_ASM() (*addr));
 }
 
 /*
@@ -220,8 +220,8 @@ static inline u32 blocking_read_reg32(volatile u32 *const addr)
 	"	.set	arch=r4000			\n"	\
 	"1:	ll	%0, %1	#custom_read_reg32	\n"	\
 	"	.set	pop				\n"	\
-	: "=r" (tmp), "=" GCC_OFF12_ASM() (*address)		\
-	: GCC_OFF12_ASM() (*address))
+	: "=r" (tmp), "=" GCC_OFF_SMALL_ASM() (*address)		\
+	: GCC_OFF_SMALL_ASM() (*address))
 
 #define custom_write_reg32(address, tmp)			\
 	__asm__ __volatile__(					\
@@ -231,7 +231,7 @@ static inline u32 blocking_read_reg32(volatile u32 *const addr)
 	"	"__beqz"%0, 1b				\n"	\
 	"	nop					\n"	\
 	"	.set	pop				\n"	\
-	: "=&r" (tmp), "=" GCC_OFF12_ASM() (*address)		\
-	: "0" (tmp), GCC_OFF12_ASM() (*address))
+	: "=&r" (tmp), "=" GCC_OFF_SMALL_ASM() (*address)		\
+	: "0" (tmp), GCC_OFF_SMALL_ASM() (*address))
 
 #endif	/* __ASM_REGOPS_H__ */
diff --git a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
index 75739c83f07e..8d05d9069823 100644
--- a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
+++ b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
@@ -275,7 +275,7 @@ static inline void __cvmx_cmd_queue_lock(cvmx_cmd_queue_id_t queue_id,
 		" lbu	%[ticket], %[now_serving]\n"
 		"4:\n"
 		".set pop\n" :
-		[ticket_ptr] "=" GCC_OFF12_ASM()(__cvmx_cmd_queue_state_ptr->ticket[__cvmx_cmd_queue_get_index(queue_id)]),
+		[ticket_ptr] "=" GCC_OFF_SMALL_ASM()(__cvmx_cmd_queue_state_ptr->ticket[__cvmx_cmd_queue_get_index(queue_id)]),
 		[now_serving] "=m"(qptr->now_serving), [ticket] "=r"(tmp),
 		[my_ticket] "=r"(my_ticket)
 	    );
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index c6d06d383ef9..b5238404c059 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -89,7 +89,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 		"	 subu	%[ticket], %[ticket], 1			\n"
 		"	.previous					\n"
 		"	.set pop					\n"
-		: [ticket_ptr] "+" GCC_OFF12_ASM() (lock->lock),
+		: [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock),
 		  [serving_now_ptr] "+m" (lock->h.serving_now),
 		  [ticket] "=&r" (tmp),
 		  [my_ticket] "=&r" (my_ticket)
@@ -122,7 +122,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 		"	 subu	%[ticket], %[ticket], 1			\n"
 		"	.previous					\n"
 		"	.set pop					\n"
-		: [ticket_ptr] "+" GCC_OFF12_ASM() (lock->lock),
+		: [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock),
 		  [serving_now_ptr] "+m" (lock->h.serving_now),
 		  [ticket] "=&r" (tmp),
 		  [my_ticket] "=&r" (my_ticket)
@@ -164,7 +164,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 		"	 li	%[ticket], 0				\n"
 		"	.previous					\n"
 		"	.set pop					\n"
-		: [ticket_ptr] "+" GCC_OFF12_ASM() (lock->lock),
+		: [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock),
 		  [ticket] "=&r" (tmp),
 		  [my_ticket] "=&r" (tmp2),
 		  [now_serving] "=&r" (tmp3)
@@ -188,7 +188,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 		"	 li	%[ticket], 0				\n"
 		"	.previous					\n"
 		"	.set pop					\n"
-		: [ticket_ptr] "+" GCC_OFF12_ASM() (lock->lock),
+		: [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock),
 		  [ticket] "=&r" (tmp),
 		  [my_ticket] "=&r" (tmp2),
 		  [now_serving] "=&r" (tmp3)
@@ -235,8 +235,8 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 		"	beqzl	%1, 1b					\n"
 		"	 nop						\n"
 		"	.set	reorder					\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		do {
@@ -245,8 +245,8 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 			"	bltz	%1, 1b				\n"
 			"	 addu	%1, 1				\n"
 			"2:	sc	%1, %0				\n"
-			: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-			: GCC_OFF12_ASM() (rw->lock)
+			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+			: GCC_OFF_SMALL_ASM() (rw->lock)
 			: "memory");
 		} while (unlikely(!tmp));
 	}
@@ -269,8 +269,8 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 		"	sub	%1, 1					\n"
 		"	sc	%1, %0					\n"
 		"	beqzl	%1, 1b					\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		do {
@@ -278,8 +278,8 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 			"1:	ll	%1, %2	# arch_read_unlock	\n"
 			"	sub	%1, 1				\n"
 			"	sc	%1, %0				\n"
-			: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-			: GCC_OFF12_ASM() (rw->lock)
+			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+			: GCC_OFF_SMALL_ASM() (rw->lock)
 			: "memory");
 		} while (unlikely(!tmp));
 	}
@@ -299,8 +299,8 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 		"	beqzl	%1, 1b					\n"
 		"	 nop						\n"
 		"	.set	reorder					\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		do {
@@ -309,8 +309,8 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 			"	bnez	%1, 1b				\n"
 			"	 lui	%1, 0x8000			\n"
 			"2:	sc	%1, %0				\n"
-			: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-			: GCC_OFF12_ASM() (rw->lock)
+			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+			: GCC_OFF_SMALL_ASM() (rw->lock)
 			: "memory");
 		} while (unlikely(!tmp));
 	}
@@ -349,8 +349,8 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 		__WEAK_LLSC_MB
 		"	li	%2, 1					\n"
 		"2:							\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		__asm__ __volatile__(
@@ -366,8 +366,8 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 		__WEAK_LLSC_MB
 		"	li	%2, 1					\n"
 		"2:							\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	}
 
@@ -393,8 +393,8 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 		"	li	%2, 1					\n"
 		"	.set	reorder					\n"
 		"2:							\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		do {
@@ -406,9 +406,9 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 			"	sc	%1, %0				\n"
 			"	li	%2, 1				\n"
 			"2:						\n"
-			: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp),
+			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp),
 			  "=&r" (ret)
-			: GCC_OFF12_ASM() (rw->lock)
+			: GCC_OFF_SMALL_ASM() (rw->lock)
 			: "memory");
 		} while (unlikely(!tmp));
 
-- 
cgit v1.2.3


From 123e4b3bbc0afd3cb596ecbe165533b368529a8e Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Fri, 19 Dec 2014 12:04:46 +0000
Subject: MIPS: Use the new "ZC" constraint for MIPS R6

GCC versions supporting MIPS R6 use the ZC constraint to enforce a
9-bit offset for MIPS R6. We will use that for all MIPS R6 LL/SC
instructions.

Cc: Matthew Fortune <Matthew.Fortune@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/compiler.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/compiler.h b/arch/mips/include/asm/compiler.h
index 34ad65a7801f..e081a265f422 100644
--- a/arch/mips/include/asm/compiler.h
+++ b/arch/mips/include/asm/compiler.h
@@ -16,13 +16,18 @@
 #define GCC_REG_ACCUM "accum"
 #endif
 
+#ifdef CONFIG_CPU_MIPSR6
+/* All MIPS R6 toolchains support the ZC constrain */
+#define GCC_OFF_SMALL_ASM() "ZC"
+#else
 #ifndef CONFIG_CPU_MICROMIPS
 #define GCC_OFF_SMALL_ASM() "R"
 #elif __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 9)
 #define GCC_OFF_SMALL_ASM() "ZC"
 #else
 #error "microMIPS compilation unsupported with GCC older than 4.9"
-#endif
+#endif /* CONFIG_CPU_MICROMIPS */
+#endif /* CONFIG_CPU_MIPSR6 */
 
 #ifdef CONFIG_CPU_MIPSR6
 #define MIPS_ISA_LEVEL "mips64r6"
-- 
cgit v1.2.3


From fa998ebbc02d11aa33a621e6f41cb15ce87e6b9e Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 20 Nov 2014 13:31:48 +0000
Subject: MIPS: asm: cmpxchg: Update ISA constraints for MIPS R6 support

MIPS R6 changed the opcodes for LL/SC instructions so we need to set
the correct ISA.

Cc: Matthew Fortune <Matthew.Fortune@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/cmpxchg.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 68baa0cf521a..d0a2a68ca600 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -39,11 +39,11 @@ static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	ll	%0, %3		# xchg_u32	\n"
 			"	.set	mips0				\n"
 			"	move	%2, %z4				\n"
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	sc	%2, %1				\n"
 			"	.set	mips0				\n"
 			: "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m),
@@ -90,7 +90,7 @@ static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val)
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	lld	%0, %3		# xchg_u64	\n"
 			"	move	%2, %z4				\n"
 			"	scd	%2, %1				\n"
@@ -165,12 +165,12 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\
-		"	.set	arch=r4000			\n"	\
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"1:	" ld "	%0, %2		# __cmpxchg_asm \n"	\
 		"	bne	%0, %z3, 2f			\n"	\
 		"	.set	mips0				\n"	\
 		"	move	$1, %z4				\n"	\
-		"	.set	arch=r4000			\n"	\
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"	" st "	$1, %1				\n"	\
 		"	beqz	$1, 1b				\n"	\
 		"	.set	pop				\n"	\
-- 
cgit v1.2.3


From 0038df2240ff01c666e5b55120ef9c3f15c281a4 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Tue, 6 Jan 2015 11:09:24 +0000
Subject: MIPS: asm: atomic: Update ISA constraints for MIPS R6 support

MIPS R6 changed the opcodes for LL/SC instructions so we need to
set the correct ISA level.

Cc: Matthew Fortune <Matthew.Fortune@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/atomic.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 3a44c2f17e53..26d436336f2e 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -61,7 +61,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 									      \
 		do {							      \
 			__asm__ __volatile__(				      \
-			"	.set	arch=r4000			\n"   \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
 			"	ll	%0, %1		# atomic_" #op "\n"   \
 			"	" #asm_op " %0, %2			\n"   \
 			"	sc	%0, %1				\n"   \
@@ -104,7 +104,7 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
 									      \
 		do {							      \
 			__asm__ __volatile__(				      \
-			"	.set	arch=r4000			\n"   \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
 			"	ll	%1, %2	# atomic_" #op "_return	\n"   \
 			"	" #asm_op " %0, %1, %3			\n"   \
 			"	sc	%0, %2				\n"   \
@@ -178,7 +178,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		int temp;
 
 		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
 		"	subu	%0, %1, %3				\n"
 		"	bltz	%0, 1f					\n"
@@ -340,7 +340,7 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 									      \
 		do {							      \
 			__asm__ __volatile__(				      \
-			"	.set	arch=r4000			\n"   \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
 			"	lld	%0, %1		# atomic64_" #op "\n" \
 			"	" #asm_op " %0, %2			\n"   \
 			"	scd	%0, %1				\n"   \
@@ -383,7 +383,7 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
 									      \
 		do {							      \
 			__asm__ __volatile__(				      \
-			"	.set	arch=r4000			\n"   \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
 			"	lld	%1, %2	# atomic64_" #op "_return\n"  \
 			"	" #asm_op " %0, %1, %3			\n"   \
 			"	scd	%0, %2				\n"   \
@@ -459,7 +459,7 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		long temp;
 
 		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
 		"	dsubu	%0, %1, %3				\n"
 		"	bltz	%0, 1f					\n"
-- 
cgit v1.2.3


From 87a927eff4da65c119c9b693df9234b4ad0c403f Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 20 Nov 2014 13:58:30 +0000
Subject: MIPS: asm: bitops: Update ISA constraints for MIPS R6 support

MIPS R6 changed the opcodes for LL/SC instructions so we need to set
the correct ISA level.

Cc: Matthew Fortune <Matthew.Fortune@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/bitops.h | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index 6cc1f539c79a..9f935f6aa996 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -81,7 +81,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 		"	.set	mips0					\n"
 		: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*m)
 		: "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m));
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
 		do {
 			__asm__ __volatile__(
@@ -91,11 +91,11 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (bit), "r" (~0));
 		} while (unlikely(!temp));
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1		# set_bit	\n"
 			"	or	%0, %2				\n"
 			"	" __SC	"%0, %1				\n"
@@ -133,7 +133,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 		"	.set	mips0					\n"
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 		: "ir" (~(1UL << bit)));
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
 		do {
 			__asm__ __volatile__(
@@ -143,11 +143,11 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (bit));
 		} while (unlikely(!temp));
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1		# clear_bit	\n"
 			"	and	%0, %2				\n"
 			"	" __SC "%0, %1				\n"
@@ -205,7 +205,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1		# change_bit	\n"
 			"	xor	%0, %2				\n"
 			"	" __SC	"%0, %1				\n"
@@ -254,7 +254,7 @@ static inline int test_and_set_bit(unsigned long nr,
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1	# test_and_set_bit	\n"
 			"	or	%2, %0, %3			\n"
 			"	" __SC	"%2, %1				\n"
@@ -308,7 +308,7 @@ static inline int test_and_set_bit_lock(unsigned long nr,
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1	# test_and_set_bit	\n"
 			"	or	%2, %0, %3			\n"
 			"	" __SC	"%2, %1				\n"
@@ -358,7 +358,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
 		: "memory");
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(nr)) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
@@ -380,7 +380,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL	"%0, %1 # test_and_clear_bit	\n"
 			"	or	%2, %0, %3			\n"
 			"	xor	%2, %3				\n"
@@ -437,7 +437,7 @@ static inline int test_and_change_bit(unsigned long nr,
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL	"%0, %1 # test_and_change_bit	\n"
 			"	xor	%2, %0, %3			\n"
 			"	" __SC	"\t%2, %1			\n"
@@ -485,7 +485,7 @@ static inline unsigned long __fls(unsigned long word)
 	    __builtin_constant_p(cpu_has_clo_clz) && cpu_has_clo_clz) {
 		__asm__(
 		"	.set	push					\n"
-		"	.set	mips32					\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"	clz	%0, %1					\n"
 		"	.set	pop					\n"
 		: "=r" (num)
@@ -498,7 +498,7 @@ static inline unsigned long __fls(unsigned long word)
 	    __builtin_constant_p(cpu_has_mips64) && cpu_has_mips64) {
 		__asm__(
 		"	.set	push					\n"
-		"	.set	mips64					\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"	dclz	%0, %1					\n"
 		"	.set	pop					\n"
 		: "=r" (num)
@@ -562,7 +562,7 @@ static inline int fls(int x)
 	if (__builtin_constant_p(cpu_has_clo_clz) && cpu_has_clo_clz) {
 		__asm__(
 		"	.set	push					\n"
-		"	.set	mips32					\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"	clz	%0, %1					\n"
 		"	.set	pop					\n"
 		: "=r" (x)
-- 
cgit v1.2.3


From 1922c356ab2d0031d1acc2979043da4a1105dc4a Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Wed, 19 Nov 2014 11:09:55 +0000
Subject: MIPS: asm: futex: Set the appropriate ISA level for MIPS R6

MIPS R6 changed the opcodes for LL/SC instructions so we need to set
the appropriate ISA level.

Cc: Matthew Fortune <Matthew.Fortune@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/futex.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index f666c0608c11..1de190bdfb9c 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -53,11 +53,11 @@
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\
-		"	.set	arch=r4000			\n"	\
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"1:	"user_ll("%1", "%4")" # __futex_atomic_op\n"	\
 		"	.set	mips0				\n"	\
 		"	" insn	"				\n"	\
-		"	.set	arch=r4000			\n"	\
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"2:	"user_sc("$1", "%2")"			\n"	\
 		"	beqz	$1, 1b				\n"	\
 		__WEAK_LLSC_MB						\
@@ -183,12 +183,12 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		"# futex_atomic_cmpxchg_inatomic			\n"
 		"	.set	push					\n"
 		"	.set	noat					\n"
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"1:	"user_ll("%1", "%3")"				\n"
 		"	bne	%1, %z4, 3f				\n"
 		"	.set	mips0					\n"
 		"	move	$1, %z5					\n"
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"2:	"user_sc("$1", "%2")"				\n"
 		"	beqz	$1, 1b					\n"
 		__WEAK_LLSC_MB
-- 
cgit v1.2.3


From 5753762cbd1cb208f6e6c916169b56139373b790 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Mon, 24 Nov 2014 14:11:39 +0000
Subject: MIPS: asm: spinlock: Replace "sub" instruction with "addiu"

"sub $reg, imm" is not a real MIPS instruction. The assembler can
replace that with "addi $reg, -imm". However, addi has been removed
from R6, so we replace the "sub" instruction with the "addiu" one.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/spinlock.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index b5238404c059..b4548690ade9 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -254,9 +254,6 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 	smp_llsc_mb();
 }
 
-/* Note the use of sub, not subu which will make the kernel die with an
-   overflow exception if we ever try to unlock an rwlock that is already
-   unlocked or is being held by a writer.  */
 static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
 	unsigned int tmp;
@@ -266,7 +263,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 	if (R10000_LLSC_WAR) {
 		__asm__ __volatile__(
 		"1:	ll	%1, %2		# arch_read_unlock	\n"
-		"	sub	%1, 1					\n"
+		"	addiu	%1, 1					\n"
 		"	sc	%1, %0					\n"
 		"	beqzl	%1, 1b					\n"
 		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
@@ -276,7 +273,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 		do {
 			__asm__ __volatile__(
 			"1:	ll	%1, %2	# arch_read_unlock	\n"
-			"	sub	%1, 1				\n"
+			"	addiu	%1, -1				\n"
 			"	sc	%1, %0				\n"
 			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
 			: GCC_OFF_SMALL_ASM() (rw->lock)
-- 
cgit v1.2.3


From 82e7ce814960c70eb8480c05d5ddb0f5575e8a64 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 15 Jan 2015 10:31:36 +0000
Subject: MIPS: asm: local: Set the appropriate ISA level for MIPS R6

MIPS R6 changed the opcodes for LL/SC instructions so we need to set
the appropriate ISA level.

Cc: Matthew Fortune <Matthew.Fortune@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/local.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/local.h b/arch/mips/include/asm/local.h
index 46dfc3c1fd49..8feaed62a2ab 100644
--- a/arch/mips/include/asm/local.h
+++ b/arch/mips/include/asm/local.h
@@ -5,6 +5,7 @@
 #include <linux/bitops.h>
 #include <linux/atomic.h>
 #include <asm/cmpxchg.h>
+#include <asm/compiler.h>
 #include <asm/war.h>
 
 typedef struct
@@ -47,7 +48,7 @@ static __inline__ long local_add_return(long i, local_t * l)
 		unsigned long temp;
 
 		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"1:"	__LL	"%1, %2		# local_add_return	\n"
 		"	addu	%0, %1, %3				\n"
 			__SC	"%0, %2					\n"
@@ -92,7 +93,7 @@ static __inline__ long local_sub_return(long i, local_t * l)
 		unsigned long temp;
 
 		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"1:"	__LL	"%1, %2		# local_sub_return	\n"
 		"	subu	%0, %1, %3				\n"
 			__SC	"%0, %2					\n"
-- 
cgit v1.2.3


From 515a6393dbac4f4492237c7b305bbf9c4c558a1c Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Fri, 14 Nov 2014 10:10:02 +0000
Subject: MIPS: kernel: proc: Add MIPS R6 support to /proc/cpuinfo

Print 'mips64r6' and/or 'mips32r6' if the kernel is running on
a MIPS R6 core.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/cpu-features.h | 3 +++
 arch/mips/kernel/proc.c              | 8 +++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 799dc6db7847..08d1bbe905eb 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -171,6 +171,9 @@
 #endif
 #endif
 
+#ifndef cpu_has_mips_1
+# define cpu_has_mips_1		(!cpu_has_mips_r6)
+#endif
 #ifndef cpu_has_mips_2
 # define cpu_has_mips_2		(cpu_data[0].isa_level & MIPS_CPU_ISA_II)
 #endif
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 097fc8d14e42..130af7d26a9c 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -82,7 +82,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "]\n");
 	}
 
-	seq_printf(m, "isa\t\t\t: mips1");
+	seq_printf(m, "isa\t\t\t:"); 
+	if (cpu_has_mips_r1)
+		seq_printf(m, " mips1");
 	if (cpu_has_mips_2)
 		seq_printf(m, "%s", " mips2");
 	if (cpu_has_mips_3)
@@ -95,10 +97,14 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "%s", " mips32r1");
 	if (cpu_has_mips32r2)
 		seq_printf(m, "%s", " mips32r2");
+	if (cpu_has_mips32r6)
+		seq_printf(m, "%s", " mips32r6");
 	if (cpu_has_mips64r1)
 		seq_printf(m, "%s", " mips64r1");
 	if (cpu_has_mips64r2)
 		seq_printf(m, "%s", " mips64r2");
+	if (cpu_has_mips64r6)
+		seq_printf(m, "%s", " mips64r6");
 	seq_printf(m, "\n");
 
 	seq_printf(m, "ASEs implemented\t:");
-- 
cgit v1.2.3


From 207083b1da59242cbbcd1752eea359ed4760914b Mon Sep 17 00:00:00 2001
From: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Date: Mon, 24 Nov 2014 11:54:19 +0000
Subject: MIPS: kernel: r4k_switch: Add support for MIPS R6

Add the MIPS R6 related preprocessor definitions for save/restore
FPU related functions. We also set the appropriate ISA level
so the final return instruction "jr ra" will produce the correct
opcode on R6.

Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/asmmacro.h | 12 +++++++-----
 arch/mips/kernel/r4k_switch.S    | 14 ++++++++------
 2 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 0af29ce84e0b..0cae4595e985 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -104,7 +104,8 @@
 	.endm
 
 	.macro	fpu_save_double thread status tmp
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	sll	\tmp, \status, 5
 	bgez	\tmp, 10f
 	fpu_save_16odd \thread
@@ -160,7 +161,8 @@
 	.endm
 
 	.macro	fpu_restore_double thread status tmp
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	sll	\tmp, \status, 5
 	bgez	\tmp, 10f				# 16 register mode?
 
@@ -170,16 +172,16 @@
 	fpu_restore_16even \thread \tmp
 	.endm
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	.macro	_EXT	rd, rs, p, s
 	ext	\rd, \rs, \p, \s
 	.endm
-#else /* !CONFIG_CPU_MIPSR2 */
+#else /* !CONFIG_CPU_MIPSR2 || !CONFIG_CPU_MIPSR6 */
 	.macro	_EXT	rd, rs, p, s
 	srl	\rd, \rs, \p
 	andi	\rd, \rd, (1 << \s) - 1
 	.endm
-#endif /* !CONFIG_CPU_MIPSR2 */
+#endif /* !CONFIG_CPU_MIPSR2 || !CONFIG_CPU_MIPSR6 */
 
 /*
  * Temporary until all gas have MT ASE support
diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S
index 64591e671878..3b1a36f13a7d 100644
--- a/arch/mips/kernel/r4k_switch.S
+++ b/arch/mips/kernel/r4k_switch.S
@@ -115,7 +115,8 @@
  * Save a thread's fp context.
  */
 LEAF(_save_fp)
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	mfc0	t0, CP0_STATUS
 #endif
 	fpu_save_double a0 t0 t1		# clobbers t1
@@ -126,7 +127,8 @@ LEAF(_save_fp)
  * Restore a thread's fp context.
  */
 LEAF(_restore_fp)
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	mfc0	t0, CP0_STATUS
 #endif
 	fpu_restore_double a0 t0 t1		# clobbers t1
@@ -240,9 +242,9 @@ LEAF(_init_fpu)
 	mtc1	t1, $f30
 	mtc1	t1, $f31
 
-#ifdef CONFIG_CPU_MIPS32_R2
+#if defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS32_R6)
 	.set    push
-	.set    mips32r2
+	.set    MIPS_ISA_LEVEL_RAW
 	.set	fp=64
 	sll     t0, t0, 5			# is Status.FR set?
 	bgez    t0, 1f				# no: skip setting upper 32b
@@ -280,9 +282,9 @@ LEAF(_init_fpu)
 	mthc1   t1, $f30
 	mthc1   t1, $f31
 1:	.set    pop
-#endif /* CONFIG_CPU_MIPS32_R2 */
+#endif /* CONFIG_CPU_MIPS32_R2 || CONFIG_CPU_MIPS32_R6 */
 #else
-	.set	arch=r4000
+	.set	MIPS_ISA_ARCH_LEVEL_RAW
 	dmtc1	t1, $f0
 	dmtc1	t1, $f2
 	dmtc1	t1, $f4
-- 
cgit v1.2.3


From 5f9f41c474befb4ebbc40b27f65bb7d649241581 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Tue, 25 Nov 2014 15:54:14 +0000
Subject: MIPS: kernel: Prepare the JR instruction for emulation on MIPS R6

The MIPS R6 JR instruction is an alias to the JALR one, so it may
need emulation for non-R6 userlands.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/branch.h |  3 +++
 arch/mips/kernel/branch.c      | 11 +++++++++--
 arch/mips/math-emu/cp1emu.c    |  3 +++
 3 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h
index de781cf54bc7..2894ea58454d 100644
--- a/arch/mips/include/asm/branch.h
+++ b/arch/mips/include/asm/branch.h
@@ -13,6 +13,9 @@
 #include <asm/ptrace.h>
 #include <asm/inst.h>
 
+static int mipsr2_emulation = 0;
+#define NO_R6EMU	(cpu_has_mips_r6 && !mipsr2_emulation)
+
 extern int __isa_exception_epc(struct pt_regs *regs);
 extern int __compute_return_epc(struct pt_regs *regs);
 extern int __compute_return_epc_for_insn(struct pt_regs *regs,
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 4d7d99d601cc..5736949896d1 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -417,6 +417,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 			regs->regs[insn.r_format.rd] = epc + 8;
 			/* Fall through */
 		case jr_op:
+			if (NO_R6EMU && insn.r_format.func == jr_op)
+				goto sigill_r6;
 			regs->cp0_epc = regs->regs[insn.r_format.rs];
 			break;
 		}
@@ -477,7 +479,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 
 		case bposge32_op:
 			if (!cpu_has_dsp)
-				goto sigill;
+				goto sigill_dsp;
 
 			dspcontrol = rddsp(0x01);
 
@@ -631,10 +633,15 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 
 	return ret;
 
-sigill:
+sigill_dsp:
 	printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm);
 	force_sig(SIGBUS, current);
 	return -EFAULT;
+sigill_r6:
+	pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n",
+		current->comm);
+	force_sig(SIGILL, current);
+	return -EFAULT;
 }
 EXPORT_SYMBOL_GPL(__compute_return_epc_for_insn);
 
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 9dfcd7fc1bc3..9bf82117b4f2 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -448,6 +448,9 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.next_pc_inc;
 			/* Fall through */
 		case jr_op:
+			/* For R6, JR already emulated in jalr_op */
+			if (NO_R6EMU && insn.r_format.opcode == jr_op)
+				break;
 			*contpc = regs->regs[insn.r_format.rs];
 			return 1;
 		}
-- 
cgit v1.2.3


From 5aed9da128be27275b0892fb413f3a0af64e00a6 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Tue, 2 Dec 2014 09:46:19 +0000
Subject: MIPS: Add LLB bit and related feature for the Config 5 CP0 register

The LLBIT (bit 4) in the Config5 CP0 register indicates the software
availability of the Load-Linked bit. This bit is only set by hardware
and it has the following meaning:

0: LLB functionality is not supported
1: LLB functionality is supported. The following feature are also
supported:

- ERETNC instruction. Similar to ERET but it does not clear the LLB
bit in the LLAddr register.
- CP0 LLAddr/LLB bit must be set
- LLbit is software accessible through the LLAddr[0]

This will be used later on to emulate R2 LL/SC instructions.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/cpu-features.h | 3 +++
 arch/mips/include/asm/cpu.h          | 1 +
 arch/mips/include/asm/mipsregs.h     | 1 +
 arch/mips/kernel/cpu-probe.c         | 2 ++
 4 files changed, 7 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 08d1bbe905eb..e686131ff995 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -38,6 +38,9 @@
 #ifndef cpu_has_maar
 #define cpu_has_maar		(cpu_data[0].options & MIPS_CPU_MAAR)
 #endif
+#ifndef cpu_has_rw_llb
+#define cpu_has_rw_llb		(cpu_data[0].options & MIPS_CPU_RW_LLB)
+#endif
 
 /*
  * For the moment we don't consider R6000 and R8000 so we can assume that
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index f604523aec3d..15687234d70a 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -376,6 +376,7 @@ enum cpu_type_enum {
 #define MIPS_CPU_RIXIEX		0x200000000ull /* CPU has unique exception codes for {Read, Execute}-Inhibit exceptions */
 #define MIPS_CPU_MAAR		0x400000000ull /* MAAR(I) registers are present */
 #define MIPS_CPU_FRE		0x800000000ull /* FRE & UFE bits implemented */
+#define MIPS_CPU_RW_LLB		0x1000000000ull /* LLADDR/LLB writes are allowed */
 
 /*
  * CPU ASE encodings
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 5e4aef304b02..093cd70e56ec 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -653,6 +653,7 @@
 #define MIPS_CONF5_NF		(_ULCAST_(1) << 0)
 #define MIPS_CONF5_UFR		(_ULCAST_(1) << 2)
 #define MIPS_CONF5_MRP		(_ULCAST_(1) << 3)
+#define MIPS_CONF5_LLB		(_ULCAST_(1) << 4)
 #define MIPS_CONF5_MVH		(_ULCAST_(1) << 5)
 #define MIPS_CONF5_FRE		(_ULCAST_(1) << 8)
 #define MIPS_CONF5_UFE		(_ULCAST_(1) << 9)
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 1b9488a17f88..81f0aedbba0f 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -514,6 +514,8 @@ static inline unsigned int decode_config5(struct cpuinfo_mips *c)
 		c->options |= MIPS_CPU_EVA;
 	if (config5 & MIPS_CONF5_MRP)
 		c->options |= MIPS_CPU_MAAR;
+	if (config5 & MIPS_CONF5_LLB)
+		c->options |= MIPS_CPU_RW_LLB;
 
 	return config5 & MIPS_CONF_M;
 }
-- 
cgit v1.2.3


From b55b9e271544a23ca23b7ca3a87baf6329fcb341 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Wed, 3 Dec 2014 12:31:42 +0000
Subject: MIPS: asm: mipsregs: Add support for the LLADDR register

If Config5/LLB is set in the core, then software can write the LLB
bit in the LLADDR register.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/mipsregs.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 093cd70e56ec..06346001ee4d 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1128,6 +1128,8 @@ do {									\
 #define write_c0_config6(val)	__write_32bit_c0_register($16, 6, val)
 #define write_c0_config7(val)	__write_32bit_c0_register($16, 7, val)
 
+#define read_c0_lladdr()	__read_ulong_c0_register($17, 0)
+#define write_c0_lladdr(val)	__write_ulong_c0_register($17, 0, val)
 #define read_c0_maar()		__read_ulong_c0_register($17, 1)
 #define write_c0_maar(val)	__write_ulong_c0_register($17, 1, val)
 #define read_c0_maari()		__read_32bit_c0_register($17, 2)
-- 
cgit v1.2.3


From b0a668fb2038d846a466c7a16a358d874002b697 Mon Sep 17 00:00:00 2001
From: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Date: Wed, 3 Dec 2014 15:47:03 +0000
Subject: MIPS: kernel: mips-r2-to-r6-emul: Add R2 emulator for MIPS R6

MIPS R6 removed quite a few R2 instructions. However, there
is plenty of <R6 userland code so we add an in-kernel emulator
so we can still be able to execute all R2 userland out there.

The emulator comes with a handy debugfs under /mips/ directory
(r2-emul-stats) to provide some basic statistics of the
instructions that are being emulated.

Below are some statistics from booting a minimal buildroot image:

Instruction     Total   BDslot
------------------------------
movs            236969  0
hilo            56686   0
muls            55279   0
divs            10941   0
dsps            0       0
bops            1       0
traps           0       0
fpus            0       0
loads           214981  17
stores          103364  0
llsc            56898   0
dsemul          150418  0
jr              370158
bltzl           43
bgezl           1594
bltzll          0
bgezll          0
bltzal          39
bgezal          39
beql            14503
bnel            138741
blezl           0
bgtzl           3988

Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/Kconfig                          |   13 +
 arch/mips/include/asm/branch.h             |    3 -
 arch/mips/include/asm/mips-r2-to-r6-emul.h |   96 ++
 arch/mips/kernel/Makefile                  |    1 +
 arch/mips/kernel/branch.c                  |    1 +
 arch/mips/kernel/mips-r2-to-r6-emul.c      | 2378 ++++++++++++++++++++++++++++
 arch/mips/kernel/traps.c                   |   28 +-
 arch/mips/math-emu/cp1emu.c                |    3 +-
 8 files changed, 2518 insertions(+), 5 deletions(-)
 create mode 100644 arch/mips/include/asm/mips-r2-to-r6-emul.h
 create mode 100644 arch/mips/kernel/mips-r2-to-r6-emul.c

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 883eb3aacedf..afa808ab9f44 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2063,6 +2063,19 @@ config MIPS_MT_FPAFF
 	default y
 	depends on MIPS_MT_SMP
 
+config MIPSR2_TO_R6_EMULATOR
+	bool "MIPS R2-to-R6 emulator"
+	depends on CPU_MIPSR6 && !SMP
+	default y
+	help
+	  Choose this option if you want to run non-R6 MIPS userland code.
+	  Even if you say 'Y' here, the emulator will still be disabled by
+	  default. You can enable it using the 'mipsr2emul' kernel option.
+	  The only reason this is a build-time option is to save ~14K from the
+	  final kernel image.
+comment "MIPS R2-to-R6 emulator is only available for UP kernels"
+	depends on SMP && CPU_MIPSR6
+
 config MIPS_VPE_LOADER
 	bool "VPE loader support."
 	depends on SYS_SUPPORTS_MULTITHREADING && MODULES
diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h
index 2894ea58454d..de781cf54bc7 100644
--- a/arch/mips/include/asm/branch.h
+++ b/arch/mips/include/asm/branch.h
@@ -13,9 +13,6 @@
 #include <asm/ptrace.h>
 #include <asm/inst.h>
 
-static int mipsr2_emulation = 0;
-#define NO_R6EMU	(cpu_has_mips_r6 && !mipsr2_emulation)
-
 extern int __isa_exception_epc(struct pt_regs *regs);
 extern int __compute_return_epc(struct pt_regs *regs);
 extern int __compute_return_epc_for_insn(struct pt_regs *regs,
diff --git a/arch/mips/include/asm/mips-r2-to-r6-emul.h b/arch/mips/include/asm/mips-r2-to-r6-emul.h
new file mode 100644
index 000000000000..60570f2c3ba2
--- /dev/null
+++ b/arch/mips/include/asm/mips-r2-to-r6-emul.h
@@ -0,0 +1,96 @@
+/*
+ * 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) 2014 Imagination Technologies Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ */
+
+#ifndef __ASM_MIPS_R2_TO_R6_EMUL_H
+#define __ASM_MIPS_R2_TO_R6_EMUL_H
+
+struct mips_r2_emulator_stats {
+	u64 movs;
+	u64 hilo;
+	u64 muls;
+	u64 divs;
+	u64 dsps;
+	u64 bops;
+	u64 traps;
+	u64 fpus;
+	u64 loads;
+	u64 stores;
+	u64 llsc;
+	u64 dsemul;
+};
+
+struct mips_r2br_emulator_stats {
+	u64 jrs;
+	u64 bltzl;
+	u64 bgezl;
+	u64 bltzll;
+	u64 bgezll;
+	u64 bltzall;
+	u64 bgezall;
+	u64 bltzal;
+	u64 bgezal;
+	u64 beql;
+	u64 bnel;
+	u64 blezl;
+	u64 bgtzl;
+};
+
+#ifdef CONFIG_DEBUG_FS
+
+#define MIPS_R2_STATS(M)						\
+do {									\
+	u32 nir;							\
+	int err;							\
+									\
+	preempt_disable();						\
+	__this_cpu_inc(mipsr2emustats.M);				\
+	err = __get_user(nir, (u32 __user *)regs->cp0_epc);		\
+	if (!err) {							\
+		if (nir == BREAK_MATH)					\
+			__this_cpu_inc(mipsr2bdemustats.M);		\
+	}								\
+	preempt_enable();						\
+} while (0)
+
+#define MIPS_R2BR_STATS(M)					\
+do {								\
+	preempt_disable();					\
+	__this_cpu_inc(mipsr2bremustats.M);			\
+	preempt_enable();					\
+} while (0)
+
+#else
+
+#define MIPS_R2_STATS(M)          do { } while (0)
+#define MIPS_R2BR_STATS(M)        do { } while (0)
+
+#endif /* CONFIG_DEBUG_FS */
+
+struct r2_decoder_table {
+	u32     mask;
+	u32     code;
+	int     (*func)(struct pt_regs *regs, u32 inst);
+};
+
+
+extern void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
+			  const char *str);
+
+#ifndef CONFIG_MIPSR2_TO_R6_EMULATOR
+static int mipsr2_emulation;
+static __maybe_unused int mipsr2_decoder(struct pt_regs *regs, u32 inst) { return 0; };
+#else
+/* MIPS R2 Emulator ON/OFF */
+extern int mipsr2_emulation;
+extern int mipsr2_decoder(struct pt_regs *regs, u32 inst);
+#endif /* CONFIG_MIPSR2_TO_R6_EMULATOR */
+
+#define NO_R6EMU	(cpu_has_mips_r6 && !mipsr2_emulation)
+
+#endif /* __ASM_MIPS_R2_TO_R6_EMUL_H */
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index de1e65366f02..d3d2ff2d76dc 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -90,6 +90,7 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_EARLY_PRINTK_8250)	+= early_printk_8250.o
 obj-$(CONFIG_SPINLOCK_TEST)	+= spinlock_test.o
 obj-$(CONFIG_MIPS_MACHINE)	+= mips_machine.o
+obj-$(CONFIG_MIPSR2_TO_R6_EMULATOR)	+= mips-r2-to-r6-emul.o
 
 CFLAGS_cpu-bugs64.o	= $(shell if $(CC) $(KBUILD_CFLAGS) -Wa,-mdaddi -c -o /dev/null -x c /dev/null >/dev/null 2>&1; then echo "-DHAVE_AS_SET_DADDI"; fi)
 
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 249c61c9acf1..c2e0f45ddf6c 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -16,6 +16,7 @@
 #include <asm/fpu.h>
 #include <asm/fpu_emulator.h>
 #include <asm/inst.h>
+#include <asm/mips-r2-to-r6-emul.h>
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
new file mode 100644
index 000000000000..64d17e41093b
--- /dev/null
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -0,0 +1,2378 @@
+/*
+ * 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) 2014 Imagination Technologies Ltd.
+ * Author: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *      MIPS R2 user space instruction emulator for MIPS R6
+ *
+ */
+#include <linux/bug.h>
+#include <linux/compiler.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/seq_file.h>
+
+#include <asm/asm.h>
+#include <asm/branch.h>
+#include <asm/break.h>
+#include <asm/fpu.h>
+#include <asm/fpu_emulator.h>
+#include <asm/inst.h>
+#include <asm/mips-r2-to-r6-emul.h>
+#include <asm/local.h>
+#include <asm/ptrace.h>
+#include <asm/uaccess.h>
+
+#ifdef CONFIG_64BIT
+#define ADDIU	"daddiu "
+#define INS	"dins "
+#define EXT	"dext "
+#else
+#define ADDIU	"addiu "
+#define INS	"ins "
+#define EXT	"ext "
+#endif /* CONFIG_64BIT */
+
+#define SB	"sb "
+#define LB	"lb "
+#define LL	"ll "
+#define SC	"sc "
+
+DEFINE_PER_CPU(struct mips_r2_emulator_stats, mipsr2emustats);
+DEFINE_PER_CPU(struct mips_r2_emulator_stats, mipsr2bdemustats);
+DEFINE_PER_CPU(struct mips_r2br_emulator_stats, mipsr2bremustats);
+
+extern const unsigned int fpucondbit[8];
+
+#define MIPS_R2_EMUL_TOTAL_PASS	10
+
+int mipsr2_emulation = 0;
+
+static int __init mipsr2emu_enable(char *s)
+{
+	mipsr2_emulation = 1;
+
+	pr_info("MIPS R2-to-R6 Emulator Enabled!");
+
+	return 1;
+}
+__setup("mipsr2emu", mipsr2emu_enable);
+
+/**
+ * mipsr6_emul - Emulate some frequent R2/R5/R6 instructions in delay slot
+ * for performance instead of the traditional way of using a stack trampoline
+ * which is rather slow.
+ * @regs: Process register set
+ * @ir: Instruction
+ */
+static inline int mipsr6_emul(struct pt_regs *regs, u32 ir)
+{
+	switch (MIPSInst_OPCODE(ir)) {
+	case addiu_op:
+		if (MIPSInst_RT(ir))
+			regs->regs[MIPSInst_RT(ir)] =
+				(s32)regs->regs[MIPSInst_RS(ir)] +
+				(s32)MIPSInst_SIMM(ir);
+		return 0;
+	case daddiu_op:
+		if (config_enabled(CONFIG_32BIT))
+			break;
+
+		if (MIPSInst_RT(ir))
+			regs->regs[MIPSInst_RT(ir)] =
+				(s64)regs->regs[MIPSInst_RS(ir)] +
+				(s64)MIPSInst_SIMM(ir);
+		return 0;
+	case lwc1_op:
+	case swc1_op:
+	case cop1_op:
+	case cop1x_op:
+		/* FPU instructions in delay slot */
+		return -SIGFPE;
+	case spec_op:
+		switch (MIPSInst_FUNC(ir)) {
+		case or_op:
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					regs->regs[MIPSInst_RS(ir)] |
+					regs->regs[MIPSInst_RT(ir)];
+			return 0;
+		case sll_op:
+			if (MIPSInst_RS(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s32)(((u32)regs->regs[MIPSInst_RT(ir)]) <<
+						MIPSInst_FD(ir));
+			return 0;
+		case srl_op:
+			if (MIPSInst_RS(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s32)(((u32)regs->regs[MIPSInst_RT(ir)]) >>
+						MIPSInst_FD(ir));
+			return 0;
+		case addu_op:
+			if (MIPSInst_FD(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s32)((u32)regs->regs[MIPSInst_RS(ir)] +
+					      (u32)regs->regs[MIPSInst_RT(ir)]);
+			return 0;
+		case subu_op:
+			if (MIPSInst_FD(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s32)((u32)regs->regs[MIPSInst_RS(ir)] -
+					      (u32)regs->regs[MIPSInst_RT(ir)]);
+			return 0;
+		case dsll_op:
+			if (config_enabled(CONFIG_32BIT) || MIPSInst_RS(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s64)(((u64)regs->regs[MIPSInst_RT(ir)]) <<
+						MIPSInst_FD(ir));
+			return 0;
+		case dsrl_op:
+			if (config_enabled(CONFIG_32BIT) || MIPSInst_RS(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s64)(((u64)regs->regs[MIPSInst_RT(ir)]) >>
+						MIPSInst_FD(ir));
+			return 0;
+		case daddu_op:
+			if (config_enabled(CONFIG_32BIT) || MIPSInst_FD(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(u64)regs->regs[MIPSInst_RS(ir)] +
+					(u64)regs->regs[MIPSInst_RT(ir)];
+			return 0;
+		case dsubu_op:
+			if (config_enabled(CONFIG_32BIT) || MIPSInst_FD(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s64)((u64)regs->regs[MIPSInst_RS(ir)] -
+					      (u64)regs->regs[MIPSInst_RT(ir)]);
+			return 0;
+		}
+		break;
+	default:
+		pr_debug("No fastpath BD emulation for instruction 0x%08x (op: %02x)\n",
+			 ir, MIPSInst_OPCODE(ir));
+	}
+
+	return SIGILL;
+}
+
+/**
+ * movt_func - Emulate a MOVT instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int movf_func(struct pt_regs *regs, u32 ir)
+{
+	u32 csr;
+	u32 cond;
+
+	csr = current->thread.fpu.fcr31;
+	cond = fpucondbit[MIPSInst_RT(ir) >> 2];
+	if (((csr & cond) == 0) && MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)];
+	MIPS_R2_STATS(movs);
+	return 0;
+}
+
+/**
+ * movt_func - Emulate a MOVT instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int movt_func(struct pt_regs *regs, u32 ir)
+{
+	u32 csr;
+	u32 cond;
+
+	csr = current->thread.fpu.fcr31;
+	cond = fpucondbit[MIPSInst_RT(ir) >> 2];
+
+	if (((csr & cond) != 0) && MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)];
+
+	MIPS_R2_STATS(movs);
+
+	return 0;
+}
+
+/**
+ * jr_func - Emulate a JR instruction.
+ * @pt_regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns SIGILL if JR was in delay slot, SIGEMT if we
+ * can't compute the EPC, SIGSEGV if we can't access the
+ * userland instruction or 0 on success.
+ */
+static int jr_func(struct pt_regs *regs, u32 ir)
+{
+	int err;
+	unsigned long cepc, epc, nepc;
+	u32 nir;
+
+	if (delay_slot(regs))
+		return SIGILL;
+
+	/* EPC after the RI/JR instruction */
+	nepc = regs->cp0_epc;
+	/* Roll back to the reserved R2 JR instruction */
+	regs->cp0_epc -= 4;
+	epc = regs->cp0_epc;
+	err = __compute_return_epc(regs);
+
+	if (err < 0)
+		return SIGEMT;
+
+
+	/* Computed EPC */
+	cepc = regs->cp0_epc;
+
+	/* Get DS instruction */
+	err = __get_user(nir, (u32 __user *)nepc);
+	if (err)
+		return SIGSEGV;
+
+	MIPS_R2BR_STATS(jrs);
+
+	/* If nir == 0(NOP), then nothing else to do */
+	if (nir) {
+		/*
+		 * Negative err means FPU instruction in BD-slot,
+		 * Zero err means 'BD-slot emulation done'
+		 * For anything else we go back to trampoline emulation.
+		 */
+		err = mipsr6_emul(regs, nir);
+		if (err > 0) {
+			regs->cp0_epc = nepc;
+			err = mips_dsemul(regs, nir, cepc);
+			if (err == SIGILL)
+				err = SIGEMT;
+			MIPS_R2_STATS(dsemul);
+		}
+	}
+
+	return err;
+}
+
+/**
+ * movz_func - Emulate a MOVZ instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int movz_func(struct pt_regs *regs, u32 ir)
+{
+	if (((regs->regs[MIPSInst_RT(ir)]) == 0) && MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)];
+	MIPS_R2_STATS(movs);
+
+	return 0;
+}
+
+/**
+ * movn_func - Emulate a MOVZ instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int movn_func(struct pt_regs *regs, u32 ir)
+{
+	if (((regs->regs[MIPSInst_RT(ir)]) != 0) && MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)];
+	MIPS_R2_STATS(movs);
+
+	return 0;
+}
+
+/**
+ * mfhi_func - Emulate a MFHI instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mfhi_func(struct pt_regs *regs, u32 ir)
+{
+	if (MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->hi;
+
+	MIPS_R2_STATS(hilo);
+
+	return 0;
+}
+
+/**
+ * mthi_func - Emulate a MTHI instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mthi_func(struct pt_regs *regs, u32 ir)
+{
+	regs->hi = regs->regs[MIPSInst_RS(ir)];
+
+	MIPS_R2_STATS(hilo);
+
+	return 0;
+}
+
+/**
+ * mflo_func - Emulate a MFLO instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mflo_func(struct pt_regs *regs, u32 ir)
+{
+	if (MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->lo;
+
+	MIPS_R2_STATS(hilo);
+
+	return 0;
+}
+
+/**
+ * mtlo_func - Emulate a MTLO instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mtlo_func(struct pt_regs *regs, u32 ir)
+{
+	regs->lo = regs->regs[MIPSInst_RS(ir)];
+
+	MIPS_R2_STATS(hilo);
+
+	return 0;
+}
+
+/**
+ * mult_func - Emulate a MULT instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mult_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (s64)rt * (s64)rs;
+
+	rs = res;
+	regs->lo = (s64)rs;
+	rt = res >> 32;
+	res = (s64)rt;
+	regs->hi = res;
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * multu_func - Emulate a MULTU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int multu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (u64)rt * (u64)rs;
+	rt = res;
+	regs->lo = (s64)rt;
+	regs->hi = (s64)(res >> 32);
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * div_func - Emulate a DIV instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int div_func(struct pt_regs *regs, u32 ir)
+{
+	s32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+
+	regs->lo = (s64)(rs / rt);
+	regs->hi = (s64)(rs % rt);
+
+	MIPS_R2_STATS(divs);
+
+	return 0;
+}
+
+/**
+ * divu_func - Emulate a DIVU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int divu_func(struct pt_regs *regs, u32 ir)
+{
+	u32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+
+	regs->lo = (s64)(rs / rt);
+	regs->hi = (s64)(rs % rt);
+
+	MIPS_R2_STATS(divs);
+
+	return 0;
+}
+
+/**
+ * dmult_func - Emulate a DMULT instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 on success or SIGILL for 32-bit kernels.
+ */
+static int dmult_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s64 rt, rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = rt * rs;
+
+	regs->lo = res;
+	__asm__ __volatile__(
+		"dmuh %0, %1, %2\t\n"
+		: "=r"(res)
+		: "r"(rt), "r"(rs));
+
+	regs->hi = res;
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * dmultu_func - Emulate a DMULTU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 on success or SIGILL for 32-bit kernels.
+ */
+static int dmultu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u64 rt, rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = rt * rs;
+
+	regs->lo = res;
+	__asm__ __volatile__(
+		"dmuhu %0, %1, %2\t\n"
+		: "=r"(res)
+		: "r"(rt), "r"(rs));
+
+	regs->hi = res;
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * ddiv_func - Emulate a DDIV instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 on success or SIGILL for 32-bit kernels.
+ */
+static int ddiv_func(struct pt_regs *regs, u32 ir)
+{
+	s64 rt, rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+
+	regs->lo = rs / rt;
+	regs->hi = rs % rt;
+
+	MIPS_R2_STATS(divs);
+
+	return 0;
+}
+
+/**
+ * ddivu_func - Emulate a DDIVU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 on success or SIGILL for 32-bit kernels.
+ */
+static int ddivu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 rt, rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+
+	regs->lo = rs / rt;
+	regs->hi = rs % rt;
+
+	MIPS_R2_STATS(divs);
+
+	return 0;
+}
+
+/* R6 removed instructions for the SPECIAL opcode */
+static struct r2_decoder_table spec_op_table[] = {
+	{ 0xfc1ff83f, 0x00000008, jr_func },
+	{ 0xfc00ffff, 0x00000018, mult_func },
+	{ 0xfc00ffff, 0x00000019, multu_func },
+	{ 0xfc00ffff, 0x0000001c, dmult_func },
+	{ 0xfc00ffff, 0x0000001d, dmultu_func },
+	{ 0xffff07ff, 0x00000010, mfhi_func },
+	{ 0xfc1fffff, 0x00000011, mthi_func },
+	{ 0xffff07ff, 0x00000012, mflo_func },
+	{ 0xfc1fffff, 0x00000013, mtlo_func },
+	{ 0xfc0307ff, 0x00000001, movf_func },
+	{ 0xfc0307ff, 0x00010001, movt_func },
+	{ 0xfc0007ff, 0x0000000a, movz_func },
+	{ 0xfc0007ff, 0x0000000b, movn_func },
+	{ 0xfc00ffff, 0x0000001a, div_func },
+	{ 0xfc00ffff, 0x0000001b, divu_func },
+	{ 0xfc00ffff, 0x0000001e, ddiv_func },
+	{ 0xfc00ffff, 0x0000001f, ddivu_func },
+	{}
+};
+
+/**
+ * madd_func - Emulate a MADD instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int madd_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (s64)rt * (s64)rs;
+	rt = regs->hi;
+	rs = regs->lo;
+	res += ((((s64)rt) << 32) | (u32)rs);
+
+	rt = res;
+	regs->lo = (s64)rt;
+	rs = res >> 32;
+	regs->hi = (s64)rs;
+
+	MIPS_R2_STATS(dsps);
+
+	return 0;
+}
+
+/**
+ * maddu_func - Emulate a MADDU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int maddu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (u64)rt * (u64)rs;
+	rt = regs->hi;
+	rs = regs->lo;
+	res += ((((s64)rt) << 32) | (u32)rs);
+
+	rt = res;
+	regs->lo = (s64)rt;
+	rs = res >> 32;
+	regs->hi = (s64)rs;
+
+	MIPS_R2_STATS(dsps);
+
+	return 0;
+}
+
+/**
+ * msub_func - Emulate a MSUB instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int msub_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (s64)rt * (s64)rs;
+	rt = regs->hi;
+	rs = regs->lo;
+	res = ((((s64)rt) << 32) | (u32)rs) - res;
+
+	rt = res;
+	regs->lo = (s64)rt;
+	rs = res >> 32;
+	regs->hi = (s64)rs;
+
+	MIPS_R2_STATS(dsps);
+
+	return 0;
+}
+
+/**
+ * msubu_func - Emulate a MSUBU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int msubu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (u64)rt * (u64)rs;
+	rt = regs->hi;
+	rs = regs->lo;
+	res = ((((s64)rt) << 32) | (u32)rs) - res;
+
+	rt = res;
+	regs->lo = (s64)rt;
+	rs = res >> 32;
+	regs->hi = (s64)rs;
+
+	MIPS_R2_STATS(dsps);
+
+	return 0;
+}
+
+/**
+ * mul_func - Emulate a MUL instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mul_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s32 rt, rs;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (s64)rt * (s64)rs;
+
+	rs = res;
+	regs->regs[MIPSInst_RD(ir)] = (s64)rs;
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * clz_func - Emulate a CLZ instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int clz_func(struct pt_regs *regs, u32 ir)
+{
+	u32 res;
+	u32 rs;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+
+	rs = regs->regs[MIPSInst_RS(ir)];
+	__asm__ __volatile__("clz %0, %1" : "=r"(res) : "r"(rs));
+	regs->regs[MIPSInst_RD(ir)] = res;
+
+	MIPS_R2_STATS(bops);
+
+	return 0;
+}
+
+/**
+ * clo_func - Emulate a CLO instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+
+static int clo_func(struct pt_regs *regs, u32 ir)
+{
+	u32 res;
+	u32 rs;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+
+	rs = regs->regs[MIPSInst_RS(ir)];
+	__asm__ __volatile__("clo %0, %1" : "=r"(res) : "r"(rs));
+	regs->regs[MIPSInst_RD(ir)] = res;
+
+	MIPS_R2_STATS(bops);
+
+	return 0;
+}
+
+/**
+ * dclz_func - Emulate a DCLZ instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int dclz_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u64 rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+
+	rs = regs->regs[MIPSInst_RS(ir)];
+	__asm__ __volatile__("dclz %0, %1" : "=r"(res) : "r"(rs));
+	regs->regs[MIPSInst_RD(ir)] = res;
+
+	MIPS_R2_STATS(bops);
+
+	return 0;
+}
+
+/**
+ * dclo_func - Emulate a DCLO instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int dclo_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u64 rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+
+	rs = regs->regs[MIPSInst_RS(ir)];
+	__asm__ __volatile__("dclo %0, %1" : "=r"(res) : "r"(rs));
+	regs->regs[MIPSInst_RD(ir)] = res;
+
+	MIPS_R2_STATS(bops);
+
+	return 0;
+}
+
+/* R6 removed instructions for the SPECIAL2 opcode */
+static struct r2_decoder_table spec2_op_table[] = {
+	{ 0xfc00ffff, 0x70000000, madd_func },
+	{ 0xfc00ffff, 0x70000001, maddu_func },
+	{ 0xfc0007ff, 0x70000002, mul_func },
+	{ 0xfc00ffff, 0x70000004, msub_func },
+	{ 0xfc00ffff, 0x70000005, msubu_func },
+	{ 0xfc0007ff, 0x70000020, clz_func },
+	{ 0xfc0007ff, 0x70000021, clo_func },
+	{ 0xfc0007ff, 0x70000024, dclz_func },
+	{ 0xfc0007ff, 0x70000025, dclo_func },
+	{ }
+};
+
+static inline int mipsr2_find_op_func(struct pt_regs *regs, u32 inst,
+				      struct r2_decoder_table *table)
+{
+	struct r2_decoder_table *p;
+	int err;
+
+	for (p = table; p->func; p++) {
+		if ((inst & p->mask) == p->code) {
+			err = (p->func)(regs, inst);
+			return err;
+		}
+	}
+	return SIGILL;
+}
+
+/**
+ * mipsr2_decoder: Decode and emulate a MIPS R2 instruction
+ * @regs: Process register set
+ * @inst: Instruction to decode and emulate
+ */
+int mipsr2_decoder(struct pt_regs *regs, u32 inst)
+{
+	int err = 0;
+	unsigned long vaddr;
+	u32 nir;
+	unsigned long cpc, epc, nepc, r31, res, rs, rt;
+
+	void __user *fault_addr = NULL;
+	int pass = 0;
+
+repeat:
+	r31 = regs->regs[31];
+	epc = regs->cp0_epc;
+	err = compute_return_epc(regs);
+	if (err < 0) {
+		BUG();
+		return SIGEMT;
+	}
+	pr_debug("Emulating the 0x%08x R2 instruction @ 0x%08lx (pass=%d))\n",
+		 inst, epc, pass);
+
+	switch (MIPSInst_OPCODE(inst)) {
+	case spec_op:
+		err = mipsr2_find_op_func(regs, inst, spec_op_table);
+		if (err < 0) {
+			/* FPU instruction under JR */
+			regs->cp0_cause |= CAUSEF_BD;
+			goto fpu_emul;
+		}
+		break;
+	case spec2_op:
+		err = mipsr2_find_op_func(regs, inst, spec2_op_table);
+		break;
+	case bcond_op:
+		rt = MIPSInst_RT(inst);
+		rs = MIPSInst_RS(inst);
+		switch (rt) {
+		case tgei_op:
+			if ((long)regs->regs[rs] >= MIPSInst_SIMM(inst))
+				do_trap_or_bp(regs, 0, "TGEI");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case tgeiu_op:
+			if (regs->regs[rs] >= MIPSInst_UIMM(inst))
+				do_trap_or_bp(regs, 0, "TGEIU");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case tlti_op:
+			if ((long)regs->regs[rs] < MIPSInst_SIMM(inst))
+				do_trap_or_bp(regs, 0, "TLTI");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case tltiu_op:
+			if (regs->regs[rs] < MIPSInst_UIMM(inst))
+				do_trap_or_bp(regs, 0, "TLTIU");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case teqi_op:
+			if (regs->regs[rs] == MIPSInst_SIMM(inst))
+				do_trap_or_bp(regs, 0, "TEQI");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case tnei_op:
+			if (regs->regs[rs] != MIPSInst_SIMM(inst))
+				do_trap_or_bp(regs, 0, "TNEI");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case bltzl_op:
+		case bgezl_op:
+		case bltzall_op:
+		case bgezall_op:
+			if (delay_slot(regs)) {
+				err = SIGILL;
+				break;
+			}
+			regs->regs[31] = r31;
+			regs->cp0_epc = epc;
+			err = __compute_return_epc(regs);
+			if (err < 0)
+				return SIGEMT;
+			if (err != BRANCH_LIKELY_TAKEN)
+				break;
+			cpc = regs->cp0_epc;
+			nepc = epc + 4;
+			err = __get_user(nir, (u32 __user *)nepc);
+			if (err) {
+				err = SIGSEGV;
+				break;
+			}
+			/*
+			 * This will probably be optimized away when
+			 * CONFIG_DEBUG_FS is not enabled
+			 */
+			switch (rt) {
+			case bltzl_op:
+				MIPS_R2BR_STATS(bltzl);
+				break;
+			case bgezl_op:
+				MIPS_R2BR_STATS(bgezl);
+				break;
+			case bltzall_op:
+				MIPS_R2BR_STATS(bltzall);
+				break;
+			case bgezall_op:
+				MIPS_R2BR_STATS(bgezall);
+				break;
+			}
+
+			switch (MIPSInst_OPCODE(nir)) {
+			case cop1_op:
+			case cop1x_op:
+			case lwc1_op:
+			case swc1_op:
+				regs->cp0_cause |= CAUSEF_BD;
+				goto fpu_emul;
+			}
+			if (nir) {
+				err = mipsr6_emul(regs, nir);
+				if (err > 0) {
+					err = mips_dsemul(regs, nir, cpc);
+					if (err == SIGILL)
+						err = SIGEMT;
+					MIPS_R2_STATS(dsemul);
+				}
+			}
+			break;
+		case bltzal_op:
+		case bgezal_op:
+			if (delay_slot(regs)) {
+				err = SIGILL;
+				break;
+			}
+			regs->regs[31] = r31;
+			regs->cp0_epc = epc;
+			err = __compute_return_epc(regs);
+			if (err < 0)
+				return SIGEMT;
+			cpc = regs->cp0_epc;
+			nepc = epc + 4;
+			err = __get_user(nir, (u32 __user *)nepc);
+			if (err) {
+				err = SIGSEGV;
+				break;
+			}
+			/*
+			 * This will probably be optimized away when
+			 * CONFIG_DEBUG_FS is not enabled
+			 */
+			switch (rt) {
+			case bltzal_op:
+				MIPS_R2BR_STATS(bltzal);
+				break;
+			case bgezal_op:
+				MIPS_R2BR_STATS(bgezal);
+				break;
+			}
+
+			switch (MIPSInst_OPCODE(nir)) {
+			case cop1_op:
+			case cop1x_op:
+			case lwc1_op:
+			case swc1_op:
+				regs->cp0_cause |= CAUSEF_BD;
+				goto fpu_emul;
+			}
+			if (nir) {
+				err = mipsr6_emul(regs, nir);
+				if (err > 0) {
+					err = mips_dsemul(regs, nir, cpc);
+					if (err == SIGILL)
+						err = SIGEMT;
+					MIPS_R2_STATS(dsemul);
+				}
+			}
+			break;
+		default:
+			regs->regs[31] = r31;
+			regs->cp0_epc = epc;
+			err = SIGILL;
+			break;
+		}
+		break;
+
+	case beql_op:
+	case bnel_op:
+	case blezl_op:
+	case bgtzl_op:
+		if (delay_slot(regs)) {
+			err = SIGILL;
+			break;
+		}
+		regs->regs[31] = r31;
+		regs->cp0_epc = epc;
+		err = __compute_return_epc(regs);
+		if (err < 0)
+			return SIGEMT;
+		if (err != BRANCH_LIKELY_TAKEN)
+			break;
+		cpc = regs->cp0_epc;
+		nepc = epc + 4;
+		err = __get_user(nir, (u32 __user *)nepc);
+		if (err) {
+			err = SIGSEGV;
+			break;
+		}
+		/*
+		 * This will probably be optimized away when
+		 * CONFIG_DEBUG_FS is not enabled
+		 */
+		switch (MIPSInst_OPCODE(inst)) {
+		case beql_op:
+			MIPS_R2BR_STATS(beql);
+			break;
+		case bnel_op:
+			MIPS_R2BR_STATS(bnel);
+			break;
+		case blezl_op:
+			MIPS_R2BR_STATS(blezl);
+			break;
+		case bgtzl_op:
+			MIPS_R2BR_STATS(bgtzl);
+			break;
+		}
+
+		switch (MIPSInst_OPCODE(nir)) {
+		case cop1_op:
+		case cop1x_op:
+		case lwc1_op:
+		case swc1_op:
+			regs->cp0_cause |= CAUSEF_BD;
+			goto fpu_emul;
+		}
+		if (nir) {
+			err = mipsr6_emul(regs, nir);
+			if (err > 0) {
+				err = mips_dsemul(regs, nir, cpc);
+				if (err == SIGILL)
+					err = SIGEMT;
+				MIPS_R2_STATS(dsemul);
+			}
+		}
+		break;
+	case lwc1_op:
+	case swc1_op:
+	case cop1_op:
+	case cop1x_op:
+fpu_emul:
+		regs->regs[31] = r31;
+		regs->cp0_epc = epc;
+		if (!used_math()) {     /* First time FPU user.  */
+			err = init_fpu();
+			set_used_math();
+		}
+		lose_fpu(1);    /* Save FPU state for the emulator. */
+
+		err = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 0,
+					       &fault_addr);
+
+		/*
+		 * this is a tricky issue - lose_fpu() uses LL/SC atomics
+		 * if FPU is owned and effectively cancels user level LL/SC.
+		 * So, it could be logical to don't restore FPU ownership here.
+		 * But the sequence of multiple FPU instructions is much much
+		 * more often than LL-FPU-SC and I prefer loop here until
+		 * next scheduler cycle cancels FPU ownership
+		 */
+		own_fpu(1);	/* Restore FPU state. */
+
+		if (err)
+			current->thread.cp0_baduaddr = (unsigned long)fault_addr;
+
+		MIPS_R2_STATS(fpus);
+
+		break;
+
+	case lwl_op:
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_READ, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set	push\n"
+			"	.set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"1:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 24, 8\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"2:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 16, 8\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"3:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 8, 8\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"4:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 0, 8\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"1:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 24, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+			"2:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 16, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+			"3:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 8, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+			"4:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 0, 8\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:	sll	%0, %0, 0\n"
+			"10:\n"
+			"	.insn\n"
+			"	.section	.fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	10b\n"
+			"	.previous\n"
+			"	.section	__ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV));
+
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = rt;
+
+		MIPS_R2_STATS(loads);
+
+		break;
+
+	case lwr_op:
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_READ, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"       .set	push\n"
+			"       .set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"1:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 0, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+			"2:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 8, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+			"3:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 16, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+			"4:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 24, 8\n"
+			"       sll	%0, %0, 0\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"1:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 0, 8\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"2:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 8, 8\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"3:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 16, 8\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"4:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 24, 8\n"
+			"       sll	%0, %0, 0\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"10:\n"
+			"	.insn\n"
+			"	.section	.fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	10b\n"
+			"       .previous\n"
+			"	.section	__ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV));
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = rt;
+
+		MIPS_R2_STATS(loads);
+
+		break;
+
+	case swl_op:
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set	push\n"
+			"	.set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+				EXT	"%1, %0, 24, 8\n"
+			"1:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 16, 8\n"
+			"2:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 8, 8\n"
+			"3:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 0, 8\n"
+			"4:"	SB	"%1, 0(%2)\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+				EXT	"%1, %0, 24, 8\n"
+			"1:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 16, 8\n"
+			"2:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 8, 8\n"
+			"3:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 0, 8\n"
+			"4:"	SB	"%1, 0(%2)\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"       .section        .fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV)
+			: "memory");
+
+		MIPS_R2_STATS(stores);
+
+		break;
+
+	case swr_op:
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set	push\n"
+			"	.set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+				EXT	"%1, %0, 0, 8\n"
+			"1:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 8, 8\n"
+			"2:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 16, 8\n"
+			"3:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 24, 8\n"
+			"4:"	SB	"%1, 0(%2)\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+				EXT	"%1, %0, 0, 8\n"
+			"1:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 8, 8\n"
+			"2:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 16, 8\n"
+			"3:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 24, 8\n"
+			"4:"	SB	"%1, 0(%2)\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"	.section        .fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV)
+			: "memory");
+
+		MIPS_R2_STATS(stores);
+
+		break;
+
+	case ldl_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_READ, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set    push\n"
+			"	.set    reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"1:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 56, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"2:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 48, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"3:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 40, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"4:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 32, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"5:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 24, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"6:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 16, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"7:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 8, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"0:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 0, 8\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"1:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 56, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"2:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 48, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"3:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 40, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"4:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 32, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"5:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 24, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"6:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 16, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"7:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 8, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"0:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 0, 8\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"	.section        .fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.word	5b,8b\n"
+			"	.word	6b,8b\n"
+			"	.word	7b,8b\n"
+			"	.word	0b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV));
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = rt;
+
+		MIPS_R2_STATS(loads);
+		break;
+
+	case ldr_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_READ, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set    push\n"
+			"	.set    reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"1:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 0, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"2:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 8, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"3:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 16, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"4:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 24, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"5:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 32, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"6:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 40, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"7:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 48, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"0:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 56, 8\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"1:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 0, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"2:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 8, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"3:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 16, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"4:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 24, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"5:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 32, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"6:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 40, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"7:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 48, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"0:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 56, 8\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"	.section        .fixup,\"ax\"\n"
+			"8:	li     %3,%4\n"
+			"	j      9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word  1b,8b\n"
+			"	.word  2b,8b\n"
+			"	.word  3b,8b\n"
+			"	.word  4b,8b\n"
+			"	.word  5b,8b\n"
+			"	.word  6b,8b\n"
+			"	.word  7b,8b\n"
+			"	.word  0b,8b\n"
+			"	.previous\n"
+			"	.set    pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV));
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = rt;
+
+		MIPS_R2_STATS(loads);
+		break;
+
+	case sdl_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set	push\n"
+			"	.set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"	dextu	%1, %0, 56, 8\n"
+			"1:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dextu	%1, %0, 48, 8\n"
+			"2:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dextu	%1, %0, 40, 8\n"
+			"3:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dextu	%1, %0, 32, 8\n"
+			"4:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dext	%1, %0, 24, 8\n"
+			"5:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dext	%1, %0, 16, 8\n"
+			"6:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dext	%1, %0, 8, 8\n"
+			"7:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dext	%1, %0, 0, 8\n"
+			"0:	sb	%1, 0(%2)\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"	dextu	%1, %0, 56, 8\n"
+			"1:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dextu	%1, %0, 48, 8\n"
+			"2:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dextu	%1, %0, 40, 8\n"
+			"3:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dextu	%1, %0, 32, 8\n"
+			"4:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dext	%1, %0, 24, 8\n"
+			"5:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dext	%1, %0, 16, 8\n"
+			"6:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dext	%1, %0, 8, 8\n"
+			"7:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dext	%1, %0, 0, 8\n"
+			"0:	sb	%1, 0(%2)\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"	.section        .fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.word	5b,8b\n"
+			"	.word	6b,8b\n"
+			"	.word	7b,8b\n"
+			"	.word	0b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV)
+			: "memory");
+
+		MIPS_R2_STATS(stores);
+		break;
+
+	case sdr_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"       .set	push\n"
+			"       .set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"       dext	%1, %0, 0, 8\n"
+			"1:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dext	%1, %0, 8, 8\n"
+			"2:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dext	%1, %0, 16, 8\n"
+			"3:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dext	%1, %0, 24, 8\n"
+			"4:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dextu	%1, %0, 32, 8\n"
+			"5:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dextu	%1, %0, 40, 8\n"
+			"6:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dextu	%1, %0, 48, 8\n"
+			"7:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dextu	%1, %0, 56, 8\n"
+			"0:     sb	%1, 0(%2)\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"       dext	%1, %0, 0, 8\n"
+			"1:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dext	%1, %0, 8, 8\n"
+			"2:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dext	%1, %0, 16, 8\n"
+			"3:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dext	%1, %0, 24, 8\n"
+			"4:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dextu	%1, %0, 32, 8\n"
+			"5:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dextu	%1, %0, 40, 8\n"
+			"6:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dextu	%1, %0, 48, 8\n"
+			"7:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dextu	%1, %0, 56, 8\n"
+			"0:     sb	%1, 0(%2)\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"       .insn\n"
+			"       .section        .fixup,\"ax\"\n"
+			"8:     li	%3,%4\n"
+			"       j	9b\n"
+			"       .previous\n"
+			"       .section        __ex_table,\"a\"\n"
+			"       .word	1b,8b\n"
+			"       .word	2b,8b\n"
+			"       .word	3b,8b\n"
+			"       .word	4b,8b\n"
+			"       .word	5b,8b\n"
+			"       .word	6b,8b\n"
+			"       .word	7b,8b\n"
+			"       .word	0b,8b\n"
+			"       .previous\n"
+			"       .set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV)
+			: "memory");
+
+		MIPS_R2_STATS(stores);
+
+		break;
+	case ll_op:
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (vaddr & 0x3) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+		if (!access_ok(VERIFY_READ, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+
+		if (!cpu_has_rw_llb) {
+			/*
+			 * An LL/SC block can't be safely emulated without
+			 * a Config5/LLB availability. So it's probably time to
+			 * kill our process before things get any worse. This is
+			 * because Config5/LLB allows us to use ERETNC so that
+			 * the LLAddr/LLB bit is not cleared when we return from
+			 * an exception. MIPS R2 LL/SC instructions trap with an
+			 * RI exception so once we emulate them here, we return
+			 * back to userland with ERETNC. That preserves the
+			 * LLAddr/LLB so the subsequent SC instruction will
+			 * succeed preserving the atomic semantics of the LL/SC
+			 * block. Without that, there is no safe way to emulate
+			 * an LL/SC block in MIPSR2 userland.
+			 */
+			pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n");
+			err = SIGKILL;
+			break;
+		}
+
+		__asm__ __volatile__(
+			"1:\n"
+			"ll	%0, 0(%2)\n"
+			"2:\n"
+			".insn\n"
+			".section        .fixup,\"ax\"\n"
+			"3:\n"
+			"li	%1, %3\n"
+			"j	2b\n"
+			".previous\n"
+			".section        __ex_table,\"a\"\n"
+			".word  1b, 3b\n"
+			".previous\n"
+			: "=&r"(res), "+&r"(err)
+			: "r"(vaddr), "i"(SIGSEGV)
+			: "memory");
+
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = res;
+		MIPS_R2_STATS(llsc);
+
+		break;
+
+	case sc_op:
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (vaddr & 0x3) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+		if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+
+		if (!cpu_has_rw_llb) {
+			/*
+			 * An LL/SC block can't be safely emulated without
+			 * a Config5/LLB availability. So it's probably time to
+			 * kill our process before things get any worse. This is
+			 * because Config5/LLB allows us to use ERETNC so that
+			 * the LLAddr/LLB bit is not cleared when we return from
+			 * an exception. MIPS R2 LL/SC instructions trap with an
+			 * RI exception so once we emulate them here, we return
+			 * back to userland with ERETNC. That preserves the
+			 * LLAddr/LLB so the subsequent SC instruction will
+			 * succeed preserving the atomic semantics of the LL/SC
+			 * block. Without that, there is no safe way to emulate
+			 * an LL/SC block in MIPSR2 userland.
+			 */
+			pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n");
+			err = SIGKILL;
+			break;
+		}
+
+		res = regs->regs[MIPSInst_RT(inst)];
+
+		__asm__ __volatile__(
+			"1:\n"
+			"sc	%0, 0(%2)\n"
+			"2:\n"
+			".insn\n"
+			".section        .fixup,\"ax\"\n"
+			"3:\n"
+			"li	%1, %3\n"
+			"j	2b\n"
+			".previous\n"
+			".section        __ex_table,\"a\"\n"
+			".word	1b, 3b\n"
+			".previous\n"
+			: "+&r"(res), "+&r"(err)
+			: "r"(vaddr), "i"(SIGSEGV));
+
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = res;
+
+		MIPS_R2_STATS(llsc);
+
+		break;
+
+	case lld_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (vaddr & 0x7) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+		if (!access_ok(VERIFY_READ, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+
+		if (!cpu_has_rw_llb) {
+			/*
+			 * An LL/SC block can't be safely emulated without
+			 * a Config5/LLB availability. So it's probably time to
+			 * kill our process before things get any worse. This is
+			 * because Config5/LLB allows us to use ERETNC so that
+			 * the LLAddr/LLB bit is not cleared when we return from
+			 * an exception. MIPS R2 LL/SC instructions trap with an
+			 * RI exception so once we emulate them here, we return
+			 * back to userland with ERETNC. That preserves the
+			 * LLAddr/LLB so the subsequent SC instruction will
+			 * succeed preserving the atomic semantics of the LL/SC
+			 * block. Without that, there is no safe way to emulate
+			 * an LL/SC block in MIPSR2 userland.
+			 */
+			pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n");
+			err = SIGKILL;
+			break;
+		}
+
+		__asm__ __volatile__(
+			"1:\n"
+			"lld	%0, 0(%2)\n"
+			"2:\n"
+			".insn\n"
+			".section        .fixup,\"ax\"\n"
+			"3:\n"
+			"li	%1, %3\n"
+			"j	2b\n"
+			".previous\n"
+			".section        __ex_table,\"a\"\n"
+			".word  1b, 3b\n"
+			".previous\n"
+			: "=&r"(res), "+&r"(err)
+			: "r"(vaddr), "i"(SIGSEGV)
+			: "memory");
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = res;
+
+		MIPS_R2_STATS(llsc);
+
+		break;
+
+	case scd_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (vaddr & 0x7) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+		if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+
+		if (!cpu_has_rw_llb) {
+			/*
+			 * An LL/SC block can't be safely emulated without
+			 * a Config5/LLB availability. So it's probably time to
+			 * kill our process before things get any worse. This is
+			 * because Config5/LLB allows us to use ERETNC so that
+			 * the LLAddr/LLB bit is not cleared when we return from
+			 * an exception. MIPS R2 LL/SC instructions trap with an
+			 * RI exception so once we emulate them here, we return
+			 * back to userland with ERETNC. That preserves the
+			 * LLAddr/LLB so the subsequent SC instruction will
+			 * succeed preserving the atomic semantics of the LL/SC
+			 * block. Without that, there is no safe way to emulate
+			 * an LL/SC block in MIPSR2 userland.
+			 */
+			pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n");
+			err = SIGKILL;
+			break;
+		}
+
+		res = regs->regs[MIPSInst_RT(inst)];
+
+		__asm__ __volatile__(
+			"1:\n"
+			"scd	%0, 0(%2)\n"
+			"2:\n"
+			".insn\n"
+			".section        .fixup,\"ax\"\n"
+			"3:\n"
+			"li	%1, %3\n"
+			"j	2b\n"
+			".previous\n"
+			".section        __ex_table,\"a\"\n"
+			".word	1b, 3b\n"
+			".previous\n"
+			: "+&r"(res), "+&r"(err)
+			: "r"(vaddr), "i"(SIGSEGV));
+
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = res;
+
+		MIPS_R2_STATS(llsc);
+
+		break;
+	case pref_op:
+		/* skip it */
+		break;
+	default:
+		err = SIGILL;
+	}
+
+	/*
+	 * Lets not return to userland just yet. It's constly and
+	 * it's likely we have more R2 instructions to emulate
+	 */
+	if (!err && (pass++ < MIPS_R2_EMUL_TOTAL_PASS)) {
+		regs->cp0_cause &= ~CAUSEF_BD;
+		err = get_user(inst, (u32 __user *)regs->cp0_epc);
+		if (!err)
+			goto repeat;
+
+		if (err < 0)
+			err = SIGSEGV;
+	}
+
+	if (err && (err != SIGEMT)) {
+		regs->regs[31] = r31;
+		regs->cp0_epc = epc;
+	}
+
+	/* Likely a MIPS R6 compatible instruction */
+	if (pass && (err == SIGILL))
+		err = 0;
+
+	return err;
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+static int mipsr2_stats_show(struct seq_file *s, void *unused)
+{
+
+	seq_printf(s, "Instruction\tTotal\tBDslot\n------------------------------\n");
+	seq_printf(s, "movs\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.movs),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.movs));
+	seq_printf(s, "hilo\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.hilo),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.hilo));
+	seq_printf(s, "muls\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.muls),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.muls));
+	seq_printf(s, "divs\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.divs),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.divs));
+	seq_printf(s, "dsps\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.dsps),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.dsps));
+	seq_printf(s, "bops\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.bops),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.bops));
+	seq_printf(s, "traps\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.traps),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.traps));
+	seq_printf(s, "fpus\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.fpus),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.fpus));
+	seq_printf(s, "loads\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.loads),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.loads));
+	seq_printf(s, "stores\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.stores),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.stores));
+	seq_printf(s, "llsc\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.llsc),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.llsc));
+	seq_printf(s, "dsemul\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.dsemul),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.dsemul));
+	seq_printf(s, "jr\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.jrs));
+	seq_printf(s, "bltzl\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bltzl));
+	seq_printf(s, "bgezl\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bgezl));
+	seq_printf(s, "bltzll\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bltzll));
+	seq_printf(s, "bgezll\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bgezll));
+	seq_printf(s, "bltzal\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bltzal));
+	seq_printf(s, "bgezal\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bgezal));
+	seq_printf(s, "beql\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.beql));
+	seq_printf(s, "bnel\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bnel));
+	seq_printf(s, "blezl\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.blezl));
+	seq_printf(s, "bgtzl\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bgtzl));
+
+	return 0;
+}
+
+static int mipsr2_stats_clear_show(struct seq_file *s, void *unused)
+{
+	mipsr2_stats_show(s, unused);
+
+	__this_cpu_write((mipsr2emustats).movs, 0);
+	__this_cpu_write((mipsr2bdemustats).movs, 0);
+	__this_cpu_write((mipsr2emustats).hilo, 0);
+	__this_cpu_write((mipsr2bdemustats).hilo, 0);
+	__this_cpu_write((mipsr2emustats).muls, 0);
+	__this_cpu_write((mipsr2bdemustats).muls, 0);
+	__this_cpu_write((mipsr2emustats).divs, 0);
+	__this_cpu_write((mipsr2bdemustats).divs, 0);
+	__this_cpu_write((mipsr2emustats).dsps, 0);
+	__this_cpu_write((mipsr2bdemustats).dsps, 0);
+	__this_cpu_write((mipsr2emustats).bops, 0);
+	__this_cpu_write((mipsr2bdemustats).bops, 0);
+	__this_cpu_write((mipsr2emustats).traps, 0);
+	__this_cpu_write((mipsr2bdemustats).traps, 0);
+	__this_cpu_write((mipsr2emustats).fpus, 0);
+	__this_cpu_write((mipsr2bdemustats).fpus, 0);
+	__this_cpu_write((mipsr2emustats).loads, 0);
+	__this_cpu_write((mipsr2bdemustats).loads, 0);
+	__this_cpu_write((mipsr2emustats).stores, 0);
+	__this_cpu_write((mipsr2bdemustats).stores, 0);
+	__this_cpu_write((mipsr2emustats).llsc, 0);
+	__this_cpu_write((mipsr2bdemustats).llsc, 0);
+	__this_cpu_write((mipsr2emustats).dsemul, 0);
+	__this_cpu_write((mipsr2bdemustats).dsemul, 0);
+	__this_cpu_write((mipsr2bremustats).jrs, 0);
+	__this_cpu_write((mipsr2bremustats).bltzl, 0);
+	__this_cpu_write((mipsr2bremustats).bgezl, 0);
+	__this_cpu_write((mipsr2bremustats).bltzll, 0);
+	__this_cpu_write((mipsr2bremustats).bgezll, 0);
+	__this_cpu_write((mipsr2bremustats).bltzal, 0);
+	__this_cpu_write((mipsr2bremustats).bgezal, 0);
+	__this_cpu_write((mipsr2bremustats).beql, 0);
+	__this_cpu_write((mipsr2bremustats).bnel, 0);
+	__this_cpu_write((mipsr2bremustats).blezl, 0);
+	__this_cpu_write((mipsr2bremustats).bgtzl, 0);
+
+	return 0;
+}
+
+static int mipsr2_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mipsr2_stats_show, inode->i_private);
+}
+
+static int mipsr2_stats_clear_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mipsr2_stats_clear_show, inode->i_private);
+}
+
+static const struct file_operations mipsr2_emul_fops = {
+	.open                   = mipsr2_stats_open,
+	.read			= seq_read,
+	.llseek			= seq_lseek,
+	.release		= single_release,
+};
+
+static const struct file_operations mipsr2_clear_fops = {
+	.open                   = mipsr2_stats_clear_open,
+	.read			= seq_read,
+	.llseek			= seq_lseek,
+	.release		= single_release,
+};
+
+
+static int __init mipsr2_init_debugfs(void)
+{
+	extern struct dentry	*mips_debugfs_dir;
+	struct dentry		*mipsr2_emul;
+
+	if (!mips_debugfs_dir)
+		return -ENODEV;
+
+	mipsr2_emul = debugfs_create_file("r2_emul_stats", S_IRUGO,
+					  mips_debugfs_dir, NULL,
+					  &mipsr2_emul_fops);
+	if (!mipsr2_emul)
+		return -ENOMEM;
+
+	mipsr2_emul = debugfs_create_file("r2_emul_stats_clear", S_IRUGO,
+					  mips_debugfs_dir, NULL,
+					  &mipsr2_clear_fops);
+	if (!mipsr2_emul)
+		return -ENOMEM;
+
+	return 0;
+}
+
+device_initcall(mipsr2_init_debugfs);
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 6e9d8505e128..fc157322f609 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -46,6 +46,7 @@
 #include <asm/fpu.h>
 #include <asm/fpu_emulator.h>
 #include <asm/idle.h>
+#include <asm/mips-r2-to-r6-emul.h>
 #include <asm/mipsregs.h>
 #include <asm/mipsmtregs.h>
 #include <asm/module.h>
@@ -837,7 +838,7 @@ out:
 	exception_exit(prev_state);
 }
 
-static void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
+void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
 	const char *str)
 {
 	siginfo_t info;
@@ -1027,7 +1028,32 @@ asmlinkage void do_ri(struct pt_regs *regs)
 	unsigned int opcode = 0;
 	int status = -1;
 
+	/*
+	 * Avoid any kernel code. Just emulate the R2 instruction
+	 * as quickly as possible.
+	 */
+	if (mipsr2_emulation && cpu_has_mips_r6 &&
+	    likely(user_mode(regs))) {
+		if (likely(get_user(opcode, epc) >= 0)) {
+			status = mipsr2_decoder(regs, opcode);
+			switch (status) {
+			case 0:
+			case SIGEMT:
+				return;
+			case SIGILL:
+				goto no_r2_instr;
+			default:
+				process_fpemu_return(status,
+						     &current->thread.cp0_baduaddr);
+				return;
+			}
+		}
+	}
+
+no_r2_instr:
+
 	prev_state = exception_enter();
+
 	if (notify_die(DIE_RI, "RI Fault", regs, 0, regs_to_trapnr(regs),
 		       SIGILL) == NOTIFY_STOP)
 		goto out;
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 6e7920b20822..3c341b08d120 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -48,6 +48,7 @@
 #include <asm/processor.h>
 #include <asm/fpu_emulator.h>
 #include <asm/fpu.h>
+#include <asm/mips-r2-to-r6-emul.h>
 
 #include "ieee754.h"
 
@@ -68,7 +69,7 @@ static int fpux_emu(struct pt_regs *,
 #define modeindex(v) ((v) & FPU_CSR_RM)
 
 /* convert condition code register number to csr bit */
-static const unsigned int fpucondbit[8] = {
+const unsigned int fpucondbit[8] = {
 	FPU_CSR_COND0,
 	FPU_CSR_COND1,
 	FPU_CSR_COND2,
-- 
cgit v1.2.3


From 7c151d3d5d7a032e08dbe86ad6088622391bf13e Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Wed, 3 Dec 2014 12:37:32 +0000
Subject: MIPS: Make use of the ERETNC instruction on MIPS R6

The ERETNC instruction, introduced in MIPS R5, is similar to the ERET
one, except it does not clear the LLB bit in the LLADDR register.
This feature is necessary to safely emulate R2 LL/SC instructions.
However, on context switches, we need to clear the LLAddr/LLB bit
in order to make sure that an SC instruction from the new thread
will never succeed if it happens to interrupt an LL operation on the
same address from the previous thread.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/switch_to.h   |  9 ++++++---
 arch/mips/include/asm/thread_info.h |  2 +-
 arch/mips/kernel/asm-offsets.c      |  1 +
 arch/mips/kernel/entry.S            | 18 ++++++++++++++++++
 arch/mips/kernel/traps.c            |  2 ++
 5 files changed, 28 insertions(+), 4 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index b928b6f898cd..e92d6c4b5ed1 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -75,9 +75,12 @@ do {									\
 #endif
 
 #define __clear_software_ll_bit()					\
-do {									\
-	if (!__builtin_constant_p(cpu_has_llsc) || !cpu_has_llsc)	\
-		ll_bit = 0;						\
+do {	if (cpu_has_rw_llb) {						\
+		write_c0_lladdr(0);					\
+	} else {							\
+		if (!__builtin_constant_p(cpu_has_llsc) || !cpu_has_llsc)\
+			ll_bit = 0;					\
+	}								\
 } while (0)
 
 #define switch_to(prev, next, last)					\
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 99eea59604e9..fb68fd2714fb 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -28,7 +28,7 @@ struct thread_info {
 	unsigned long		tp_value;	/* thread pointer */
 	__u32			cpu;		/* current CPU */
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
-
+	int			r2_emul_return; /* 1 => Returning from R2 emulator */
 	mm_segment_t		addr_limit;	/*
 						 * thread address space limit:
 						 * 0x7fffffff for user-thead
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index b1d84bd4efb3..7b6c11aa1cae 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -97,6 +97,7 @@ void output_thread_info_defines(void)
 	OFFSET(TI_TP_VALUE, thread_info, tp_value);
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
+	OFFSET(TI_R2_EMUL_RET, thread_info, r2_emul_return);
 	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
 	OFFSET(TI_RESTART_BLOCK, thread_info, restart_block);
 	OFFSET(TI_REGS, thread_info, regs);
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index d5ab21c3fd12..af41ba6db960 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -46,6 +46,11 @@ resume_userspace:
 	local_irq_disable		# make sure we dont miss an
 					# interrupt setting need_resched
 					# between sampling and return
+#ifdef CONFIG_MIPSR2_TO_R6_EMULATOR
+	lw	k0, TI_R2_EMUL_RET($28)
+	bnez	k0, restore_all_from_r2_emul
+#endif
+
 	LONG_L	a2, TI_FLAGS($28)	# current->work
 	andi	t0, a2, _TIF_WORK_MASK	# (ignoring syscall_trace)
 	bnez	t0, work_pending
@@ -114,6 +119,19 @@ restore_partial:		# restore partial frame
 	RESTORE_SP_AND_RET
 	.set	at
 
+#ifdef CONFIG_MIPSR2_TO_R6_EMULATOR
+restore_all_from_r2_emul:			# restore full frame
+	.set	noat
+	sw	zero, TI_R2_EMUL_RET($28)	# reset it
+	RESTORE_TEMP
+	RESTORE_AT
+	RESTORE_STATIC
+	RESTORE_SOME
+	LONG_L	sp, PT_R29(sp)
+	eretnc
+	.set	at
+#endif
+
 work_pending:
 	andi	t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS
 	beqz	t0, work_notifysig
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index fc157322f609..afa447e5e97f 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1039,12 +1039,14 @@ asmlinkage void do_ri(struct pt_regs *regs)
 			switch (status) {
 			case 0:
 			case SIGEMT:
+				task_thread_info(current)->r2_emul_return = 1;
 				return;
 			case SIGILL:
 				goto no_r2_instr;
 			default:
 				process_fpemu_return(status,
 						     &current->thread.cp0_baduaddr);
+				task_thread_info(current)->r2_emul_return = 1;
 				return;
 			}
 		}
-- 
cgit v1.2.3


From e0d32f33e651a393a23826c06a9301917372f3e2 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 15 Jan 2015 10:11:17 +0000
Subject: MIPS: Handle MIPS IV, V and R2 FPU instructions on MIPS R6 as well

MIPS R2 FPU instructions are also present in MIPS R6 so amend the
preprocessor definitions to take MIPS R6 into consideration.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/cpu-features.h | 3 ++-
 arch/mips/math-emu/cp1emu.c          | 8 ++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index e686131ff995..0d8208de9a3f 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -220,7 +220,8 @@
 #define cpu_has_mips_4_5_r	(cpu_has_mips_4 | cpu_has_mips_5_r)
 #define cpu_has_mips_5_r	(cpu_has_mips_5 | cpu_has_mips_r)
 
-#define cpu_has_mips_4_5_r2	(cpu_has_mips_4_5 | cpu_has_mips_r2)
+#define cpu_has_mips_4_5_r2_r6	(cpu_has_mips_4_5 | cpu_has_mips_r2 | \
+				 cpu_has_mips_r6)
 
 #define cpu_has_mips32	(cpu_has_mips32r1 | cpu_has_mips32r2 | cpu_has_mips32r6)
 #define cpu_has_mips64	(cpu_has_mips64r1 | cpu_has_mips64r2 | cpu_has_mips64r6)
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 3c341b08d120..b30bf65c7d7d 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1561,14 +1561,14 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 		 * achieve full IEEE-754 accuracy - however this emulator does.
 		 */
 		case frsqrt_op:
-			if (!cpu_has_mips_4_5_r2)
+			if (!cpu_has_mips_4_5_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_sp_rsqrt;
 			goto scopuop;
 
 		case frecip_op:
-			if (!cpu_has_mips_4_5_r2)
+			if (!cpu_has_mips_4_5_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_sp_recip;
@@ -1763,13 +1763,13 @@ copcsr:
 		 * achieve full IEEE-754 accuracy - however this emulator does.
 		 */
 		case frsqrt_op:
-			if (!cpu_has_mips_4_5_r2)
+			if (!cpu_has_mips_4_5_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_dp_rsqrt;
 			goto dcopuop;
 		case frecip_op:
-			if (!cpu_has_mips_4_5_r2)
+			if (!cpu_has_mips_4_5_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_dp_recip;
-- 
cgit v1.2.3


From 6134d94923d03556b4f74a7864759dc333030c98 Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Fri, 30 Jan 2015 10:20:28 +0000
Subject: MIPS: asm: fpu: Allow 64-bit FPU on MIPS32 R6

MIPS32 R6 has a 64-bit FPU so add the necessary MIPS R6
definition.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/include/asm/fpu.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 994d21939676..b96d9d327626 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -68,7 +68,8 @@ static inline int __enable_fpu(enum fpu_mode mode)
 		goto fr_common;
 
 	case FPU_64BIT:
-#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_64BIT))
+#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS32_R6) \
+      || defined(CONFIG_64BIT))
 		/* we only have a 32-bit FPU */
 		return SIGFPE;
 #endif
-- 
cgit v1.2.3


From 46490b572544fa908be051f7872beb2941e55ede Mon Sep 17 00:00:00 2001
From: Markos Chandras <markos.chandras@imgtec.com>
Date: Thu, 8 Jan 2015 09:32:25 +0000
Subject: MIPS: kernel: elf: Improve the overall ABI and FPU mode checks

The previous implementation did not cover all possible FPU combinations
and it silently allowed ABI incompatible objects to be loaded with the
wrong ABI. For example, the previous logic would set the FP_64 ABI as
the matching ABI for an FP_XX object combined with an FP_64A object.
This was wrong, and the matching ABI should have been FP_64A.
The previous logic is now replaced with a new one which determines
the appropriate FPU mode to be used rather than the FP ABI. This has
the advantage that the entire logic is much simpler since it is the FPU
mode we are interested in rather than the FP ABI resulting to code
simplifications. This also removes the now obsolete FP32XX_HYBRID_FPRS
option.

Cc: Matthew Fortune <Matthew.Fortune@imgtec.com>
Cc: Paul Burton <paul.burton@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
---
 arch/mips/Kconfig.debug     |  13 --
 arch/mips/include/asm/elf.h |  10 +-
 arch/mips/kernel/elf.c      | 303 +++++++++++++++++++++++++++-----------------
 3 files changed, 194 insertions(+), 132 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 88a9f433f6fc..3a2b775e8458 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -122,17 +122,4 @@ config SPINLOCK_TEST
 	help
 	  Add several files to the debugfs to test spinlock speed.
 
-config FP32XX_HYBRID_FPRS
-	bool "Run FP32 & FPXX code with hybrid FPRs"
-	depends on MIPS_O32_FP64_SUPPORT
-	help
-	  The hybrid FPR scheme is normally used only when a program needs to
-	  execute a mix of FP32 & FP64A code, since the trapping & emulation
-	  that it entails is expensive. When enabled, this option will lead
-	  to the kernel running programs which use the FP32 & FPXX FP ABIs
-	  using the hybrid FPR scheme, which can be useful for debugging
-	  purposes.
-
-	  If unsure, say N.
-
 endmenu
diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h
index eb4d95de619c..535f196ffe02 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -417,13 +417,15 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 struct arch_elf_state {
 	int fp_abi;
 	int interp_fp_abi;
-	int overall_abi;
+	int overall_fp_mode;
 };
 
+#define MIPS_ABI_FP_UNKNOWN	(-1)	/* Unknown FP ABI (kernel internal) */
+
 #define INIT_ARCH_ELF_STATE {			\
-	.fp_abi = -1,				\
-	.interp_fp_abi = -1,			\
-	.overall_abi = -1,			\
+	.fp_abi = MIPS_ABI_FP_UNKNOWN,		\
+	.interp_fp_abi = MIPS_ABI_FP_UNKNOWN,	\
+	.overall_fp_mode = -1,			\
 }
 
 extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf,
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index c92b15df6893..d2c09f6475c5 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -11,29 +11,112 @@
 #include <linux/elf.h>
 #include <linux/sched.h>
 
+/* FPU modes */
 enum {
-	FP_ERROR = -1,
-	FP_DOUBLE_64A = -2,
+	FP_FRE,
+	FP_FR0,
+	FP_FR1,
 };
 
+/**
+ * struct mode_req - ABI FPU mode requirements
+ * @single:	The program being loaded needs an FPU but it will only issue
+ *		single precision instructions meaning that it can execute in
+ *		either FR0 or FR1.
+ * @soft:	The soft(-float) requirement means that the program being
+ *		loaded needs has no FPU dependency at all (i.e. it has no
+ *		FPU instructions).
+ * @fr1:	The program being loaded depends on FPU being in FR=1 mode.
+ * @frdefault:	The program being loaded depends on the default FPU mode.
+ *		That is FR0 for O32 and FR1 for N32/N64.
+ * @fre:	The program being loaded depends on FPU with FRE=1. This mode is
+ *		a bridge which uses FR=1 whilst still being able to maintain
+ *		full compatibility with pre-existing code using the O32 FP32
+ *		ABI.
+ *
+ * More information about the FP ABIs can be found here:
+ *
+ * https://dmz-portal.mips.com/wiki/MIPS_O32_ABI_-_FR0_and_FR1_Interlinking#10.4.1._Basic_mode_set-up
+ *
+ */
+
+struct mode_req {
+	bool single;
+	bool soft;
+	bool fr1;
+	bool frdefault;
+	bool fre;
+};
+
+static const struct mode_req fpu_reqs[] = {
+	[MIPS_ABI_FP_ANY]    = { true,  true,  true,  true,  true  },
+	[MIPS_ABI_FP_DOUBLE] = { false, false, false, true,  true  },
+	[MIPS_ABI_FP_SINGLE] = { true,  false, false, false, false },
+	[MIPS_ABI_FP_SOFT]   = { false, true,  false, false, false },
+	[MIPS_ABI_FP_OLD_64] = { false, false, false, false, false },
+	[MIPS_ABI_FP_XX]     = { false, false, true,  true,  true  },
+	[MIPS_ABI_FP_64]     = { false, false, true,  false, false },
+	[MIPS_ABI_FP_64A]    = { false, false, true,  false, true  }
+};
+
+/*
+ * Mode requirements when .MIPS.abiflags is not present in the ELF.
+ * Not present means that everything is acceptable except FR1.
+ */
+static struct mode_req none_req = { true, true, false, true, true };
+
 int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
 		     bool is_interp, struct arch_elf_state *state)
 {
-	struct elfhdr *ehdr = _ehdr;
-	struct elf_phdr *phdr = _phdr;
+	struct elf32_hdr *ehdr32 = _ehdr;
+	struct elf32_phdr *phdr32 = _phdr;
+	struct elf64_phdr *phdr64 = _phdr;
 	struct mips_elf_abiflags_v0 abiflags;
 	int ret;
 
-	if (config_enabled(CONFIG_64BIT) &&
-	    (ehdr->e_ident[EI_CLASS] != ELFCLASS32))
-		return 0;
-	if (phdr->p_type != PT_MIPS_ABIFLAGS)
-		return 0;
-	if (phdr->p_filesz < sizeof(abiflags))
-		return -EINVAL;
+	/* Lets see if this is an O32 ELF */
+	if (ehdr32->e_ident[EI_CLASS] == ELFCLASS32) {
+		/* FR = 1 for N32 */
+		if (ehdr32->e_flags & EF_MIPS_ABI2)
+			state->overall_fp_mode = FP_FR1;
+		else
+			/* Set a good default FPU mode for O32 */
+			state->overall_fp_mode = cpu_has_mips_r6 ?
+				FP_FRE : FP_FR0;
+
+		if (ehdr32->e_flags & EF_MIPS_FP64) {
+			/*
+			 * Set MIPS_ABI_FP_OLD_64 for EF_MIPS_FP64. We will override it
+			 * later if needed
+			 */
+			if (is_interp)
+				state->interp_fp_abi = MIPS_ABI_FP_OLD_64;
+			else
+				state->fp_abi = MIPS_ABI_FP_OLD_64;
+		}
+		if (phdr32->p_type != PT_MIPS_ABIFLAGS)
+			return 0;
+
+		if (phdr32->p_filesz < sizeof(abiflags))
+			return -EINVAL;
+
+		ret = kernel_read(elf, phdr32->p_offset,
+				  (char *)&abiflags,
+				  sizeof(abiflags));
+	} else {
+		/* FR=1 is really the only option for 64-bit */
+		state->overall_fp_mode = FP_FR1;
+
+		if (phdr64->p_type != PT_MIPS_ABIFLAGS)
+			return 0;
+		if (phdr64->p_filesz < sizeof(abiflags))
+			return -EINVAL;
+
+		ret = kernel_read(elf, phdr64->p_offset,
+				  (char *)&abiflags,
+				  sizeof(abiflags));
+	}
 
-	ret = kernel_read(elf, phdr->p_offset, (char *)&abiflags,
-			  sizeof(abiflags));
 	if (ret < 0)
 		return ret;
 	if (ret != sizeof(abiflags))
@@ -48,35 +131,30 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
 	return 0;
 }
 
-static inline unsigned get_fp_abi(struct elfhdr *ehdr, int in_abi)
+static inline unsigned get_fp_abi(int in_abi)
 {
 	/* If the ABI requirement is provided, simply return that */
-	if (in_abi != -1)
+	if (in_abi != MIPS_ABI_FP_UNKNOWN)
 		return in_abi;
 
-	/* If the EF_MIPS_FP64 flag was set, return MIPS_ABI_FP_64 */
-	if (ehdr->e_flags & EF_MIPS_FP64)
-		return MIPS_ABI_FP_64;
-
-	/* Default to MIPS_ABI_FP_DOUBLE */
-	return MIPS_ABI_FP_DOUBLE;
+	/* Unknown ABI */
+	return MIPS_ABI_FP_UNKNOWN;
 }
 
 int arch_check_elf(void *_ehdr, bool has_interpreter,
 		   struct arch_elf_state *state)
 {
-	struct elfhdr *ehdr = _ehdr;
-	unsigned fp_abi, interp_fp_abi, abi0, abi1;
+	struct elf32_hdr *ehdr = _ehdr;
+	struct mode_req prog_req, interp_req;
+	int fp_abi, interp_fp_abi, abi0, abi1, max_abi;
 
-	/* Ignore non-O32 binaries */
-	if (config_enabled(CONFIG_64BIT) &&
-	    (ehdr->e_ident[EI_CLASS] != ELFCLASS32))
+	if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
 		return 0;
 
-	fp_abi = get_fp_abi(ehdr, state->fp_abi);
+	fp_abi = get_fp_abi(state->fp_abi);
 
 	if (has_interpreter) {
-		interp_fp_abi = get_fp_abi(ehdr, state->interp_fp_abi);
+		interp_fp_abi = get_fp_abi(state->interp_fp_abi);
 
 		abi0 = min(fp_abi, interp_fp_abi);
 		abi1 = max(fp_abi, interp_fp_abi);
@@ -84,108 +162,103 @@ int arch_check_elf(void *_ehdr, bool has_interpreter,
 		abi0 = abi1 = fp_abi;
 	}
 
-	state->overall_abi = FP_ERROR;
-
-	if (abi0 == abi1) {
-		state->overall_abi = abi0;
-	} else if (abi0 == MIPS_ABI_FP_ANY) {
-		state->overall_abi = abi1;
-	} else if (abi0 == MIPS_ABI_FP_DOUBLE) {
-		switch (abi1) {
-		case MIPS_ABI_FP_XX:
-			state->overall_abi = MIPS_ABI_FP_DOUBLE;
-			break;
-
-		case MIPS_ABI_FP_64A:
-			state->overall_abi = FP_DOUBLE_64A;
-			break;
-		}
-	} else if (abi0 == MIPS_ABI_FP_SINGLE ||
-		   abi0 == MIPS_ABI_FP_SOFT) {
-		/* Cannot link with other ABIs */
-	} else if (abi0 == MIPS_ABI_FP_OLD_64) {
-		switch (abi1) {
-		case MIPS_ABI_FP_XX:
-		case MIPS_ABI_FP_64:
-		case MIPS_ABI_FP_64A:
-			state->overall_abi = MIPS_ABI_FP_64;
-			break;
-		}
-	} else if (abi0 == MIPS_ABI_FP_XX ||
-		   abi0 == MIPS_ABI_FP_64 ||
-		   abi0 == MIPS_ABI_FP_64A) {
-		state->overall_abi = MIPS_ABI_FP_64;
-	}
+	/* ABI limits. O32 = FP_64A, N32/N64 = FP_SOFT */
+	max_abi = ((ehdr->e_ident[EI_CLASS] == ELFCLASS32) &&
+		   (!(ehdr->e_flags & EF_MIPS_ABI2))) ?
+		MIPS_ABI_FP_64A : MIPS_ABI_FP_SOFT;
 
-	switch (state->overall_abi) {
-	case MIPS_ABI_FP_64:
-	case MIPS_ABI_FP_64A:
-	case FP_DOUBLE_64A:
-		if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
-			return -ELIBBAD;
-		break;
+	if ((abi0 > max_abi && abi0 != MIPS_ABI_FP_UNKNOWN) ||
+	    (abi1 > max_abi && abi1 != MIPS_ABI_FP_UNKNOWN))
+		return -ELIBBAD;
+
+	/* It's time to determine the FPU mode requirements */
+	prog_req = (abi0 == MIPS_ABI_FP_UNKNOWN) ? none_req : fpu_reqs[abi0];
+	interp_req = (abi1 == MIPS_ABI_FP_UNKNOWN) ? none_req : fpu_reqs[abi1];
 
-	case FP_ERROR:
+	/*
+	 * Check whether the program's and interp's ABIs have a matching FPU
+	 * mode requirement.
+	 */
+	prog_req.single = interp_req.single && prog_req.single;
+	prog_req.soft = interp_req.soft && prog_req.soft;
+	prog_req.fr1 = interp_req.fr1 && prog_req.fr1;
+	prog_req.frdefault = interp_req.frdefault && prog_req.frdefault;
+	prog_req.fre = interp_req.fre && prog_req.fre;
+
+	/*
+	 * Determine the desired FPU mode
+	 *
+	 * Decision making:
+	 *
+	 * - We want FR_FRE if FRE=1 and both FR=1 and FR=0 are false. This
+	 *   means that we have a combination of program and interpreter
+	 *   that inherently require the hybrid FP mode.
+	 * - If FR1 and FRDEFAULT is true, that means we hit the any-abi or
+	 *   fpxx case. This is because, in any-ABI (or no-ABI) we have no FPU
+	 *   instructions so we don't care about the mode. We will simply use
+	 *   the one preferred by the hardware. In fpxx case, that ABI can
+	 *   handle both FR=1 and FR=0, so, again, we simply choose the one
+	 *   preferred by the hardware. Next, if we only use single-precision
+	 *   FPU instructions, and the default ABI FPU mode is not good
+	 *   (ie single + any ABI combination), we set again the FPU mode to the
+	 *   one is preferred by the hardware. Next, if we know that the code
+	 *   will only use single-precision instructions, shown by single being
+	 *   true but frdefault being false, then we again set the FPU mode to
+	 *   the one that is preferred by the hardware.
+	 * - We want FP_FR1 if that's the only matching mode and the default one
+	 *   is not good.
+	 * - Return with -ELIBADD if we can't find a matching FPU mode.
+	 */
+	if (prog_req.fre && !prog_req.frdefault && !prog_req.fr1)
+		state->overall_fp_mode = FP_FRE;
+	else if ((prog_req.fr1 && prog_req.frdefault) ||
+		 (prog_req.single && !prog_req.frdefault))
+		/* Make sure 64-bit MIPS III/IV/64R1 will not pick FR1 */
+		state->overall_fp_mode = ((current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
+					  cpu_has_mips_r2_r6) ?
+					  FP_FR1 : FP_FR0;
+	else if (prog_req.fr1)
+		state->overall_fp_mode = FP_FR1;
+	else  if (!prog_req.fre && !prog_req.frdefault &&
+		  !prog_req.fr1 && !prog_req.single && !prog_req.soft)
 		return -ELIBBAD;
-	}
 
 	return 0;
 }
 
-void mips_set_personality_fp(struct arch_elf_state *state)
+static inline void set_thread_fp_mode(int hybrid, int regs32)
 {
-	if (config_enabled(CONFIG_FP32XX_HYBRID_FPRS)) {
-		/*
-		 * Use hybrid FPRs for all code which can correctly execute
-		 * with that mode.
-		 */
-		switch (state->overall_abi) {
-		case MIPS_ABI_FP_DOUBLE:
-		case MIPS_ABI_FP_SINGLE:
-		case MIPS_ABI_FP_SOFT:
-		case MIPS_ABI_FP_XX:
-		case MIPS_ABI_FP_ANY:
-			/* FR=1, FRE=1 */
-			clear_thread_flag(TIF_32BIT_FPREGS);
-			set_thread_flag(TIF_HYBRID_FPREGS);
-			return;
-		}
-	}
-
-	switch (state->overall_abi) {
-	case MIPS_ABI_FP_DOUBLE:
-	case MIPS_ABI_FP_SINGLE:
-	case MIPS_ABI_FP_SOFT:
-		/* FR=0 */
-		set_thread_flag(TIF_32BIT_FPREGS);
+	if (hybrid)
+		set_thread_flag(TIF_HYBRID_FPREGS);
+	else
 		clear_thread_flag(TIF_HYBRID_FPREGS);
-		break;
-
-	case FP_DOUBLE_64A:
-		/* FR=1, FRE=1 */
+	if (regs32)
+		set_thread_flag(TIF_32BIT_FPREGS);
+	else
 		clear_thread_flag(TIF_32BIT_FPREGS);
-		set_thread_flag(TIF_HYBRID_FPREGS);
-		break;
+}
 
-	case MIPS_ABI_FP_64:
-	case MIPS_ABI_FP_64A:
-		/* FR=1, FRE=0 */
-		clear_thread_flag(TIF_32BIT_FPREGS);
-		clear_thread_flag(TIF_HYBRID_FPREGS);
-		break;
+void mips_set_personality_fp(struct arch_elf_state *state)
+{
+	/*
+	 * This function is only ever called for O32 ELFs so we should
+	 * not be worried about N32/N64 binaries.
+	 */
 
-	case MIPS_ABI_FP_XX:
-	case MIPS_ABI_FP_ANY:
-		if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
-			set_thread_flag(TIF_32BIT_FPREGS);
-		else
-			clear_thread_flag(TIF_32BIT_FPREGS);
+	if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
+		return;
 
-		clear_thread_flag(TIF_HYBRID_FPREGS);
+	switch (state->overall_fp_mode) {
+	case FP_FRE:
+		set_thread_fp_mode(1, 0);
+		break;
+	case FP_FR0:
+		set_thread_fp_mode(0, 1);
+		break;
+	case FP_FR1:
+		set_thread_fp_mode(0, 0);
 		break;
-
 	default:
-	case FP_ERROR:
 		BUG();
 	}
 }
-- 
cgit v1.2.3


From 8cb48fe169dd682b6c29a3b7ef18333e4f577890 Mon Sep 17 00:00:00 2001
From: Petr Malat <oss@malat.biz>
Date: Fri, 12 Dec 2014 15:28:01 +0100
Subject: MIPS: Provide correct siginfo_t.si_stime

Provide correct siginfo_t.si_stime on MIPS64

Bug description:
MIPS version of copy_siginfo() is not aware of alignment on platforms with
64-bit long integers, which leads to an incorrect si_stime passed to signal
handlers, because the last element (si_stime) of _sifields._sigchld is not
copied. If _MIPS_SZLONG is 64, then the _sifields starts at the offset of
4 * sizeof(int).

Patch description:
Use the generic copy_siginfo, which doesn't have this problem.

Signed-off-by: Petr Malat <oss@malat.biz>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/8671/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/siginfo.h      | 29 -----------------------------
 arch/mips/include/uapi/asm/siginfo.h | 11 +++--------
 2 files changed, 3 insertions(+), 37 deletions(-)
 delete mode 100644 arch/mips/include/asm/siginfo.h

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/siginfo.h b/arch/mips/include/asm/siginfo.h
deleted file mode 100644
index dd9a762646fc..000000000000
--- a/arch/mips/include/asm/siginfo.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * 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) 1998, 1999, 2001, 2003 Ralf Baechle
- * Copyright (C) 2000, 2001 Silicon Graphics, Inc.
- */
-#ifndef _ASM_SIGINFO_H
-#define _ASM_SIGINFO_H
-
-#include <uapi/asm/siginfo.h>
-
-
-/*
- * Duplicated here because of <asm-generic/siginfo.h> braindamage ...
- */
-#include <linux/string.h>
-
-static inline void copy_siginfo(struct siginfo *to, struct siginfo *from)
-{
-	if (from->si_code < 0)
-		memcpy(to, from, sizeof(*to));
-	else
-		/* _sigchld is currently the largest know union member */
-		memcpy(to, from, 3*sizeof(int) + sizeof(from->_sifields._sigchld));
-}
-
-#endif /* _ASM_SIGINFO_H */
diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h
index d08f83f19db5..2cb7fdead570 100644
--- a/arch/mips/include/uapi/asm/siginfo.h
+++ b/arch/mips/include/uapi/asm/siginfo.h
@@ -15,13 +15,6 @@
 
 #define HAVE_ARCH_SIGINFO_T
 
-/*
- * We duplicate the generic versions - <asm-generic/siginfo.h> is just borked
- * by design ...
- */
-#define HAVE_ARCH_COPY_SIGINFO
-struct siginfo;
-
 /*
  * Careful to keep union _sifields from shifting ...
  */
@@ -35,8 +28,9 @@ struct siginfo;
 
 #define __ARCH_SIGSYS
 
-#include <asm-generic/siginfo.h>
+#include <uapi/asm-generic/siginfo.h>
 
+/* We can't use generic siginfo_t, because our si_code and si_errno are swapped */
 typedef struct siginfo {
 	int si_signo;
 	int si_code;
@@ -124,5 +118,6 @@ typedef struct siginfo {
 #define SI_TIMER __SI_CODE(__SI_TIMER, -3) /* sent by timer expiration */
 #define SI_MESGQ __SI_CODE(__SI_MESGQ, -4) /* sent by real time mesq state change */
 
+#include <asm-generic/siginfo.h>
 
 #endif /* _UAPI_ASM_SIGINFO_H */
-- 
cgit v1.2.3


From 05f9883a2899d50ff96f05b7a76b7597009b0680 Mon Sep 17 00:00:00 2001
From: "Steven J. Hill" <Steven.Hill@imgtec.com>
Date: Thu, 19 Feb 2015 10:18:50 -0600
Subject: MIPS: Usage and cosmetic cleanups of page table bits.

* Clean up white spaces and tabs.
   * Get rid of remaining hardcoded values for calculating
     shifts and masks.
   * Get rid of redundant macro values.
   * Do not use page table bits directly in #ifdef's.

Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/9287/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/pgtable-bits.h | 96 ++++++++++++++----------------------
 arch/mips/include/asm/pgtable.h      |  4 +-
 2 files changed, 38 insertions(+), 62 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index ca11f14f40a3..156fd6eb1e03 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -35,7 +35,7 @@
 #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
 
 /*
- * The following bits are directly used by the TLB hardware
+ * The following bits are implemented by the TLB hardware
  */
 #define _PAGE_GLOBAL_SHIFT	0
 #define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
@@ -48,8 +48,6 @@
 
 /*
  * The following bits are implemented in software
- *
- * _PAGE_FILE semantics: set:pagecache unset:swap
  */
 #define _PAGE_PRESENT_SHIFT	(_CACHE_SHIFT + 3)
 #define _PAGE_PRESENT		(1 << _PAGE_PRESENT_SHIFT)
@@ -62,48 +60,40 @@
 #define _PAGE_MODIFIED_SHIFT	(_PAGE_ACCESSED_SHIFT + 1)
 #define _PAGE_MODIFIED		(1 << _PAGE_MODIFIED_SHIFT)
 
-#define _PAGE_SILENT_READ	_PAGE_VALID
-#define _PAGE_SILENT_WRITE	_PAGE_DIRTY
-#define _PAGE_FILE		_PAGE_MODIFIED
-
 #define _PFN_SHIFT		(PAGE_SHIFT - 12 + _CACHE_SHIFT + 3)
 
 #elif defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
 
 /*
- * The following are implemented by software
- *
- * _PAGE_FILE semantics: set:pagecache unset:swap
+ * The following bits are implemented in software
  */
-#define _PAGE_PRESENT_SHIFT	0
-#define _PAGE_PRESENT		(1 <<  _PAGE_PRESENT_SHIFT)
-#define _PAGE_READ_SHIFT	1
-#define _PAGE_READ		(1 <<  _PAGE_READ_SHIFT)
-#define _PAGE_WRITE_SHIFT	2
-#define _PAGE_WRITE		(1 <<  _PAGE_WRITE_SHIFT)
-#define _PAGE_ACCESSED_SHIFT	3
-#define _PAGE_ACCESSED		(1 <<  _PAGE_ACCESSED_SHIFT)
-#define _PAGE_MODIFIED_SHIFT	4
-#define _PAGE_MODIFIED		(1 <<  _PAGE_MODIFIED_SHIFT)
-#define _PAGE_FILE_SHIFT	4
-#define _PAGE_FILE		(1 <<  _PAGE_FILE_SHIFT)
+#define _PAGE_PRESENT_SHIFT	(0)
+#define _PAGE_PRESENT		(1 << _PAGE_PRESENT_SHIFT)
+#define _PAGE_READ_SHIFT	(_PAGE_PRESENT_SHIFT + 1)
+#define _PAGE_READ		(1 << _PAGE_READ_SHIFT)
+#define _PAGE_WRITE_SHIFT	(_PAGE_READ_SHIFT + 1)
+#define _PAGE_WRITE		(1 << _PAGE_WRITE_SHIFT)
+#define _PAGE_ACCESSED_SHIFT	(_PAGE_WRITE_SHIFT + 1)
+#define _PAGE_ACCESSED		(1 << _PAGE_ACCESSED_SHIFT)
+#define _PAGE_MODIFIED_SHIFT	(_PAGE_ACCESSED_SHIFT + 1)
+#define _PAGE_MODIFIED		(1 << _PAGE_MODIFIED_SHIFT)
 
 /*
- * And these are the hardware TLB bits
+ * The following bits are implemented by the TLB hardware
  */
-#define _PAGE_GLOBAL_SHIFT	8
-#define _PAGE_GLOBAL		(1 <<  _PAGE_GLOBAL_SHIFT)
-#define _PAGE_VALID_SHIFT	9
-#define _PAGE_VALID		(1 <<  _PAGE_VALID_SHIFT)
-#define _PAGE_SILENT_READ	(1 <<  _PAGE_VALID_SHIFT)	/* synonym  */
-#define _PAGE_DIRTY_SHIFT	10
+#define _PAGE_GLOBAL_SHIFT	(_PAGE_MODIFIED_SHIFT + 4)
+#define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
+#define _PAGE_VALID_SHIFT	(_PAGE_GLOBAL_SHIFT + 1)
+#define _PAGE_VALID		(1 << _PAGE_VALID_SHIFT)
+#define _PAGE_DIRTY_SHIFT	(_PAGE_VALID_SHIFT + 1)
 #define _PAGE_DIRTY		(1 << _PAGE_DIRTY_SHIFT)
-#define _PAGE_SILENT_WRITE	(1 << _PAGE_DIRTY_SHIFT)
-#define _CACHE_UNCACHED_SHIFT	11
+#define _CACHE_UNCACHED_SHIFT	(_PAGE_DIRTY_SHIFT + 1)
 #define _CACHE_UNCACHED		(1 << _CACHE_UNCACHED_SHIFT)
-#define _CACHE_MASK		(1 << _CACHE_UNCACHED_SHIFT)
+#define _CACHE_MASK		_CACHE_UNCACHED
+
+#define _PFN_SHIFT		PAGE_SHIFT
 
-#else /* 'Normal' r4K case */
+#else
 /*
  * When using the RI/XI bit support, we have 13 bits of flags below
  * the physical address. The RI/XI bits are placed such that a SRL 5
@@ -114,11 +104,8 @@
 
 /*
  * The following bits are implemented in software
- *
- * _PAGE_READ / _PAGE_READ_SHIFT should be unused if cpu_has_rixi.
- * _PAGE_FILE semantics: set:pagecache unset:swap
  */
-#define _PAGE_PRESENT_SHIFT	(0)
+#define _PAGE_PRESENT_SHIFT	0
 #define _PAGE_PRESENT		(1 << _PAGE_PRESENT_SHIFT)
 #define _PAGE_READ_SHIFT	(cpu_has_rixi ? _PAGE_PRESENT_SHIFT : _PAGE_PRESENT_SHIFT + 1)
 #define _PAGE_READ ({BUG_ON(cpu_has_rixi); 1 << _PAGE_READ_SHIFT; })
@@ -128,22 +115,16 @@
 #define _PAGE_ACCESSED		(1 << _PAGE_ACCESSED_SHIFT)
 #define _PAGE_MODIFIED_SHIFT	(_PAGE_ACCESSED_SHIFT + 1)
 #define _PAGE_MODIFIED		(1 << _PAGE_MODIFIED_SHIFT)
-#define _PAGE_FILE		(_PAGE_MODIFIED)
 
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 /* huge tlb page */
 #define _PAGE_HUGE_SHIFT	(_PAGE_MODIFIED_SHIFT + 1)
 #define _PAGE_HUGE		(1 << _PAGE_HUGE_SHIFT)
-#else
-#define _PAGE_HUGE_SHIFT	(_PAGE_MODIFIED_SHIFT)
-#define _PAGE_HUGE		({BUG(); 1; })	/* Dummy value */
-#endif
-
-#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
-/* huge tlb page */
 #define _PAGE_SPLITTING_SHIFT	(_PAGE_HUGE_SHIFT + 1)
 #define _PAGE_SPLITTING		(1 << _PAGE_SPLITTING_SHIFT)
 #else
+#define _PAGE_HUGE_SHIFT	(_PAGE_MODIFIED_SHIFT)
+#define _PAGE_HUGE		({BUG(); 1; })	/* Dummy value */
 #define _PAGE_SPLITTING_SHIFT	(_PAGE_HUGE_SHIFT)
 #define _PAGE_SPLITTING		({BUG(); 1; })	/* Dummy value */
 #endif
@@ -158,17 +139,10 @@
 
 #define _PAGE_GLOBAL_SHIFT	(_PAGE_NO_READ_SHIFT + 1)
 #define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
-
 #define _PAGE_VALID_SHIFT	(_PAGE_GLOBAL_SHIFT + 1)
 #define _PAGE_VALID		(1 << _PAGE_VALID_SHIFT)
-/* synonym		   */
-#define _PAGE_SILENT_READ	(_PAGE_VALID)
-
-/* The MIPS dirty bit	   */
 #define _PAGE_DIRTY_SHIFT	(_PAGE_VALID_SHIFT + 1)
 #define _PAGE_DIRTY		(1 << _PAGE_DIRTY_SHIFT)
-#define _PAGE_SILENT_WRITE	(_PAGE_DIRTY)
-
 #define _CACHE_SHIFT		(_PAGE_DIRTY_SHIFT + 1)
 #define _CACHE_MASK		(7 << _CACHE_SHIFT)
 
@@ -176,9 +150,13 @@
 
 #endif /* defined(CONFIG_PHYS_ADDR_T_64BIT && defined(CONFIG_CPU_MIPS32) */
 
-#ifndef _PFN_SHIFT
-#define _PFN_SHIFT		    PAGE_SHIFT
-#endif
+/*
+ * _PAGE_FILE semantics: set:pagecache unset:swap
+ */
+#define _PAGE_FILE		_PAGE_MODIFIED
+#define _PAGE_SILENT_READ	_PAGE_VALID
+#define _PAGE_SILENT_WRITE	_PAGE_DIRTY
+
 #define _PFN_MASK		(~((1 << (_PFN_SHIFT)) - 1))
 
 #ifndef _PAGE_NO_READ
@@ -188,9 +166,6 @@
 #ifndef _PAGE_NO_EXEC
 #define _PAGE_NO_EXEC ({BUG(); 0; })
 #endif
-#ifndef _PAGE_GLOBAL_SHIFT
-#define _PAGE_GLOBAL_SHIFT ilog2(_PAGE_GLOBAL)
-#endif
 
 
 #ifndef __ASSEMBLY__
@@ -275,8 +250,9 @@ static inline uint64_t pte_to_entrylo(unsigned long pte_val)
 #endif
 
 #define __READABLE	(_PAGE_SILENT_READ | _PAGE_ACCESSED | (cpu_has_rixi ? 0 : _PAGE_READ))
-#define __WRITEABLE	(_PAGE_WRITE | _PAGE_SILENT_WRITE | _PAGE_MODIFIED)
+#define __WRITEABLE	(_PAGE_SILENT_WRITE | _PAGE_WRITE | _PAGE_MODIFIED)
 
-#define _PAGE_CHG_MASK	(_PFN_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED | _CACHE_MASK)
+#define _PAGE_CHG_MASK	(_PAGE_ACCESSED | _PAGE_MODIFIED |	\
+			 _PFN_MASK | _CACHE_MASK)
 
 #endif /* _ASM_PGTABLE_BITS_H */
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 845016d1cdbd..3435e84356a5 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -344,7 +344,7 @@ static inline pte_t pte_mkyoung(pte_t pte)
 	return pte;
 }
 
-#ifdef _PAGE_HUGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 static inline int pte_huge(pte_t pte)	{ return pte_val(pte) & _PAGE_HUGE; }
 
 static inline pte_t pte_mkhuge(pte_t pte)
@@ -352,7 +352,7 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	pte_val(pte) |= _PAGE_HUGE;
 	return pte;
 }
-#endif /* _PAGE_HUGE */
+#endif /* CONFIG_MIPS_HUGE_TLB_SUPPORT */
 #endif
 static inline int pte_special(pte_t pte)	{ return 0; }
 static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
-- 
cgit v1.2.3


From a5770df09541f88021390375f324b25124675355 Mon Sep 17 00:00:00 2001
From: "Steven J. Hill" <Steven.Hill@imgtec.com>
Date: Thu, 19 Feb 2015 10:18:52 -0600
Subject: MIPS: Add set/clear CP0 macros for PageGrain register

Build set and clear macros for the PageGrain register.

Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/9289/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/mipsregs.h | 1 +
 arch/mips/kernel/cpu-probe.c     | 2 +-
 arch/mips/mm/tlb-r4k.c           | 6 +++---
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 06346001ee4d..235469a23e99 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1897,6 +1897,7 @@ __BUILD_SET_C0(config5)
 __BUILD_SET_C0(intcontrol)
 __BUILD_SET_C0(intctl)
 __BUILD_SET_C0(srsmap)
+__BUILD_SET_C0(pagegrain)
 __BUILD_SET_C0(brcm_config_0)
 __BUILD_SET_C0(brcm_bus_pll)
 __BUILD_SET_C0(brcm_reset)
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 81f0aedbba0f..48dfb9de853d 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -550,7 +550,7 @@ static void decode_configs(struct cpuinfo_mips *c)
 
 	if (cpu_has_rixi) {
 		/* Enable the RIXI exceptions */
-		write_c0_pagegrain(read_c0_pagegrain() | PG_IEC);
+		set_c0_pagegrain(PG_IEC);
 		back_to_back_c0_hazard();
 		/* Verify the IEC bit is set */
 		if (read_c0_pagegrain() & PG_IEC)
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index e90b2e899291..b2afa49beab0 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -485,11 +485,11 @@ static void r4k_tlb_configure(void)
 		 * Enable the no read, no exec bits, and enable large virtual
 		 * address.
 		 */
-		u32 pg = PG_RIE | PG_XIE;
 #ifdef CONFIG_64BIT
-		pg |= PG_ELPA;
+		set_c0_pagegrain(PG_RIE | PG_XIE | PG_ELPA);
+#else
+		set_c0_pagegrain(PG_RIE | PG_XIE);
 #endif
-		write_c0_pagegrain(pg);
 	}
 
 	temp_tlb_entry = current_cpu_data.tlbsize - 1;
-- 
cgit v1.2.3


From 6fb8a163fcb2cc2ee073a1ffda33e402b1092548 Mon Sep 17 00:00:00 2001
From: Zubair Lutfullah Kakakhel <Zubair.Kakakhel@imgtec.com>
Date: Fri, 12 Dec 2014 12:45:39 +0000
Subject: mips: pci: Add ifdef around pci_proc_domain

Without these, there are multiple definitions of pci_proc_domain()
and pci_domain_nr() if linux/pci.h and asm/pci.h are included.

Add #ifdefs around them

Signed-off-by: Zubair Lutfullah Kakakhel <Zubair.Kakakhel@imgtec.com>
Reviewed-by: Markos Chandras <Markos.Chandras@imgtec.com>
Cc: Markos.Chandras@imgtec.com
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8670/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/pci.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 69529624a005..193b4c6b7541 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -121,6 +121,7 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 }
 #endif
 
+#ifdef CONFIG_PCI_DOMAINS
 #define pci_domain_nr(bus) ((struct pci_controller *)(bus)->sysdata)->index
 
 static inline int pci_proc_domain(struct pci_bus *bus)
@@ -128,6 +129,7 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 	struct pci_controller *hose = bus->sysdata;
 	return hose->need_domain_info;
 }
+#endif /* CONFIG_PCI_DOMAINS */
 
 #endif /* __KERNEL__ */
 
-- 
cgit v1.2.3


From fa75da8ecd29a91ffe338cd8f992e6fb1f5ef046 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sun, 11 Jan 2015 17:06:56 +0100
Subject: MIPS: ip22-gio: Remove legacy suspend/resume support

There are currently no gio device drivers that implement suspend/resume
and this patch removes the bus specific legacy suspend and resume callbacks.
This will allow us to eventually remove struct bus_type legacy suspend and
resume support altogether.

gio device drivers wanting to implement suspend and resume can use dev PM
ops which will work out of the box without further modifications necessary.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/8920/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/gio_device.h |  2 --
 arch/mips/sgi-ip22/ip22-gio.c      | 24 ------------------------
 2 files changed, 26 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/gio_device.h b/arch/mips/include/asm/gio_device.h
index 4be1a57cdbb0..71a986e9b694 100644
--- a/arch/mips/include/asm/gio_device.h
+++ b/arch/mips/include/asm/gio_device.h
@@ -25,8 +25,6 @@ struct gio_driver {
 
 	int  (*probe)(struct gio_device *, const struct gio_device_id *);
 	void (*remove)(struct gio_device *);
-	int  (*suspend)(struct gio_device *, pm_message_t);
-	int  (*resume)(struct gio_device *);
 	void (*shutdown)(struct gio_device *);
 
 	struct device_driver driver;
diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c
index 8f1b86d4da84..cdf187600010 100644
--- a/arch/mips/sgi-ip22/ip22-gio.c
+++ b/arch/mips/sgi-ip22/ip22-gio.c
@@ -152,28 +152,6 @@ static int gio_device_remove(struct device *dev)
 	return 0;
 }
 
-static int gio_device_suspend(struct device *dev, pm_message_t state)
-{
-	struct gio_device *gio_dev = to_gio_device(dev);
-	struct gio_driver *drv = to_gio_driver(dev->driver);
-	int error = 0;
-
-	if (dev->driver && drv->suspend)
-		error = drv->suspend(gio_dev, state);
-	return error;
-}
-
-static int gio_device_resume(struct device *dev)
-{
-	struct gio_device *gio_dev = to_gio_device(dev);
-	struct gio_driver *drv = to_gio_driver(dev->driver);
-	int error = 0;
-
-	if (dev->driver && drv->resume)
-		error = drv->resume(gio_dev);
-	return error;
-}
-
 static void gio_device_shutdown(struct device *dev)
 {
 	struct gio_device *gio_dev = to_gio_device(dev);
@@ -400,8 +378,6 @@ static struct bus_type gio_bus_type = {
 	.match	   = gio_bus_match,
 	.probe	   = gio_device_probe,
 	.remove	   = gio_device_remove,
-	.suspend   = gio_device_suspend,
-	.resume	   = gio_device_resume,
 	.shutdown  = gio_device_shutdown,
 	.uevent	   = gio_device_uevent,
 };
-- 
cgit v1.2.3


From 151f9148d1af9ed3b5e29ab49800b0669bfe6a6a Mon Sep 17 00:00:00 2001
From: David Daney <david.daney@cavium.com>
Date: Thu, 18 Dec 2014 13:59:53 +0300
Subject: MIPS: Remove unneeded #ifdef __KERNEL__ from asm/processor.h

Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8737/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/processor.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 9daa38608cd8..be903acf4fe4 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -54,9 +54,7 @@ extern unsigned int vced_count, vcei_count;
 #define TASK_SIZE	0x7fff8000UL
 #endif
 
-#ifdef __KERNEL__
 #define STACK_TOP_MAX	TASK_SIZE
-#endif
 
 #define TASK_IS_32BIT_ADDR 1
 
@@ -73,11 +71,7 @@ extern unsigned int vced_count, vcei_count;
 #define TASK_SIZE32	0x7fff8000UL
 #define TASK_SIZE64	0x10000000000UL
 #define TASK_SIZE (test_thread_flag(TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE64)
-
-#ifdef __KERNEL__
 #define STACK_TOP_MAX	TASK_SIZE64
-#endif
-
 
 #define TASK_SIZE_OF(tsk)						\
 	(test_tsk_thread_flag(tsk, TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE64)
-- 
cgit v1.2.3


From ac655fb7626ea63b12ee5f449a082c79db6d2f26 Mon Sep 17 00:00:00 2001
From: David Daney <david.daney@cavium.com>
Date: Thu, 15 Jan 2015 16:11:05 +0300
Subject: MIPS: OCTEON: Save/Restore wider multiply registers in OCTEON III
 CPUs

The wide multiplier is twice as wide, so we need to save twice as much
state.  Detect the multiplier type (CPU type) at start up and install
model specific handlers.

[aleksey.makarov@auriga.com:
	conflict resolution,
	support for old compilers]

Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Leonid Rosenboim <lrosenboim@caviumnetworks.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8933/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/cavium-octeon/setup.c       |  37 ++++++++++
 arch/mips/include/asm/octeon/octeon.h |  13 ++++
 arch/mips/include/asm/ptrace.h        |   4 +-
 arch/mips/kernel/octeon_switch.S      | 128 ++++++++++++++++++++++++++--------
 4 files changed, 150 insertions(+), 32 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 94f888d3384e..2d8a53100e41 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -615,6 +615,7 @@ void __init prom_init(void)
 	const char *arg;
 	char *p;
 	int i;
+	u64 t;
 	int argc;
 #ifdef CONFIG_CAVIUM_RESERVE32
 	int64_t addr = -1;
@@ -663,6 +664,42 @@ void __init prom_init(void)
 		octeon_io_clock_rate = sysinfo->cpu_clock_hz;
 	}
 
+	t = read_c0_cvmctl();
+	if ((t & (1ull << 27)) == 0) {
+		/*
+		 * Setup the multiplier save/restore code if
+		 * CvmCtl[NOMUL] clear.
+		 */
+		void *save;
+		void *save_end;
+		void *restore;
+		void *restore_end;
+		int save_len;
+		int restore_len;
+		int save_max = (char *)octeon_mult_save_end -
+			(char *)octeon_mult_save;
+		int restore_max = (char *)octeon_mult_restore_end -
+			(char *)octeon_mult_restore;
+		if (current_cpu_data.cputype == CPU_CAVIUM_OCTEON3) {
+			save = octeon_mult_save3;
+			save_end = octeon_mult_save3_end;
+			restore = octeon_mult_restore3;
+			restore_end = octeon_mult_restore3_end;
+		} else {
+			save = octeon_mult_save2;
+			save_end = octeon_mult_save2_end;
+			restore = octeon_mult_restore2;
+			restore_end = octeon_mult_restore2_end;
+		}
+		save_len = (char *)save_end - (char *)save;
+		restore_len = (char *)restore_end - (char *)restore;
+		if (!WARN_ON(save_len > save_max ||
+				restore_len > restore_max)) {
+			memcpy(octeon_mult_save, save, save_len);
+			memcpy(octeon_mult_restore, restore, restore_len);
+		}
+	}
+
 	/*
 	 * Only enable the LED controller if we're running on a CN38XX, CN58XX,
 	 * or CN56XX. The CN30XX and CN31XX don't have an LED controller.
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index d781f9e66884..3e505a272189 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -229,6 +229,19 @@ static inline void octeon_npi_write32(uint64_t address, uint32_t val)
 	cvmx_read64_uint32(address ^ 4);
 }
 
+/* Octeon multiplier save/restore routines from octeon_switch.S */
+void octeon_mult_save(void);
+void octeon_mult_restore(void);
+void octeon_mult_save_end(void);
+void octeon_mult_restore_end(void);
+void octeon_mult_save3(void);
+void octeon_mult_save3_end(void);
+void octeon_mult_save2(void);
+void octeon_mult_save2_end(void);
+void octeon_mult_restore3(void);
+void octeon_mult_restore3_end(void);
+void octeon_mult_restore2(void);
+void octeon_mult_restore2_end(void);
 
 /**
  * Read a 32bit value from the Octeon NPI register space
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index fc783f843bdc..ffc320389f40 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -40,8 +40,8 @@ struct pt_regs {
 	unsigned long cp0_cause;
 	unsigned long cp0_epc;
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
-	unsigned long long mpl[3];	  /* MTM{0,1,2} */
-	unsigned long long mtp[3];	  /* MTP{0,1,2} */
+	unsigned long long mpl[6];        /* MTM{0-5} */
+	unsigned long long mtp[6];        /* MTP{0-5} */
 #endif
 } __aligned(8);
 
diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S
index f6547680c81c..3dec1e8becf0 100644
--- a/arch/mips/kernel/octeon_switch.S
+++ b/arch/mips/kernel/octeon_switch.S
@@ -450,18 +450,23 @@ done_restore:
  * void octeon_mult_save()
  * sp is assumed to point to a struct pt_regs
  *
- * NOTE: This is called in SAVE_SOME in stackframe.h. It can only
- *	 safely modify k0 and k1.
+ * NOTE: This is called in SAVE_TEMP in stackframe.h. It can
+ *       safely modify v1,k0, k1,$10-$15, and $24.  It will
+ *	 be overwritten with a processor specific version of the code.
  */
-	.align	7
+	.p2align 7
 	.set push
 	.set noreorder
 	LEAF(octeon_mult_save)
-	dmfc0	k0, $9,7	/* CvmCtl register. */
-	bbit1	k0, 27, 1f	/* Skip CvmCtl[NOMUL] */
+	jr	ra
 	 nop
+	.space 30 * 4, 0
+octeon_mult_save_end:
+	EXPORT(octeon_mult_save_end)
+	END(octeon_mult_save)
 
-	/* Save the multiplier state */
+	LEAF(octeon_mult_save2)
+	/* Save the multiplier state OCTEON II and earlier*/
 	v3mulu	k0, $0, $0
 	v3mulu	k1, $0, $0
 	sd	k0, PT_MTP(sp)	      /* PT_MTP	   has P0 */
@@ -476,44 +481,107 @@ done_restore:
 	sd	k0, PT_MPL+8(sp)      /* PT_MPL+8  has MPL1 */
 	jr	ra
 	 sd	k1, PT_MPL+16(sp)     /* PT_MPL+16 has MPL2 */
-
-1:	/* Resume here if CvmCtl[NOMUL] */
+octeon_mult_save2_end:
+	EXPORT(octeon_mult_save2_end)
+	END(octeon_mult_save2)
+
+	LEAF(octeon_mult_save3)
+	/* Save the multiplier state OCTEON III */
+	v3mulu	$10, $0, $0		/* read P0 */
+	v3mulu	$11, $0, $0		/* read P1 */
+	v3mulu	$12, $0, $0		/* read P2 */
+	sd	$10, PT_MTP+(0*8)(sp)	/* store P0 */
+	v3mulu	$10, $0, $0		/* read P3 */
+	sd	$11, PT_MTP+(1*8)(sp)	/*  store P1 */
+	v3mulu	$11, $0, $0		/* read P4 */
+	sd	$12, PT_MTP+(2*8)(sp)	/* store P2 */
+	ori	$13, $0, 1
+	v3mulu	$12, $0, $0		/* read P5 */
+	sd	$10, PT_MTP+(3*8)(sp)	/* store P3 */
+	v3mulu	$13, $13, $0		/* P4-P0 = MPL5-MPL1, $13 = MPL0 */
+	sd	$11, PT_MTP+(4*8)(sp)	/* store P4 */
+	v3mulu	$10, $0, $0		/* read MPL1 */
+	sd	$12, PT_MTP+(5*8)(sp)	/* store P5 */
+	v3mulu	$11, $0, $0		/* read MPL2 */
+	sd	$13, PT_MPL+(0*8)(sp)	/* store MPL0 */
+	v3mulu	$12, $0, $0		/* read MPL3 */
+	sd	$10, PT_MPL+(1*8)(sp)	/* store MPL1 */
+	v3mulu	$10, $0, $0		/* read MPL4 */
+	sd	$11, PT_MPL+(2*8)(sp)	/* store MPL2 */
+	v3mulu	$11, $0, $0		/* read MPL5 */
+	sd	$12, PT_MPL+(3*8)(sp)	/* store MPL3 */
+	sd	$10, PT_MPL+(4*8)(sp)	/* store MPL4 */
 	jr	ra
-	END(octeon_mult_save)
+	 sd	$11, PT_MPL+(5*8)(sp)	/* store MPL5 */
+octeon_mult_save3_end:
+	EXPORT(octeon_mult_save3_end)
+	END(octeon_mult_save3)
 	.set pop
 
 /*
  * void octeon_mult_restore()
  * sp is assumed to point to a struct pt_regs
  *
- * NOTE: This is called in RESTORE_SOME in stackframe.h.
+ * NOTE: This is called in RESTORE_TEMP in stackframe.h.
  */
-	.align	7
+	.p2align 7
 	.set push
 	.set noreorder
 	LEAF(octeon_mult_restore)
-	dmfc0	k1, $9,7		/* CvmCtl register. */
-	ld	v0, PT_MPL(sp)		/* MPL0 */
-	ld	v1, PT_MPL+8(sp)	/* MPL1 */
-	ld	k0, PT_MPL+16(sp)	/* MPL2 */
-	bbit1	k1, 27, 1f		/* Skip CvmCtl[NOMUL] */
-	/* Normally falls through, so no time wasted here */
-	nop
+	jr	ra
+	 nop
+	.space 30 * 4, 0
+octeon_mult_restore_end:
+	EXPORT(octeon_mult_restore_end)
+	END(octeon_mult_restore)
 
+	LEAF(octeon_mult_restore2)
+	ld	v0, PT_MPL(sp)        	/* MPL0 */
+	ld	v1, PT_MPL+8(sp)      	/* MPL1 */
+	ld	k0, PT_MPL+16(sp)     	/* MPL2 */
 	/* Restore the multiplier state */
-	ld	k1, PT_MTP+16(sp)	/* P2 */
-	MTM0	v0			/* MPL0 */
+	ld	k1, PT_MTP+16(sp)     	/* P2 */
+	mtm0	v0			/* MPL0 */
 	ld	v0, PT_MTP+8(sp)	/* P1 */
-	MTM1	v1			/* MPL1 */
-	ld	v1, PT_MTP(sp)		/* P0 */
-	MTM2	k0			/* MPL2 */
-	MTP2	k1			/* P2 */
-	MTP1	v0			/* P1 */
+	mtm1	v1			/* MPL1 */
+	ld	v1, PT_MTP(sp)   	/* P0 */
+	mtm2	k0			/* MPL2 */
+	mtp2	k1			/* P2 */
+	mtp1	v0			/* P1 */
 	jr	ra
-	 MTP0	v1			/* P0 */
-
-1:	/* Resume here if CvmCtl[NOMUL] */
+	 mtp0	v1			/* P0 */
+octeon_mult_restore2_end:
+	EXPORT(octeon_mult_restore2_end)
+	END(octeon_mult_restore2)
+
+	LEAF(octeon_mult_restore3)
+	ld	$12, PT_MPL+(0*8)(sp)	/* read MPL0 */
+	ld	$13, PT_MPL+(3*8)(sp)	/* read MPL3 */
+	ld	$10, PT_MPL+(1*8)(sp)	/* read MPL1 */
+	ld	$11, PT_MPL+(4*8)(sp)	/* read MPL4 */
+	.word	0x718d0008
+	/* mtm0	$12, $13		   restore MPL0 and MPL3 */
+	ld	$12, PT_MPL+(2*8)(sp)	/* read MPL2 */
+	.word	0x714b000c
+	/* mtm1	$10, $11		   restore MPL1 and MPL4 */
+	ld	$13, PT_MPL+(5*8)(sp)	/* read MPL5 */
+	ld	$10, PT_MTP+(0*8)(sp)	/* read P0 */
+	ld	$11, PT_MTP+(3*8)(sp)	/* read P3 */
+	.word	0x718d000d
+	/* mtm2	$12, $13		   restore MPL2 and MPL5 */
+	ld	$12, PT_MTP+(1*8)(sp)	/* read P1 */
+	.word	0x714b0009
+	/* mtp0	$10, $11		   restore P0 and P3 */
+	ld	$13, PT_MTP+(4*8)(sp)	/* read P4 */
+	ld	$10, PT_MTP+(2*8)(sp)	/* read P2 */
+	ld	$11, PT_MTP+(5*8)(sp)	/* read P5 */
+	.word	0x718d000a
+	/* mtp1	$12, $13		   restore P1 and P4 */
 	jr	ra
-	 nop
-	END(octeon_mult_restore)
+	.word	0x714b000b
+	/* mtp2	$10, $11		   restore P2 and P5 */
+
+octeon_mult_restore3_end:
+	EXPORT(octeon_mult_restore3_end)
+	END(octeon_mult_restore3)
 	.set pop
-- 
cgit v1.2.3


From 6b3a287e6351b00df6624b41c160e1c0817f40e2 Mon Sep 17 00:00:00 2001
From: David Daney <david.daney@cavium.com>
Date: Thu, 15 Jan 2015 16:11:07 +0300
Subject: MIPS: OCTEON: Save and restore CP2 SHA3 state

Allocate new save space, and then save/restore the registers if
OCTEON III.

Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8935/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/processor.h |  2 ++
 arch/mips/kernel/asm-offsets.c    |  1 +
 arch/mips/kernel/octeon_switch.S  | 43 +++++++++++++++++++++++++++++----------
 3 files changed, 35 insertions(+), 11 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index be903acf4fe4..b5dcbee01fd7 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -205,6 +205,8 @@ struct octeon_cop2_state {
 	unsigned long	cop2_gfm_poly;
 	/* DMFC2 rt, 0x025A; DMFC2 rt, 0x025B - Pass2 */
 	unsigned long	cop2_gfm_result[2];
+	/* DMFC2 rt, 0x24F, DMFC2 rt, 0x50, OCTEON III */
+	unsigned long	cop2_sha3[2];
 };
 #define COP2_INIT						\
 	.cp2			= {0,},
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index 7b6c11aa1cae..dad6ce602a7c 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -383,6 +383,7 @@ void output_octeon_cop2_state_defines(void)
 	OFFSET(OCTEON_CP2_GFM_RESULT,	octeon_cop2_state, cop2_gfm_result);
 	OFFSET(OCTEON_CP2_HSH_DATW,	octeon_cop2_state, cop2_hsh_datw);
 	OFFSET(OCTEON_CP2_HSH_IVW,	octeon_cop2_state, cop2_hsh_ivw);
+	OFFSET(OCTEON_CP2_SHA3,		octeon_cop2_state, cop2_sha3);
 	OFFSET(THREAD_CP2,	task_struct, thread.cp2);
 	OFFSET(THREAD_CVMSEG,	task_struct, thread.cvmseg.cvmseg);
 	BLANK();
diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S
index 2787c014ec56..590ca2d56b6a 100644
--- a/arch/mips/kernel/octeon_switch.S
+++ b/arch/mips/kernel/octeon_switch.S
@@ -142,6 +142,8 @@
  * void octeon_cop2_save(struct octeon_cop2_state *a0)
  */
 	.align	7
+	.set push
+	.set noreorder
 	LEAF(octeon_cop2_save)
 
 	dmfc0	t9, $9,7	/* CvmCtl register. */
@@ -152,17 +154,17 @@
 	dmfc2	t2, 0x0200
 	sd	t0, OCTEON_CP2_CRC_IV(a0)
 	sd	t1, OCTEON_CP2_CRC_LENGTH(a0)
-	sd	t2, OCTEON_CP2_CRC_POLY(a0)
 	/* Skip next instructions if CvmCtl[NODFA_CP2] set */
 	bbit1	t9, 28, 1f
+	 sd	t2, OCTEON_CP2_CRC_POLY(a0)
 
 	/* Save the LLM state */
 	dmfc2	t0, 0x0402
 	dmfc2	t1, 0x040A
 	sd	t0, OCTEON_CP2_LLM_DAT(a0)
-	sd	t1, OCTEON_CP2_LLM_DAT+8(a0)
 
 1:	bbit1	t9, 26, 3f	/* done if CvmCtl[NOCRYPTO] set */
+	 sd	t1, OCTEON_CP2_LLM_DAT+8(a0)
 
 	/* Save the COP2 crypto state */
 	/* this part is mostly common to both pass 1 and later revisions */
@@ -193,18 +195,20 @@
 	sd	t2, OCTEON_CP2_AES_KEY+16(a0)
 	dmfc2	t2, 0x0101
 	sd	t3, OCTEON_CP2_AES_KEY+24(a0)
-	mfc0	t3, $15,0	/* Get the processor ID register */
+	mfc0	v0, $15,0	/* Get the processor ID register */
 	sd	t0, OCTEON_CP2_AES_KEYLEN(a0)
-	li	t0, 0x000d0000	/* This is the processor ID of Octeon Pass1 */
+	li	v1, 0x000d0000	/* This is the processor ID of Octeon Pass1 */
 	sd	t1, OCTEON_CP2_AES_RESULT(a0)
-	sd	t2, OCTEON_CP2_AES_RESULT+8(a0)
 	/* Skip to the Pass1 version of the remainder of the COP2 state */
-	beq	t3, t0, 2f
+	beq	v0, v1, 2f
+	 sd	t2, OCTEON_CP2_AES_RESULT+8(a0)
 
 	/* the non-pass1 state when !CvmCtl[NOCRYPTO] */
 	dmfc2	t1, 0x0240
 	dmfc2	t2, 0x0241
+	ori	v1, v1, 0x9500 /* lowest OCTEON III PrId*/
 	dmfc2	t3, 0x0242
+	subu	v1, v0, v1 /* prid - lowest OCTEON III PrId */
 	dmfc2	t0, 0x0243
 	sd	t1, OCTEON_CP2_HSH_DATW(a0)
 	dmfc2	t1, 0x0244
@@ -257,8 +261,16 @@
 	sd	t1, OCTEON_CP2_GFM_MULT+8(a0)
 	sd	t2, OCTEON_CP2_GFM_POLY(a0)
 	sd	t3, OCTEON_CP2_GFM_RESULT(a0)
-	sd	t0, OCTEON_CP2_GFM_RESULT+8(a0)
+	bltz	v1, 4f
+	 sd	t0, OCTEON_CP2_GFM_RESULT+8(a0)
+	/* OCTEON III things*/
+	dmfc2	t0, 0x024F
+	dmfc2	t1, 0x0050
+	sd	t0, OCTEON_CP2_SHA3(a0)
+	sd	t1, OCTEON_CP2_SHA3+8(a0)
+4:
 	jr	ra
+	 nop
 
 2:	/* pass 1 special stuff when !CvmCtl[NOCRYPTO] */
 	dmfc2	t3, 0x0040
@@ -284,7 +296,9 @@
 
 3:	/* pass 1 or CvmCtl[NOCRYPTO] set */
 	jr	ra
+	 nop
 	END(octeon_cop2_save)
+	.set pop
 
 /*
  * void octeon_cop2_restore(struct octeon_cop2_state *a0)
@@ -349,9 +363,9 @@
 	ld	t2, OCTEON_CP2_AES_RESULT+8(a0)
 	mfc0	t3, $15,0	/* Get the processor ID register */
 	dmtc2	t0, 0x0110
-	li	t0, 0x000d0000	/* This is the processor ID of Octeon Pass1 */
+	li	v0, 0x000d0000	/* This is the processor ID of Octeon Pass1 */
 	dmtc2	t1, 0x0100
-	bne	t0, t3, 3f	/* Skip the next stuff for non-pass1 */
+	bne	v0, t3, 3f	/* Skip the next stuff for non-pass1 */
 	 dmtc2	t2, 0x0101
 
 	/* this code is specific for pass 1 */
@@ -379,6 +393,7 @@
 
 3:	/* this is post-pass1 code */
 	ld	t2, OCTEON_CP2_HSH_DATW(a0)
+	ori	v0, v0, 0x9500 /* lowest OCTEON III PrId*/
 	ld	t0, OCTEON_CP2_HSH_DATW+8(a0)
 	ld	t1, OCTEON_CP2_HSH_DATW+16(a0)
 	dmtc2	t2, 0x0240
@@ -432,9 +447,15 @@
 	dmtc2	t2, 0x0259
 	ld	t2, OCTEON_CP2_GFM_RESULT+8(a0)
 	dmtc2	t0, 0x025E
+	subu	v0, t3, v0 /* prid - lowest OCTEON III PrId */
 	dmtc2	t1, 0x025A
-	dmtc2	t2, 0x025B
-
+	bltz	v0, done_restore
+	 dmtc2	t2, 0x025B
+	/* OCTEON III things*/
+	ld	t0, OCTEON_CP2_SHA3(a0)
+	ld	t1, OCTEON_CP2_SHA3+8(a0)
+	dmtc2	t0, 0x0051
+	dmtc2	t1, 0x0050
 done_restore:
 	jr	ra
 	 nop
-- 
cgit v1.2.3


From 664d699af24ee73cbc147c4c0f76c8c8ff9ef66f Mon Sep 17 00:00:00 2001
From: David Daney <david.daney@cavium.com>
Date: Thu, 15 Jan 2015 16:11:10 +0300
Subject: MIPS: OCTEON: Implement the core-16057 workaround

Disable ICache prefetch for certian Octeon II processors.

Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8938/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 .../asm/mach-cavium-octeon/kernel-entry-init.h     | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
index 1668ee57acb9..21732c306635 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
@@ -63,6 +63,28 @@ skip:
 	li	v1, ~(7 << 7)
 	and	v0, v0, v1
 	ori	v0, v0, (6 << 7)
+
+	mfc0	v1, CP0_PRID_REG
+	and	t1, v1, 0xfff8
+	xor	t1, t1, 0x9000		# 63-P1
+	beqz	t1, 4f
+	and	t1, v1, 0xfff8
+	xor	t1, t1, 0x9008		# 63-P2
+	beqz	t1, 4f
+	and	t1, v1, 0xfff8
+	xor	t1, t1, 0x9100		# 68-P1
+	beqz	t1, 4f
+	and	t1, v1, 0xff00
+	xor	t1, t1, 0x9200		# 66-PX
+	bnez	t1, 5f			# Skip WAR for others.
+	and	t1, v1, 0x00ff
+	slti	t1, t1, 2		# 66-P1.2 and later good.
+	beqz	t1, 5f
+
+4:	# core-16057 work around
+	or	v0, v0, 0x2000		# Set IPREF bit.
+
+5:	# No core-16057 work around
 	# Write the cavium control register
 	dmtc0	v0, CP0_CVMCTL_REG
 	sync
-- 
cgit v1.2.3


From 664f1ae53d60943093db9bdb14ac3d95cac4b68c Mon Sep 17 00:00:00 2001
From: David Daney <david.daney@cavium.com>
Date: Thu, 15 Jan 2015 16:11:12 +0300
Subject: MIPS: OCTEON: Add little-endian support to asm/octeon/octeon.h

Also update union octeon_cvmemctl with new OCTEON II fields.

[aleksey.makarov@auriga.com: use __BITFIELD_FIELD]

Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8940/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/octeon/octeon.h | 135 ++++++++++++++++++++++++++--------
 1 file changed, 105 insertions(+), 30 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index 3e505a272189..ba5df5023bae 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -9,6 +9,7 @@
 #define __ASM_OCTEON_OCTEON_H
 
 #include <asm/octeon/cvmx.h>
+#include <asm/bitfield.h>
 
 extern uint64_t octeon_bootmem_alloc_range_phys(uint64_t size,
 						uint64_t alignment,
@@ -58,6 +59,7 @@ extern void octeon_io_clk_delay(unsigned long);
 #define OCTOEN_SERIAL_LEN	20
 
 struct octeon_boot_descriptor {
+#ifdef __BIG_ENDIAN_BITFIELD
 	/* Start of block referenced by assembly code - do not change! */
 	uint32_t desc_version;
 	uint32_t desc_size;
@@ -109,77 +111,149 @@ struct octeon_boot_descriptor {
 	uint8_t mac_addr_base[6];
 	uint8_t mac_addr_count;
 	uint64_t cvmx_desc_vaddr;
+#else
+	uint32_t desc_size;
+	uint32_t desc_version;
+	uint64_t stack_top;
+	uint64_t heap_base;
+	uint64_t heap_end;
+	/* Only used by bootloader */
+	uint64_t entry_point;
+	uint64_t desc_vaddr;
+	/* End of This block referenced by assembly code - do not change! */
+	uint32_t stack_size;
+	uint32_t exception_base_addr;
+	uint32_t argc;
+	uint32_t heap_size;
+	/*
+	 * Argc count for application.
+	 * Warning low bit scrambled in little-endian.
+	 */
+	uint32_t argv[OCTEON_ARGV_MAX_ARGS];
+
+#define  BOOT_FLAG_INIT_CORE		(1 << 0)
+#define  OCTEON_BL_FLAG_DEBUG		(1 << 1)
+#define  OCTEON_BL_FLAG_NO_MAGIC	(1 << 2)
+	/* If set, use uart1 for console */
+#define  OCTEON_BL_FLAG_CONSOLE_UART1	(1 << 3)
+	/* If set, use PCI console */
+#define  OCTEON_BL_FLAG_CONSOLE_PCI	(1 << 4)
+	/* Call exit on break on serial port */
+#define  OCTEON_BL_FLAG_BREAK		(1 << 5)
+
+	uint32_t core_mask;
+	uint32_t flags;
+	/* physical address of free memory descriptor block. */
+	uint32_t phy_mem_desc_addr;
+	/* DRAM size in megabyes. */
+	uint32_t dram_size;
+	/* CPU clock speed, in hz. */
+	uint32_t eclock_hz;
+	/* used to pass flags from app to debugger. */
+	uint32_t debugger_flags_base_addr;
+	/* SPI4 clock in hz. */
+	uint32_t spi_clock_hz;
+	/* DRAM clock speed, in hz. */
+	uint32_t dclock_hz;
+	uint8_t chip_rev_minor;
+	uint8_t chip_rev_major;
+	uint16_t chip_type;
+	uint8_t board_rev_minor;
+	uint8_t board_rev_major;
+	uint16_t board_type;
+
+	uint64_t unused1[4]; /* Not even filled in by bootloader. */
+
+	uint64_t cvmx_desc_vaddr;
+#endif
 };
 
 union octeon_cvmemctl {
 	uint64_t u64;
 	struct {
 		/* RO 1 = BIST fail, 0 = BIST pass */
-		uint64_t tlbbist:1;
+		__BITFIELD_FIELD(uint64_t tlbbist:1,
 		/* RO 1 = BIST fail, 0 = BIST pass */
-		uint64_t l1cbist:1;
+		__BITFIELD_FIELD(uint64_t l1cbist:1,
 		/* RO 1 = BIST fail, 0 = BIST pass */
-		uint64_t l1dbist:1;
+		__BITFIELD_FIELD(uint64_t l1dbist:1,
 		/* RO 1 = BIST fail, 0 = BIST pass */
-		uint64_t dcmbist:1;
+		__BITFIELD_FIELD(uint64_t dcmbist:1,
 		/* RO 1 = BIST fail, 0 = BIST pass */
-		uint64_t ptgbist:1;
+		__BITFIELD_FIELD(uint64_t ptgbist:1,
 		/* RO 1 = BIST fail, 0 = BIST pass */
-		uint64_t wbfbist:1;
+		__BITFIELD_FIELD(uint64_t wbfbist:1,
 		/* Reserved */
-		uint64_t reserved:22;
+		__BITFIELD_FIELD(uint64_t reserved:17,
+		/* OCTEON II - TLB replacement policy: 0 = bitmask LRU; 1 = NLU.
+		 * This field selects between the TLB replacement policies:
+		 * bitmask LRU or NLU. Bitmask LRU maintains a mask of
+		 * recently used TLB entries and avoids them as new entries
+		 * are allocated. NLU simply guarantees that the next
+		 * allocation is not the last used TLB entry. */
+		__BITFIELD_FIELD(uint64_t tlbnlu:1,
+		/* OCTEON II - Selects the bit in the counter used for
+		 * releasing a PAUSE. This counter trips every 2(8+PAUSETIME)
+		 * cycles. If not already released, the cnMIPS II core will
+		 * always release a given PAUSE instruction within
+		 * 2(8+PAUSETIME). If the counter trip happens to line up,
+		 * the cnMIPS II core may release the PAUSE instantly. */
+		__BITFIELD_FIELD(uint64_t pausetime:3,
+		/* OCTEON II - This field is an extension of
+		 * CvmMemCtl[DIDTTO] */
+		__BITFIELD_FIELD(uint64_t didtto2:1,
 		/* R/W If set, marked write-buffer entries time out
 		 * the same as as other entries; if clear, marked
 		 * write-buffer entries use the maximum timeout. */
-		uint64_t dismarkwblongto:1;
+		__BITFIELD_FIELD(uint64_t dismarkwblongto:1,
 		/* R/W If set, a merged store does not clear the
 		 * write-buffer entry timeout state. */
-		uint64_t dismrgclrwbto:1;
+		__BITFIELD_FIELD(uint64_t dismrgclrwbto:1,
 		/* R/W Two bits that are the MSBs of the resultant
 		 * CVMSEG LM word location for an IOBDMA. The other 8
 		 * bits come from the SCRADDR field of the IOBDMA. */
-		uint64_t iobdmascrmsb:2;
+		__BITFIELD_FIELD(uint64_t iobdmascrmsb:2,
 		/* R/W If set, SYNCWS and SYNCS only order marked
 		 * stores; if clear, SYNCWS and SYNCS only order
 		 * unmarked stores. SYNCWSMARKED has no effect when
 		 * DISSYNCWS is set. */
-		uint64_t syncwsmarked:1;
+		__BITFIELD_FIELD(uint64_t syncwsmarked:1,
 		/* R/W If set, SYNCWS acts as SYNCW and SYNCS acts as
 		 * SYNC. */
-		uint64_t dissyncws:1;
+		__BITFIELD_FIELD(uint64_t dissyncws:1,
 		/* R/W If set, no stall happens on write buffer
 		 * full. */
-		uint64_t diswbfst:1;
+		__BITFIELD_FIELD(uint64_t diswbfst:1,
 		/* R/W If set (and SX set), supervisor-level
 		 * loads/stores can use XKPHYS addresses with
 		 * VA<48>==0 */
-		uint64_t xkmemenas:1;
+		__BITFIELD_FIELD(uint64_t xkmemenas:1,
 		/* R/W If set (and UX set), user-level loads/stores
 		 * can use XKPHYS addresses with VA<48>==0 */
-		uint64_t xkmemenau:1;
+		__BITFIELD_FIELD(uint64_t xkmemenau:1,
 		/* R/W If set (and SX set), supervisor-level
 		 * loads/stores can use XKPHYS addresses with
 		 * VA<48>==1 */
-		uint64_t xkioenas:1;
+		__BITFIELD_FIELD(uint64_t xkioenas:1,
 		/* R/W If set (and UX set), user-level loads/stores
 		 * can use XKPHYS addresses with VA<48>==1 */
-		uint64_t xkioenau:1;
+		__BITFIELD_FIELD(uint64_t xkioenau:1,
 		/* R/W If set, all stores act as SYNCW (NOMERGE must
 		 * be set when this is set) RW, reset to 0. */
-		uint64_t allsyncw:1;
+		__BITFIELD_FIELD(uint64_t allsyncw:1,
 		/* R/W If set, no stores merge, and all stores reach
 		 * the coherent bus in order. */
-		uint64_t nomerge:1;
+		__BITFIELD_FIELD(uint64_t nomerge:1,
 		/* R/W Selects the bit in the counter used for DID
 		 * time-outs 0 = 231, 1 = 230, 2 = 229, 3 =
 		 * 214. Actual time-out is between 1x and 2x this
 		 * interval. For example, with DIDTTO=3, expiration
 		 * interval is between 16K and 32K. */
-		uint64_t didtto:2;
+		__BITFIELD_FIELD(uint64_t didtto:2,
 		/* R/W If set, the (mem) CSR clock never turns off. */
-		uint64_t csrckalwys:1;
+		__BITFIELD_FIELD(uint64_t csrckalwys:1,
 		/* R/W If set, mclk never turns off. */
-		uint64_t mclkalwys:1;
+		__BITFIELD_FIELD(uint64_t mclkalwys:1,
 		/* R/W Selects the bit in the counter used for write
 		 * buffer flush time-outs (WBFLT+11) is the bit
 		 * position in an internal counter used to determine
@@ -187,25 +261,26 @@ union octeon_cvmemctl {
 		 * 2x this interval. For example, with WBFLT = 0, a
 		 * write buffer expires between 2K and 4K cycles after
 		 * the write buffer entry is allocated. */
-		uint64_t wbfltime:3;
+		__BITFIELD_FIELD(uint64_t wbfltime:3,
 		/* R/W If set, do not put Istream in the L2 cache. */
-		uint64_t istrnol2:1;
+		__BITFIELD_FIELD(uint64_t istrnol2:1,
 		/* R/W The write buffer threshold. */
-		uint64_t wbthresh:4;
+		__BITFIELD_FIELD(uint64_t wbthresh:4,
 		/* Reserved */
-		uint64_t reserved2:2;
+		__BITFIELD_FIELD(uint64_t reserved2:2,
 		/* R/W If set, CVMSEG is available for loads/stores in
 		 * kernel/debug mode. */
-		uint64_t cvmsegenak:1;
+		__BITFIELD_FIELD(uint64_t cvmsegenak:1,
 		/* R/W If set, CVMSEG is available for loads/stores in
 		 * supervisor mode. */
-		uint64_t cvmsegenas:1;
+		__BITFIELD_FIELD(uint64_t cvmsegenas:1,
 		/* R/W If set, CVMSEG is available for loads/stores in
 		 * user mode. */
-		uint64_t cvmsegenau:1;
+		__BITFIELD_FIELD(uint64_t cvmsegenau:1,
 		/* R/W Size of local memory in cache blocks, 54 (6912
 		 * bytes) is max legal value. */
-		uint64_t lmemsz:6;
+		__BITFIELD_FIELD(uint64_t lmemsz:6,
+		;)))))))))))))))))))))))))))))))))
 	} s;
 };
 
-- 
cgit v1.2.3


From e3d0ead59f6c1167c817ea338dd9395d517940e1 Mon Sep 17 00:00:00 2001
From: David Daney <david.daney@cavium.com>
Date: Thu, 15 Jan 2015 16:11:13 +0300
Subject: MIPS: OCTEON: Implement DCache errata workaround for all CN6XXX

Make messages refer to all CN6XXX.

Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8941/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/cavium-octeon/setup.c                | 7 ++++---
 arch/mips/include/asm/mach-cavium-octeon/war.h | 3 +++
 arch/mips/mm/uasm.c                            | 2 +-
 3 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 2d8a53100e41..6c51ef6d57c7 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -1041,7 +1041,7 @@ EXPORT_SYMBOL(prom_putchar);
 
 void prom_free_prom_memory(void)
 {
-	if (OCTEON_IS_MODEL(OCTEON_CN63XX_PASS1_X)) {
+	if (CAVIUM_OCTEON_DCACHE_PREFETCH_WAR) {
 		/* Check for presence of Core-14449 fix.  */
 		u32 insn;
 		u32 *foo;
@@ -1063,8 +1063,9 @@ void prom_free_prom_memory(void)
 			panic("No PREF instruction at Core-14449 probe point.");
 
 		if (((insn >> 16) & 0x1f) != 28)
-			panic("Core-14449 WAR not in place (%04x).\n"
-			      "Please build kernel with proper options (CONFIG_CAVIUM_CN63XXP1).", insn);
+			panic("OCTEON II DCache prefetch workaround not in place (%04x).\n"
+			      "Please build kernel with proper options (CONFIG_CAVIUM_CN63XXP1).",
+			      insn);
 	}
 }
 
diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h
index eb72b35cf04b..35c80be92207 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/war.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/war.h
@@ -22,4 +22,7 @@
 #define R10000_LLSC_WAR			0
 #define MIPS34K_MISSED_ITLB_WAR		0
 
+#define CAVIUM_OCTEON_DCACHE_PREFETCH_WAR	\
+	OCTEON_IS_MODEL(OCTEON_CN6XXX)
+
 #endif /* __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H */
diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c
index f86d293463a6..319051c34343 100644
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@@ -341,7 +341,7 @@ I_u3u1u2(_ldx)
 void ISAFUNC(uasm_i_pref)(u32 **buf, unsigned int a, signed int b,
 			    unsigned int c)
 {
-	if (OCTEON_IS_MODEL(OCTEON_CN63XX_PASS1_X) && a <= 24 && a != 5)
+	if (CAVIUM_OCTEON_DCACHE_PREFETCH_WAR && a <= 24 && a != 5)
 		/*
 		 * As per erratum Core-14449, replace prefetches 0-4,
 		 * 6-24 with 'pref 28'.
-- 
cgit v1.2.3


From debe6a623d3cdc7f0374124830587fb8d1a04b63 Mon Sep 17 00:00:00 2001
From: David Daney <david.daney@cavium.com>
Date: Thu, 15 Jan 2015 16:11:14 +0300
Subject: MIPS: OCTEON: Update octeon-model.h code for new SoCs.

Add coverage for OCTEON III models.

Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8942/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/cavium-octeon/dma-octeon.c               |   4 +-
 .../cavium-octeon/executive/cvmx-helper-board.c    |   2 +-
 arch/mips/cavium-octeon/octeon-irq.c               |   2 +-
 arch/mips/cavium-octeon/setup.c                    |   2 +-
 arch/mips/include/asm/octeon/octeon-model.h        | 107 ++++++++++++++++-----
 5 files changed, 90 insertions(+), 27 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 3778655c4a37..7d8987818ccf 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -276,7 +276,7 @@ void __init plat_swiotlb_setup(void)
 			continue;
 
 		/* These addresses map low for PCI. */
-		if (e->addr > 0x410000000ull && !OCTEON_IS_MODEL(OCTEON_CN6XXX))
+		if (e->addr > 0x410000000ull && !OCTEON_IS_OCTEON2())
 			continue;
 
 		addr_size += e->size;
@@ -308,7 +308,7 @@ void __init plat_swiotlb_setup(void)
 #endif
 #ifdef CONFIG_USB_OCTEON_OHCI
 	/* OCTEON II ohci is only 32-bit. */
-	if (OCTEON_IS_MODEL(OCTEON_CN6XXX) && max_addr >= 0x100000000ul)
+	if (OCTEON_IS_OCTEON2() && max_addr >= 0x100000000ul)
 		swiotlbsize = 64 * (1<<20);
 #endif
 	swiotlb_nslabs = swiotlbsize >> IO_TLB_SHIFT;
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c
index 5dfef84b9576..9eb0feef4417 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c
@@ -767,7 +767,7 @@ enum cvmx_helper_board_usb_clock_types __cvmx_helper_board_usb_get_clock_type(vo
 		break;
 	}
 	/* Most boards except NIC10e use a 12MHz crystal */
-	if (OCTEON_IS_MODEL(OCTEON_FAM_2))
+	if (OCTEON_IS_OCTEON2())
 		return USB_CLOCK_TYPE_CRYSTAL_12;
 	return USB_CLOCK_TYPE_REF_48;
 }
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 2bc4aa95944e..01bb01cf49ee 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1210,7 +1210,7 @@ static void __init octeon_irq_init_ciu(void)
 	if (OCTEON_IS_MODEL(OCTEON_CN58XX_PASS2_X) ||
 	    OCTEON_IS_MODEL(OCTEON_CN56XX_PASS2_X) ||
 	    OCTEON_IS_MODEL(OCTEON_CN52XX_PASS2_X) ||
-	    OCTEON_IS_MODEL(OCTEON_CN6XXX)) {
+	    OCTEON_IS_OCTEON2() || OCTEON_IS_OCTEON3()) {
 		chip = &octeon_irq_chip_ciu_v2;
 		chip_mbox = &octeon_irq_chip_ciu_mbox_v2;
 		chip_wd = &octeon_irq_chip_ciu_wd_v2;
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 6c51ef6d57c7..8d2b82327a72 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -655,7 +655,7 @@ void __init prom_init(void)
 	sysinfo->dfa_ref_clock_hz = octeon_bootinfo->dfa_ref_clock_hz;
 	sysinfo->bootloader_config_flags = octeon_bootinfo->config_flags;
 
-	if (OCTEON_IS_MODEL(OCTEON_CN6XXX)) {
+	if (OCTEON_IS_OCTEON2() || OCTEON_IS_OCTEON3()) {
 		/* I/O clock runs at a different rate than the CPU. */
 		union cvmx_mio_rst_boot rst_boot;
 		rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT);
diff --git a/arch/mips/include/asm/octeon/octeon-model.h b/arch/mips/include/asm/octeon/octeon-model.h
index e8a1c2fd52cd..92b377e36dac 100644
--- a/arch/mips/include/asm/octeon/octeon-model.h
+++ b/arch/mips/include/asm/octeon/octeon-model.h
@@ -45,6 +45,7 @@
  */
 
 #define OCTEON_FAMILY_MASK	0x00ffff00
+#define OCTEON_PRID_MASK	0x00ffffff
 
 /* Flag bits in top byte */
 /* Ignores revision in model checks */
@@ -63,11 +64,52 @@
 #define OM_MATCH_6XXX_FAMILY_MODELS	0x40000000
 /* Match all cnf7XXX Octeon models. */
 #define OM_MATCH_F7XXX_FAMILY_MODELS	0x80000000
+/* Match all cn7XXX Octeon models. */
+#define OM_MATCH_7XXX_FAMILY_MODELS     0x10000000
+#define OM_MATCH_FAMILY_MODELS		(OM_MATCH_5XXX_FAMILY_MODELS |	\
+					 OM_MATCH_6XXX_FAMILY_MODELS |	\
+					 OM_MATCH_F7XXX_FAMILY_MODELS | \
+					 OM_MATCH_7XXX_FAMILY_MODELS)
+/*
+ * CN7XXX models with new revision encoding
+ */
+
+#define OCTEON_CN73XX_PASS1_0	0x000d9700
+#define OCTEON_CN73XX		(OCTEON_CN73XX_PASS1_0 | OM_IGNORE_REVISION)
+#define OCTEON_CN73XX_PASS1_X	(OCTEON_CN73XX_PASS1_0 | \
+				 OM_IGNORE_MINOR_REVISION)
+
+#define OCTEON_CN70XX_PASS1_0	0x000d9600
+#define OCTEON_CN70XX_PASS1_1	0x000d9601
+#define OCTEON_CN70XX_PASS1_2	0x000d9602
+
+#define OCTEON_CN70XX_PASS2_0	0x000d9608
+
+#define OCTEON_CN70XX		(OCTEON_CN70XX_PASS1_0 | OM_IGNORE_REVISION)
+#define OCTEON_CN70XX_PASS1_X	(OCTEON_CN70XX_PASS1_0 | \
+				 OM_IGNORE_MINOR_REVISION)
+#define OCTEON_CN70XX_PASS2_X	(OCTEON_CN70XX_PASS2_0 | \
+				 OM_IGNORE_MINOR_REVISION)
+
+#define OCTEON_CN71XX		OCTEON_CN70XX
+
+#define OCTEON_CN78XX_PASS1_0	0x000d9500
+#define OCTEON_CN78XX_PASS1_1	0x000d9501
+#define OCTEON_CN78XX_PASS2_0	0x000d9508
+
+#define OCTEON_CN78XX		(OCTEON_CN78XX_PASS1_0 | OM_IGNORE_REVISION)
+#define OCTEON_CN78XX_PASS1_X	(OCTEON_CN78XX_PASS1_0 | \
+				 OM_IGNORE_MINOR_REVISION)
+#define OCTEON_CN78XX_PASS2_X	(OCTEON_CN78XX_PASS2_0 | \
+				 OM_IGNORE_MINOR_REVISION)
+
+#define OCTEON_CN76XX		(0x000d9540 | OM_CHECK_SUBMODEL)
 
 /*
  * CNF7XXX models with new revision encoding
  */
 #define OCTEON_CNF71XX_PASS1_0	0x000d9400
+#define OCTEON_CNF71XX_PASS1_1  0x000d9401
 
 #define OCTEON_CNF71XX		(OCTEON_CNF71XX_PASS1_0 | OM_IGNORE_REVISION)
 #define OCTEON_CNF71XX_PASS1_X	(OCTEON_CNF71XX_PASS1_0 | OM_IGNORE_MINOR_REVISION)
@@ -79,6 +121,8 @@
 #define OCTEON_CN68XX_PASS1_1	0x000d9101
 #define OCTEON_CN68XX_PASS1_2	0x000d9102
 #define OCTEON_CN68XX_PASS2_0	0x000d9108
+#define OCTEON_CN68XX_PASS2_1   0x000d9109
+#define OCTEON_CN68XX_PASS2_2   0x000d910a
 
 #define OCTEON_CN68XX		(OCTEON_CN68XX_PASS2_0 | OM_IGNORE_REVISION)
 #define OCTEON_CN68XX_PASS1_X	(OCTEON_CN68XX_PASS1_0 | OM_IGNORE_MINOR_REVISION)
@@ -104,11 +148,18 @@
 #define OCTEON_CN63XX_PASS1_X	(OCTEON_CN63XX_PASS1_0 | OM_IGNORE_MINOR_REVISION)
 #define OCTEON_CN63XX_PASS2_X	(OCTEON_CN63XX_PASS2_0 | OM_IGNORE_MINOR_REVISION)
 
+/* CN62XX is same as CN63XX with 1 MB cache */
+#define OCTEON_CN62XX           OCTEON_CN63XX
+
 #define OCTEON_CN61XX_PASS1_0	0x000d9300
+#define OCTEON_CN61XX_PASS1_1   0x000d9301
 
 #define OCTEON_CN61XX		(OCTEON_CN61XX_PASS1_0 | OM_IGNORE_REVISION)
 #define OCTEON_CN61XX_PASS1_X	(OCTEON_CN61XX_PASS1_0 | OM_IGNORE_MINOR_REVISION)
 
+/* CN60XX is same as CN61XX with 512 KB cache */
+#define OCTEON_CN60XX           OCTEON_CN61XX
+
 /*
  * CN5XXX models with new revision encoding
  */
@@ -120,7 +171,7 @@
 #define OCTEON_CN58XX_PASS2_2	0x000d030a
 #define OCTEON_CN58XX_PASS2_3	0x000d030b
 
-#define OCTEON_CN58XX		(OCTEON_CN58XX_PASS1_0 | OM_IGNORE_REVISION)
+#define OCTEON_CN58XX		(OCTEON_CN58XX_PASS2_0 | OM_IGNORE_REVISION)
 #define OCTEON_CN58XX_PASS1_X	(OCTEON_CN58XX_PASS1_0 | OM_IGNORE_MINOR_REVISION)
 #define OCTEON_CN58XX_PASS2_X	(OCTEON_CN58XX_PASS2_0 | OM_IGNORE_MINOR_REVISION)
 #define OCTEON_CN58XX_PASS1	OCTEON_CN58XX_PASS1_X
@@ -217,12 +268,10 @@
 #define OCTEON_CN3XXX		(OCTEON_CN58XX_PASS1_0 | OM_MATCH_PREVIOUS_MODELS | OM_IGNORE_REVISION)
 #define OCTEON_CN5XXX		(OCTEON_CN58XX_PASS1_0 | OM_MATCH_5XXX_FAMILY_MODELS)
 #define OCTEON_CN6XXX		(OCTEON_CN63XX_PASS1_0 | OM_MATCH_6XXX_FAMILY_MODELS)
-
-/* These are used to cover entire families of OCTEON processors */
-#define OCTEON_FAM_1		(OCTEON_CN3XXX)
-#define OCTEON_FAM_PLUS		(OCTEON_CN5XXX)
-#define OCTEON_FAM_1_PLUS	(OCTEON_FAM_PLUS | OM_MATCH_PREVIOUS_MODELS)
-#define OCTEON_FAM_2		(OCTEON_CN6XXX)
+#define OCTEON_CNF7XXX		(OCTEON_CNF71XX_PASS1_0 | \
+				 OM_MATCH_F7XXX_FAMILY_MODELS)
+#define OCTEON_CN7XXX		(OCTEON_CN78XX_PASS1_0 | \
+				 OM_MATCH_7XXX_FAMILY_MODELS)
 
 /* The revision byte (low byte) has two different encodings.
  * CN3XXX:
@@ -232,7 +281,7 @@
  *     <4>:   alternate package
  *     <3:0>: revision
  *
- * CN5XXX:
+ * CN5XXX and older models:
  *
  *     bits
  *     <7>:   reserved (0)
@@ -251,17 +300,21 @@
 /* CN5XXX and later use different layout of bits in the revision ID field */
 #define OCTEON_58XX_FAMILY_MASK	     OCTEON_38XX_FAMILY_MASK
 #define OCTEON_58XX_FAMILY_REV_MASK  0x00ffff3f
-#define OCTEON_58XX_MODEL_MASK	     0x00ffffc0
+#define OCTEON_58XX_MODEL_MASK	     0x00ffff40
 #define OCTEON_58XX_MODEL_REV_MASK   (OCTEON_58XX_FAMILY_REV_MASK | OCTEON_58XX_MODEL_MASK)
-#define OCTEON_58XX_MODEL_MINOR_REV_MASK (OCTEON_58XX_MODEL_REV_MASK & 0x00fffff8)
+#define OCTEON_58XX_MODEL_MINOR_REV_MASK (OCTEON_58XX_MODEL_REV_MASK & 0x00ffff38)
 #define OCTEON_5XXX_MODEL_MASK	     0x00ff0fc0
 
-/* forward declarations */
 static inline uint32_t cvmx_get_proc_id(void) __attribute__ ((pure));
 static inline uint64_t cvmx_read_csr(uint64_t csr_addr);
 
 #define __OCTEON_MATCH_MASK__(x, y, z) (((x) & (z)) == ((y) & (z)))
 
+/*
+ * __OCTEON_IS_MODEL_COMPILE__(arg_model, chip_model)
+ * returns true if chip_model is identical or belong to the OCTEON
+ * model group specified in arg_model.
+ */
 /* NOTE: This for internal use only! */
 #define __OCTEON_IS_MODEL_COMPILE__(arg_model, chip_model)		\
 ((((arg_model & OCTEON_38XX_FAMILY_MASK) < OCTEON_CN58XX_PASS1_0)  && ( \
@@ -286,11 +339,18 @@ static inline uint64_t cvmx_read_csr(uint64_t csr_addr);
 		((((arg_model) & (OM_FLAG_MASK)) == OM_IGNORE_REVISION) \
 			&& __OCTEON_MATCH_MASK__((chip_model), (arg_model), OCTEON_58XX_FAMILY_MASK)) || \
 		((((arg_model) & (OM_FLAG_MASK)) == OM_CHECK_SUBMODEL)	\
-			&& __OCTEON_MATCH_MASK__((chip_model), (arg_model), OCTEON_58XX_MODEL_REV_MASK)) || \
+			&& __OCTEON_MATCH_MASK__((chip_model), (arg_model), OCTEON_58XX_MODEL_MASK)) || \
 		((((arg_model) & (OM_MATCH_5XXX_FAMILY_MODELS)) == OM_MATCH_5XXX_FAMILY_MODELS) \
-			&& ((chip_model) >= OCTEON_CN58XX_PASS1_0) && ((chip_model) < OCTEON_CN63XX_PASS1_0)) || \
+			&& ((chip_model & OCTEON_PRID_MASK) >= OCTEON_CN58XX_PASS1_0) \
+			&& ((chip_model & OCTEON_PRID_MASK) < OCTEON_CN63XX_PASS1_0)) || \
 		((((arg_model) & (OM_MATCH_6XXX_FAMILY_MODELS)) == OM_MATCH_6XXX_FAMILY_MODELS) \
-			&& ((chip_model) >= OCTEON_CN63XX_PASS1_0)) ||	\
+			&& ((chip_model & OCTEON_PRID_MASK) >= OCTEON_CN63XX_PASS1_0) \
+			&& ((chip_model & OCTEON_PRID_MASK) < OCTEON_CNF71XX_PASS1_0)) || \
+		((((arg_model) & (OM_MATCH_F7XXX_FAMILY_MODELS)) == OM_MATCH_F7XXX_FAMILY_MODELS) \
+			&& ((chip_model & OCTEON_PRID_MASK) >= OCTEON_CNF71XX_PASS1_0) \
+			&& ((chip_model & OCTEON_PRID_MASK) < OCTEON_CN78XX_PASS1_0)) || \
+		((((arg_model) & (OM_MATCH_7XXX_FAMILY_MODELS)) == OM_MATCH_7XXX_FAMILY_MODELS) \
+			&& ((chip_model & OCTEON_PRID_MASK) >= OCTEON_CN78XX_PASS1_0)) || \
 		((((arg_model) & (OM_MATCH_PREVIOUS_MODELS)) == OM_MATCH_PREVIOUS_MODELS) \
 			&& (((chip_model) & OCTEON_58XX_MODEL_MASK) < ((arg_model) & OCTEON_58XX_MODEL_MASK))) \
 		)))
@@ -300,14 +360,6 @@ static inline int __octeon_is_model_runtime__(uint32_t model)
 {
 	uint32_t cpuid = cvmx_get_proc_id();
 
-	/*
-	 * Check for special case of mismarked 3005 samples. We only
-	 * need to check if the sub model isn't being ignored
-	 */
-	if ((model & OM_CHECK_SUBMODEL) == OM_CHECK_SUBMODEL) {
-		if (cpuid == OCTEON_CN3010_PASS1 && (cvmx_read_csr(0x80011800800007B8ull) & (1ull << 34)))
-			cpuid |= 0x10;
-	}
 	return __OCTEON_IS_MODEL_COMPILE__(model, cpuid);
 }
 
@@ -326,10 +378,21 @@ static inline int __octeon_is_model_runtime__(uint32_t model)
 #define OCTEON_IS_COMMON_BINARY() 1
 #undef OCTEON_MODEL
 
+#define OCTEON_IS_OCTEON1()	OCTEON_IS_MODEL(OCTEON_CN3XXX)
+#define OCTEON_IS_OCTEONPLUS()	OCTEON_IS_MODEL(OCTEON_CN5XXX)
+#define OCTEON_IS_OCTEON2()						\
+	(OCTEON_IS_MODEL(OCTEON_CN6XXX) || OCTEON_IS_MODEL(OCTEON_CNF71XX))
+
+#define OCTEON_IS_OCTEON3()	OCTEON_IS_MODEL(OCTEON_CN7XXX)
+
+#define OCTEON_IS_OCTEON1PLUS()	(OCTEON_IS_OCTEON1() || OCTEON_IS_OCTEONPLUS())
+
 const char *__init octeon_model_get_string(uint32_t chip_id);
 
 /*
  * Return the octeon family, i.e., ProcessorID of the PrID register.
+ *
+ * @return the octeon family on success, ((unint32_t)-1) on error.
  */
 static inline uint32_t cvmx_get_octeon_family(void)
 {
-- 
cgit v1.2.3


From 726da2f82a1659da5d4d3473427fdb198ffde370 Mon Sep 17 00:00:00 2001
From: David Daney <david.daney@cavium.com>
Date: Thu, 15 Jan 2015 16:11:15 +0300
Subject: MIPS: OCTEON: Core-15169 Workaround and general CVMSEG cleanup.

Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8943/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/cavium-octeon/setup.c                       |  4 +---
 .../asm/mach-cavium-octeon/kernel-entry-init.h        | 19 ++++++++++++++++---
 2 files changed, 17 insertions(+), 6 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 8d2b82327a72..8b6b72a3e3c4 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -579,12 +579,10 @@ void octeon_user_io_init(void)
 	/* R/W If set, CVMSEG is available for loads/stores in user
 	 * mode. */
 	cvmmemctl.s.cvmsegenau = 0;
-	/* R/W Size of local memory in cache blocks, 54 (6912 bytes)
-	 * is max legal value. */
-	cvmmemctl.s.lmemsz = CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE;
 
 	write_c0_cvmmemctl(cvmmemctl.u64);
 
+	/* Setup of CVMSEG is done in kernel-entry-init.h */
 	if (smp_processor_id() == 0)
 		pr_notice("CVMSEG size: %d cache lines (%d bytes)\n",
 			  CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE,
diff --git a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
index 21732c306635..c7ce0811657d 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
@@ -8,11 +8,10 @@
 #ifndef __ASM_MACH_CAVIUM_OCTEON_KERNEL_ENTRY_H
 #define __ASM_MACH_CAVIUM_OCTEON_KERNEL_ENTRY_H
 
-
-#define CP0_CYCLE_COUNTER $9, 6
 #define CP0_CVMCTL_REG $9, 7
 #define CP0_CVMMEMCTL_REG $11,7
 #define CP0_PRID_REG $15, 0
+#define CP0_DCACHE_ERR_REG $27, 1
 #define CP0_PRID_OCTEON_PASS1 0x000d0000
 #define CP0_PRID_OCTEON_CN30XX 0x000d0200
 
@@ -60,7 +59,7 @@
 skip:
 	# First clear off CvmCtl[IPPCI] bit and move the performance
 	# counters interrupt to IRQ 6
-	li	v1, ~(7 << 7)
+	dli	v1, ~(7 << 7)
 	and	v0, v0, v1
 	ori	v0, v0, (6 << 7)
 
@@ -90,6 +89,20 @@ skip:
 	sync
 	# Flush dcache after config change
 	cache	9, 0($0)
+	# Zero all of CVMSEG to make sure parity is correct
+	dli	v0, CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE
+	dsll	v0, 7
+	beqz	v0, 2f
+1:	dsubu	v0, 8
+	sd	$0, -32768(v0)
+	bnez	v0, 1b
+2:
+	mfc0	v0, CP0_PRID_REG
+	bbit0	v0, 15, 1f
+	# OCTEON II or better have bit 15 set.  Clear the error bits.
+	dli	v0, 0x27
+	dmtc0	v0, CP0_DCACHE_ERR_REG
+1:
 	# Get my core id
 	rdhwr	v0, $0
 	# Jump the master to kernel_entry
-- 
cgit v1.2.3


From 920cda3870557a50105f0c5eb783059b3aced86e Mon Sep 17 00:00:00 2001
From: Chad Reese <kreese@caviumnetworks.com>
Date: Thu, 15 Jan 2015 16:11:16 +0300
Subject: MIPS: OCTEON: Remove setting of processor specific CVMCTL icache
 bits.

CN38XX pass 1 required icache prefetching to be turned off. This chip never
reached production and is long dead. Other processor specific icache settings
are done by the bootloader. Remove these bits from the kernel.

Signed-off-by: Chad Reese <kreese@caviumnetworks.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: David Daney <david.daney@cavium.com>
Patchwork: https://patchwork.linux-mips.org/patch/8944/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 .../asm/mach-cavium-octeon/kernel-entry-init.h       | 20 --------------------
 1 file changed, 20 deletions(-)

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
index c7ce0811657d..4bef539e1f07 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
@@ -37,26 +37,6 @@
 	# Needed for octeon specific memcpy
 	or  v0, v0, 0x5001
 	xor v0, v0, 0x1001
-	# Read the processor ID register
-	mfc0 v1, CP0_PRID_REG
-	# Disable instruction prefetching (Octeon Pass1 errata)
-	or  v0, v0, 0x2000
-	# Skip reenable of prefetching for Octeon Pass1
-	beq v1, CP0_PRID_OCTEON_PASS1, skip
-	nop
-	# Reenable instruction prefetching, not on Pass1
-	xor v0, v0, 0x2000
-	# Strip off pass number off of processor id
-	srl v1, 8
-	sll v1, 8
-	# CN30XX needs some extra stuff turned off for better performance
-	bne v1, CP0_PRID_OCTEON_CN30XX, skip
-	nop
-	# CN30XX Use random Icache replacement
-	or  v0, v0, 0x400
-	# CN30XX Disable instruction prefetching
-	or  v0, v0, 0x2000
-skip:
 	# First clear off CvmCtl[IPPCI] bit and move the performance
 	# counters interrupt to IRQ 6
 	dli	v1, ~(7 << 7)
-- 
cgit v1.2.3


From ac6d9b3a03930820bec0ebd3a28f9dae32d27342 Mon Sep 17 00:00:00 2001
From: Chandrakala Chavva <cchavva@caviumnetworks.com>
Date: Thu, 15 Jan 2015 16:11:17 +0300
Subject: MIPS: OCTEON: More OCTEONIII support

Read clock rate from the correct CSR. Don't clear COP0_DCACHE for OCTEONIII.

Signed-off-by: Chandrakala Chavva <cchavva@caviumnetworks.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Signed-off-by: David Daney <david.daney@cavium.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8945/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/cavium-octeon/csrc-octeon.c              |  11 +-
 arch/mips/cavium-octeon/setup.c                    |   8 +-
 .../asm/mach-cavium-octeon/kernel-entry-init.h     |   3 +
 arch/mips/include/asm/octeon/cvmx-rst-defs.h       | 306 +++++++++++++++++++++
 4 files changed, 326 insertions(+), 2 deletions(-)
 create mode 100644 arch/mips/include/asm/octeon/cvmx-rst-defs.h

(limited to 'arch/mips/include/asm')

diff --git a/arch/mips/cavium-octeon/csrc-octeon.c b/arch/mips/cavium-octeon/csrc-octeon.c
index b752c4ed0b79..1882e6475dd0 100644
--- a/arch/mips/cavium-octeon/csrc-octeon.c
+++ b/arch/mips/cavium-octeon/csrc-octeon.c
@@ -18,7 +18,7 @@
 #include <asm/octeon/octeon.h>
 #include <asm/octeon/cvmx-ipd-defs.h>
 #include <asm/octeon/cvmx-mio-defs.h>
-
+#include <asm/octeon/cvmx-rst-defs.h>
 
 static u64 f;
 static u64 rdiv;
@@ -39,11 +39,20 @@ void __init octeon_setup_delays(void)
 
 	if (current_cpu_type() == CPU_CAVIUM_OCTEON2) {
 		union cvmx_mio_rst_boot rst_boot;
+
 		rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT);
 		rdiv = rst_boot.s.c_mul;	/* CPU clock */
 		sdiv = rst_boot.s.pnr_mul;	/* I/O clock */
 		f = (0x8000000000000000ull / sdiv) * 2;
+	} else if (current_cpu_type() == CPU_CAVIUM_OCTEON3) {
+		union cvmx_rst_boot rst_boot;
+
+		rst_boot.u64 = cvmx_read_csr(CVMX_RST_BOOT);
+		rdiv = rst_boot.s.c_mul;	/* CPU clock */
+		sdiv = rst_boot.s.pnr_mul;	/* I/O clock */
+		f = (0x8000000000000000ull / sdiv) * 2;
 	}
+
 }
 
 /*
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 8b6b72a3e3c4..a42110e7edbc 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -41,6 +41,7 @@
 #include <asm/octeon/octeon.h>
 #include <asm/octeon/pci-octeon.h>
 #include <asm/octeon/cvmx-mio-defs.h>
+#include <asm/octeon/cvmx-rst-defs.h>
 
 extern struct plat_smp_ops octeon_smp_ops;
 
@@ -653,11 +654,16 @@ void __init prom_init(void)
 	sysinfo->dfa_ref_clock_hz = octeon_bootinfo->dfa_ref_clock_hz;
 	sysinfo->bootloader_config_flags = octeon_bootinfo->config_flags;
 
-	if (OCTEON_IS_OCTEON2() || OCTEON_IS_OCTEON3()) {
+	if (OCTEON_IS_OCTEON2()) {
 		/* I/O clock runs at a different rate than the CPU. */
 		union cvmx_mio_rst_boot rst_boot;
 		rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT);
 		octeon_io_clock_rate = 50000000 * rst_boot.s.pnr_mul;
+	} else if (OCTEON_IS_OCTEON3()) {
+		/* I/O clock runs at a different rate than the CPU. */
+		union cvmx_rst_boot rst_boot;
+		rst_boot.u64 = cvmx_read_csr(CVMX_RST_BOOT);
+		octeon_io_clock_rate = 50000000 * rst_boot.s.pnr_mul;
 	} else {
 		octeon_io_clock_rate = sysinfo->cpu_clock_hz;
 	}
diff --git a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
index 4bef539e1f07..cf92fe733995 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
@@ -80,6 +80,9 @@
 	mfc0	v0, CP0_PRID_REG
 	bbit0	v0, 15, 1f
 	# OCTEON II or better have bit 15 set.  Clear the error bits.
+	and	t1, v0, 0xff00
+	dli	v0, 0x9500
+	bge	t1, v0, 1f  # OCTEON III has no DCACHE_ERR_REG COP0
 	dli	v0, 0x27
 	dmtc0	v0, CP0_DCACHE_ERR_REG
 1:
diff --git a/arch/mips/include/asm/octeon/cvmx-rst-defs.h b/arch/mips/include/asm/octeon/cvmx-rst-defs.h
new file mode 100644
index 000000000000..0c9c3e74d4ae
--- /dev/null
+++ b/arch/mips/include/asm/octeon/cvmx-rst-defs.h
@@ -0,0 +1,306 @@
+/***********************license start***************
+ * Author: Cavium Inc.
+ *
+ * Contact: support@cavium.com
+ * This file is part of the OCTEON SDK
+ *
+ * Copyright (c) 2003-2014 Cavium Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this file; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ * or visit http://www.gnu.org/licenses/.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium Inc. for more information
+ ***********************license end**************************************/
+
+#ifndef __CVMX_RST_DEFS_H__
+#define __CVMX_RST_DEFS_H__
+
+#define CVMX_RST_BOOT (CVMX_ADD_IO_SEG(0x0001180006001600ull))
+#define CVMX_RST_CFG (CVMX_ADD_IO_SEG(0x0001180006001610ull))
+#define CVMX_RST_CKILL (CVMX_ADD_IO_SEG(0x0001180006001638ull))
+#define CVMX_RST_CTLX(offset) (CVMX_ADD_IO_SEG(0x0001180006001640ull) + ((offset) & 3) * 8)
+#define CVMX_RST_DELAY (CVMX_ADD_IO_SEG(0x0001180006001608ull))
+#define CVMX_RST_ECO (CVMX_ADD_IO_SEG(0x00011800060017B8ull))
+#define CVMX_RST_INT (CVMX_ADD_IO_SEG(0x0001180006001628ull))
+#define CVMX_RST_OCX (CVMX_ADD_IO_SEG(0x0001180006001618ull))
+#define CVMX_RST_POWER_DBG (CVMX_ADD_IO_SEG(0x0001180006001708ull))
+#define CVMX_RST_PP_POWER (CVMX_ADD_IO_SEG(0x0001180006001700ull))
+#define CVMX_RST_SOFT_PRSTX(offset) (CVMX_ADD_IO_SEG(0x00011800060016C0ull) + ((offset) & 3) * 8)
+#define CVMX_RST_SOFT_RST (CVMX_ADD_IO_SEG(0x0001180006001680ull))
+
+union cvmx_rst_boot {
+	uint64_t u64;
+	struct cvmx_rst_boot_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t chipkill:1;
+		uint64_t jtcsrdis:1;
+		uint64_t ejtagdis:1;
+		uint64_t romen:1;
+		uint64_t ckill_ppdis:1;
+		uint64_t jt_tstmode:1;
+		uint64_t vrm_err:1;
+		uint64_t reserved_37_56:20;
+		uint64_t c_mul:7;
+		uint64_t pnr_mul:6;
+		uint64_t reserved_21_23:3;
+		uint64_t lboot_oci:3;
+		uint64_t lboot_ext:6;
+		uint64_t lboot:10;
+		uint64_t rboot:1;
+		uint64_t rboot_pin:1;
+#else
+		uint64_t rboot_pin:1;
+		uint64_t rboot:1;
+		uint64_t lboot:10;
+		uint64_t lboot_ext:6;
+		uint64_t lboot_oci:3;
+		uint64_t reserved_21_23:3;
+		uint64_t pnr_mul:6;
+		uint64_t c_mul:7;
+		uint64_t reserved_37_56:20;
+		uint64_t vrm_err:1;
+		uint64_t jt_tstmode:1;
+		uint64_t ckill_ppdis:1;
+		uint64_t romen:1;
+		uint64_t ejtagdis:1;
+		uint64_t jtcsrdis:1;
+		uint64_t chipkill:1;
+#endif
+	} s;
+	struct cvmx_rst_boot_s cn70xx;
+	struct cvmx_rst_boot_s cn70xxp1;
+	struct cvmx_rst_boot_s cn78xx;
+};
+
+union cvmx_rst_cfg {
+	uint64_t u64;
+	struct cvmx_rst_cfg_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t bist_delay:58;
+		uint64_t reserved_3_5:3;
+		uint64_t cntl_clr_bist:1;
+		uint64_t warm_clr_bist:1;
+		uint64_t soft_clr_bist:1;
+#else
+		uint64_t soft_clr_bist:1;
+		uint64_t warm_clr_bist:1;
+		uint64_t cntl_clr_bist:1;
+		uint64_t reserved_3_5:3;
+		uint64_t bist_delay:58;
+#endif
+	} s;
+	struct cvmx_rst_cfg_s cn70xx;
+	struct cvmx_rst_cfg_s cn70xxp1;
+	struct cvmx_rst_cfg_s cn78xx;
+};
+
+union cvmx_rst_ckill {
+	uint64_t u64;
+	struct cvmx_rst_ckill_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_47_63:17;
+		uint64_t timer:47;
+#else
+		uint64_t timer:47;
+		uint64_t reserved_47_63:17;
+#endif
+	} s;
+	struct cvmx_rst_ckill_s cn70xx;
+	struct cvmx_rst_ckill_s cn70xxp1;
+	struct cvmx_rst_ckill_s cn78xx;
+};
+
+union cvmx_rst_ctlx {
+	uint64_t u64;
+	struct cvmx_rst_ctlx_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_10_63:54;
+		uint64_t prst_link:1;
+		uint64_t rst_done:1;
+		uint64_t rst_link:1;
+		uint64_t host_mode:1;
+		uint64_t reserved_4_5:2;
+		uint64_t rst_drv:1;
+		uint64_t rst_rcv:1;
+		uint64_t rst_chip:1;
+		uint64_t rst_val:1;
+#else
+		uint64_t rst_val:1;
+		uint64_t rst_chip:1;
+		uint64_t rst_rcv:1;
+		uint64_t rst_drv:1;
+		uint64_t reserved_4_5:2;
+		uint64_t host_mode:1;
+		uint64_t rst_link:1;
+		uint64_t rst_done:1;
+		uint64_t prst_link:1;
+		uint64_t reserved_10_63:54;
+#endif
+	} s;
+	struct cvmx_rst_ctlx_s cn70xx;
+	struct cvmx_rst_ctlx_s cn70xxp1;
+	struct cvmx_rst_ctlx_s cn78xx;
+};
+
+union cvmx_rst_delay {
+	uint64_t u64;
+	struct cvmx_rst_delay_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_32_63:32;
+		uint64_t warm_rst_dly:16;
+		uint64_t soft_rst_dly:16;
+#else
+		uint64_t soft_rst_dly:16;
+		uint64_t warm_rst_dly:16;
+		uint64_t reserved_32_63:32;
+#endif
+	} s;
+	struct cvmx_rst_delay_s cn70xx;
+	struct cvmx_rst_delay_s cn70xxp1;
+	struct cvmx_rst_delay_s cn78xx;
+};
+
+union cvmx_rst_eco {
+	uint64_t u64;
+	struct cvmx_rst_eco_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_32_63:32;
+		uint64_t eco_rw:32;
+#else
+		uint64_t eco_rw:32;
+		uint64_t reserved_32_63:32;
+#endif
+	} s;
+	struct cvmx_rst_eco_s cn78xx;
+};
+
+union cvmx_rst_int {
+	uint64_t u64;
+	struct cvmx_rst_int_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_12_63:52;
+		uint64_t perst:4;
+		uint64_t reserved_4_7:4;
+		uint64_t rst_link:4;
+#else
+		uint64_t rst_link:4;
+		uint64_t reserved_4_7:4;
+		uint64_t perst:4;
+		uint64_t reserved_12_63:52;
+#endif
+	} s;
+	struct cvmx_rst_int_cn70xx {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_11_63:53;
+		uint64_t perst:3;
+		uint64_t reserved_3_7:5;
+		uint64_t rst_link:3;
+#else
+		uint64_t rst_link:3;
+		uint64_t reserved_3_7:5;
+		uint64_t perst:3;
+		uint64_t reserved_11_63:53;
+#endif
+	} cn70xx;
+	struct cvmx_rst_int_cn70xx cn70xxp1;
+	struct cvmx_rst_int_s cn78xx;
+};
+
+union cvmx_rst_ocx {
+	uint64_t u64;
+	struct cvmx_rst_ocx_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_3_63:61;
+		uint64_t rst_link:3;
+#else
+		uint64_t rst_link:3;
+		uint64_t reserved_3_63:61;
+#endif
+	} s;
+	struct cvmx_rst_ocx_s cn78xx;
+};
+
+union cvmx_rst_power_dbg {
+	uint64_t u64;
+	struct cvmx_rst_power_dbg_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_3_63:61;
+		uint64_t str:3;
+#else
+		uint64_t str:3;
+		uint64_t reserved_3_63:61;
+#endif
+	} s;
+	struct cvmx_rst_power_dbg_s cn78xx;
+};
+
+union cvmx_rst_pp_power {
+	uint64_t u64;
+	struct cvmx_rst_pp_power_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_48_63:16;
+		uint64_t gate:48;
+#else
+		uint64_t gate:48;
+		uint64_t reserved_48_63:16;
+#endif
+	} s;
+	struct cvmx_rst_pp_power_cn70xx {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_4_63:60;
+		uint64_t gate:4;
+#else
+		uint64_t gate:4;
+		uint64_t reserved_4_63:60;
+#endif
+	} cn70xx;
+	struct cvmx_rst_pp_power_cn70xx cn70xxp1;
+	struct cvmx_rst_pp_power_s cn78xx;
+};
+
+union cvmx_rst_soft_prstx {
+	uint64_t u64;
+	struct cvmx_rst_soft_prstx_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_1_63:63;
+		uint64_t soft_prst:1;
+#else
+		uint64_t soft_prst:1;
+		uint64_t reserved_1_63:63;
+#endif
+	} s;
+	struct cvmx_rst_soft_prstx_s cn70xx;
+	struct cvmx_rst_soft_prstx_s cn70xxp1;
+	struct cvmx_rst_soft_prstx_s cn78xx;
+};
+
+union cvmx_rst_soft_rst {
+	uint64_t u64;
+	struct cvmx_rst_soft_rst_s {
+#ifdef __BIG_ENDIAN_BITFIELD
+		uint64_t reserved_1_63:63;
+		uint64_t soft_rst:1;
+#else
+		uint64_t soft_rst:1;
+		uint64_t reserved_1_63:63;
+#endif
+	} s;
+	struct cvmx_rst_soft_rst_s cn70xx;
+	struct cvmx_rst_soft_rst_s cn70xxp1;
+	struct cvmx_rst_soft_rst_s cn78xx;
+};
+
+#endif
-- 
cgit v1.2.3