MIPS: microMIPS: Add unaligned access support.

Add logic needed to handle unaligned accesses in microMIPS mode.

Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com>
Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>

1 files changed, 1011 insertions, 201 deletions

diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index f4c94ff..0213906 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -87,6 +87,8 @@
 #include <asm/fpu_emulator.h>
 #include <asm/inst.h>
 #include <asm/uaccess.h>
+#include <asm/fpu.h>
+#include <asm/fpu_emulator.h>
 
 #define STR(x)	__STR(x)
 #define __STR(x)  #x
@@ -104,14 +106,333 @@ static u32 unaligned_action;
 #endif
 extern void show_registers(struct pt_regs *regs);
 
+#ifdef __BIG_ENDIAN
+#define     LoadHW(addr, value, res)  \
+		__asm__ __volatile__ (".set\tnoat\n"        \
+			"1:\tlb\t%0, 0(%2)\n"               \
+			"2:\tlbu\t$1, 1(%2)\n\t"            \
+			"sll\t%0, 0x8\n\t"                  \
+			"or\t%0, $1\n\t"                    \
+			"li\t%1, 0\n"                       \
+			"3:\t.set\tat\n\t"                  \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadW(addr, value, res)   \
+		__asm__ __volatile__ (                      \
+			"1:\tlwl\t%0, (%2)\n"               \
+			"2:\tlwr\t%0, 3(%2)\n\t"            \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadHWU(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tnoat\n"                      \
+			"1:\tlbu\t%0, 0(%2)\n"              \
+			"2:\tlbu\t$1, 1(%2)\n\t"            \
+			"sll\t%0, 0x8\n\t"                  \
+			"or\t%0, $1\n\t"                    \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".set\tat\n\t"                      \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadWU(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tlwl\t%0, (%2)\n"               \
+			"2:\tlwr\t%0, 3(%2)\n\t"            \
+			"dsll\t%0, %0, 32\n\t"              \
+			"dsrl\t%0, %0, 32\n\t"              \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			"\t.section\t.fixup,\"ax\"\n\t"     \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadDW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tldl\t%0, (%2)\n"               \
+			"2:\tldr\t%0, 7(%2)\n\t"            \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			"\t.section\t.fixup,\"ax\"\n\t"     \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     StoreHW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tnoat\n"                      \
+			"1:\tsb\t%1, 1(%2)\n\t"             \
+			"srl\t$1, %1, 0x8\n"                \
+			"2:\tsb\t$1, 0(%2)\n\t"             \
+			".set\tat\n\t"                      \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=r" (res)                        \
+			: "r" (value), "r" (addr), "i" (-EFAULT));
+
+#define     StoreW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tswl\t%1,(%2)\n"                \
+			"2:\tswr\t%1, 3(%2)\n\t"            \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+		: "=r" (res)                                \
+		: "r" (value), "r" (addr), "i" (-EFAULT));
+
+#define     StoreDW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			"1:\tsdl\t%1,(%2)\n"                \
+			"2:\tsdr\t%1, 7(%2)\n\t"            \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+		: "=r" (res)                                \
+		: "r" (value), "r" (addr), "i" (-EFAULT));
+#endif
+
+#ifdef __LITTLE_ENDIAN
+#define     LoadHW(addr, value, res)  \
+		__asm__ __volatile__ (".set\tnoat\n"        \
+			"1:\tlb\t%0, 1(%2)\n"               \
+			"2:\tlbu\t$1, 0(%2)\n\t"            \
+			"sll\t%0, 0x8\n\t"                  \
+			"or\t%0, $1\n\t"                    \
+			"li\t%1, 0\n"                       \
+			"3:\t.set\tat\n\t"                  \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadW(addr, value, res)   \
+		__asm__ __volatile__ (                      \
+			"1:\tlwl\t%0, 3(%2)\n"              \
+			"2:\tlwr\t%0, (%2)\n\t"             \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadHWU(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tnoat\n"                      \
+			"1:\tlbu\t%0, 1(%2)\n"              \
+			"2:\tlbu\t$1, 0(%2)\n\t"            \
+			"sll\t%0, 0x8\n\t"                  \
+			"or\t%0, $1\n\t"                    \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".set\tat\n\t"                      \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadWU(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tlwl\t%0, 3(%2)\n"              \
+			"2:\tlwr\t%0, (%2)\n\t"             \
+			"dsll\t%0, %0, 32\n\t"              \
+			"dsrl\t%0, %0, 32\n\t"              \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			"\t.section\t.fixup,\"ax\"\n\t"     \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadDW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tldl\t%0, 7(%2)\n"              \
+			"2:\tldr\t%0, (%2)\n\t"             \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			"\t.section\t.fixup,\"ax\"\n\t"     \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     StoreHW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tnoat\n"                      \
+			"1:\tsb\t%1, 0(%2)\n\t"             \
+			"srl\t$1,%1, 0x8\n"                 \
+			"2:\tsb\t$1, 1(%2)\n\t"             \
+			".set\tat\n\t"                      \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=r" (res)                        \
+			: "r" (value), "r" (addr), "i" (-EFAULT));
+
+#define     StoreW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tswl\t%1, 3(%2)\n"              \
+			"2:\tswr\t%1, (%2)\n\t"             \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+		: "=r" (res)                                \
+		: "r" (value), "r" (addr), "i" (-EFAULT));
+
+#define     StoreDW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			"1:\tsdl\t%1, 7(%2)\n"              \
+			"2:\tsdr\t%1, (%2)\n\t"             \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+		: "=r" (res)                                \
+		: "r" (value), "r" (addr), "i" (-EFAULT));
+#endif
+
 static void emulate_load_store_insn(struct pt_regs *regs,
 	void __user *addr, unsigned int __user *pc)
 {
 	union mips_instruction insn;
 	unsigned long value;
 	unsigned int res;
+	unsigned long origpc;
+	unsigned long orig31;
 	void __user *fault_addr = NULL;
 
+	origpc = (unsigned long)pc;
+	orig31 = regs->regs[31];
+
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
 	/*
@@ -120,22 +441,22 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	__get_user(insn.word, pc);
 
 	switch (insn.i_format.opcode) {
-	/*
-	 * These are instructions that a compiler doesn't generate.  We
-	 * can assume therefore that the code is MIPS-aware and
-	 * really buggy.  Emulating these instructions would break the
-	 * semantics anyway.
-	 */
+		/*
+		 * These are instructions that a compiler doesn't generate.  We
+		 * can assume therefore that the code is MIPS-aware and
+		 * really buggy.  Emulating these instructions would break the
+		 * semantics anyway.
+		 */
 	case ll_op:
 	case lld_op:
 	case sc_op:
 	case scd_op:
 
-	/*
-	 * For these instructions the only way to create an address
-	 * error is an attempted access to kernel/supervisor address
-	 * space.
-	 */
+		/*
+		 * For these instructions the only way to create an address
+		 * error is an attempted access to kernel/supervisor address
+		 * space.
+		 */
 	case ldl_op:
 	case ldr_op:
 	case lwl_op:
@@ -149,36 +470,15 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	case sb_op:
 		goto sigbus;
 
-	/*
-	 * The remaining opcodes are the ones that are really of interest.
-	 */
+		/*
+		 * The remaining opcodes are the ones that are really of
+		 * interest.
+		 */
 	case lh_op:
 		if (!access_ok(VERIFY_READ, addr, 2))
 			goto sigbus;
 
-		__asm__ __volatile__ (".set\tnoat\n"
-#ifdef __BIG_ENDIAN
-			"1:\tlb\t%0, 0(%2)\n"
-			"2:\tlbu\t$1, 1(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tlb\t%0, 1(%2)\n"
-			"2:\tlbu\t$1, 0(%2)\n\t"
-#endif
-			"sll\t%0, 0x8\n\t"
-			"or\t%0, $1\n\t"
-			"li\t%1, 0\n"
-			"3:\t.set\tat\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadHW(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -189,26 +489,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_READ, addr, 4))
 			goto sigbus;
 
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tlwl\t%0, (%2)\n"
-			"2:\tlwr\t%0, 3(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tlwl\t%0, 3(%2)\n"
-			"2:\tlwr\t%0, (%2)\n\t"
-#endif
-			"li\t%1, 0\n"
-			"3:\t.section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadW(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -219,30 +500,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_READ, addr, 2))
 			goto sigbus;
 
-		__asm__ __volatile__ (
-			".set\tnoat\n"
-#ifdef __BIG_ENDIAN
-			"1:\tlbu\t%0, 0(%2)\n"
-			"2:\tlbu\t$1, 1(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tlbu\t%0, 1(%2)\n"
-			"2:\tlbu\t$1, 0(%2)\n\t"
-#endif
-			"sll\t%0, 0x8\n\t"
-			"or\t%0, $1\n\t"
-			"li\t%1, 0\n"
-			"3:\t.set\tat\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadHWU(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -261,28 +519,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_READ, addr, 4))
 			goto sigbus;
 
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tlwl\t%0, (%2)\n"
-			"2:\tlwr\t%0, 3(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tlwl\t%0, 3(%2)\n"
-			"2:\tlwr\t%0, (%2)\n\t"
-#endif
-			"dsll\t%0, %0, 32\n\t"
-			"dsrl\t%0, %0, 32\n\t"
-			"li\t%1, 0\n"
-			"3:\t.section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadWU(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -305,26 +542,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_READ, addr, 8))
 			goto sigbus;
 
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tldl\t%0, (%2)\n"
-			"2:\tldr\t%0, 7(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tldl\t%0, 7(%2)\n"
-			"2:\tldr\t%0, (%2)\n\t"
-#endif
-			"li\t%1, 0\n"
-			"3:\t.section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadDW(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -339,68 +557,22 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_WRITE, addr, 2))
 			goto sigbus;
 
+		compute_return_epc(regs);
 		value = regs->regs[insn.i_format.rt];
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			".set\tnoat\n"
-			"1:\tsb\t%1, 1(%2)\n\t"
-			"srl\t$1, %1, 0x8\n"
-			"2:\tsb\t$1, 0(%2)\n\t"
-			".set\tat\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			".set\tnoat\n"
-			"1:\tsb\t%1, 0(%2)\n\t"
-			"srl\t$1,%1, 0x8\n"
-			"2:\tsb\t$1, 1(%2)\n\t"
-			".set\tat\n\t"
-#endif
-			"li\t%0, 0\n"
-			"3:\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%0, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=r" (res)
-			: "r" (value), "r" (addr), "i" (-EFAULT));
+		StoreHW(addr, value, res);
 		if (res)
 			goto fault;
-		compute_return_epc(regs);
 		break;
 
 	case sw_op:
 		if (!access_ok(VERIFY_WRITE, addr, 4))
 			goto sigbus;
 
+		compute_return_epc(regs);
 		value = regs->regs[insn.i_format.rt];
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tswl\t%1,(%2)\n"
-			"2:\tswr\t%1, 3(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tswl\t%1, 3(%2)\n"
-			"2:\tswr\t%1, (%2)\n\t"
-#endif
-			"li\t%0, 0\n"
-			"3:\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%0, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-		: "=r" (res)
-		: "r" (value), "r" (addr), "i" (-EFAULT));
+		StoreW(addr, value, res);
 		if (res)
 			goto fault;
-		compute_return_epc(regs);
 		break;
 
 	case sd_op:
@@ -415,31 +587,11 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_WRITE, addr, 8))
 			goto sigbus;
 
+		compute_return_epc(regs);
 		value = regs->regs[insn.i_format.rt];
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tsdl\t%1,(%2)\n"
-			"2:\tsdr\t%1, 7(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tsdl\t%1, 7(%2)\n"
-			"2:\tsdr\t%1, (%2)\n\t"
-#endif
-			"li\t%0, 0\n"
-			"3:\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%0, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-		: "=r" (res)
-		: "r" (value), "r" (addr), "i" (-EFAULT));
+		StoreDW(addr, value, res);
 		if (res)
 			goto fault;
-		compute_return_epc(regs);
 		break;
 #endif /* CONFIG_64BIT */
 
@@ -502,6 +654,635 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	return;
 
 fault:
+	/* roll back jump/branch */
+	regs->cp0_epc = origpc;
+	regs->regs[31] = orig31;
+	/* Did we have an exception handler installed? */
+	if (fixup_exception(regs))
+		return;
+
+	die_if_kernel("Unhandled kernel unaligned access", regs);
+	force_sig(SIGSEGV, current);
+
+	return;
+
+sigbus:
+	die_if_kernel("Unhandled kernel unaligned access", regs);
+	force_sig(SIGBUS, current);
+
+	return;
+
+sigill:
+	die_if_kernel
+	    ("Unhandled kernel unaligned access or invalid instruction", regs);
+	force_sig(SIGILL, current);
+}
+
+/* Recode table from 16-bit register notation to 32-bit GPR. */
+const int reg16to32[] = { 16, 17, 2, 3, 4, 5, 6, 7 };
+
+/* Recode table from 16-bit STORE register notation to 32-bit GPR. */
+const int reg16to32st[] = { 0, 17, 2, 3, 4, 5, 6, 7 };
+
+void emulate_load_store_microMIPS(struct pt_regs *regs, void __user * addr)
+{
+	unsigned long value;
+	unsigned int res;
+	int i;
+	unsigned int reg = 0, rvar;
+	unsigned long orig31;
+	u16 __user *pc16;
+	u16 halfword;
+	unsigned int word;
+	unsigned long origpc, contpc;
+	union mips_instruction insn;
+	struct mm_decoded_insn mminsn;
+	void __user *fault_addr = NULL;
+
+	origpc = regs->cp0_epc;
+	orig31 = regs->regs[31];
+
+	mminsn.micro_mips_mode = 1;
+
+	/*
+	 * This load never faults.
+	 */
+	pc16 = (unsigned short __user *)msk_isa16_mode(regs->cp0_epc);
+	__get_user(halfword, pc16);
+	pc16++;
+	contpc = regs->cp0_epc + 2;
+	word = ((unsigned int)halfword << 16);
+	mminsn.pc_inc = 2;
+
+	if (!mm_insn_16bit(halfword)) {
+		__get_user(halfword, pc16);
+		pc16++;
+		contpc = regs->cp0_epc + 4;
+		mminsn.pc_inc = 4;
+		word |= halfword;
+	}
+	mminsn.insn = word;
+
+	if (get_user(halfword, pc16))
+		goto fault;
+	mminsn.next_pc_inc = 2;
+	word = ((unsigned int)halfword << 16);
+
+	if (!mm_insn_16bit(halfword)) {
+		pc16++;
+		if (get_user(halfword, pc16))
+			goto fault;
+		mminsn.next_pc_inc = 4;
+		word |= halfword;
+	}
+	mminsn.next_insn = word;
+
+	insn = (union mips_instruction)(mminsn.insn);
+	if (mm_isBranchInstr(regs, mminsn, &contpc))
+		insn = (union mips_instruction)(mminsn.next_insn);
+
+	/*  Parse instruction to find what to do */
+
+	switch (insn.mm_i_format.opcode) {
+
+	case mm_pool32a_op:
+		switch (insn.mm_x_format.func) {
+		case mm_lwxs_op:
+			reg = insn.mm_x_format.rd;
+			goto loadW;
+		}
+
+		goto sigbus;
+
+	case mm_pool32b_op:
+		switch (insn.mm_m_format.func) {
+		case mm_lwp_func:
+			reg = insn.mm_m_format.rd;
+			if (reg == 31)
+				goto sigbus;
+
+			if (!access_ok(VERIFY_READ, addr, 8))
+				goto sigbus;
+
+			LoadW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[reg] = value;
+			addr += 4;
+			LoadW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[reg + 1] = value;
+			goto success;
+
+		case mm_swp_func:
+			reg = insn.mm_m_format.rd;
+			if (reg == 31)
+				goto sigbus;
+
+			if (!access_ok(VERIFY_WRITE, addr, 8))
+				goto sigbus;
+
+			value = regs->regs[reg];
+			StoreW(addr, value, res);
+			if (res)
+				goto fault;
+			addr += 4;
+			value = regs->regs[reg + 1];
+			StoreW(addr, value, res);
+			if (res)
+				goto fault;
+			goto success;
+
+		case mm_ldp_func:
+#ifdef CONFIG_64BIT
+			reg = insn.mm_m_format.rd;
+			if (reg == 31)
+				goto sigbus;
+
+			if (!access_ok(VERIFY_READ, addr, 16))
+				goto sigbus;
+
+			LoadDW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[reg] = value;
+			addr += 8;
+			LoadDW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[reg + 1] = value;
+			goto success;
+#endif /* CONFIG_64BIT */
+
+			goto sigill;
+
+		case mm_sdp_func:
+#ifdef CONFIG_64BIT
+			reg = insn.mm_m_format.rd;
+			if (reg == 31)
+				goto sigbus;
+
+			if (!access_ok(VERIFY_WRITE, addr, 16))
+				goto sigbus;
+
+			value = regs->regs[reg];
+			StoreDW(addr, value, res);
+			if (res)
+				goto fault;
+			addr += 8;
+			value = regs->regs[reg + 1];
+			StoreDW(addr, value, res);
+			if (res)
+				goto fault;
+			goto success;
+#endif /* CONFIG_64BIT */
+
+			goto sigill;
+
+		case mm_lwm32_func:
+			reg = insn.mm_m_format.rd;
+			rvar = reg & 0xf;
+			if ((rvar > 9) || !reg)
+				goto sigill;
+			if (reg & 0x10) {
+				if (!access_ok
+				    (VERIFY_READ, addr, 4 * (rvar + 1)))
+					goto sigbus;
+			} else {
+				if (!access_ok(VERIFY_READ, addr, 4 * rvar))
+					goto sigbus;
+			}
+			if (rvar == 9)
+				rvar = 8;
+			for (i = 16; rvar; rvar--, i++) {
+				LoadW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+				regs->regs[i] = value;
+			}
+			if ((reg & 0xf) == 9) {
+				LoadW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+				regs->regs[30] = value;
+			}
+			if (reg & 0x10) {
+				LoadW(addr, value, res);
+				if (res)
+					goto fault;
+				regs->regs[31] = value;
+			}
+			goto success;
+
+		case mm_swm32_func:
+			reg = insn.mm_m_format.rd;
+			rvar = reg & 0xf;
+			if ((rvar > 9) || !reg)
+				goto sigill;
+			if (reg & 0x10) {
+				if (!access_ok
+				    (VERIFY_WRITE, addr, 4 * (rvar + 1)))
+					goto sigbus;
+			} else {
+				if (!access_ok(VERIFY_WRITE, addr, 4 * rvar))
+					goto sigbus;
+			}
+			if (rvar == 9)
+				rvar = 8;
+			for (i = 16; rvar; rvar--, i++) {
+				value = regs->regs[i];
+				StoreW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+			}
+			if ((reg & 0xf) == 9) {
+				value = regs->regs[30];
+				StoreW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+			}
+			if (reg & 0x10) {
+				value = regs->regs[31];
+				StoreW(addr, value, res);
+				if (res)
+					goto fault;
+			}
+			goto success;
+
+		case mm_ldm_func:
+#ifdef CONFIG_64BIT
+			reg = insn.mm_m_format.rd;
+			rvar = reg & 0xf;
+			if ((rvar > 9) || !reg)
+				goto sigill;
+			if (reg & 0x10) {
+				if (!access_ok
+				    (VERIFY_READ, addr, 8 * (rvar + 1)))
+					goto sigbus;
+			} else {
+				if (!access_ok(VERIFY_READ, addr, 8 * rvar))
+					goto sigbus;
+			}
+			if (rvar == 9)
+				rvar = 8;
+
+			for (i = 16; rvar; rvar--, i++) {
+				LoadDW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+				regs->regs[i] = value;
+			}
+			if ((reg & 0xf) == 9) {
+				LoadDW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 8;
+				regs->regs[30] = value;
+			}
+			if (reg & 0x10) {
+				LoadDW(addr, value, res);
+				if (res)
+					goto fault;
+				regs->regs[31] = value;
+			}
+			goto success;
+#endif /* CONFIG_64BIT */
+
+			goto sigill;
+
+		case mm_sdm_func:
+#ifdef CONFIG_64BIT
+			reg = insn.mm_m_format.rd;
+			rvar = reg & 0xf;
+			if ((rvar > 9) || !reg)
+				goto sigill;
+			if (reg & 0x10) {
+				if (!access_ok
+				    (VERIFY_WRITE, addr, 8 * (rvar + 1)))
+					goto sigbus;
+			} else {
+				if (!access_ok(VERIFY_WRITE, addr, 8 * rvar))
+					goto sigbus;
+			}
+			if (rvar == 9)
+				rvar = 8;
+
+			for (i = 16; rvar; rvar--, i++) {
+				value = regs->regs[i];
+				StoreDW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 8;
+			}
+			if ((reg & 0xf) == 9) {
+				value = regs->regs[30];
+				StoreDW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 8;
+			}
+			if (reg & 0x10) {
+				value = regs->regs[31];
+				StoreDW(addr, value, res);
+				if (res)
+					goto fault;
+			}
+			goto success;
+#endif /* CONFIG_64BIT */
+
+			goto sigill;
+
+			/*  LWC2, SWC2, LDC2, SDC2 are not serviced */
+		}
+
+		goto sigbus;
+
+	case mm_pool32c_op:
+		switch (insn.mm_m_format.func) {
+		case mm_lwu_func:
+			reg = insn.mm_m_format.rd;
+			goto loadWU;
+		}
+
+		/*  LL,SC,LLD,SCD are not serviced */
+		goto sigbus;
+
+	case mm_pool32f_op:
+		switch (insn.mm_x_format.func) {
+		case mm_lwxc1_func:
+		case mm_swxc1_func:
+		case mm_ldxc1_func:
+		case mm_sdxc1_func:
+			goto fpu_emul;
+		}
+
+		goto sigbus;
+
+	case mm_ldc132_op:
+	case mm_sdc132_op:
+	case mm_lwc132_op:
+	case mm_swc132_op:
+fpu_emul:
+		/* roll back jump/branch */
+		regs->cp0_epc = origpc;
+		regs->regs[31] = orig31;
+
+		die_if_kernel("Unaligned FP access in kernel code", regs);
+		BUG_ON(!used_math());
+		BUG_ON(!is_fpu_owner());
+
+		lose_fpu(1);	/* save the FPU state for the emulator */
+		res = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
+					       &fault_addr);
+		own_fpu(1);	/* restore FPU state */
+
+		/* If something went wrong, signal */
+		process_fpemu_return(res, fault_addr);
+
+		if (res == 0)
+			goto success;
+		return;
+
+	case mm_lh32_op:
+		reg = insn.mm_i_format.rt;
+		goto loadHW;
+
+	case mm_lhu32_op:
+		reg = insn.mm_i_format.rt;
+		goto loadHWU;
+
+	case mm_lw32_op:
+		reg = insn.mm_i_format.rt;
+		goto loadW;
+
+	case mm_sh32_op:
+		reg = insn.mm_i_format.rt;
+		goto storeHW;
+
+	case mm_sw32_op:
+		reg = insn.mm_i_format.rt;
+		goto storeW;
+
+	case mm_ld32_op:
+		reg = insn.mm_i_format.rt;
+		goto loadDW;
+
+	case mm_sd32_op:
+		reg = insn.mm_i_format.rt;
+		goto storeDW;
+
+	case mm_pool16c_op:
+		switch (insn.mm16_m_format.func) {
+		case mm_lwm16_op:
+			reg = insn.mm16_m_format.rlist;
+			rvar = reg + 1;
+			if (!access_ok(VERIFY_READ, addr, 4 * rvar))
+				goto sigbus;
+
+			for (i = 16; rvar; rvar--, i++) {
+				LoadW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+				regs->regs[i] = value;
+			}
+			LoadW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[31] = value;
+
+			goto success;
+
+		case mm_swm16_op:
+			reg = insn.mm16_m_format.rlist;
+			rvar = reg + 1;
+			if (!access_ok(VERIFY_WRITE, addr, 4 * rvar))
+				goto sigbus;
+
+			for (i = 16; rvar; rvar--, i++) {
+				value = regs->regs[i];
+				StoreW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+			}
+			value = regs->regs[31];
+			StoreW(addr, value, res);
+			if (res)
+				goto fault;
+
+			goto success;
+
+		}
+
+		goto sigbus;
+
+	case mm_lhu16_op:
+		reg = reg16to32[insn.mm16_rb_format.rt];
+		goto loadHWU;
+
+	case mm_lw16_op:
+		reg = reg16to32[insn.mm16_rb_format.rt];
+		goto loadW;
+
+	case mm_sh16_op:
+		reg = reg16to32st[insn.mm16_rb_format.rt];
+		goto storeHW;
+
+	case mm_sw16_op:
+		reg = reg16to32st[insn.mm16_rb_format.rt];
+		goto storeW;
+
+	case mm_lwsp16_op:
+		reg = insn.mm16_r5_format.rt;
+		goto loadW;
+
+	case mm_swsp16_op:
+		reg = insn.mm16_r5_format.rt;
+		goto storeW;
+
+	case mm_lwgp16_op:
+		reg = reg16to32[insn.mm16_r3_format.rt];
+		goto loadW;
+
+	default:
+		goto sigill;
+	}
+
+loadHW:
+	if (!access_ok(VERIFY_READ, addr, 2))
+		goto sigbus;
+
+	LoadHW(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+
+loadHWU:
+	if (!access_ok(VERIFY_READ, addr, 2))
+		goto sigbus;
+
+	LoadHWU(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+
+loadW:
+	if (!access_ok(VERIFY_READ, addr, 4))
+		goto sigbus;
+
+	LoadW(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+
+loadWU:
+#ifdef CONFIG_64BIT
+	/*
+	 * A 32-bit kernel might be running on a 64-bit processor.  But
+	 * if we're on a 32-bit processor and an i-cache incoherency
+	 * or race makes us see a 64-bit instruction here the sdl/sdr
+	 * would blow up, so for now we don't handle unaligned 64-bit
+	 * instructions on 32-bit kernels.
+	 */
+	if (!access_ok(VERIFY_READ, addr, 4))
+		goto sigbus;
+
+	LoadWU(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+#endif /* CONFIG_64BIT */
+
+	/* Cannot handle 64-bit instructions in 32-bit kernel */
+	goto sigill;
+
+loadDW:
+#ifdef CONFIG_64BIT
+	/*
+	 * A 32-bit kernel might be running on a 64-bit processor.  But
+	 * if we're on a 32-bit processor and an i-cache incoherency
+	 * or race makes us see a 64-bit instruction here the sdl/sdr
+	 * would blow up, so for now we don't handle unaligned 64-bit
+	 * instructions on 32-bit kernels.
+	 */
+	if (!access_ok(VERIFY_READ, addr, 8))
+		goto sigbus;
+
+	LoadDW(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+#endif /* CONFIG_64BIT */
+
+	/* Cannot handle 64-bit instructions in 32-bit kernel */
+	goto sigill;
+
+storeHW:
+	if (!access_ok(VERIFY_WRITE, addr, 2))
+		goto sigbus;
+
+	value = regs->regs[reg];
+	StoreHW(addr, value, res);
+	if (res)
+		goto fault;
+	goto success;
+
+storeW:
+	if (!access_ok(VERIFY_WRITE, addr, 4))
+		goto sigbus;
+
+	value = regs->regs[reg];
+	StoreW(addr, value, res);
+	if (res)
+		goto fault;
+	goto success;
+
+storeDW:
+#ifdef CONFIG_64BIT
+	/*
+	 * A 32-bit kernel might be running on a 64-bit processor.  But
+	 * if we're on a 32-bit processor and an i-cache incoherency
+	 * or race makes us see a 64-bit instruction here the sdl/sdr
+	 * would blow up, so for now we don't handle unaligned 64-bit
+	 * instructions on 32-bit kernels.
+	 */
+	if (!access_ok(VERIFY_WRITE, addr, 8))
+		goto sigbus;
+
+	value = regs->regs[reg];
+	StoreDW(addr, value, res);
+	if (res)
+		goto fault;
+	goto success;
+#endif /* CONFIG_64BIT */
+
+	/* Cannot handle 64-bit instructions in 32-bit kernel */
+	goto sigill;
+
+success:
+	regs->cp0_epc = contpc;	/* advance or branch */
+
+#ifdef CONFIG_DEBUG_FS
+	unaligned_instructions++;
+#endif
+	return;
+
+fault:
+	/* roll back jump/branch */
+	regs->cp0_epc = origpc;
+	regs->regs[31] = orig31;
 	/* Did we have an exception handler installed? */
 	if (fixup_exception(regs))
 		return;
@@ -518,7 +1299,8 @@ sigbus:
 	return;
 
 sigill:
-	die_if_kernel("Unhandled kernel unaligned access or invalid instruction", regs);
+	die_if_kernel
+	    ("Unhandled kernel unaligned access or invalid instruction", regs);
 	force_sig(SIGILL, current);
 }
 
@@ -531,23 +1313,51 @@ asmlinkage void do_ade(struct pt_regs *regs)
 			1, regs, regs->cp0_badvaddr);
 	/*
 	 * Did we catch a fault trying to load an instruction?
-	 * Or are we running in MIPS16 mode?
 	 */
-	if ((regs->cp0_badvaddr == regs->cp0_epc) || (regs->cp0_epc & 0x1))
+	if (regs->cp0_badvaddr == regs->cp0_epc)
 		goto sigbus;
 
-	pc = (unsigned int __user *) exception_epc(regs);
 	if (user_mode(regs) && !test_thread_flag(TIF_FIXADE))
 		goto sigbus;
 	if (unaligned_action == UNALIGNED_ACTION_SIGNAL)
 		goto sigbus;
-	else if (unaligned_action == UNALIGNED_ACTION_SHOW)
-		show_registers(regs);
 
 	/*
 	 * Do branch emulation only if we didn't forward the exception.
 	 * This is all so but ugly ...
 	 */
+
+	/*
+	 * Are we running in microMIPS mode?
+	 */
+	if (get_isa16_mode(regs->cp0_epc)) {
+		/*
+		 * Did we catch a fault trying to load an instruction in
+		 * 16-bit mode?
+		 */
+		if (regs->cp0_badvaddr == msk_isa16_mode(regs->cp0_epc))
+			goto sigbus;
+		if (unaligned_action == UNALIGNED_ACTION_SHOW)
+			show_registers(regs);
+
+		if (cpu_has_mmips) {
+			seg = get_fs();
+			if (!user_mode(regs))
+				set_fs(KERNEL_DS);
+			emulate_load_store_microMIPS(regs,
+				(void __user *)regs->cp0_badvaddr);
+			set_fs(seg);
+
+			return;
+		}
+
+		goto sigbus;
+	}
+
+	if (unaligned_action == UNALIGNED_ACTION_SHOW)
+		show_registers(regs);
+	pc = (unsigned int __user *)exception_epc(regs);
+
 	seg = get_fs();
 	if (!user_mode(regs))
 		set_fs(KERNEL_DS);