Merge linux-3.0.31 from korg into jellybean

Conflicts:
	arch/arm/mm/proc-v7.S
	drivers/base/core.c
	drivers/gpu/drm/i915/i915_gem_execbuffer.c
	drivers/gpu/drm/i915/intel_display.c
	drivers/gpu/drm/i915/intel_lvds.c
	drivers/gpu/drm/radeon/evergreen.c
	drivers/gpu/drm/radeon/r100.c
	drivers/gpu/drm/radeon/radeon_connectors.c
	drivers/gpu/drm/radeon/rs600.c
	drivers/usb/core/hub.c
	drivers/usb/host/xhci-pci.c
	drivers/usb/host/xhci.c
	drivers/usb/serial/qcserial.c
	fs/proc/base.c

Change-Id: Ia98b35db3f8c0bfd95817867d3acb85be8e5e772

18 files changed, 278 insertions, 1051 deletions

diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile
index ad1fb5d..eddcfb3 100644
--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -31,7 +31,7 @@ UTS_MACHINE    := sparc
 
 #KBUILD_CFLAGS += -g -pipe -fcall-used-g5 -fcall-used-g7
 KBUILD_CFLAGS += -m32 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7
-KBUILD_AFLAGS += -m32
+KBUILD_AFLAGS += -m32 -Wa,-Av8
 
 #LDFLAGS_vmlinux = -N -Ttext 0xf0004000
 #  Since 2.5.40, the first stage is left not btfix-ed.
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 5b31a8e..a790cc6 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -431,10 +431,6 @@ extern unsigned long *sparc_valid_addr_bitmap;
 #define kern_addr_valid(addr) \
 	(test_bit(__pa((unsigned long)(addr))>>20, sparc_valid_addr_bitmap))
 
-extern int io_remap_pfn_range(struct vm_area_struct *vma,
-			      unsigned long from, unsigned long pfn,
-			      unsigned long size, pgprot_t prot);
-
 /*
  * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
  * its high 4 bits.  These macros/functions put it there or get it from there.
@@ -443,6 +439,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma,
 #define GET_IOSPACE(pfn)		(pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)			(pfn & 0x0fffffffUL)
 
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+			   unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+				     unsigned long from, unsigned long pfn,
+				     unsigned long size, pgprot_t prot)
+{
+	unsigned long long offset, space, phys_base;
+
+	offset = ((unsigned long long) GET_PFN(pfn)) << PAGE_SHIFT;
+	space = GET_IOSPACE(pfn);
+	phys_base = offset | (space << 32ULL);
+
+	return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 #define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
 ({									  \
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 1e03c5a..9822628 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -750,10 +750,6 @@ static inline bool kern_addr_valid(unsigned long addr)
 
 extern int page_in_phys_avail(unsigned long paddr);
 
-extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-			       unsigned long pfn,
-			       unsigned long size, pgprot_t prot);
-
 /*
  * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
  * its high 4 bits.  These macros/functions put it there or get it from there.
@@ -762,6 +758,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
 #define GET_IOSPACE(pfn)		(pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)			(pfn & 0x0fffffffffffffffUL)
 
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+			   unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+				     unsigned long from, unsigned long pfn,
+				     unsigned long size, pgprot_t prot)
+{
+	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
+	int space = GET_IOSPACE(pfn);
+	unsigned long phys_base;
+
+	phys_base = offset | (((unsigned long) space) << 32UL);
+
+	return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
 #include <asm-generic/pgtable.h>
 
 /* We provide our own get_unmapped_area to cope with VA holes and
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 7429b47..dcae702 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1269,4 +1269,4 @@ static int __init ds_init(void)
 	return vio_register_driver(&ds_driver);
 }
 
-subsys_initcall(ds_init);
+fs_initcall(ds_init);
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index e27f8ea..0c218e4 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -42,6 +42,9 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 extern void fpload(unsigned long *fpregs, unsigned long *fsr);
 
 #else /* CONFIG_SPARC32 */
+
+#include <asm/trap_block.h>
+
 struct popc_3insn_patch_entry {
 	unsigned int	addr;
 	unsigned int	insns[3];
@@ -57,6 +60,10 @@ extern struct popc_6insn_patch_entry __popc_6insn_patch,
 	__popc_6insn_patch_end;
 
 extern void __init per_cpu_patch(void);
+extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
+				    struct sun4v_1insn_patch_entry *);
+extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+				    struct sun4v_2insn_patch_entry *);
 extern void __init sun4v_patch(void);
 extern void __init boot_cpu_id_too_large(int cpu);
 extern unsigned int dcache_parity_tl1_occurred;
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index 99ba5ba..8172c18 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -17,6 +17,8 @@
 #include <asm/processor.h>
 #include <asm/spitfire.h>
 
+#include "entry.h"
+
 #ifdef CONFIG_SPARC64
 
 #include <linux/jump_label.h>
@@ -220,6 +222,29 @@ int apply_relocate_add(Elf_Shdr *sechdrs,
 }
 
 #ifdef CONFIG_SPARC64
+static void do_patch_sections(const Elf_Ehdr *hdr,
+			      const Elf_Shdr *sechdrs)
+{
+	const Elf_Shdr *s, *sun4v_1insn = NULL, *sun4v_2insn = NULL;
+	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+		if (!strcmp(".sun4v_1insn_patch", secstrings + s->sh_name))
+			sun4v_1insn = s;
+		if (!strcmp(".sun4v_2insn_patch", secstrings + s->sh_name))
+			sun4v_2insn = s;
+	}
+
+	if (sun4v_1insn && tlb_type == hypervisor) {
+		void *p = (void *) sun4v_1insn->sh_addr;
+		sun4v_patch_1insn_range(p, p + sun4v_1insn->sh_size);
+	}
+	if (sun4v_2insn && tlb_type == hypervisor) {
+		void *p = (void *) sun4v_2insn->sh_addr;
+		sun4v_patch_2insn_range(p, p + sun4v_2insn->sh_size);
+	}
+}
+
 int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
@@ -227,6 +252,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	/* make jump label nops */
 	jump_label_apply_nops(me);
 
+	do_patch_sections(hdr, sechdrs);
+
 	/* Cheetah's I-cache is fully coherent.  */
 	if (tlb_type == spitfire) {
 		unsigned long va;
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index b01a06e..9e73c4a 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -848,10 +848,10 @@ static int pci_sun4v_msiq_build_irq(struct pci_pbm_info *pbm,
 	if (!irq)
 		return -ENOMEM;
 
-	if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE))
-		return -EINVAL;
 	if (pci_sun4v_msiq_setvalid(pbm->devhandle, msiqid, HV_MSIQ_VALID))
 		return -EINVAL;
+	if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE))
+		return -EINVAL;
 
 	return irq;
 }
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 77f1b95..9171fc2 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -20,11 +20,6 @@
 
 		.text
 		.align			32
-__handle_softirq:
-		call			do_softirq
-		 nop
-		ba,a,pt			%xcc, __handle_softirq_continue
-		 nop
 __handle_preemption:
 		call			schedule
 		 wrpr			%g0, RTRAP_PSTATE, %pstate
@@ -89,9 +84,7 @@ rtrap:
 		cmp			%l1, 0
 
 		/* mm/ultra.S:xcall_report_regs KNOWS about this load. */
-		bne,pn			%icc, __handle_softirq
 		 ldx			[%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
-__handle_softirq_continue:
 rtrap_xcall:
 		sethi			%hi(0xf << 20), %l4
 		and			%l1, %l4, %l4
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 3c5bb78..4e7d3ff 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -234,40 +234,50 @@ void __init per_cpu_patch(void)
 	}
 }
 
-void __init sun4v_patch(void)
+void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *start,
+			     struct sun4v_1insn_patch_entry *end)
 {
-	extern void sun4v_hvapi_init(void);
-	struct sun4v_1insn_patch_entry *p1;
-	struct sun4v_2insn_patch_entry *p2;
-
-	if (tlb_type != hypervisor)
-		return;
+	while (start < end) {
+		unsigned long addr = start->addr;
 
-	p1 = &__sun4v_1insn_patch;
-	while (p1 < &__sun4v_1insn_patch_end) {
-		unsigned long addr = p1->addr;
-
-		*(unsigned int *) (addr +  0) = p1->insn;
+		*(unsigned int *) (addr +  0) = start->insn;
 		wmb();
 		__asm__ __volatile__("flush	%0" : : "r" (addr +  0));
 
-		p1++;
+		start++;
 	}
+}
 
-	p2 = &__sun4v_2insn_patch;
-	while (p2 < &__sun4v_2insn_patch_end) {
-		unsigned long addr = p2->addr;
+void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+			     struct sun4v_2insn_patch_entry *end)
+{
+	while (start < end) {
+		unsigned long addr = start->addr;
 
-		*(unsigned int *) (addr +  0) = p2->insns[0];
+		*(unsigned int *) (addr +  0) = start->insns[0];
 		wmb();
 		__asm__ __volatile__("flush	%0" : : "r" (addr +  0));
 
-		*(unsigned int *) (addr +  4) = p2->insns[1];
+		*(unsigned int *) (addr +  4) = start->insns[1];
 		wmb();
 		__asm__ __volatile__("flush	%0" : : "r" (addr +  4));
 
-		p2++;
+		start++;
 	}
+}
+
+void __init sun4v_patch(void)
+{
+	extern void sun4v_hvapi_init(void);
+
+	if (tlb_type != hypervisor)
+		return;
+
+	sun4v_patch_1insn_range(&__sun4v_1insn_patch,
+				&__sun4v_1insn_patch_end);
+
+	sun4v_patch_2insn_range(&__sun4v_2insn_patch,
+				&__sun4v_2insn_patch_end);
 
 	sun4v_hvapi_init();
 }
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 5d92488..2e58328 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -829,21 +829,23 @@ static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-void do_signal32(sigset_t *oldset, struct pt_regs * regs,
-		 int restart_syscall, unsigned long orig_i0)
+void do_signal32(sigset_t *oldset, struct pt_regs * regs)
 {
 	struct k_sigaction ka;
+	unsigned long orig_i0;
+	int restart_syscall;
 	siginfo_t info;
 	int signr;
 	
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 
-	/* If the debugger messes with the program counter, it clears
-	 * the "in syscall" bit, directing us to not perform a syscall
-	 * restart.
-	 */
-	if (restart_syscall && !pt_regs_is_syscall(regs))
-		restart_syscall = 0;
+	restart_syscall = 0;
+	orig_i0 = 0;
+	if (pt_regs_is_syscall(regs) &&
+	    (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+		restart_syscall = 1;
+		orig_i0 = regs->u_regs[UREG_G6];
+	}
 
 	if (signr > 0) {
 		if (restart_syscall)
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 04ede8f..2302567 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -525,10 +525,26 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	siginfo_t info;
 	int signr;
 
+	/* It's a lot of work and synchronization to add a new ptrace
+	 * register for GDB to save and restore in order to get
+	 * orig_i0 correct for syscall restarts when debugging.
+	 *
+	 * Although it should be the case that most of the global
+	 * registers are volatile across a system call, glibc already
+	 * depends upon that fact that we preserve them.  So we can't
+	 * just use any global register to save away the orig_i0 value.
+	 *
+	 * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+	 * preserved across a system call trap by various pieces of
+	 * code in glibc.
+	 *
+	 * %g7 is used as the "thread register".   %g6 is not used in
+	 * any fixed manner.  %g6 is used as a scratch register and
+	 * a compiler temporary, but it's value is never used across
+	 * a system call.  Therefore %g6 is usable for orig_i0 storage.
+	 */
 	if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C))
-		restart_syscall = 1;
-	else
-		restart_syscall = 0;
+		regs->u_regs[UREG_G6] = orig_i0;
 
 	if (test_thread_flag(TIF_RESTORE_SIGMASK))
 		oldset = &current->saved_sigmask;
@@ -541,8 +557,12 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	 * the software "in syscall" bit, directing us to not perform
 	 * a syscall restart.
 	 */
-	if (restart_syscall && !pt_regs_is_syscall(regs))
-		restart_syscall = 0;
+	restart_syscall = 0;
+	if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C)) {
+		restart_syscall = 1;
+		orig_i0 = regs->u_regs[UREG_G6];
+	}
+
 
 	if (signr > 0) {
 		if (restart_syscall)
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 47509df..d58260b 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -535,11 +535,27 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	siginfo_t info;
 	int signr;
 	
+	/* It's a lot of work and synchronization to add a new ptrace
+	 * register for GDB to save and restore in order to get
+	 * orig_i0 correct for syscall restarts when debugging.
+	 *
+	 * Although it should be the case that most of the global
+	 * registers are volatile across a system call, glibc already
+	 * depends upon that fact that we preserve them.  So we can't
+	 * just use any global register to save away the orig_i0 value.
+	 *
+	 * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+	 * preserved across a system call trap by various pieces of
+	 * code in glibc.
+	 *
+	 * %g7 is used as the "thread register".   %g6 is not used in
+	 * any fixed manner.  %g6 is used as a scratch register and
+	 * a compiler temporary, but it's value is never used across
+	 * a system call.  Therefore %g6 is usable for orig_i0 storage.
+	 */
 	if (pt_regs_is_syscall(regs) &&
-	    (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
-		restart_syscall = 1;
-	} else
-		restart_syscall = 0;
+	    (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY)))
+		regs->u_regs[UREG_G6] = orig_i0;
 
 	if (current_thread_info()->status & TS_RESTORE_SIGMASK)
 		oldset = &current->saved_sigmask;
@@ -548,22 +564,20 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 
 #ifdef CONFIG_COMPAT
 	if (test_thread_flag(TIF_32BIT)) {
-		extern void do_signal32(sigset_t *, struct pt_regs *,
-					int restart_syscall,
-					unsigned long orig_i0);
-		do_signal32(oldset, regs, restart_syscall, orig_i0);
+		extern void do_signal32(sigset_t *, struct pt_regs *);
+		do_signal32(oldset, regs);
 		return;
 	}
 #endif	
 
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 
-	/* If the debugger messes with the program counter, it clears
-	 * the software "in syscall" bit, directing us to not perform
-	 * a syscall restart.
-	 */
-	if (restart_syscall && !pt_regs_is_syscall(regs))
-		restart_syscall = 0;
+	restart_syscall = 0;
+	if (pt_regs_is_syscall(regs) &&
+	    (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+		restart_syscall = 1;
+		orig_i0 = regs->u_regs[UREG_G6];
+	}
 
 	if (signr > 0) {
 		if (restart_syscall)
diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c
index 3635771..9384a0c 100644
--- a/arch/sparc/kernel/visemul.c
+++ b/arch/sparc/kernel/visemul.c
@@ -713,17 +713,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 			s16 b = (rs2 >> (i * 16)) & 0xffff;
 
 			if (a > b)
-				rd_val |= 1 << i;
+				rd_val |= 8 >> i;
 		}
 		break;
 
 	case FCMPGT32_OPF:
 		for (i = 0; i < 2; i++) {
-			s32 a = (rs1 >> (i * 32)) & 0xffff;
-			s32 b = (rs2 >> (i * 32)) & 0xffff;
+			s32 a = (rs1 >> (i * 32)) & 0xffffffff;
+			s32 b = (rs2 >> (i * 32)) & 0xffffffff;
 
 			if (a > b)
-				rd_val |= 1 << i;
+				rd_val |= 2 >> i;
 		}
 		break;
 
@@ -733,17 +733,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 			s16 b = (rs2 >> (i * 16)) & 0xffff;
 
 			if (a <= b)
-				rd_val |= 1 << i;
+				rd_val |= 8 >> i;
 		}
 		break;
 
 	case FCMPLE32_OPF:
 		for (i = 0; i < 2; i++) {
-			s32 a = (rs1 >> (i * 32)) & 0xffff;
-			s32 b = (rs2 >> (i * 32)) & 0xffff;
+			s32 a = (rs1 >> (i * 32)) & 0xffffffff;
+			s32 b = (rs2 >> (i * 32)) & 0xffffffff;
 
 			if (a <= b)
-				rd_val |= 1 << i;
+				rd_val |= 2 >> i;
 		}
 		break;
 
@@ -753,17 +753,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 			s16 b = (rs2 >> (i * 16)) & 0xffff;
 
 			if (a != b)
-				rd_val |= 1 << i;
+				rd_val |= 8 >> i;
 		}
 		break;
 
 	case FCMPNE32_OPF:
 		for (i = 0; i < 2; i++) {
-			s32 a = (rs1 >> (i * 32)) & 0xffff;
-			s32 b = (rs2 >> (i * 32)) & 0xffff;
+			s32 a = (rs1 >> (i * 32)) & 0xffffffff;
+			s32 b = (rs2 >> (i * 32)) & 0xffffffff;
 
 			if (a != b)
-				rd_val |= 1 << i;
+				rd_val |= 2 >> i;
 		}
 		break;
 
@@ -773,17 +773,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf)
 			s16 b = (rs2 >> (i * 16)) & 0xffff;
 
 			if (a == b)
-				rd_val |= 1 << i;
+				rd_val |= 8 >> i;
 		}
 		break;
 
 	case FCMPEQ32_OPF:
 		for (i = 0; i < 2; i++) {
-			s32 a = (rs1 >> (i * 32)) & 0xffff;
-			s32 b = (rs2 >> (i * 32)) & 0xffff;
+			s32 a = (rs1 >> (i * 32)) & 0xffffffff;
+			s32 b = (rs2 >> (i * 32)) & 0xffffffff;
 
 			if (a == b)
-				rd_val |= 1 << i;
+				rd_val |= 2 >> i;
 		}
 		break;
 	}
diff --git a/arch/sparc/lib/memcpy.S b/arch/sparc/lib/memcpy.S
index 34fe657..4d8c497 100644
--- a/arch/sparc/lib/memcpy.S
+++ b/arch/sparc/lib/memcpy.S
@@ -7,40 +7,12 @@
  * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
  */
 
-#ifdef __KERNEL__
-
-#define FUNC(x) 											\
+#define FUNC(x) 		\
 	.globl	x;		\
 	.type	x,@function;	\
-	.align	4;											\
+	.align	4;		\
 x:
 
-#undef FASTER_REVERSE
-#undef FASTER_NONALIGNED
-#define FASTER_ALIGNED
-
-/* In kernel these functions don't return a value.
- * One should use macros in asm/string.h for that purpose.
- * We return 0, so that bugs are more apparent.
- */
-#define SETUP_RETL
-#define RETL_INSN	clr	%o0
-
-#else
-
-/* libc */
-
-#include "DEFS.h"
-
-#define FASTER_REVERSE
-#define FASTER_NONALIGNED
-#define FASTER_ALIGNED
-
-#define SETUP_RETL	mov	%o0, %g6
-#define RETL_INSN	mov	%g6, %o0
-
-#endif
-
 /* Both these macros have to start with exactly the same insn */
 #define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
 	ldd	[%src + (offset) + 0x00], %t0; \
@@ -164,30 +136,6 @@ x:
 	.text
 	.align	4
 
-#ifdef FASTER_REVERSE
-
-70:	/* rdword_align */
-
-	andcc		%o1, 1, %g0
-	be		4f
-	 andcc		%o1, 2, %g0
-
-	ldub		[%o1 - 1], %g2
-	sub		%o1, 1, %o1
-	stb		%g2, [%o0 - 1]
-	sub		%o2, 1, %o2
-	be		3f
-	 sub		%o0, 1, %o0
-4:
-	lduh		[%o1 - 2], %g2
-	sub		%o1, 2, %o1
-	sth		%g2, [%o0 - 2]
-	sub		%o2, 2, %o2
-	b		3f
-	 sub		%o0, 2, %o0
-
-#endif /* FASTER_REVERSE */
-
 0:
 	retl
 	 nop		! Only bcopy returns here and it retuns void...
@@ -198,7 +146,7 @@ FUNC(__memmove)
 #endif
 FUNC(memmove)
 	cmp		%o0, %o1
-	SETUP_RETL
+	mov		%o0, %g7
 	bleu		9f
 	 sub		%o0, %o1, %o4
 
@@ -207,8 +155,6 @@ FUNC(memmove)
 	bleu		0f
 	 andcc		%o4, 3, %o5
 
-#ifndef FASTER_REVERSE
-
 	add		%o1, %o2, %o1
 	add		%o0, %o2, %o0
 	sub		%o1, 1, %o1
@@ -224,295 +170,7 @@ FUNC(memmove)
 	 sub		%o0, 1, %o0
 
 	retl
-	 RETL_INSN
-
-#else /* FASTER_REVERSE */
-
-	add		%o1, %o2, %o1
-	add		%o0, %o2, %o0
-	bne		77f
-	 cmp		%o2, 15
-	bleu		91f
-	 andcc		%o1, 3, %g0
-	bne		70b
-3:
-	 andcc		%o1, 4, %g0
-
-	be		2f
-	 mov		%o2, %g1
-
-	ld		[%o1 - 4], %o4
-	sub		%g1, 4, %g1
-	st		%o4, [%o0 - 4]
-	sub		%o1, 4, %o1
-	sub		%o0, 4, %o0
-2:
-	andcc		%g1, 0xffffff80, %g7
-	be		3f
-	 andcc		%o0, 4, %g0
-
-	be		74f + 4
-5:
-	RMOVE_BIGCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5)
-	RMOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
-	RMOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
-	RMOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-	subcc		%g7, 128, %g7
-	sub		%o1, 128, %o1
-	bne		5b
-	 sub		%o0, 128, %o0
-3:
-	andcc		%g1, 0x70, %g7
-	be		72f
-	 andcc		%g1, 8, %g0
-
-	sethi		%hi(72f), %o5
-	srl		%g7, 1, %o4
-	add		%g7, %o4, %o4
-	sub		%o1, %g7, %o1
-	sub		%o5, %o4, %o5
-	jmpl		%o5 + %lo(72f), %g0
-	 sub		%o0, %g7, %o0
-
-71:	/* rmemcpy_table */
-	RMOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5)
-	RMOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5)
-	RMOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5)
-	RMOVE_LASTCHUNK(o1, o0, 0x30, g2, g3, g4, g5)
-	RMOVE_LASTCHUNK(o1, o0, 0x20, g2, g3, g4, g5)
-	RMOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5)
-	RMOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
-
-72:	/* rmemcpy_table_end */
-
-	be		73f
-	 andcc		%g1, 4, %g0
-
-	ldd		[%o1 - 0x08], %g2
-	sub		%o0, 8, %o0
-	sub		%o1, 8, %o1
-	st		%g2, [%o0]
-	st		%g3, [%o0 + 0x04]
-
-73:	/* rmemcpy_last7 */
-
-	be		1f
-	 andcc		%g1, 2, %g0
-
-	ld		[%o1 - 4], %g2
-	sub		%o1, 4, %o1
-	st		%g2, [%o0 - 4]
-	sub		%o0, 4, %o0
-1:
-	be		1f
-	 andcc		%g1, 1, %g0
-
-	lduh		[%o1 - 2], %g2
-	sub		%o1, 2, %o1
-	sth		%g2, [%o0 - 2]
-	sub		%o0, 2, %o0
-1:
-	be		1f
-	 nop
-
-	ldub		[%o1 - 1], %g2
-	stb		%g2, [%o0 - 1]
-1:
-	retl
- 	 RETL_INSN
-
-74:	/* rldd_std */
-	RMOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5)
-	RMOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
-	RMOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
-	RMOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-	subcc		%g7, 128, %g7
-	sub		%o1, 128, %o1
-	bne		74b
-	 sub		%o0, 128, %o0
-
-	andcc		%g1, 0x70, %g7
-	be		72b
-	 andcc		%g1, 8, %g0
-
-	sethi		%hi(72b), %o5
-	srl		%g7, 1, %o4
-	add		%g7, %o4, %o4
-	sub		%o1, %g7, %o1
-	sub		%o5, %o4, %o5
-	jmpl		%o5 + %lo(72b), %g0
-	 sub		%o0, %g7, %o0
-
-75:	/* rshort_end */
-
-	and		%o2, 0xe, %o3
-2:
-	sethi		%hi(76f), %o5
-	sll		%o3, 3, %o4
-	sub		%o0, %o3, %o0
-	sub		%o5, %o4, %o5
-	sub		%o1, %o3, %o1
-	jmpl		%o5 + %lo(76f), %g0
-	 andcc		%o2, 1, %g0
-
-	RMOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
-	RMOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
-	RMOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3)
-	RMOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3)
-	RMOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3)
-	RMOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3)
-	RMOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3)
-
-76:	/* rshort_table_end */
-
-	be		1f
-	 nop
-	ldub		[%o1 - 1], %g2
-	stb		%g2, [%o0 - 1]
-1:
-	retl
- 	 RETL_INSN
-
-91:	/* rshort_aligned_end */
-
-	bne		75b
-	 andcc		%o2, 8, %g0
-
-	be		1f
-	 andcc		%o2, 4, %g0
-
-	ld		[%o1 - 0x08], %g2
-	ld		[%o1 - 0x04], %g3
-	sub		%o1, 8, %o1
-	st		%g2, [%o0 - 0x08]
-	st		%g3, [%o0 - 0x04]
-	sub		%o0, 8, %o0
-1:
-	b		73b
-	 mov		%o2, %g1
-
-77:	/* rnon_aligned */
-	cmp		%o2, 15
-	bleu		75b
-	 andcc		%o0, 3, %g0
-	be		64f
-	 andcc		%o0, 1, %g0
-	be		63f
-	 andcc		%o0, 2, %g0
-	ldub		[%o1 - 1], %g5
-	sub		%o1, 1, %o1
-	stb		%g5, [%o0 - 1]
-	sub		%o0, 1, %o0
-	be		64f
-	 sub		%o2, 1, %o2
-63:
-	ldub		[%o1 - 1], %g5
-	sub		%o1, 2, %o1
-	stb		%g5, [%o0 - 1]
-	sub		%o0, 2, %o0
-	ldub		[%o1], %g5
-	sub		%o2, 2, %o2
-	stb		%g5, [%o0]
-64:	
-	and		%o1, 3, %g2
-	and		%o1, -4, %o1
-	and		%o2, 0xc, %g3
-	add		%o1, 4, %o1
-	cmp		%g3, 4
-	sll		%g2, 3, %g4
-	mov		32, %g2
-	be		4f
-	 sub		%g2, %g4, %g7
-
-	blu		3f
-	 cmp		%g3, 8
-
-	be		2f
-	 srl		%o2, 2, %g3
-
-	ld		[%o1 - 4], %o3
-	add		%o0, -8, %o0
-	ld		[%o1 - 8], %o4
-	add		%o1, -16, %o1
-	b		7f
-	 add		%g3, 1, %g3
-2:
-	ld		[%o1 - 4], %o4
-	add		%o0, -4, %o0
-	ld		[%o1 - 8], %g1
-	add		%o1, -12, %o1
-	b		8f
-	 add		%g3, 2, %g3
-3:
-	ld		[%o1 - 4], %o5
-	add		%o0, -12, %o0
-	ld		[%o1 - 8], %o3
-	add		%o1, -20, %o1
-	b		6f
-	 srl		%o2, 2, %g3
-4:
-	ld		[%o1 - 4], %g1
-	srl		%o2, 2, %g3
-	ld		[%o1 - 8], %o5
-	add		%o1, -24, %o1
-	add		%o0, -16, %o0
-	add		%g3, -1, %g3
-
-	ld		[%o1 + 12], %o3
-5:
-	sll		%o5, %g4, %g2
-	srl		%g1, %g7, %g5
-	or		%g2, %g5, %g2
-	st		%g2, [%o0 + 12]
-6:
-	ld		[%o1 + 8], %o4
-	sll		%o3, %g4, %g2
-	srl		%o5, %g7, %g5
-	or		%g2, %g5, %g2
-	st		%g2, [%o0 + 8]
-7:
-	ld		[%o1 + 4], %g1
-	sll		%o4, %g4, %g2
-	srl		%o3, %g7, %g5
-	or		%g2, %g5, %g2
-	st		%g2, [%o0 + 4]
-8:
-	ld		[%o1], %o5
-	sll		%g1, %g4, %g2
-	srl		%o4, %g7, %g5
-	addcc		%g3, -4, %g3
-	or		%g2, %g5, %g2
-	add		%o1, -16, %o1
-	st		%g2, [%o0]
-	add		%o0, -16, %o0
-	bne,a		5b	
-	 ld		[%o1 + 12], %o3
-	sll		%o5, %g4, %g2
-	srl		%g1, %g7, %g5
-	srl		%g4, 3, %g3
-	or		%g2, %g5, %g2
-	add		%o1, %g3, %o1
-	andcc		%o2, 2, %g0
-	st		%g2, [%o0 + 12]
-	be		1f
-	 andcc		%o2, 1, %g0
-	
-	ldub		[%o1 + 15], %g5
-	add		%o1, -2, %o1
-	stb		%g5, [%o0 + 11]
-	add		%o0, -2, %o0
-	ldub		[%o1 + 16], %g5
-	stb		%g5, [%o0 + 12]
-1:
-	be		1f
-	 nop
-	ldub		[%o1 + 15], %g5
-	stb		%g5, [%o0 + 11]
-1:
-	retl
-	 RETL_INSN
-
-#endif /* FASTER_REVERSE */
+	 mov		%g7, %o0
 
 /* NOTE: This code is executed just for the cases,
          where %src (=%o1) & 3 is != 0.
@@ -546,7 +204,7 @@ FUNC(memmove)
 FUNC(memcpy)	/* %o0=dst %o1=src %o2=len */
 
 	sub		%o0, %o1, %o4
-	SETUP_RETL
+	mov		%o0, %g7
 9:
 	andcc		%o4, 3, %o5
 0:
@@ -569,7 +227,7 @@ FUNC(memcpy)	/* %o0=dst %o1=src %o2=len */
 	add		%o1, 4, %o1
 	add		%o0, 4, %o0
 2:
-	andcc		%g1, 0xffffff80, %g7
+	andcc		%g1, 0xffffff80, %g0
 	be		3f
 	 andcc		%o0, 4, %g0
 
@@ -579,22 +237,23 @@ FUNC(memcpy)	/* %o0=dst %o1=src %o2=len */
 	MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-	subcc		%g7, 128, %g7
+	sub		%g1, 128, %g1
 	add		%o1, 128, %o1
-	bne		5b
+	cmp		%g1, 128
+	bge		5b
 	 add		%o0, 128, %o0
 3:
-	andcc		%g1, 0x70, %g7
+	andcc		%g1, 0x70, %g4
 	be		80f
 	 andcc		%g1, 8, %g0
 
 	sethi		%hi(80f), %o5
-	srl		%g7, 1, %o4
-	add		%g7, %o4, %o4
-	add		%o1, %g7, %o1
+	srl		%g4, 1, %o4
+	add		%g4, %o4, %o4
+	add		%o1, %g4, %o1
 	sub		%o5, %o4, %o5
 	jmpl		%o5 + %lo(80f), %g0
-	 add		%o0, %g7, %o0
+	 add		%o0, %g4, %o0
 
 79:	/* memcpy_table */
 
@@ -641,43 +300,28 @@ FUNC(memcpy)	/* %o0=dst %o1=src %o2=len */
 	stb		%g2, [%o0]
 1:
 	retl
- 	 RETL_INSN
+	 mov		%g7, %o0
 
 82:	/* ldd_std */
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-	subcc		%g7, 128, %g7
+	subcc		%g1, 128, %g1
 	add		%o1, 128, %o1
-	bne		82b
+	cmp		%g1, 128
+	bge		82b
 	 add		%o0, 128, %o0
 
-#ifndef FASTER_ALIGNED
-
-	andcc		%g1, 0x70, %g7
-	be		80b
-	 andcc		%g1, 8, %g0
-
-	sethi		%hi(80b), %o5
-	srl		%g7, 1, %o4
-	add		%g7, %o4, %o4
-	add		%o1, %g7, %o1
-	sub		%o5, %o4, %o5
-	jmpl		%o5 + %lo(80b), %g0
-	 add		%o0, %g7, %o0
-
-#else /* FASTER_ALIGNED */
-
-	andcc		%g1, 0x70, %g7
+	andcc		%g1, 0x70, %g4
 	be		84f
 	 andcc		%g1, 8, %g0
 
 	sethi		%hi(84f), %o5
-	add		%o1, %g7, %o1
-	sub		%o5, %g7, %o5
+	add		%o1, %g4, %o1
+	sub		%o5, %g4, %o5
 	jmpl		%o5 + %lo(84f), %g0
-	 add		%o0, %g7, %o0
+	 add		%o0, %g4, %o0
 
 83:	/* amemcpy_table */
 
@@ -721,382 +365,132 @@ FUNC(memcpy)	/* %o0=dst %o1=src %o2=len */
 	stb		%g2, [%o0]
 1:
 	retl
- 	 RETL_INSN
-
-#endif /* FASTER_ALIGNED */
+	 mov		%g7, %o0
 
 86:	/* non_aligned */
 	cmp		%o2, 6
 	bleu		88f
+	 nop
 
-#ifdef FASTER_NONALIGNED
-
-	 cmp		%o2, 256
-	bcc		87f
-
-#endif /* FASTER_NONALIGNED */
-
-	 andcc		%o0, 3, %g0
+	save		%sp, -96, %sp
+	andcc		%i0, 3, %g0
 	be		61f
-	 andcc		%o0, 1, %g0
+	 andcc		%i0, 1, %g0
 	be		60f
-	 andcc		%o0, 2, %g0
+	 andcc		%i0, 2, %g0
 
-	ldub		[%o1], %g5
-	add		%o1, 1, %o1
-	stb		%g5, [%o0]
-	sub		%o2, 1, %o2
+	ldub		[%i1], %g5
+	add		%i1, 1, %i1
+	stb		%g5, [%i0]
+	sub		%i2, 1, %i2
 	bne		61f
-	 add		%o0, 1, %o0
+	 add		%i0, 1, %i0
 60:
-	ldub		[%o1], %g3
-	add		%o1, 2, %o1
-	stb		%g3, [%o0]
-	sub		%o2, 2, %o2
-	ldub		[%o1 - 1], %g3
-	add		%o0, 2, %o0
-	stb		%g3, [%o0 - 1]
+	ldub		[%i1], %g3
+	add		%i1, 2, %i1
+	stb		%g3, [%i0]
+	sub		%i2, 2, %i2
+	ldub		[%i1 - 1], %g3
+	add		%i0, 2, %i0
+	stb		%g3, [%i0 - 1]
 61:
-	and		%o1, 3, %g2
-	and		%o2, 0xc, %g3
-	and		%o1, -4, %o1
+	and		%i1, 3, %g2
+	and		%i2, 0xc, %g3
+	and		%i1, -4, %i1
 	cmp		%g3, 4
 	sll		%g2, 3, %g4
 	mov		32, %g2
 	be		4f
-	 sub		%g2, %g4, %g7
+	 sub		%g2, %g4, %l0
 	
 	blu		3f
 	 cmp		%g3, 0x8
 
 	be		2f
-	 srl		%o2, 2, %g3
+	 srl		%i2, 2, %g3
 
-	ld		[%o1], %o3
-	add		%o0, -8, %o0
-	ld		[%o1 + 4], %o4
+	ld		[%i1], %i3
+	add		%i0, -8, %i0
+	ld		[%i1 + 4], %i4
 	b		8f
 	 add		%g3, 1, %g3
 2:
-	ld		[%o1], %o4
-	add		%o0, -12, %o0
-	ld		[%o1 + 4], %o5
+	ld		[%i1], %i4
+	add		%i0, -12, %i0
+	ld		[%i1 + 4], %i5
 	add		%g3, 2, %g3
 	b		9f
-	 add		%o1, -4, %o1
+	 add		%i1, -4, %i1
 3:
-	ld		[%o1], %g1
-	add		%o0, -4, %o0
-	ld		[%o1 + 4], %o3
-	srl		%o2, 2, %g3
+	ld		[%i1], %g1
+	add		%i0, -4, %i0
+	ld		[%i1 + 4], %i3
+	srl		%i2, 2, %g3
 	b		7f
-	 add		%o1, 4, %o1
+	 add		%i1, 4, %i1
 4:
-	ld		[%o1], %o5
-	cmp		%o2, 7
-	ld		[%o1 + 4], %g1
-	srl		%o2, 2, %g3
+	ld		[%i1], %i5
+	cmp		%i2, 7
+	ld		[%i1 + 4], %g1
+	srl		%i2, 2, %g3
 	bleu		10f
-	 add		%o1, 8, %o1
+	 add		%i1, 8, %i1
 
-	ld		[%o1], %o3
+	ld		[%i1], %i3
 	add		%g3, -1, %g3
 5:
-	sll		%o5, %g4, %g2
-	srl		%g1, %g7, %g5
+	sll		%i5, %g4, %g2
+	srl		%g1, %l0, %g5
 	or		%g2, %g5, %g2
-	st		%g2, [%o0]
+	st		%g2, [%i0]
 7:
-	ld		[%o1 + 4], %o4
+	ld		[%i1 + 4], %i4
 	sll		%g1, %g4, %g2
-	srl		%o3, %g7, %g5
+	srl		%i3, %l0, %g5
 	or		%g2, %g5, %g2
-	st		%g2, [%o0 + 4]
+	st		%g2, [%i0 + 4]
 8:
-	ld		[%o1 + 8], %o5
-	sll		%o3, %g4, %g2
-	srl		%o4, %g7, %g5
+	ld		[%i1 + 8], %i5
+	sll		%i3, %g4, %g2
+	srl		%i4, %l0, %g5
 	or		%g2, %g5, %g2
-	st		%g2, [%o0 + 8]
+	st		%g2, [%i0 + 8]
 9:
-	ld		[%o1 + 12], %g1
-	sll		%o4, %g4, %g2
-	srl		%o5, %g7, %g5
+	ld		[%i1 + 12], %g1
+	sll		%i4, %g4, %g2
+	srl		%i5, %l0, %g5
 	addcc		%g3, -4, %g3
 	or		%g2, %g5, %g2
-	add		%o1, 16, %o1
-	st		%g2, [%o0 + 12]
-	add		%o0, 16, %o0
+	add		%i1, 16, %i1
+	st		%g2, [%i0 + 12]
+	add		%i0, 16, %i0
 	bne,a		5b
-	 ld		[%o1], %o3
+	 ld		[%i1], %i3
 10:
-	sll		%o5, %g4, %g2
-	srl		%g1, %g7, %g5
-	srl		%g7, 3, %g3
+	sll		%i5, %g4, %g2
+	srl		%g1, %l0, %g5
+	srl		%l0, 3, %g3
 	or		%g2, %g5, %g2
-	sub		%o1, %g3, %o1
-	andcc		%o2, 2, %g0
-	st		%g2, [%o0]
+	sub		%i1, %g3, %i1
+	andcc		%i2, 2, %g0
+	st		%g2, [%i0]
 	be		1f
-	 andcc		%o2, 1, %g0
-
-	ldub		[%o1], %g2
-	add		%o1, 2, %o1
-	stb		%g2, [%o0 + 4]
-	add		%o0, 2, %o0
-	ldub		[%o1 - 1], %g2
-	stb		%g2, [%o0 + 3]
+	 andcc		%i2, 1, %g0
+
+	ldub		[%i1], %g2
+	add		%i1, 2, %i1
+	stb		%g2, [%i0 + 4]
+	add		%i0, 2, %i0
+	ldub		[%i1 - 1], %g2
+	stb		%g2, [%i0 + 3]
 1:
 	be		1f
 	 nop
-	ldub		[%o1], %g2
-	stb		%g2, [%o0 + 4]
-1:
-	retl
-	 RETL_INSN
-
-#ifdef FASTER_NONALIGNED
-
-87:	/* faster_nonaligned */
-
-	andcc		%o1, 3, %g0
-	be		3f
-	 andcc		%o1, 1, %g0
-
-	be		4f
-	 andcc		%o1, 2, %g0
-
-	ldub		[%o1], %g2
-	add		%o1, 1, %o1
-	stb		%g2, [%o0]
-	sub		%o2, 1, %o2
-	bne		3f
-	 add		%o0, 1, %o0
-4:
-	lduh		[%o1], %g2
-	add		%o1, 2, %o1
-	srl		%g2, 8, %g3
-	sub		%o2, 2, %o2
-	stb		%g3, [%o0]
-	add		%o0, 2, %o0
-	stb		%g2, [%o0 - 1]
-3:
-	 andcc		%o1, 4, %g0
-
-	bne		2f
-	 cmp		%o5, 1
-
-	ld		[%o1], %o4
-	srl		%o4, 24, %g2
-	stb		%g2, [%o0]
-	srl		%o4, 16, %g3
-	stb		%g3, [%o0 + 1]
-	srl		%o4, 8, %g2
-	stb		%g2, [%o0 + 2]
-	sub		%o2, 4, %o2
-	stb		%o4, [%o0 + 3]
-	add		%o1, 4, %o1
-	add		%o0, 4, %o0
-2:
-	be		33f
-	 cmp		%o5, 2
-	be		32f
-	 sub		%o2, 4, %o2
-31:
-	ld		[%o1], %g2
-	add		%o1, 4, %o1
-	srl		%g2, 24, %g3
-	and		%o0, 7, %g5
-	stb		%g3, [%o0]
-	cmp		%g5, 7
-	sll		%g2, 8, %g1
-	add		%o0, 4, %o0
-	be		41f
-	 and		%o2, 0xffffffc0, %o3
-	ld		[%o0 - 7], %o4
-4:
-	SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	subcc		%o3, 64, %o3
-	add		%o1, 64, %o1
-	bne		4b
-	 add		%o0, 64, %o0
-
-	andcc		%o2, 0x30, %o3
-	be,a		1f
-	 srl		%g1, 16, %g2
-4:
-	SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	subcc		%o3, 16, %o3
-	add		%o1, 16, %o1
-	bne		4b
-	 add		%o0, 16, %o0
-
-	srl		%g1, 16, %g2
-1:
-	st		%o4, [%o0 - 7]
-	sth		%g2, [%o0 - 3]
-	srl		%g1, 8, %g4
-	b		88f
-	 stb		%g4, [%o0 - 1]
-32:
-	ld		[%o1], %g2
-	add		%o1, 4, %o1
-	srl		%g2, 16, %g3
-	and		%o0, 7, %g5
-	sth		%g3, [%o0]
-	cmp		%g5, 6
-	sll		%g2, 16, %g1
-	add		%o0, 4, %o0
-	be		42f
-	 and		%o2, 0xffffffc0, %o3
-	ld		[%o0 - 6], %o4
-4:
-	SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	subcc		%o3, 64, %o3
-	add		%o1, 64, %o1
-	bne		4b
-	 add		%o0, 64, %o0
-
-	andcc		%o2, 0x30, %o3
-	be,a		1f
-	 srl		%g1, 16, %g2
-4:
-	SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	subcc		%o3, 16, %o3
-	add		%o1, 16, %o1
-	bne		4b
-	 add		%o0, 16, %o0
-
-	srl		%g1, 16, %g2
-1:
-	st		%o4, [%o0 - 6]
-	b		88f
-	 sth		%g2, [%o0 - 2]
-33:
-	ld		[%o1], %g2
-	sub		%o2, 4, %o2
-	srl		%g2, 24, %g3
-	and		%o0, 7, %g5
-	stb		%g3, [%o0]
-	cmp		%g5, 5
-	srl		%g2, 8, %g4
-	sll		%g2, 24, %g1
-	sth		%g4, [%o0 + 1]
-	add		%o1, 4, %o1
-	be		43f
-	 and		%o2, 0xffffffc0, %o3
-
-	ld		[%o0 - 1], %o4
-	add		%o0, 4, %o0
-4:
-	SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1)
-	SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1)
-	SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1)
-	SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1)
-	subcc		%o3, 64, %o3
-	add		%o1, 64, %o1
-	bne		4b
-	 add		%o0, 64, %o0
-
-	andcc		%o2, 0x30, %o3
-	be,a		1f
-	 srl		%g1, 24, %g2
-4:
-	SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1)
-	subcc		%o3, 16, %o3
-	add		%o1, 16, %o1
-	bne		4b
-	 add		%o0, 16, %o0
-
-	srl		%g1, 24, %g2
-1:
-	st		%o4, [%o0 - 5]
-	b		88f
-	 stb		%g2, [%o0 - 1]
-41:
-	SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	subcc		%o3, 64, %o3
-	add		%o1, 64, %o1
-	bne		41b
-	 add		%o0, 64, %o0
-	 
-	andcc		%o2, 0x30, %o3
-	be,a		1f
-	 srl		%g1, 16, %g2
-4:
-	SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3)
-	subcc		%o3, 16, %o3
-	add		%o1, 16, %o1
-	bne		4b
-	 add		%o0, 16, %o0
-
-	srl		%g1, 16, %g2
+	ldub		[%i1], %g2
+	stb		%g2, [%i0 + 4]
 1:
-	sth		%g2, [%o0 - 3]
-	srl		%g1, 8, %g4
-	b		88f
-	 stb		%g4, [%o0 - 1]
-43:
-	SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3)
-	SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3)
-	SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3)
-	SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3)
-	subcc		%o3, 64, %o3
-	add		%o1, 64, %o1
-	bne		43b
-	 add		%o0, 64, %o0
-
-	andcc		%o2, 0x30, %o3
-	be,a		1f
-	 srl		%g1, 24, %g2
-4:
-	SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3)
-	subcc		%o3, 16, %o3
-	add		%o1, 16, %o1
-	bne		4b
-	 add		%o0, 16, %o0
-
-	srl		%g1, 24, %g2
-1:
-	stb		%g2, [%o0 + 3]
-	b		88f
-	 add		%o0, 4, %o0
-42:
-	SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	subcc		%o3, 64, %o3
-	add		%o1, 64, %o1
-	bne		42b
-	 add		%o0, 64, %o0
-	 
-	andcc		%o2, 0x30, %o3
-	be,a		1f
-	 srl		%g1, 16, %g2
-4:
-	SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2)
-	subcc		%o3, 16, %o3
-	add		%o1, 16, %o1
-	bne		4b
-	 add		%o0, 16, %o0
-
-	srl		%g1, 16, %g2
-1:
-	sth		%g2, [%o0 - 2]
-
-	/* Fall through */
-	 
-#endif /* FASTER_NONALIGNED */
+	ret
+	 restore	%g7, %g0, %o0
 
 88:	/* short_end */
 
@@ -1127,7 +521,7 @@ FUNC(memcpy)	/* %o0=dst %o1=src %o2=len */
 	stb		%g2, [%o0]
 1:
 	retl
- 	 RETL_INSN
+	 mov		%g7, %o0
 
 90:	/* short_aligned_end */
 	bne		88b
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index 79836a7..3b6e248 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -8,7 +8,6 @@ obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o
 obj-y                   += fault_$(BITS).o
 obj-y                   += init_$(BITS).o
 obj-$(CONFIG_SPARC32)   += loadmmu.o
-obj-y                   += generic_$(BITS).o
 obj-$(CONFIG_SPARC32)   += extable.o btfixup.o srmmu.o iommu.o io-unit.o
 obj-$(CONFIG_SPARC32)   += hypersparc.o viking.o tsunami.o swift.o
 obj-$(CONFIG_SPARC_LEON)+= leon_mm.o
diff --git a/arch/sparc/mm/btfixup.c b/arch/sparc/mm/btfixup.c
index 5175ac2..8a7f817 100644
--- a/arch/sparc/mm/btfixup.c
+++ b/arch/sparc/mm/btfixup.c
@@ -302,8 +302,7 @@ void __init btfixup(void)
 				case 'i':	/* INT */
 					if ((insn & 0xc1c00000) == 0x01000000) /* %HI */
 						set_addr(addr, q[1], fmangled, (insn & 0xffc00000) | (p[1] >> 10));
-					else if ((insn & 0x80002000) == 0x80002000 &&
-					         (insn & 0x01800000) != 0x01800000) /* %LO */
+					else if ((insn & 0x80002000) == 0x80002000) /* %LO */
 						set_addr(addr, q[1], fmangled, (insn & 0xffffe000) | (p[1] & 0x3ff));
 					else {
 						prom_printf(insn_i, p, addr, insn);
diff --git a/arch/sparc/mm/generic_32.c b/arch/sparc/mm/generic_32.c
deleted file mode 100644
index e6067b7..0000000
--- a/arch/sparc/mm/generic_32.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- *            MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/pagemap.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, unsigned long address, unsigned long size,
-	unsigned long offset, pgprot_t prot, int space)
-{
-	unsigned long end;
-
-	address &= ~PMD_MASK;
-	end = address + size;
-	if (end > PMD_SIZE)
-		end = PMD_SIZE;
-	do {
-		set_pte_at(mm, address, pte, mk_pte_io(offset, prot, space));
-		address += PAGE_SIZE;
-		offset += PAGE_SIZE;
-		pte++;
-	} while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
-	unsigned long offset, pgprot_t prot, int space)
-{
-	unsigned long end;
-
-	address &= ~PGDIR_MASK;
-	end = address + size;
-	if (end > PGDIR_SIZE)
-		end = PGDIR_SIZE;
-	offset -= address;
-	do {
-		pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
-		if (!pte)
-			return -ENOMEM;
-		io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
-		address = (address + PMD_SIZE) & PMD_MASK;
-		pmd++;
-	} while (address < end);
-	return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-		       unsigned long pfn, unsigned long size, pgprot_t prot)
-{
-	int error = 0;
-	pgd_t * dir;
-	unsigned long beg = from;
-	unsigned long end = from + size;
-	struct mm_struct *mm = vma->vm_mm;
-	int space = GET_IOSPACE(pfn);
-	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
-
-	/* See comment in mm/memory.c remap_pfn_range */
-	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
-	vma->vm_pgoff = (offset >> PAGE_SHIFT) |
-		((unsigned long)space << 28UL);
-
-	offset -= from;
-	dir = pgd_offset(mm, from);
-	flush_cache_range(vma, beg, end);
-
-	while (from < end) {
-		pmd_t *pmd = pmd_alloc(mm, dir, from);
-		error = -ENOMEM;
-		if (!pmd)
-			break;
-		error = io_remap_pmd_range(mm, pmd, from, end - from, offset + from, prot, space);
-		if (error)
-			break;
-		from = (from + PGDIR_SIZE) & PGDIR_MASK;
-		dir++;
-	}
-
-	flush_tlb_range(vma, beg, end);
-	return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);
diff --git a/arch/sparc/mm/generic_64.c b/arch/sparc/mm/generic_64.c
deleted file mode 100644
index 3cb00df..0000000
--- a/arch/sparc/mm/generic_64.c
+++ /dev/null
@@ -1,164 +0,0 @@
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- *            MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/pagemap.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte,
-				      unsigned long address,
-				      unsigned long size,
-				      unsigned long offset, pgprot_t prot,
-				      int space)
-{
-	unsigned long end;
-
-	/* clear hack bit that was used as a write_combine side-effect flag */
-	offset &= ~0x1UL;
-	address &= ~PMD_MASK;
-	end = address + size;
-	if (end > PMD_SIZE)
-		end = PMD_SIZE;
-	do {
-		pte_t entry;
-		unsigned long curend = address + PAGE_SIZE;
-		
-		entry = mk_pte_io(offset, prot, space, PAGE_SIZE);
-		if (!(address & 0xffff)) {
-			if (PAGE_SIZE < (4 * 1024 * 1024) &&
-			    !(address & 0x3fffff) &&
-			    !(offset & 0x3ffffe) &&
-			    end >= address + 0x400000) {
-				entry = mk_pte_io(offset, prot, space,
-						  4 * 1024 * 1024);
-				curend = address + 0x400000;
-				offset += 0x400000;
-			} else if (PAGE_SIZE < (512 * 1024) &&
-				   !(address & 0x7ffff) &&
-				   !(offset & 0x7fffe) &&
-				   end >= address + 0x80000) {
-				entry = mk_pte_io(offset, prot, space,
-						  512 * 1024 * 1024);
-				curend = address + 0x80000;
-				offset += 0x80000;
-			} else if (PAGE_SIZE < (64 * 1024) &&
-				   !(offset & 0xfffe) &&
-				   end >= address + 0x10000) {
-				entry = mk_pte_io(offset, prot, space,
-						  64 * 1024);
-				curend = address + 0x10000;
-				offset += 0x10000;
-			} else
-				offset += PAGE_SIZE;
-		} else
-			offset += PAGE_SIZE;
-
-		if (pte_write(entry))
-			entry = pte_mkdirty(entry);
-		do {
-			BUG_ON(!pte_none(*pte));
-			set_pte_at(mm, address, pte, entry);
-			address += PAGE_SIZE;
-			pte_val(entry) += PAGE_SIZE;
-			pte++;
-		} while (address < curend);
-	} while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
-	unsigned long offset, pgprot_t prot, int space)
-{
-	unsigned long end;
-
-	address &= ~PGDIR_MASK;
-	end = address + size;
-	if (end > PGDIR_SIZE)
-		end = PGDIR_SIZE;
-	offset -= address;
-	do {
-		pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
-		if (!pte)
-			return -ENOMEM;
-		io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
-		pte_unmap(pte);
-		address = (address + PMD_SIZE) & PMD_MASK;
-		pmd++;
-	} while (address < end);
-	return 0;
-}
-
-static inline int io_remap_pud_range(struct mm_struct *mm, pud_t * pud, unsigned long address, unsigned long size,
-	unsigned long offset, pgprot_t prot, int space)
-{
-	unsigned long end;
-
-	address &= ~PUD_MASK;
-	end = address + size;
-	if (end > PUD_SIZE)
-		end = PUD_SIZE;
-	offset -= address;
-	do {
-		pmd_t *pmd = pmd_alloc(mm, pud, address);
-		if (!pud)
-			return -ENOMEM;
-		io_remap_pmd_range(mm, pmd, address, end - address, address + offset, prot, space);
-		address = (address + PUD_SIZE) & PUD_MASK;
-		pud++;
-	} while (address < end);
-	return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-		unsigned long pfn, unsigned long size, pgprot_t prot)
-{
-	int error = 0;
-	pgd_t * dir;
-	unsigned long beg = from;
-	unsigned long end = from + size;
-	struct mm_struct *mm = vma->vm_mm;
-	int space = GET_IOSPACE(pfn);
-	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
-	unsigned long phys_base;
-
-	phys_base = offset | (((unsigned long) space) << 32UL);
-
-	/* See comment in mm/memory.c remap_pfn_range */
-	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
-	vma->vm_pgoff = phys_base >> PAGE_SHIFT;
-
-	offset -= from;
-	dir = pgd_offset(mm, from);
-	flush_cache_range(vma, beg, end);
-
-	while (from < end) {
-		pud_t *pud = pud_alloc(mm, dir, from);
-		error = -ENOMEM;
-		if (!pud)
-			break;
-		error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space);
-		if (error)
-			break;
-		from = (from + PGDIR_SIZE) & PGDIR_MASK;
-		dir++;
-	}
-
-	flush_tlb_range(vma, beg, end);
-	return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);