Merge branch 'parisc-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux

Pull parisc updates from Helge Deller.

The bulk of this is optimized page coping/clearing and cache flushing
(virtual caches are lovely) by John David Anglin.

* 'parisc-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux: (31 commits)
  arch/parisc/include/asm: use ARRAY_SIZE macro in mmzone.h
  parisc: remove empty lines and unnecessary #ifdef coding in include/asm/signal.h
  parisc: sendfile and sendfile64 syscall cleanups
  parisc: switch to available compat_sched_rr_get_interval implementation
  parisc: fix fallocate syscall
  parisc: fix error return codes for rt_sigaction and rt_sigprocmask
  parisc: convert msgrcv and msgsnd syscalls to use compat layer
  parisc: correctly wire up mq_* functions for CONFIG_COMPAT case
  parisc: fix personality on 32bit kernel
  parisc: wire up process_vm_readv, process_vm_writev, kcmp and finit_module syscalls
  parisc: led driver requires CONFIG_VM_EVENT_COUNTERS
  parisc: remove unused compat_rt_sigframe.h header
  parisc/mm/fault.c: Port OOM changes to do_page_fault
  parisc: space register variables need to be in native length (unsigned long)
  parisc: fix ptrace breakage
  parisc: always detect multiple physical ranges
  parisc: ensure that mmapped shared pages are aligned at SHMLBA addresses
  parisc: disable preemption while flushing D- or I-caches through TMPALIAS region
  parisc: remove IRQF_DISABLED
  parisc: fixes and cleanups in page cache flushing (4/4)
  ...

27 files changed, 697 insertions, 299 deletions

diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index c600f39aa453..7f9b3c53f74a 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -160,6 +160,23 @@ config PREFETCH
 	def_bool y
 	depends on PA8X00 || PA7200
 
+config MLONGCALLS
+	bool "Enable the -mlong-calls compiler option for big kernels"
+	def_bool y if (!MODULES)
+	depends on PA8X00
+	help
+	  If you configure the kernel to include many drivers built-in instead
+	  as modules, the kernel executable may become too big, so that the
+	  linker will not be able to resolve some long branches and fails to link
+	  your vmlinux kernel. In that case enabling this option will help you
+	  to overcome this limit by using the -mlong-calls compiler option.
+
+	  Usually you want to say N here, unless you e.g. want to build
+	  a kernel which includes all necessary drivers built-in and which can
+	  be used for TFTP booting without the need to have an initrd ramdisk.
+
+	  Enabling this option will probably slow down your kernel.
+
 config 64BIT
 	bool "64-bit kernel"
 	depends on PA8X00
@@ -254,6 +271,10 @@ config COMPAT
 	def_bool y
 	depends on 64BIT
 
+config SYSVIPC_COMPAT
+	def_bool y
+	depends on COMPAT && SYSVIPC
+
 config HPUX
 	bool "Support for HP-UX binaries"
 	depends on !64BIT
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 5707f1a62341..ed9a14ccd066 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -32,11 +32,6 @@ ifdef CONFIG_64BIT
 UTS_MACHINE	:= parisc64
 CHECKFLAGS	+= -D__LP64__=1 -m64
 WIDTH		:= 64
-
-# FIXME: if no default set, should really try to locate dynamically
-ifeq ($(CROSS_COMPILE),)
-CROSS_COMPILE	:= hppa64-linux-gnu-
-endif
 else # 32-bit
 WIDTH		:=
 endif
@@ -44,6 +39,10 @@ endif
 # attempt to help out folks who are cross-compiling
 ifeq ($(NATIVE),1)
 CROSS_COMPILE	:= hppa$(WIDTH)-linux-
+else
+ ifeq ($(CROSS_COMPILE),)
+ CROSS_COMPILE	:= hppa$(WIDTH)-linux-gnu-
+ endif
 endif
 
 OBJCOPY_FLAGS =-O binary -R .note -R .comment -S
@@ -65,6 +64,10 @@ ifndef CONFIG_FUNCTION_TRACER
   cflags-y	+= -ffunction-sections
 endif
 
+# Use long jumps instead of long branches (needed if your linker fails to
+# link a too big vmlinux executable)
+cflags-$(CONFIG_MLONGCALLS)	+= -mlong-calls
+
 # select which processor to optimise for
 cflags-$(CONFIG_PA7100)		+= -march=1.1 -mschedule=7100
 cflags-$(CONFIG_PA7200)		+= -march=1.1 -mschedule=7200
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index a0760b87fd4e..838b479a42c4 100644
--- a/arch/parisc/hpux/fs.c
+++ b/arch/parisc/hpux/fs.c
@@ -43,8 +43,7 @@ int hpux_execve(struct pt_regs *regs)
 
 	error = do_execve(filename->name,
 			  (const char __user *const __user *) regs->gr[25],
-			  (const char __user *const __user *) regs->gr[24],
-			  regs);
+			  (const char __user *const __user *) regs->gr[24]);
 
 	putname(filename);
 
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 9f21ab0c02e3..79f694f3ad9b 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -115,7 +115,9 @@ flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vma
 {
 	if (PageAnon(page)) {
 		flush_tlb_page(vma, vmaddr);
+		preempt_disable();
 		flush_dcache_page_asm(page_to_phys(page), vmaddr);
+		preempt_enable();
 	}
 }
 
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
index db7a662691a8..94710cfc1ce8 100644
--- a/arch/parisc/include/asm/compat.h
+++ b/arch/parisc/include/asm/compat.h
@@ -28,6 +28,7 @@ typedef u16	compat_nlink_t;
 typedef u16	compat_ipc_pid_t;
 typedef s32	compat_daddr_t;
 typedef u32	compat_caddr_t;
+typedef s32	compat_key_t;
 typedef s32	compat_timer_t;
 
 typedef s32	compat_int_t;
@@ -188,6 +189,66 @@ typedef struct compat_siginfo {
 #define COMPAT_OFF_T_MAX	0x7fffffff
 #define COMPAT_LOFF_T_MAX	0x7fffffffffffffffL
 
+struct compat_ipc64_perm {
+	compat_key_t key;
+	__compat_uid_t uid;
+	__compat_gid_t gid;
+	__compat_uid_t cuid;
+	__compat_gid_t cgid;
+	unsigned short int __pad1;
+	compat_mode_t mode;
+	unsigned short int __pad2;
+	unsigned short int seq;
+	unsigned int __pad3;
+	unsigned long __unused1;	/* yes they really are 64bit pads */
+	unsigned long __unused2;
+};
+
+struct compat_semid64_ds {
+	struct compat_ipc64_perm sem_perm;
+	compat_time_t sem_otime;
+	unsigned int __unused1;
+	compat_time_t sem_ctime;
+	unsigned int __unused2;
+	compat_ulong_t sem_nsems;
+	compat_ulong_t __unused3;
+	compat_ulong_t __unused4;
+};
+
+struct compat_msqid64_ds {
+	struct compat_ipc64_perm msg_perm;
+	unsigned int __unused1;
+	compat_time_t msg_stime;
+	unsigned int __unused2;
+	compat_time_t msg_rtime;
+	unsigned int __unused3;
+	compat_time_t msg_ctime;
+	compat_ulong_t msg_cbytes;
+	compat_ulong_t msg_qnum;
+	compat_ulong_t msg_qbytes;
+	compat_pid_t msg_lspid;
+	compat_pid_t msg_lrpid;
+	compat_ulong_t __unused4;
+	compat_ulong_t __unused5;
+};
+
+struct compat_shmid64_ds {
+	struct compat_ipc64_perm shm_perm;
+	unsigned int __unused1;
+	compat_time_t shm_atime;
+	unsigned int __unused2;
+	compat_time_t shm_dtime;
+	unsigned int __unused3;
+	compat_time_t shm_ctime;
+	unsigned int __unused4;
+	compat_size_t shm_segsz;
+	compat_pid_t shm_cpid;
+	compat_pid_t shm_lpid;
+	compat_ulong_t shm_nattch;
+	compat_ulong_t __unused5;
+	compat_ulong_t __unused6;
+};
+
 /*
  * A pointer passed in from user mode. This should not
  * be used for syscall parameters, just declare them
diff --git a/arch/parisc/include/asm/compat_rt_sigframe.h b/arch/parisc/include/asm/compat_rt_sigframe.h
deleted file mode 100644
index b3f95a7f18b4..000000000000
--- a/arch/parisc/include/asm/compat_rt_sigframe.h
+++ /dev/null
@@ -1,50 +0,0 @@
-#include <linux/compat.h>
-#include <linux/compat_siginfo.h>
-#include <asm/compat_ucontext.h>
-
-#ifndef _ASM_PARISC_COMPAT_RT_SIGFRAME_H
-#define _ASM_PARISC_COMPAT_RT_SIGFRAME_H
-
-/* In a deft move of uber-hackery, we decide to carry the top half of all
- * 64-bit registers in a non-portable, non-ABI, hidden structure.
- * Userspace can read the hidden structure if it *wants* but is never
- * guaranteed to be in the same place. Infact the uc_sigmask from the 
- * ucontext_t structure may push the hidden register file downards
- */
-struct compat_regfile {
-	/* Upper half of all the 64-bit registers that were truncated
-	   on a copy to a 32-bit userspace */
-	compat_int_t rf_gr[32];
-	compat_int_t rf_iasq[2];
-	compat_int_t rf_iaoq[2];
-	compat_int_t rf_sar;
-};
-
-#define COMPAT_SIGRETURN_TRAMP 4
-#define COMPAT_SIGRESTARTBLOCK_TRAMP 5 
-#define COMPAT_TRAMP_SIZE (COMPAT_SIGRETURN_TRAMP + COMPAT_SIGRESTARTBLOCK_TRAMP)
-
-struct compat_rt_sigframe {
-	/* XXX: Must match trampoline size in arch/parisc/kernel/signal.c 
-	        Secondary to that it must protect the ERESTART_RESTARTBLOCK
-		trampoline we left on the stack (we were bad and didn't 
-		change sp so we could run really fast.) */
-	compat_uint_t tramp[COMPAT_TRAMP_SIZE];
-	compat_siginfo_t info;
-	struct compat_ucontext uc;
-	/* Hidden location of truncated registers, *must* be last. */
-	struct compat_regfile regs; 
-};
-
-/*
- * The 32-bit ABI wants at least 48 bytes for a function call frame:
- * 16 bytes for arg0-arg3, and 32 bytes for magic (the only part of
- * which Linux/parisc uses is sp-20 for the saved return pointer...)
- * Then, the stack pointer must be rounded to a cache line (64 bytes).
- */
-#define SIGFRAME32		64
-#define FUNCTIONCALLFRAME32	48
-#define PARISC_RT_SIGFRAME_SIZE32					\
-	(((sizeof(struct compat_rt_sigframe) + FUNCTIONCALLFRAME32) + SIGFRAME32) & -SIGFRAME32)
-
-#endif
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
index 19f6cb1a4a1c..ad2b50397894 100644
--- a/arch/parisc/include/asm/elf.h
+++ b/arch/parisc/include/asm/elf.h
@@ -247,7 +247,7 @@ typedef unsigned long elf_greg_t;
 #define ELF_PLATFORM  ("PARISC\0")
 
 #define SET_PERSONALITY(ex) \
-	current->personality = PER_LINUX; \
+	set_personality((current->personality & ~PER_MASK) | PER_LINUX); \
 	current->thread.map_base = DEFAULT_MAP_BASE; \
 	current->thread.task_size = DEFAULT_TASK_SIZE \
 
diff --git a/arch/parisc/include/asm/floppy.h b/arch/parisc/include/asm/floppy.h
index 4ca69f558fae..f84ff12574b7 100644
--- a/arch/parisc/include/asm/floppy.h
+++ b/arch/parisc/include/asm/floppy.h
@@ -157,10 +157,10 @@ static int fd_request_irq(void)
 {
 	if(can_use_virtual_dma)
 		return request_irq(FLOPPY_IRQ, floppy_hardint,
-				   IRQF_DISABLED, "floppy", NULL);
+				   0, "floppy", NULL);
 	else
 		return request_irq(FLOPPY_IRQ, floppy_interrupt,
-				   IRQF_DISABLED, "floppy", NULL);
+				   0, "floppy", NULL);
 }
 
 static unsigned long dma_mem_alloc(unsigned long size)
diff --git a/arch/parisc/include/asm/mmzone.h b/arch/parisc/include/asm/mmzone.h
index e67eb9c3d1bf..0e625ab9aaec 100644
--- a/arch/parisc/include/asm/mmzone.h
+++ b/arch/parisc/include/asm/mmzone.h
@@ -1,9 +1,10 @@
 #ifndef _PARISC_MMZONE_H
 #define _PARISC_MMZONE_H
 
+#define MAX_PHYSMEM_RANGES 8 /* Fix the size for now (current known max is 3) */
+
 #ifdef CONFIG_DISCONTIGMEM
 
-#define MAX_PHYSMEM_RANGES 8 /* Fix the size for now (current known max is 3) */
 extern int npmem_ranges;
 
 struct node_map_data {
@@ -44,7 +45,7 @@ static inline int pfn_to_nid(unsigned long pfn)
 		return 0;
 
 	i = pfn >> PFNNID_SHIFT;
-	BUG_ON(i >= sizeof(pfnnid_map) / sizeof(pfnnid_map[0]));
+	BUG_ON(i >= ARRAY_SIZE(pfnnid_map));
 	r = pfnnid_map[i];
 	BUG_ON(r == 0xff);
 
@@ -60,7 +61,5 @@ static inline int pfn_valid(int pfn)
 	return 0;
 }
 
-#else /* !CONFIG_DISCONTIGMEM */
-#define MAX_PHYSMEM_RANGES 	1 
 #endif
 #endif /* _PARISC_MMZONE_H */
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index 4e0e7dbf0f3f..b7adb2ac049c 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -21,15 +21,27 @@
 #include <asm/types.h>
 #include <asm/cache.h>
 
-#define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
-#define copy_page(to,from)      copy_user_page_asm((void *)(to), (void *)(from))
+#define clear_page(page)	clear_page_asm((void *)(page))
+#define copy_page(to, from)	copy_page_asm((void *)(to), (void *)(from))
 
 struct page;
 
-void copy_user_page_asm(void *to, void *from);
+void clear_page_asm(void *page);
+void copy_page_asm(void *to, void *from);
+void clear_user_page(void *vto, unsigned long vaddr, struct page *pg);
 void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
 			   struct page *pg);
-void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
+
+/* #define CONFIG_PARISC_TMPALIAS */
+
+#ifdef CONFIG_PARISC_TMPALIAS
+void clear_user_highpage(struct page *page, unsigned long vaddr);
+#define clear_user_highpage clear_user_highpage
+struct vm_area_struct;
+void copy_user_highpage(struct page *to, struct page *from,
+	unsigned long vaddr, struct vm_area_struct *vma);
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+#endif
 
 /*
  * These are used to make use of C type-checking..
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index ee99f2339356..7df49fad29f9 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -12,11 +12,10 @@
 
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
+#include <linux/mm_types.h>
 #include <asm/processor.h>
 #include <asm/cache.h>
 
-struct vm_area_struct;
-
 /*
  * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
  * memory.  For the return value to be meaningful, ADDR must be >=
@@ -40,7 +39,14 @@ struct vm_area_struct;
         do{                                                     \
                 *(pteptr) = (pteval);                           \
         } while(0)
-#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+
+extern void purge_tlb_entries(struct mm_struct *, unsigned long);
+
+#define set_pte_at(mm, addr, ptep, pteval)                      \
+	do {                                                    \
+		set_pte(ptep, pteval);                          \
+		purge_tlb_entries(mm, addr);                    \
+	} while (0)
 
 #endif /* !__ASSEMBLY__ */
 
@@ -466,6 +472,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 		old = pte_val(*ptep);
 		new = pte_val(pte_wrprotect(__pte (old)));
 	} while (cmpxchg((unsigned long *) ptep, old, new) != old);
+	purge_tlb_entries(mm, addr);
 #else
 	pte_t old_pte = *ptep;
 	set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
diff --git a/arch/parisc/include/asm/signal.h b/arch/parisc/include/asm/signal.h
index 0fdb3c835952..b1a7c4c4a53a 100644
--- a/arch/parisc/include/asm/signal.h
+++ b/arch/parisc/include/asm/signal.h
@@ -3,16 +3,12 @@
 
 #include <uapi/asm/signal.h>
 
-
 #define _NSIG		64
 /* bits-per-word, where word apparently means 'long' not 'int' */
 #define _NSIG_BPW	BITS_PER_LONG
 #define _NSIG_WORDS	(_NSIG / _NSIG_BPW)
 
 # ifndef __ASSEMBLY__
-#ifdef CONFIG_64BIT
-#else
-#endif
 
 /* Most things should be clean enough to redefine this at will, if care
    is taken to make libc match.  */
diff --git a/arch/parisc/include/asm/unistd.h b/arch/parisc/include/asm/unistd.h
index 3043194547cd..74f801ebbe77 100644
--- a/arch/parisc/include/asm/unistd.h
+++ b/arch/parisc/include/asm/unistd.h
@@ -149,6 +149,7 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5)	\
 #define __ARCH_WANT_SYS_SIGNAL
 #define __ARCH_WANT_SYS_TIME
 #define __ARCH_WANT_COMPAT_SYS_TIME
+#define __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL
 #define __ARCH_WANT_SYS_UTIME
 #define __ARCH_WANT_SYS_WAITPID
 #define __ARCH_WANT_SYS_SOCKETCALL
@@ -166,6 +167,7 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5)	\
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_COMPAT_SYS_SENDFILE
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index e178f30f2ccc..2c8b9bde18eb 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -822,8 +822,12 @@
 #define __NR_syncfs		(__NR_Linux + 327)
 #define __NR_setns		(__NR_Linux + 328)
 #define __NR_sendmmsg		(__NR_Linux + 329)
+#define __NR_process_vm_readv	(__NR_Linux + 330)
+#define __NR_process_vm_writev	(__NR_Linux + 331)
+#define __NR_kcmp		(__NR_Linux + 332)
+#define __NR_finit_module	(__NR_Linux + 333)
 
-#define __NR_Linux_syscalls	(__NR_sendmmsg + 1)
+#define __NR_Linux_syscalls	(__NR_finit_module + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 48e16dc20102..4b12890642eb 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -267,9 +267,11 @@ static inline void
 __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 		   unsigned long physaddr)
 {
+	preempt_disable();
 	flush_dcache_page_asm(physaddr, vmaddr);
 	if (vma->vm_flags & VM_EXEC)
 		flush_icache_page_asm(physaddr, vmaddr);
+	preempt_enable();
 }
 
 void flush_dcache_page(struct page *page)
@@ -329,17 +331,6 @@ EXPORT_SYMBOL(flush_kernel_dcache_page_asm);
 EXPORT_SYMBOL(flush_data_cache_local);
 EXPORT_SYMBOL(flush_kernel_icache_range_asm);
 
-void clear_user_page_asm(void *page, unsigned long vaddr)
-{
-	unsigned long flags;
-	/* This function is implemented in assembly in pacache.S */
-	extern void __clear_user_page_asm(void *page, unsigned long vaddr);
-
-	purge_tlb_start(flags);
-	__clear_user_page_asm(page, vaddr);
-	purge_tlb_end(flags);
-}
-
 #define FLUSH_THRESHOLD 0x80000 /* 0.5MB */
 int parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
 
@@ -373,20 +364,9 @@ void __init parisc_setup_cache_timing(void)
 	printk(KERN_INFO "Setting cache flush threshold to %x (%d CPUs online)\n", parisc_cache_flush_threshold, num_online_cpus());
 }
 
-extern void purge_kernel_dcache_page(unsigned long);
-extern void clear_user_page_asm(void *page, unsigned long vaddr);
-
-void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
-{
-	unsigned long flags;
-
-	purge_kernel_dcache_page((unsigned long)page);
-	purge_tlb_start(flags);
-	pdtlb_kernel(page);
-	purge_tlb_end(flags);
-	clear_user_page_asm(page, vaddr);
-}
-EXPORT_SYMBOL(clear_user_page);
+extern void purge_kernel_dcache_page_asm(unsigned long);
+extern void clear_user_page_asm(void *, unsigned long);
+extern void copy_user_page_asm(void *, void *, unsigned long);
 
 void flush_kernel_dcache_page_addr(void *addr)
 {
@@ -399,11 +379,26 @@ void flush_kernel_dcache_page_addr(void *addr)
 }
 EXPORT_SYMBOL(flush_kernel_dcache_page_addr);
 
+void clear_user_page(void *vto, unsigned long vaddr, struct page *page)
+{
+	clear_page_asm(vto);
+	if (!parisc_requires_coherency())
+		flush_kernel_dcache_page_asm(vto);
+}
+EXPORT_SYMBOL(clear_user_page);
+
 void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
-		    struct page *pg)
+	struct page *pg)
 {
-	/* no coherency needed (all in kmap/kunmap) */
-	copy_user_page_asm(vto, vfrom);
+	/* Copy using kernel mapping.  No coherency is needed
+	   (all in kmap/kunmap) on machines that don't support
+	   non-equivalent aliasing.  However, the `from' page
+	   needs to be flushed before it can be accessed through
+	   the kernel mapping. */
+	preempt_disable();
+	flush_dcache_page_asm(__pa(vfrom), vaddr);
+	preempt_enable();
+	copy_page_asm(vto, vfrom);
 	if (!parisc_requires_coherency())
 		flush_kernel_dcache_page_asm(vto);
 }
@@ -419,6 +414,24 @@ void kunmap_parisc(void *addr)
 EXPORT_SYMBOL(kunmap_parisc);
 #endif
 
+void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+{
+	unsigned long flags;
+
+	/* Note: purge_tlb_entries can be called at startup with
+	   no context.  */
+
+	/* Disable preemption while we play with %sr1.  */
+	preempt_disable();
+	mtsp(mm->context, 1);
+	purge_tlb_start(flags);
+	pdtlb(addr);
+	pitlb(addr);
+	purge_tlb_end(flags);
+	preempt_enable();
+}
+EXPORT_SYMBOL(purge_tlb_entries);
+
 void __flush_tlb_range(unsigned long sid, unsigned long start,
 		       unsigned long end)
 {
@@ -458,8 +471,66 @@ void flush_cache_all(void)
 	on_each_cpu(cacheflush_h_tmp_function, NULL, 1);
 }
 
+static inline unsigned long mm_total_size(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+	unsigned long usize = 0;
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next)
+		usize += vma->vm_end - vma->vm_start;
+	return usize;
+}
+
+static inline pte_t *get_ptep(pgd_t *pgd, unsigned long addr)
+{
+	pte_t *ptep = NULL;
+
+	if (!pgd_none(*pgd)) {
+		pud_t *pud = pud_offset(pgd, addr);
+		if (!pud_none(*pud)) {
+			pmd_t *pmd = pmd_offset(pud, addr);
+			if (!pmd_none(*pmd))
+				ptep = pte_offset_map(pmd, addr);
+		}
+	}
+	return ptep;
+}
+
 void flush_cache_mm(struct mm_struct *mm)
 {
+	/* Flushing the whole cache on each cpu takes forever on
+	   rp3440, etc.  So, avoid it if the mm isn't too big.  */
+	if (mm_total_size(mm) < parisc_cache_flush_threshold) {
+		struct vm_area_struct *vma;
+
+		if (mm->context == mfsp(3)) {
+			for (vma = mm->mmap; vma; vma = vma->vm_next) {
+				flush_user_dcache_range_asm(vma->vm_start,
+					vma->vm_end);
+				if (vma->vm_flags & VM_EXEC)
+					flush_user_icache_range_asm(
+					  vma->vm_start, vma->vm_end);
+			}
+		} else {
+			pgd_t *pgd = mm->pgd;
+
+			for (vma = mm->mmap; vma; vma = vma->vm_next) {
+				unsigned long addr;
+
+				for (addr = vma->vm_start; addr < vma->vm_end;
+				     addr += PAGE_SIZE) {
+					pte_t *ptep = get_ptep(pgd, addr);
+					if (ptep != NULL) {
+						pte_t pte = *ptep;
+						__flush_cache_page(vma, addr,
+						  page_to_phys(pte_page(pte)));
+					}
+				}
+			}
+		}
+		return;
+	}
+
 #ifdef CONFIG_SMP
 	flush_cache_all();
 #else
@@ -485,20 +556,36 @@ flush_user_icache_range(unsigned long start, unsigned long end)
 		flush_instruction_cache();
 }
 
-
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 {
-	int sr3;
-
 	BUG_ON(!vma->vm_mm->context);
 
-	sr3 = mfsp(3);
-	if (vma->vm_mm->context == sr3) {
-		flush_user_dcache_range(start,end);
-		flush_user_icache_range(start,end);
+	if ((end - start) < parisc_cache_flush_threshold) {
+		if (vma->vm_mm->context == mfsp(3)) {
+			flush_user_dcache_range_asm(start, end);
+			if (vma->vm_flags & VM_EXEC)
+				flush_user_icache_range_asm(start, end);
+		} else {
+			unsigned long addr;
+			pgd_t *pgd = vma->vm_mm->pgd;
+
+			for (addr = start & PAGE_MASK; addr < end;
+			     addr += PAGE_SIZE) {
+				pte_t *ptep = get_ptep(pgd, addr);
+				if (ptep != NULL) {
+					pte_t pte = *ptep;
+					flush_cache_page(vma,
+					   addr, pte_pfn(pte));
+				}
+			}
+		}
 	} else {
+#ifdef CONFIG_SMP
 		flush_cache_all();
+#else
+		flush_cache_all_local();
+#endif
 	}
 }
 
@@ -511,3 +598,67 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 	__flush_cache_page(vma, vmaddr, page_to_phys(pfn_to_page(pfn)));
 
 }
+
+#ifdef CONFIG_PARISC_TMPALIAS
+
+void clear_user_highpage(struct page *page, unsigned long vaddr)
+{
+	void *vto;
+	unsigned long flags;
+
+	/* Clear using TMPALIAS region.  The page doesn't need to
+	   be flushed but the kernel mapping needs to be purged.  */
+
+	vto = kmap_atomic(page, KM_USER0);
+
+	/* The PA-RISC 2.0 Architecture book states on page F-6:
+	   "Before a write-capable translation is enabled, *all*
+	   non-equivalently-aliased translations must be removed
+	   from the page table and purged from the TLB.  (Note
+	   that the caches are not required to be flushed at this
+	   time.)  Before any non-equivalent aliased translation
+	   is re-enabled, the virtual address range for the writeable
+	   page (the entire page) must be flushed from the cache,
+	   and the write-capable translation removed from the page
+	   table and purged from the TLB."  */
+
+	purge_kernel_dcache_page_asm((unsigned long)vto);
+	purge_tlb_start(flags);
+	pdtlb_kernel(vto);
+	purge_tlb_end(flags);
+	preempt_disable();
+	clear_user_page_asm(vto, vaddr);
+	preempt_enable();
+
+	pagefault_enable();		/* kunmap_atomic(addr, KM_USER0); */
+}
+
+void copy_user_highpage(struct page *to, struct page *from,
+	unsigned long vaddr, struct vm_area_struct *vma)
+{
+	void *vfrom, *vto;
+	unsigned long flags;
+
+	/* Copy using TMPALIAS region.  This has the advantage
+	   that the `from' page doesn't need to be flushed.  However,
+	   the `to' page must be flushed in copy_user_page_asm since
+	   it can be used to bring in executable code.  */
+
+	vfrom = kmap_atomic(from, KM_USER0);
+	vto = kmap_atomic(to, KM_USER1);
+
+	purge_kernel_dcache_page_asm((unsigned long)vto);
+	purge_tlb_start(flags);
+	pdtlb_kernel(vto);
+	pdtlb_kernel(vfrom);
+	purge_tlb_end(flags);
+	preempt_disable();
+	copy_user_page_asm(vto, vfrom, vaddr);
+	flush_dcache_page_asm(__pa(vto), vaddr);
+	preempt_enable();
+
+	pagefault_enable();		/* kunmap_atomic(addr, KM_USER1); */
+	pagefault_enable();		/* kunmap_atomic(addr, KM_USER0); */
+}
+
+#endif /* CONFIG_PARISC_TMPALIAS */
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index eb7850b46c25..7c9648919c91 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -483,7 +483,7 @@
 	 * B <-> _PAGE_DMB (memory break)
 	 *
 	 * Then incredible subtlety: The access rights are
-	 * _PAGE_GATEWAY _PAGE_EXEC _PAGE_READ
+	 * _PAGE_GATEWAY, _PAGE_EXEC and _PAGE_WRITE
 	 * See 3-14 of the parisc 2.0 manual
 	 *
 	 * Finally, _PAGE_READ goes in the top bit of PL1 (so we
@@ -493,7 +493,7 @@
 
 	/* PAGE_USER indicates the page can be read with user privileges,
 	 * so deposit X1|11 to PL1|PL2 (remember the upper bit of PL1
-	 * contains _PAGE_READ */
+	 * contains _PAGE_READ) */
 	extrd,u,*=      \pte,_PAGE_USER_BIT+32,1,%r0
 	depdi		7,11,3,\prot
 	/* If we're a gateway page, drop PL2 back to zero for promotion
diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c
index 08324aac3544..3295ef4a185d 100644
--- a/arch/parisc/kernel/inventory.c
+++ b/arch/parisc/kernel/inventory.c
@@ -186,12 +186,14 @@ pat_query_module(ulong pcell_loc, ulong mod_index)
 
 	if (status != PDC_OK) {
 		/* no more cell modules or error */
+		kfree(pa_pdc_cell);
 		return status;
 	}
 
 	temp = pa_pdc_cell->cba;
 	dev = alloc_pa_dev(PAT_GET_CBA(temp), &(pa_pdc_cell->mod_path));
 	if (!dev) {
+		kfree(pa_pdc_cell);
 		return PDC_OK;
 	}
 
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 0299d63cd112..8094d3ed3b64 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -379,14 +379,14 @@ void do_cpu_irq_mask(struct pt_regs *regs)
 static struct irqaction timer_action = {
 	.handler = timer_interrupt,
 	.name = "timer",
-	.flags = IRQF_DISABLED | IRQF_TIMER | IRQF_PERCPU | IRQF_IRQPOLL,
+	.flags = IRQF_TIMER | IRQF_PERCPU | IRQF_IRQPOLL,
 };
 
 #ifdef CONFIG_SMP
 static struct irqaction ipi_action = {
 	.handler = ipi_interrupt,
 	.name = "IPI",
-	.flags = IRQF_DISABLED | IRQF_PERCPU,
+	.flags = IRQF_PERCPU,
 };
 #endif
 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 5d7218ad885c..312b48422a56 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -199,7 +199,6 @@ ENTRY(flush_instruction_cache_local)
 	.callinfo NO_CALLS
 	.entry
 
-	mtsp		%r0, %sr1
 	load32		cache_info, %r1
 
 	/* Flush Instruction Cache */
@@ -208,7 +207,8 @@ ENTRY(flush_instruction_cache_local)
 	LDREG		ICACHE_STRIDE(%r1), %arg1
 	LDREG		ICACHE_COUNT(%r1), %arg2
 	LDREG		ICACHE_LOOP(%r1), %arg3
-	rsm             PSW_SM_I, %r22		/* No mmgt ops during loop*/
+	rsm		PSW_SM_I, %r22		/* No mmgt ops during loop*/
+	mtsp		%r0, %sr1
 	addib,COND(=)		-1, %arg3, fioneloop	/* Preadjust and test */
 	movb,<,n	%arg3, %r31, fisync	/* If loop < 0, do sync */
 
@@ -220,7 +220,33 @@ fimanyloop:					/* Loop if LOOP >= 2 */
 	addib,COND(<=),n	-1, %arg2, fisync	/* Outer loop decr */
 
 fioneloop:					/* Loop if LOOP = 1 */
-	addib,COND(>)		-1, %arg2, fioneloop	/* Outer loop count decr */
+	/* Some implementations may flush with a single fice instruction */
+	cmpib,COND(>>=),n	15, %arg2, fioneloop2
+
+fioneloop1:
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	fice,m		%arg1(%sr1, %arg0)
+	addib,COND(>)	-16, %arg2, fioneloop1
+	fice,m		%arg1(%sr1, %arg0)
+
+	/* Check if done */
+	cmpb,COND(=),n	%arg2, %r0, fisync	/* Predict branch taken */
+
+fioneloop2:
+	addib,COND(>)	-1, %arg2, fioneloop2	/* Outer loop count decr */
 	fice,m		%arg1(%sr1, %arg0)	/* Fice for one loop */
 
 fisync:
@@ -240,8 +266,7 @@ ENTRY(flush_data_cache_local)
 	.callinfo NO_CALLS
 	.entry
 
-	mtsp		%r0, %sr1
-	load32 		cache_info, %r1
+	load32		cache_info, %r1
 
 	/* Flush Data Cache */
 
@@ -249,7 +274,8 @@ ENTRY(flush_data_cache_local)
 	LDREG		DCACHE_STRIDE(%r1), %arg1
 	LDREG		DCACHE_COUNT(%r1), %arg2
 	LDREG		DCACHE_LOOP(%r1), %arg3
-	rsm		PSW_SM_I, %r22
+	rsm		PSW_SM_I, %r22		/* No mmgt ops during loop*/
+	mtsp		%r0, %sr1
 	addib,COND(=)		-1, %arg3, fdoneloop	/* Preadjust and test */
 	movb,<,n	%arg3, %r31, fdsync	/* If loop < 0, do sync */
 
@@ -261,7 +287,33 @@ fdmanyloop:					/* Loop if LOOP >= 2 */
 	addib,COND(<=),n	-1, %arg2, fdsync	/* Outer loop decr */
 
 fdoneloop:					/* Loop if LOOP = 1 */
-	addib,COND(>)		-1, %arg2, fdoneloop	/* Outer loop count decr */
+	/* Some implementations may flush with a single fdce instruction */
+	cmpib,COND(>>=),n	15, %arg2, fdoneloop2
+
+fdoneloop1:
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	fdce,m		%arg1(%sr1, %arg0)
+	addib,COND(>)	-16, %arg2, fdoneloop1
+	fdce,m		%arg1(%sr1, %arg0)
+
+	/* Check if done */
+	cmpb,COND(=),n	%arg2, %r0, fdsync	/* Predict branch taken */
+
+fdoneloop2:
+	addib,COND(>)	-1, %arg2, fdoneloop2	/* Outer loop count decr */
 	fdce,m		%arg1(%sr1, %arg0)	/* Fdce for one loop */
 
 fdsync:
@@ -277,7 +329,104 @@ ENDPROC(flush_data_cache_local)
 
 	.align	16
 
-ENTRY(copy_user_page_asm)
+/* Macros to serialize TLB purge operations on SMP.  */
+
+	.macro	tlb_lock	la,flags,tmp
+#ifdef CONFIG_SMP
+	ldil		L%pa_tlb_lock,%r1
+	ldo		R%pa_tlb_lock(%r1),\la
+	rsm		PSW_SM_I,\flags
+1:	LDCW		0(\la),\tmp
+	cmpib,<>,n	0,\tmp,3f
+2:	ldw		0(\la),\tmp
+	cmpb,<>		%r0,\tmp,1b
+	nop
+	b,n		2b
+3:
+#endif
+	.endm
+
+	.macro	tlb_unlock	la,flags,tmp
+#ifdef CONFIG_SMP
+	ldi		1,\tmp
+	stw		\tmp,0(\la)
+	mtsm		\flags
+#endif
+	.endm
+
+/* Clear page using kernel mapping.  */
+
+ENTRY(clear_page_asm)
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+#ifdef CONFIG_64BIT
+
+	/* Unroll the loop.  */
+	ldi		(PAGE_SIZE / 128), %r1
+
+1:
+	std		%r0, 0(%r26)
+	std		%r0, 8(%r26)
+	std		%r0, 16(%r26)
+	std		%r0, 24(%r26)
+	std		%r0, 32(%r26)
+	std		%r0, 40(%r26)
+	std		%r0, 48(%r26)
+	std		%r0, 56(%r26)
+	std		%r0, 64(%r26)
+	std		%r0, 72(%r26)
+	std		%r0, 80(%r26)
+	std		%r0, 88(%r26)
+	std		%r0, 96(%r26)
+	std		%r0, 104(%r26)
+	std		%r0, 112(%r26)
+	std		%r0, 120(%r26)
+
+	/* Note reverse branch hint for addib is taken.  */
+	addib,COND(>),n	-1, %r1, 1b
+	ldo		128(%r26), %r26
+
+#else
+
+	/*
+	 * Note that until (if) we start saving the full 64-bit register
+	 * values on interrupt, we can't use std on a 32 bit kernel.
+	 */
+	ldi		(PAGE_SIZE / 64), %r1
+
+1:
+	stw		%r0, 0(%r26)
+	stw		%r0, 4(%r26)
+	stw		%r0, 8(%r26)
+	stw		%r0, 12(%r26)
+	stw		%r0, 16(%r26)
+	stw		%r0, 20(%r26)
+	stw		%r0, 24(%r26)
+	stw		%r0, 28(%r26)
+	stw		%r0, 32(%r26)
+	stw		%r0, 36(%r26)
+	stw		%r0, 40(%r26)
+	stw		%r0, 44(%r26)
+	stw		%r0, 48(%r26)
+	stw		%r0, 52(%r26)
+	stw		%r0, 56(%r26)
+	stw		%r0, 60(%r26)
+
+	addib,COND(>),n	-1, %r1, 1b
+	ldo		64(%r26), %r26
+#endif
+	bv		%r0(%r2)
+	nop
+	.exit
+
+	.procend
+ENDPROC(clear_page_asm)
+
+/* Copy page using kernel mapping.  */
+
+ENTRY(copy_page_asm)
 	.proc
 	.callinfo NO_CALLS
 	.entry
@@ -285,18 +434,14 @@ ENTRY(copy_user_page_asm)
 #ifdef CONFIG_64BIT
 	/* PA8x00 CPUs can consume 2 loads or 1 store per cycle.
 	 * Unroll the loop by hand and arrange insn appropriately.
-	 * GCC probably can do this just as well.
+	 * Prefetch doesn't improve performance on rp3440.
+	 * GCC probably can do this just as well...
 	 */
 
-	ldd		0(%r25), %r19
 	ldi		(PAGE_SIZE / 128), %r1
 
-	ldw		64(%r25), %r0		/* prefetch 1 cacheline ahead */
-	ldw		128(%r25), %r0		/* prefetch 2 */
-
-1:	ldd		8(%r25), %r20
-	ldw		192(%r25), %r0		/* prefetch 3 */
-	ldw		256(%r25), %r0		/* prefetch 4 */
+1:	ldd		0(%r25), %r19
+	ldd		8(%r25), %r20
 
 	ldd		16(%r25), %r21
 	ldd		24(%r25), %r22
@@ -330,20 +475,16 @@ ENTRY(copy_user_page_asm)
 
 	ldd		112(%r25), %r21
 	ldd		120(%r25), %r22
+	ldo		128(%r25), %r25
 	std		%r19, 96(%r26)
 	std		%r20, 104(%r26)
 
-	ldo		128(%r25), %r25
 	std		%r21, 112(%r26)
 	std		%r22, 120(%r26)
-	ldo		128(%r26), %r26
 
-	/* conditional branches nullify on forward taken branch, and on
-	 * non-taken backward branch. Note that .+4 is a backwards branch.
-	 * The ldd should only get executed if the branch is taken.
-	 */
-	addib,COND(>),n	-1, %r1, 1b		/* bundle 10 */
-	ldd		0(%r25), %r19		/* start next loads */
+	/* Note reverse branch hint for addib is taken.  */
+	addib,COND(>),n	-1, %r1, 1b
+	ldo		128(%r26), %r26
 
 #else
 
@@ -399,7 +540,7 @@ ENTRY(copy_user_page_asm)
 	.exit
 
 	.procend
-ENDPROC(copy_user_page_asm)
+ENDPROC(copy_page_asm)
 
 /*
  * NOTE: Code in clear_user_page has a hard coded dependency on the
@@ -422,8 +563,6 @@ ENDPROC(copy_user_page_asm)
  *          %r23 physical page (shifted for tlb insert) of "from" translation
  */
 
-#if 0
-
 	/*
 	 * We can't do this since copy_user_page is used to bring in
 	 * file data that might have instructions. Since the data would
@@ -435,6 +574,7 @@ ENDPROC(copy_user_page_asm)
 	 * use it if more information is passed into copy_user_page().
 	 * Have to do some measurements to see if it is worthwhile to
 	 * lobby for such a change.
+	 *
 	 */
 
 ENTRY(copy_user_page_asm)
@@ -442,16 +582,21 @@ ENTRY(copy_user_page_asm)
 	.callinfo NO_CALLS
 	.entry
 
+	/* Convert virtual `to' and `from' addresses to physical addresses.
+	   Move `from' physical address to non shadowed register.  */
 	ldil		L%(__PAGE_OFFSET), %r1
 	sub		%r26, %r1, %r26
-	sub		%r25, %r1, %r23		/* move physical addr into non shadowed reg */
+	sub		%r25, %r1, %r23
 
 	ldil		L%(TMPALIAS_MAP_START), %r28
 	/* FIXME for different page sizes != 4k */
 #ifdef CONFIG_64BIT
-	extrd,u		%r26,56,32, %r26		/* convert phys addr to tlb insert format */
-	extrd,u		%r23,56,32, %r23		/* convert phys addr to tlb insert format */
-	depd		%r24,63,22, %r28		/* Form aliased virtual address 'to' */
+#if (TMPALIAS_MAP_START >= 0x80000000)
+	depdi		0, 31,32, %r28		/* clear any sign extension */
+#endif
+	extrd,u		%r26,56,32, %r26	/* convert phys addr to tlb insert format */
+	extrd,u		%r23,56,32, %r23	/* convert phys addr to tlb insert format */
+	depd		%r24,63,22, %r28	/* Form aliased virtual address 'to' */
 	depdi		0, 63,12, %r28		/* Clear any offset bits */
 	copy		%r28, %r29
 	depdi		1, 41,1, %r29		/* Form aliased virtual address 'from' */
@@ -466,10 +611,76 @@ ENTRY(copy_user_page_asm)
 
 	/* Purge any old translations */
 
+#ifdef CONFIG_PA20
+	pdtlb,l		0(%r28)
+	pdtlb,l		0(%r29)
+#else
+	tlb_lock	%r20,%r21,%r22
 	pdtlb		0(%r28)
 	pdtlb		0(%r29)
+	tlb_unlock	%r20,%r21,%r22
+#endif
+
+#ifdef CONFIG_64BIT
+	/* PA8x00 CPUs can consume 2 loads or 1 store per cycle.
+	 * Unroll the loop by hand and arrange insn appropriately.
+	 * GCC probably can do this just as well.
+	 */
 
-	ldi		64, %r1
+	ldd		0(%r29), %r19
+	ldi		(PAGE_SIZE / 128), %r1
+
+1:	ldd		8(%r29), %r20
+
+	ldd		16(%r29), %r21
+	ldd		24(%r29), %r22
+	std		%r19, 0(%r28)
+	std		%r20, 8(%r28)
+
+	ldd		32(%r29), %r19
+	ldd		40(%r29), %r20
+	std		%r21, 16(%r28)
+	std		%r22, 24(%r28)
+
+	ldd		48(%r29), %r21
+	ldd		56(%r29), %r22
+	std		%r19, 32(%r28)
+	std		%r20, 40(%r28)
+
+	ldd		64(%r29), %r19
+	ldd		72(%r29), %r20
+	std		%r21, 48(%r28)
+	std		%r22, 56(%r28)
+
+	ldd		80(%r29), %r21
+	ldd		88(%r29), %r22
+	std		%r19, 64(%r28)
+	std		%r20, 72(%r28)
+
+	ldd		 96(%r29), %r19
+	ldd		104(%r29), %r20
+	std		%r21, 80(%r28)
+	std		%r22, 88(%r28)
+
+	ldd		112(%r29), %r21
+	ldd		120(%r29), %r22
+	std		%r19, 96(%r28)
+	std		%r20, 104(%r28)
+
+	ldo		128(%r29), %r29
+	std		%r21, 112(%r28)
+	std		%r22, 120(%r28)
+	ldo		128(%r28), %r28
+
+	/* conditional branches nullify on forward taken branch, and on
+	 * non-taken backward branch. Note that .+4 is a backwards branch.
+	 * The ldd should only get executed if the branch is taken.
+	 */
+	addib,COND(>),n	-1, %r1, 1b		/* bundle 10 */
+	ldd		0(%r29), %r19		/* start next loads */
+
+#else
+	ldi		(PAGE_SIZE / 64), %r1
 
 	/*
 	 * This loop is optimized for PCXL/PCXL2 ldw/ldw and stw/stw
@@ -480,9 +691,7 @@ ENTRY(copy_user_page_asm)
 	 * use ldd/std on a 32 bit kernel.
 	 */
 
-
-1:
-	ldw		0(%r29), %r19
+1:	ldw		0(%r29), %r19
 	ldw		4(%r29), %r20
 	ldw		8(%r29), %r21
 	ldw		12(%r29), %r22
@@ -515,8 +724,10 @@ ENTRY(copy_user_page_asm)
 	stw		%r21, 56(%r28)
 	stw		%r22, 60(%r28)
 	ldo		64(%r28), %r28
+
 	addib,COND(>)		-1, %r1,1b
 	ldo		64(%r29), %r29
+#endif
 
 	bv		%r0(%r2)
 	nop
@@ -524,9 +735,8 @@ ENTRY(copy_user_page_asm)
 
 	.procend
 ENDPROC(copy_user_page_asm)
-#endif
 
-ENTRY(__clear_user_page_asm)
+ENTRY(clear_user_page_asm)
 	.proc
 	.callinfo NO_CALLS
 	.entry
@@ -550,7 +760,13 @@ ENTRY(__clear_user_page_asm)
 
 	/* Purge any old translation */
 
+#ifdef CONFIG_PA20
+	pdtlb,l		0(%r28)
+#else
+	tlb_lock	%r20,%r21,%r22
 	pdtlb		0(%r28)
+	tlb_unlock	%r20,%r21,%r22
+#endif
 
 #ifdef CONFIG_64BIT
 	ldi		(PAGE_SIZE / 128), %r1
@@ -580,8 +796,7 @@ ENTRY(__clear_user_page_asm)
 #else	/* ! CONFIG_64BIT */
 	ldi		(PAGE_SIZE / 64), %r1
 
-1:
-	stw		%r0, 0(%r28)
+1:	stw		%r0, 0(%r28)
 	stw		%r0, 4(%r28)
 	stw		%r0, 8(%r28)
 	stw		%r0, 12(%r28)
@@ -606,7 +821,7 @@ ENTRY(__clear_user_page_asm)
 	.exit
 
 	.procend
-ENDPROC(__clear_user_page_asm)
+ENDPROC(clear_user_page_asm)
 
 ENTRY(flush_dcache_page_asm)
 	.proc
@@ -630,7 +845,13 @@ ENTRY(flush_dcache_page_asm)
 
 	/* Purge any old translation */
 
+#ifdef CONFIG_PA20
+	pdtlb,l		0(%r28)
+#else
+	tlb_lock	%r20,%r21,%r22
 	pdtlb		0(%r28)
+	tlb_unlock	%r20,%r21,%r22
+#endif
 
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r1
@@ -663,8 +884,17 @@ ENTRY(flush_dcache_page_asm)
 	fdc,m		%r1(%r28)
 
 	sync
+
+#ifdef CONFIG_PA20
+	pdtlb,l		0(%r25)
+#else
+	tlb_lock	%r20,%r21,%r22
+	pdtlb		0(%r25)
+	tlb_unlock	%r20,%r21,%r22
+#endif
+
 	bv		%r0(%r2)
-	pdtlb		(%r25)
+	nop
 	.exit
 
 	.procend
@@ -692,7 +922,13 @@ ENTRY(flush_icache_page_asm)
 
 	/* Purge any old translation */
 
-	pitlb		(%sr4,%r28)
+#ifdef CONFIG_PA20
+	pitlb,l         %r0(%sr4,%r28)
+#else
+	tlb_lock        %r20,%r21,%r22
+	pitlb           (%sr4,%r28)
+	tlb_unlock      %r20,%r21,%r22
+#endif
 
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r1
@@ -727,8 +963,17 @@ ENTRY(flush_icache_page_asm)
 	fic,m		%r1(%sr4,%r28)
 
 	sync
+
+#ifdef CONFIG_PA20
+	pitlb,l         %r0(%sr4,%r25)
+#else
+	tlb_lock        %r20,%r21,%r22
+	pitlb           (%sr4,%r25)
+	tlb_unlock      %r20,%r21,%r22
+#endif
+
 	bv		%r0(%r2)
-	pitlb		(%sr4,%r25)
+	nop
 	.exit
 
 	.procend
@@ -777,7 +1022,7 @@ ENTRY(flush_kernel_dcache_page_asm)
 	.procend
 ENDPROC(flush_kernel_dcache_page_asm)
 
-ENTRY(purge_kernel_dcache_page)
+ENTRY(purge_kernel_dcache_page_asm)
 	.proc
 	.callinfo NO_CALLS
 	.entry
@@ -817,7 +1062,7 @@ ENTRY(purge_kernel_dcache_page)
 	.exit
 
 	.procend
-ENDPROC(purge_kernel_dcache_page)
+ENDPROC(purge_kernel_dcache_page_asm)
 
 ENTRY(flush_user_dcache_range_asm)
 	.proc
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index ceec85de6290..6795dc6c995f 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -157,5 +157,6 @@ extern void _mcount(void);
 EXPORT_SYMBOL(_mcount);
 #endif
 
-/* from pacache.S -- needed for copy_page */
-EXPORT_SYMBOL(copy_user_page_asm);
+/* from pacache.S -- needed for clear/copy_page */
+EXPORT_SYMBOL(clear_page_asm);
+EXPORT_SYMBOL(copy_page_asm);
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index fd051705a407..52c85b2f502e 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -312,7 +312,7 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 #if DEBUG_SIG
 	/* Assert that we're flushing in the correct space... */
 	{
-		int sid;
+		unsigned long sid;
 		asm ("mfsp %%sr3,%0" : "=r" (sid));
 		DBG(1,"setup_rt_frame: Flushing 64 bytes at space %#x offset %p\n",
 		       sid, frame->tramp);
diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c
index 5dede04f2f3e..2ddcabb616ce 100644
--- a/arch/parisc/kernel/signal32.c
+++ b/arch/parisc/kernel/signal32.c
@@ -65,7 +65,7 @@ put_sigset32(compat_sigset_t __user *up, sigset_t *set, size_t sz)
 {
 	compat_sigset_t s;
 
-	if (sz != sizeof *set)
+	if (sz != sizeof(compat_sigset_t))
 		return -EINVAL;
 	sigset_64to32(&s, set);
 
@@ -78,7 +78,7 @@ get_sigset32(compat_sigset_t __user *up, sigset_t *set, size_t sz)
 	compat_sigset_t s;
 	int r;
 
-	if (sz != sizeof *set)
+	if (sz != sizeof(compat_sigset_t))
 		return -EINVAL;
 
 	if ((r = copy_from_user(&s, up, sz)) == 0) {
@@ -94,8 +94,11 @@ int sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_sigset_t _
 	sigset_t old_set, new_set;
 	int ret;
 
-	if (set && get_sigset32(set, &new_set, sigsetsize))
-		return -EFAULT;
+	if (set) {
+		ret = get_sigset32(set, &new_set, sigsetsize);
+		if (ret)
+			return ret;
+	}
 	
 	KERNEL_SYSCALL(ret, sys_rt_sigprocmask, how, set ? (sigset_t __user *)&new_set : NULL,
 				 oset ? (sigset_t __user *)&old_set : NULL, sigsetsize);
@@ -128,6 +131,10 @@ sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, struct sigacti
 	struct k_sigaction new_sa, old_sa;
 	int ret = -EINVAL;
 
+	/* XXX: Don't preclude handling different sized sigset_t's.  */
+	if (sigsetsize != sizeof(compat_sigset_t))
+		return -EINVAL;
+
 	if (act) {
 		if (copy_from_user(&new_sa32.sa, act, sizeof new_sa32.sa))
 			return -EFAULT;
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index f76c10863c62..54d619d4cac6 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -94,11 +94,12 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 {
 	if (len > TASK_SIZE)
 		return -ENOMEM;
-	/* Might want to check for cache aliasing issues for MAP_FIXED case
-	 * like ARM or MIPS ??? --BenH.
-	 */
-	if (flags & MAP_FIXED)
+	if (flags & MAP_FIXED) {
+		if ((flags & MAP_SHARED) &&
+		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+			return -EINVAL;
 		return addr;
+	}
 	if (!addr)
 		addr = TASK_UNMAPPED_BASE;
 
@@ -212,6 +213,13 @@ asmlinkage long parisc_sync_file_range(int fd,
 			(loff_t)hi_nbytes << 32 | lo_nbytes, flags);
 }
 
+asmlinkage long parisc_fallocate(int fd, int mode, u32 offhi, u32 offlo,
+				u32 lenhi, u32 lenlo)
+{
+        return sys_fallocate(fd, mode, ((u64)offhi << 32) | offlo,
+                             ((u64)lenhi << 32) | lenlo);
+}
+
 asmlinkage unsigned long sys_alloc_hugepages(int key, unsigned long addr, unsigned long len, int prot, int flag)
 {
 	return -ENOMEM;
diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c
index 9cfdaa19ab63..eca69bb8ef5f 100644
--- a/arch/parisc/kernel/sys_parisc32.c
+++ b/arch/parisc/kernel/sys_parisc32.c
@@ -21,7 +21,6 @@
 #include <linux/time.h>
 #include <linux/smp.h>
 #include <linux/sem.h>
-#include <linux/msg.h>
 #include <linux/shm.h>
 #include <linux/slab.h>
 #include <linux/uio.h>
@@ -61,111 +60,23 @@ asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23,
     return -ENOSYS;
 }
 
-asmlinkage long sys32_sched_rr_get_interval(pid_t pid,
-	struct compat_timespec __user *interval)
-{
-	struct timespec t;
-	int ret;
-
-	KERNEL_SYSCALL(ret, sys_sched_rr_get_interval, pid, (struct timespec __user *)&t);
-	if (put_compat_timespec(&t, interval))
-		return -EFAULT;
-	return ret;
-}
-
-struct msgbuf32 {
-    int mtype;
-    char mtext[1];
-};
-
-asmlinkage long sys32_msgsnd(int msqid,
-				struct msgbuf32 __user *umsgp32,
-				size_t msgsz, int msgflg)
-{
-	struct msgbuf *mb;
-	struct msgbuf32 mb32;
-	int err;
-
-	if ((mb = kmalloc(msgsz + sizeof *mb + 4, GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-
-	err = get_user(mb32.mtype, &umsgp32->mtype);
-	mb->mtype = mb32.mtype;
-	err |= copy_from_user(mb->mtext, &umsgp32->mtext, msgsz);
-
-	if (err)
-		err = -EFAULT;
-	else
-		KERNEL_SYSCALL(err, sys_msgsnd, msqid, (struct msgbuf __user *)mb, msgsz, msgflg);
-
-	kfree(mb);
-	return err;
-}
-
-asmlinkage long sys32_msgrcv(int msqid,
-				struct msgbuf32 __user *umsgp32,
-				size_t msgsz, long msgtyp, int msgflg)
-{
-	struct msgbuf *mb;
-	struct msgbuf32 mb32;
-	int err, len;
-
-	if ((mb = kmalloc(msgsz + sizeof *mb + 4, GFP_KERNEL)) == NULL)
-		return -ENOMEM;
-
-	KERNEL_SYSCALL(err, sys_msgrcv, msqid, (struct msgbuf __user *)mb, msgsz, msgtyp, msgflg);
-
-	if (err >= 0) {
-		len = err;
-		mb32.mtype = mb->mtype;
-		err = put_user(mb32.mtype, &umsgp32->mtype);
-		err |= copy_to_user(&umsgp32->mtext, mb->mtext, len);
-		if (err)
-			err = -EFAULT;
-		else
-			err = len;
-	}
-
-	kfree(mb);
-	return err;
-}
-
-asmlinkage int sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, s32 count)
+/* Note: it is necessary to treat out_fd and in_fd as unsigned ints, with the
+ * corresponding cast to a signed int to insure that the proper conversion
+ * (sign extension) between the register representation of a signed int (msr in
+ * 32-bit mode) and the register representation of a signed int (msr in 64-bit
+ * mode) is performed.
+ */
+asmlinkage long sys32_sendfile(u32 out_fd, u32 in_fd,
+			       compat_off_t __user *offset, compat_size_t count)
 {
-        mm_segment_t old_fs = get_fs();
-        int ret;
-        off_t of;
-
-        if (offset && get_user(of, offset))
-                return -EFAULT;
-
-        set_fs(KERNEL_DS);
-        ret = sys_sendfile(out_fd, in_fd, offset ? (off_t __user *)&of : NULL, count);
-        set_fs(old_fs);
-
-        if (offset && put_user(of, offset))
-                return -EFAULT;
-
-        return ret;
+	return compat_sys_sendfile((int)out_fd, (int)in_fd, offset, count);
 }
 
-asmlinkage int sys32_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count)
+asmlinkage long sys32_sendfile64(u32 out_fd, u32 in_fd,
+				 compat_loff_t __user *offset, compat_size_t count)
 {
-	mm_segment_t old_fs = get_fs();
-	int ret;
-	loff_t lof;
-	
-	if (offset && get_user(lof, offset))
-		return -EFAULT;
-		
-	set_fs(KERNEL_DS);
-	ret = sys_sendfile64(out_fd, in_fd, offset ? (loff_t __user *)&lof : NULL, count);
-	set_fs(old_fs);
-	
-	if (offset && put_user(lof, offset))
-		return -EFAULT;
-		
-	return ret;
+	return sys_sendfile64((int)out_fd, (int)in_fd,
+				(loff_t __user *)offset, count);
 }
 
 
@@ -200,13 +111,6 @@ long sys32_lookup_dcookie(u32 cookie_high, u32 cookie_low, char __user *buf,
 				  buf, len);
 }
 
-asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo,
-				u32 lenhi, u32 lenlo)
-{
-        return sys_fallocate(fd, mode, ((loff_t)offhi << 32) | offlo,
-                             ((loff_t)lenhi << 32) | lenlo);
-}
-
 asmlinkage long compat_sys_fanotify_mark(int fan_fd, int flags, u32 mask_hi,
 					 u32 mask_lo, int fd,
 					 const char __user *pathname)
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 86742df0b194..5e055240f00b 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -309,10 +309,13 @@ tracesys_next:
 	LDREG   TASK_PT_GR25(%r1), %r25
 	LDREG   TASK_PT_GR24(%r1), %r24
 	LDREG   TASK_PT_GR23(%r1), %r23
-#ifdef CONFIG_64BIT
 	LDREG   TASK_PT_GR22(%r1), %r22
 	LDREG   TASK_PT_GR21(%r1), %r21
+#ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29			/* Reference param save area */
+#else
+	stw     %r22, -52(%r30)                 /* 5th argument */
+	stw     %r21, -56(%r30)                 /* 6th argument */
 #endif
 
 	comiclr,>>=	__NR_Linux_syscalls, %r20, %r0
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 54d950b067b7..129fd472c471 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -247,10 +247,7 @@
 	ENTRY_SAME(sched_yield)
 	ENTRY_SAME(sched_get_priority_max)
 	ENTRY_SAME(sched_get_priority_min)	/* 160 */
-	/* These 2 would've worked if someone had defined struct timespec
-	 * carefully, like timeval for example (which is about the same).
-	 * Unfortunately it contains a long :-( */
-	ENTRY_DIFF(sched_rr_get_interval)
+	ENTRY_COMP(sched_rr_get_interval)
 	ENTRY_COMP(nanosleep)
 	ENTRY_SAME(mremap)
 	ENTRY_SAME(setresuid)
@@ -286,8 +283,8 @@
 	ENTRY_SAME(semop)		/* 185 */
 	ENTRY_SAME(semget)
 	ENTRY_DIFF(semctl)
-	ENTRY_DIFF(msgsnd)
-	ENTRY_DIFF(msgrcv)
+	ENTRY_COMP(msgsnd)
+	ENTRY_COMP(msgrcv)
 	ENTRY_SAME(msgget)		/* 190 */
 	ENTRY_SAME(msgctl)
 	ENTRY_SAME(shmat)
@@ -307,7 +304,7 @@
 	ENTRY_SAME(gettid)
 	ENTRY_OURS(readahead)
 	ENTRY_SAME(tkill)
-	ENTRY_SAME(sendfile64)
+	ENTRY_DIFF(sendfile64)
 	ENTRY_COMP(futex)		/* 210 */
 	ENTRY_COMP(sched_setaffinity)
 	ENTRY_COMP(sched_getaffinity)
@@ -327,12 +324,12 @@
 	ENTRY_SAME(epoll_wait)
  	ENTRY_SAME(remap_file_pages)
 	ENTRY_SAME(semtimedop)
-	ENTRY_SAME(mq_open)
+	ENTRY_COMP(mq_open)
 	ENTRY_SAME(mq_unlink)		/* 230 */
-	ENTRY_SAME(mq_timedsend)
-	ENTRY_SAME(mq_timedreceive)
-	ENTRY_SAME(mq_notify)
-	ENTRY_SAME(mq_getsetattr)
+	ENTRY_COMP(mq_timedsend)
+	ENTRY_COMP(mq_timedreceive)
+	ENTRY_COMP(mq_notify)
+	ENTRY_COMP(mq_getsetattr)
 	ENTRY_COMP(waitid)		/* 235 */
 	ENTRY_OURS(fadvise64_64)
 	ENTRY_SAME(set_tid_address)
@@ -403,7 +400,7 @@
 	ENTRY_COMP(signalfd)
 	ENTRY_SAME(ni_syscall)		/* was timerfd */
 	ENTRY_SAME(eventfd)
-	ENTRY_COMP(fallocate)		/* 305 */
+	ENTRY_OURS(fallocate)		/* 305 */
 	ENTRY_SAME(timerfd_create)
 	ENTRY_COMP(timerfd_settime)
 	ENTRY_COMP(timerfd_gettime)
@@ -428,6 +425,10 @@
 	ENTRY_SAME(syncfs)
 	ENTRY_SAME(setns)
 	ENTRY_COMP(sendmmsg)
+	ENTRY_COMP(process_vm_readv)	/* 330 */
+	ENTRY_COMP(process_vm_writev)
+	ENTRY_SAME(kcmp)
+	ENTRY_SAME(finit_module)
 
 	/* Nothing yet */
 
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 18162ce4261e..f247a3480e8e 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -175,10 +175,12 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	struct mm_struct *mm = tsk->mm;
 	unsigned long acc_type;
 	int fault;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (in_atomic() || !mm)
 		goto no_context;
 
+retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma_prev(mm, address, &prev_vma);
 	if (!vma || address < vma->vm_start)
@@ -201,7 +203,12 @@ good_area:
 	 * fault.
 	 */
 
-	fault = handle_mm_fault(mm, vma, address, (acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address,
+			flags | ((acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0));
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		/*
 		 * We hit a shared mapping outside of the file, or some
@@ -214,10 +221,23 @@ good_area:
 			goto bad_area;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR)
-		current->maj_flt++;
-	else
-		current->min_flt++;
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR)
+			current->maj_flt++;
+		else
+			current->min_flt++;
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			/*
+			 * No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
+	}
 	up_read(&mm->mmap_sem);
 	return;