Re: Linux 3.4-rc7

From: John David Anglin
Date: Wed Aug 01 2012 - 21:53:43 EST

Next message: Feng Tang: "Re: linux-next: build failure after merge of the acpi tree"
Previous message: Jon Mason: "Re: [RFC v2 1/2] PCI-Express Non-Transparent Bridge Support"
In reply to: Mikulas Patocka: "Re: Linux 3.4-rc7"
Next in thread: Mikulas Patocka: "Re: Linux 3.4-rc7"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On 1-Aug-12, at 9:00 PM, Mikulas Patocka wrote:

On Sun, 13 May 2012, John David Anglin wrote:

On 13-May-12, at 4:40 PM, John David Anglin wrote:

Yes, the revised change fixes the compilation error. I'll know in a while
if
my config boots.

I successfully booted 3.4-rc7 with this change on rp3440 (4 cpu smp). My
build also
included cache and other fixes that are being discussed on the parisc list.

Dave

Hi David

Can I download a series of your PA-RISC patches somewhere?

I applied this http://www.spinics.net/lists/linux-parisc/ msg03352.html and
it improved stability for me (I had no gcc crashes since that, only
about two aptitude crashes).

How stable is it for you? Do you have some random crashes or not?

Attached are my latest patch sets for linux-stable 3.4 and 3.5 branches.
There is no place to to download them directly. I added Jiri Kosina's
personality fix today to the 3.5 patch set. Otherwise, they are similar.

In general, stability with 3.4 has been pretty good. I just started testing
3.5 a couple of days ago. I went about three weeks without a random
crash with 3.4 after I removed Al Viro's restart patch. It was causing
problems with irq handling.

This is on 64-bit rp3440. I have been using it to build debian unstable
and test GCC 4.8. So, the machine gets a fair bit of exercise. In the last
little while, it has been pretty easy to keep up with the changes in unstable.

Sorry, I haven't had time to submit my changes. Some of the cache fixes
are a bit hard to explain.

Dave
--
John David Anglin dave.anglin@xxxxxxxx

diff --git a/arch/parisc/hpux/gate.S b/arch/parisc/hpux/gate.S
index 38a1c1b..8e52a3b 100644
--- a/arch/parisc/hpux/gate.S
+++ b/arch/parisc/hpux/gate.S
@@ -72,6 +72,7 @@ ENTRY(hpux_gateway_page)
STREG %r27, TASK_PT_GR27(%r1) /* user dp */
STREG %r28, TASK_PT_GR28(%r1) /* return value 0 */
STREG %r28, TASK_PT_ORIG_R28(%r1) /* return value 0 (saved for signals) */
+ STREG %r0, TASK_PT_ORIG_R28(%r1) /* don't prohibit restarts */
STREG %r29, TASK_PT_GR29(%r1) /* 8th argument */
STREG %r31, TASK_PT_GR31(%r1) /* preserve syscall return ptr */

diff --git a/arch/parisc/hpux/wrappers.S b/arch/parisc/hpux/wrappers.S
index 58c53c8..bdcea33 100644
--- a/arch/parisc/hpux/wrappers.S
+++ b/arch/parisc/hpux/wrappers.S
@@ -88,7 +88,7 @@ ENTRY(hpux_fork_wrapper)

STREG %r2,-20(%r30)
ldo 64(%r30),%r30
- STREG %r2,PT_GR19(%r1) ;! save for child
+ STREG %r2,PT_SYSCALL_RP(%r1) ;! save for child
STREG %r30,PT_GR21(%r1) ;! save for child

LDREG PT_GR30(%r1),%r25
@@ -132,7 +132,7 @@ ENTRY(hpux_child_return)
bl,n schedule_tail, %r2
#endif

- LDREG TASK_PT_GR19-TASK_SZ_ALGN-128(%r30),%r2
+ LDREG TASK_PT_SYSCALL_RP-TASK_SZ_ALGN-128(%r30),%r2
b fork_return
copy %r0,%r28
ENDPROC(hpux_child_return)
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 9f21ab0..79f694f 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_rt_sigframe.h b/arch/parisc/include/asm/compat_rt_sigframe.h
deleted file mode 100644
index 81bec28..0000000
--- 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/mmzone.h b/arch/parisc/include/asm/mmzone.h
index e67eb9c..31835b9 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 {
@@ -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 4e0e7db..d9812d8 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 ee99f23..563724d 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__ */

@@ -462,10 +468,13 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
#ifdef CONFIG_SMP
unsigned long new, old;

+ /* ??? This might be racy because the page table updates in
+ entry.S don't use the same lock. */
do {
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/real.h b/arch/parisc/include/asm/real.h
deleted file mode 100644
index 82acb25..0000000
--- a/arch/parisc/include/asm/real.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifndef _PARISC_REAL_H
-#define _PARISC_REAL_H
-
-
-#endif
diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c
index dcd5510..5df1597 100644
--- a/arch/parisc/kernel/asm-offsets.c
+++ b/arch/parisc/kernel/asm-offsets.c
@@ -141,6 +141,7 @@ int main(void)
DEFINE(TASK_PT_IAOQ0, offsetof(struct task_struct, thread.regs.iaoq[0]));
DEFINE(TASK_PT_IAOQ1, offsetof(struct task_struct, thread.regs.iaoq[1]));
DEFINE(TASK_PT_CR27, offsetof(struct task_struct, thread.regs.cr27));
+ DEFINE(TASK_PT_SYSCALL_RP, offsetof(struct task_struct, thread.regs.pad0));
DEFINE(TASK_PT_ORIG_R28, offsetof(struct task_struct, thread.regs.orig_r28));
DEFINE(TASK_PT_KSP, offsetof(struct task_struct, thread.regs.ksp));
DEFINE(TASK_PT_KPC, offsetof(struct task_struct, thread.regs.kpc));
@@ -230,6 +231,7 @@ int main(void)
DEFINE(PT_IAOQ0, offsetof(struct pt_regs, iaoq[0]));
DEFINE(PT_IAOQ1, offsetof(struct pt_regs, iaoq[1]));
DEFINE(PT_CR27, offsetof(struct pt_regs, cr27));
+ DEFINE(PT_SYSCALL_RP, offsetof(struct pt_regs, pad0));
DEFINE(PT_ORIG_R28, offsetof(struct pt_regs, orig_r28));
DEFINE(PT_KSP, offsetof(struct pt_regs, ksp));
DEFINE(PT_KPC, offsetof(struct pt_regs, kpc));
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 9d18189..795d392 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)
@@ -315,7 +317,7 @@ void flush_dcache_page(struct page *page)
flush_tlb_page(mpnt, addr);
if (old_addr == 0 || (old_addr & (SHMLBA - 1)) != (addr & (SHMLBA - 1))) {
__flush_cache_page(mpnt, addr, page_to_phys(page));
- if (old_addr)
+ if (old_addr && parisc_requires_coherency())
printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %s\n", old_addr, addr, mpnt->vm_file ? (char *)mpnt->vm_file->f_path.dentry->d_name.name : "(null)");
old_addr = addr;
}
@@ -330,17 +332,6 @@ 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;

@@ -374,20 +365,9 @@ 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)
{
@@ -400,11 +380,26 @@ 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);
}
@@ -420,6 +415,25 @@ void kunmap_parisc(void *addr)
EXPORT_SYMBOL(kunmap_parisc);
#endif

+void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+{
+ unsigned long flags, sid;
+
+ /* Note: purge_tlb_entries can be called at startup with
+ no context. */
+
+ /* Disable preemption while we play with %sr1. */
+ preempt_disable();
+ sid = mfsp(1);
+ mtsp(mm->context,1);
+ purge_tlb_start(flags);
+ pdtlb(addr);
+ pitlb(addr);
+ purge_tlb_end(flags);
+ mtsp(sid,1);
+ preempt_enable();
+}
+
void __flush_tlb_range(unsigned long sid, unsigned long start,
unsigned long end)
{
@@ -459,8 +473,65 @@ 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.
+ Note: This approach is faster than a range flush when the
+ context is current, and it works even when non current. */
+ 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
@@ -486,20 +557,34 @@ 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
}
}

@@ -512,3 +597,67 @@ 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 07ef351..e15ebf5 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
@@ -1785,9 +1785,9 @@ ENTRY(sys_fork_wrapper)
ldo -16(%r30),%r29 /* Reference param save area */
#endif

- /* These are call-clobbered registers and therefore
- also syscall-clobbered (we hope). */
- STREG %r2,PT_GR19(%r1) /* save for child */
+ STREG %r2,PT_SYSCALL_RP(%r1) /* save for child */
+
+ /* WARNING - Clobbers r21, userspace must save! */
STREG %r30,PT_GR21(%r1)

LDREG PT_GR30(%r1),%r25
@@ -1817,7 +1817,7 @@ ENTRY(child_return)
nop

LDREG TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE-FRAME_SIZE(%r30), %r1
- LDREG TASK_PT_GR19(%r1),%r2
+ LDREG TASK_PT_SYSCALL_RP(%r1),%r2
b wrapper_exit
copy %r0,%r28
ENDPROC(child_return)
@@ -1836,8 +1836,9 @@ ENTRY(sys_clone_wrapper)
ldo -16(%r30),%r29 /* Reference param save area */
#endif

- /* WARNING - Clobbers r19 and r21, userspace must save these! */
- STREG %r2,PT_GR19(%r1) /* save for child */
+ STREG %r2,PT_SYSCALL_RP(%r1) /* save for child */
+
+ /* WARNING - Clobbers r21, userspace must save! */
STREG %r30,PT_GR21(%r1)
BL sys_clone,%r2
copy %r1,%r24
@@ -1860,7 +1861,7 @@ ENTRY(sys_vfork_wrapper)
ldo -16(%r30),%r29 /* Reference param save area */
#endif

- STREG %r2,PT_GR19(%r1) /* save for child */
+ STREG %r2,PT_SYSCALL_RP(%r1) /* save for child */
STREG %r30,PT_GR21(%r1)

BL sys_vfork,%r2
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index c0b1aff..8094d3e 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

@@ -410,11 +410,13 @@ void __init init_IRQ(void)
{
local_irq_disable(); /* PARANOID - should already be disabled */
mtctl(~0UL, 23); /* EIRR : clear all pending external intr */
- claim_cpu_irqs();
#ifdef CONFIG_SMP
- if (!cpu_eiem)
+ if (!cpu_eiem) {
+ claim_cpu_irqs();
cpu_eiem = EIEM_MASK(IPI_IRQ) | EIEM_MASK(TIMER_IRQ);
+ }
#else
+ claim_cpu_irqs();
cpu_eiem = EIEM_MASK(TIMER_IRQ);
#endif
set_eiem(cpu_eiem); /* EIEM : enable all external intr */
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 5d7218a..ed401dd 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 */
@@ -208,20 +207,46 @@ 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*/
addib,COND(=) -1, %arg3, fioneloop /* Preadjust and test */
movb,<,n %arg3, %r31, fisync /* If loop < 0, do sync */

fimanyloop: /* Loop if LOOP >= 2 */
addib,COND(>) -1, %r31, fimanyloop /* Adjusted inner loop decr */
- fice %r0(%sr1, %arg0)
- fice,m %arg1(%sr1, %arg0) /* Last fice and addr adjust */
+ fice %r0(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0) /* Last fice and addr adjust */
movb,tr %arg3, %r31, fimanyloop /* Re-init inner loop count */
addib,COND(<=),n -1, %arg2, fisync /* Outer loop decr */

fioneloop: /* Loop if LOOP = 1 */
- addib,COND(>) -1, %arg2, fioneloop /* Outer loop count decr */
- fice,m %arg1(%sr1, %arg0) /* Fice for one loop */
+ /* Some implementations may flush with a single fice instruction */
+ cmpib,COND(>>=),n 15, %arg2, fioneloop2
+
+fioneloop1:
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ addib,COND(>) -16, %arg2, fioneloop1
+ fice,m %arg1(%sr4, %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(%sr4, %arg0) /* Fice for one loop */

fisync:
sync
@@ -240,8 +265,7 @@ ENTRY(flush_data_cache_local)
.callinfo NO_CALLS
.entry

- mtsp %r0, %sr1
- load32 cache_info, %r1
+ load32 cache_info, %r1

/* Flush Data Cache */

@@ -249,20 +273,46 @@ 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*/
addib,COND(=) -1, %arg3, fdoneloop /* Preadjust and test */
movb,<,n %arg3, %r31, fdsync /* If loop < 0, do sync */

fdmanyloop: /* Loop if LOOP >= 2 */
addib,COND(>) -1, %r31, fdmanyloop /* Adjusted inner loop decr */
- fdce %r0(%sr1, %arg0)
- fdce,m %arg1(%sr1, %arg0) /* Last fdce and addr adjust */
+ fdce %r0(%arg0)
+ fdce,m %arg1(%arg0) /* Last fdce and addr adjust */
movb,tr %arg3, %r31, fdmanyloop /* Re-init inner loop count */
addib,COND(<=),n -1, %arg2, fdsync /* Outer loop decr */

fdoneloop: /* Loop if LOOP = 1 */
- addib,COND(>) -1, %arg2, fdoneloop /* Outer loop count decr */
- fdce,m %arg1(%sr1, %arg0) /* Fdce for one loop */
+ /* Some implementations may flush with a single fdce instruction */
+ cmpib,COND(>>=),n 15, %arg2, fdoneloop2
+
+fdoneloop1:
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ addib,COND(>) -16, %arg2, fdoneloop1
+ fdce,m %arg1(%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(%arg0) /* Fdce for one loop */

fdsync:
syncdma
@@ -277,7 +327,104 @@ 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 +432,14 @@ 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 +473,16 @@ 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 +538,7 @@ 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 +561,6 @@ 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 +572,7 @@ 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 +580,21 @@ 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 +609,76 @@ 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

- ldi 64, %r1
+#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.
+ */
+
+ 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 +689,7 @@ 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 +722,10 @@ 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 +733,8 @@ 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 +758,13 @@ 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 +794,7 @@ 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 +819,7 @@ 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 +843,13 @@ 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 +882,17 @@ 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 +920,13 @@ 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 +961,17 @@ 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 +1020,7 @@ 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 +1060,7 @@ 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 a7bb757..25835d8 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -158,5 +158,6 @@ 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 12c1ed3..5dd1059 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -314,7 +314,7 @@ 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/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index c9b9322..f0cb56e 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -92,11 +92,12 @@ 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;

diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 82a52b2..837c602 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -180,9 +180,10 @@ linux_gateway_entry:

/* Are we being ptraced? */
mfctl %cr30, %r1
- LDREG TI_TASK(%r1),%r1
- ldw TASK_PTRACE(%r1), %r1
- bb,<,n %r1,31,.Ltracesys
+ LDREG TI_FLAGS(%r1),%r1
+ ldi (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | _TIF_BLOCKSTEP), %r19
+ and,COND(=) %r19, %r1, %r0
+ b,n .Ltracesys

/* Note! We cannot use the syscall table that is mapped
nearby since the gateway page is mapped execute-only. */
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 70e105d..4a24ba7 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -77,7 +77,7 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)

cycles_elapsed = now - next_tick;

- if ((cycles_elapsed >> 6) < cpt) {
+ if ((cycles_elapsed >> 7) < cpt) {
/* use "cheap" math (add/subtract) instead
* of the more expensive div/mul method
*/
diff --git a/arch/parisc/math-emu/cnv_float.h b/arch/parisc/math-emu/cnv_float.h
index 9071e09..37299c7 100644
--- a/arch/parisc/math-emu/cnv_float.h
+++ b/arch/parisc/math-emu/cnv_float.h
@@ -347,16 +347,15 @@
Sgl_isinexact_to_fix(sgl_value,exponent)

#define Duint_from_sgl_mantissa(sgl_value,exponent,dresultA,dresultB) \
- {Sall(sgl_value) <<= SGL_EXP_LENGTH; /* left-justify */ \
+ {unsigned int val = Sall(sgl_value) << SGL_EXP_LENGTH; \
if (exponent <= 31) { \
Dintp1(dresultA) = 0; \
- Dintp2(dresultB) = (unsigned)Sall(sgl_value) >> (31 - exponent); \
+ Dintp2(dresultB) = val >> (31 - exponent); \
} \
else { \
- Dintp1(dresultA) = Sall(sgl_value) >> (63 - exponent); \
- Dintp2(dresultB) = Sall(sgl_value) << (exponent - 31); \
+ Dintp1(dresultA) = val >> (63 - exponent); \
+ Dintp2(dresultB) = exponent <= 62 ? val << (exponent - 31) : 0; \
} \
- Sall(sgl_value) >>= SGL_EXP_LENGTH; /* return to original */ \
}

#define Duint_setzero(dresultA,dresultB) \
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 18162ce..524bf5a 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 +221,22 @@ 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;

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 3914c1e..90139f0 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -575,6 +575,7 @@ out_eoi:
void
handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
{
+ struct irqaction *action;
struct irq_chip *chip = irq_desc_get_chip(desc);

kstat_incr_irqs_this_cpu(irq, desc);
@@ -582,7 +583,9 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);

- handle_irq_event_percpu(desc, desc->action);
+ action = desc->action;
+ if (action)
+ handle_irq_event_percpu(desc, action);

if (chip->irq_eoi)
chip->irq_eoi(&desc->irq_data);
diff --git a/arch/parisc/hpux/gate.S b/arch/parisc/hpux/gate.S
index 38a1c1b..8e52a3b 100644
--- a/arch/parisc/hpux/gate.S
+++ b/arch/parisc/hpux/gate.S
@@ -72,6 +72,7 @@ ENTRY(hpux_gateway_page)
STREG %r27, TASK_PT_GR27(%r1) /* user dp */
STREG %r28, TASK_PT_GR28(%r1) /* return value 0 */
STREG %r28, TASK_PT_ORIG_R28(%r1) /* return value 0 (saved for signals) */
+ STREG %r0, TASK_PT_ORIG_R28(%r1) /* don't prohibit restarts */
STREG %r29, TASK_PT_GR29(%r1) /* 8th argument */
STREG %r31, TASK_PT_GR31(%r1) /* preserve syscall return ptr */

diff --git a/arch/parisc/hpux/wrappers.S b/arch/parisc/hpux/wrappers.S
index 58c53c8..bdcea33 100644
--- a/arch/parisc/hpux/wrappers.S
+++ b/arch/parisc/hpux/wrappers.S
@@ -88,7 +88,7 @@ ENTRY(hpux_fork_wrapper)

STREG %r2,-20(%r30)
ldo 64(%r30),%r30
- STREG %r2,PT_GR19(%r1) ;! save for child
+ STREG %r2,PT_SYSCALL_RP(%r1) ;! save for child
STREG %r30,PT_GR21(%r1) ;! save for child

LDREG PT_GR30(%r1),%r25
@@ -132,7 +132,7 @@ ENTRY(hpux_child_return)
bl,n schedule_tail, %r2
#endif

- LDREG TASK_PT_GR19-TASK_SZ_ALGN-128(%r30),%r2
+ LDREG TASK_PT_SYSCALL_RP-TASK_SZ_ALGN-128(%r30),%r2
b fork_return
copy %r0,%r28
ENDPROC(hpux_child_return)
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 9f21ab0..79f694f 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_rt_sigframe.h b/arch/parisc/include/asm/compat_rt_sigframe.h
deleted file mode 100644
index 81bec28..0000000
--- 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/mmzone.h b/arch/parisc/include/asm/mmzone.h
index e67eb9c..31835b9 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 {
@@ -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 4e0e7db..d9812d8 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 ee99f23..563724d 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__ */

@@ -462,10 +468,13 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
#ifdef CONFIG_SMP
unsigned long new, old;

+ /* ??? This might be racy because the page table updates in
+ entry.S don't use the same lock. */
do {
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/real.h b/arch/parisc/include/asm/real.h
deleted file mode 100644
index 82acb25..0000000
--- a/arch/parisc/include/asm/real.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifndef _PARISC_REAL_H
-#define _PARISC_REAL_H
-
-
-#endif
diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c
index dcd5510..5df1597 100644
--- a/arch/parisc/kernel/asm-offsets.c
+++ b/arch/parisc/kernel/asm-offsets.c
@@ -141,6 +141,7 @@ int main(void)
DEFINE(TASK_PT_IAOQ0, offsetof(struct task_struct, thread.regs.iaoq[0]));
DEFINE(TASK_PT_IAOQ1, offsetof(struct task_struct, thread.regs.iaoq[1]));
DEFINE(TASK_PT_CR27, offsetof(struct task_struct, thread.regs.cr27));
+ DEFINE(TASK_PT_SYSCALL_RP, offsetof(struct task_struct, thread.regs.pad0));
DEFINE(TASK_PT_ORIG_R28, offsetof(struct task_struct, thread.regs.orig_r28));
DEFINE(TASK_PT_KSP, offsetof(struct task_struct, thread.regs.ksp));
DEFINE(TASK_PT_KPC, offsetof(struct task_struct, thread.regs.kpc));
@@ -230,6 +231,7 @@ int main(void)
DEFINE(PT_IAOQ0, offsetof(struct pt_regs, iaoq[0]));
DEFINE(PT_IAOQ1, offsetof(struct pt_regs, iaoq[1]));
DEFINE(PT_CR27, offsetof(struct pt_regs, cr27));
+ DEFINE(PT_SYSCALL_RP, offsetof(struct pt_regs, pad0));
DEFINE(PT_ORIG_R28, offsetof(struct pt_regs, orig_r28));
DEFINE(PT_KSP, offsetof(struct pt_regs, ksp));
DEFINE(PT_KPC, offsetof(struct pt_regs, kpc));
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 9d18189..795d392 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)
@@ -315,7 +317,7 @@ void flush_dcache_page(struct page *page)
flush_tlb_page(mpnt, addr);
if (old_addr == 0 || (old_addr & (SHMLBA - 1)) != (addr & (SHMLBA - 1))) {
__flush_cache_page(mpnt, addr, page_to_phys(page));
- if (old_addr)
+ if (old_addr && parisc_requires_coherency())
printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %s\n", old_addr, addr, mpnt->vm_file ? (char *)mpnt->vm_file->f_path.dentry->d_name.name : "(null)");
old_addr = addr;
}
@@ -330,17 +332,6 @@ 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;

@@ -374,20 +365,9 @@ 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)
{
@@ -400,11 +380,26 @@ 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);
}
@@ -420,6 +415,25 @@ void kunmap_parisc(void *addr)
EXPORT_SYMBOL(kunmap_parisc);
#endif

+void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+{
+ unsigned long flags, sid;
+
+ /* Note: purge_tlb_entries can be called at startup with
+ no context. */
+
+ /* Disable preemption while we play with %sr1. */
+ preempt_disable();
+ sid = mfsp(1);
+ mtsp(mm->context,1);
+ purge_tlb_start(flags);
+ pdtlb(addr);
+ pitlb(addr);
+ purge_tlb_end(flags);
+ mtsp(sid,1);
+ preempt_enable();
+}
+
void __flush_tlb_range(unsigned long sid, unsigned long start,
unsigned long end)
{
@@ -459,8 +473,65 @@ 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.
+ Note: This approach is faster than a range flush when the
+ context is current, and it works even when non current. */
+ 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
@@ -486,20 +557,34 @@ 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
}
}

@@ -512,3 +597,67 @@ 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 18670a0..fcef82d 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
@@ -1785,9 +1785,9 @@ ENTRY(sys_fork_wrapper)
ldo -16(%r30),%r29 /* Reference param save area */
#endif

- /* These are call-clobbered registers and therefore
- also syscall-clobbered (we hope). */
- STREG %r2,PT_GR19(%r1) /* save for child */
+ STREG %r2,PT_SYSCALL_RP(%r1) /* save for child */
+
+ /* WARNING - Clobbers r21, userspace must save! */
STREG %r30,PT_GR21(%r1)

LDREG PT_GR30(%r1),%r25
@@ -1817,7 +1817,7 @@ ENTRY(child_return)
nop

LDREG TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE-FRAME_SIZE(%r30), %r1
- LDREG TASK_PT_GR19(%r1),%r2
+ LDREG TASK_PT_SYSCALL_RP(%r1),%r2
b wrapper_exit
copy %r0,%r28
ENDPROC(child_return)
@@ -1836,8 +1836,9 @@ ENTRY(sys_clone_wrapper)
ldo -16(%r30),%r29 /* Reference param save area */
#endif

- /* WARNING - Clobbers r19 and r21, userspace must save these! */
- STREG %r2,PT_GR19(%r1) /* save for child */
+ STREG %r2,PT_SYSCALL_RP(%r1) /* save for child */
+
+ /* WARNING - Clobbers r21, userspace must save! */
STREG %r30,PT_GR21(%r1)
BL sys_clone,%r2
copy %r1,%r24
@@ -1860,7 +1861,7 @@ ENTRY(sys_vfork_wrapper)
ldo -16(%r30),%r29 /* Reference param save area */
#endif

- STREG %r2,PT_GR19(%r1) /* save for child */
+ STREG %r2,PT_SYSCALL_RP(%r1) /* save for child */
STREG %r30,PT_GR21(%r1)

BL sys_vfork,%r2
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index c0b1aff..8094d3e 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

@@ -410,11 +410,13 @@ void __init init_IRQ(void)
{
local_irq_disable(); /* PARANOID - should already be disabled */
mtctl(~0UL, 23); /* EIRR : clear all pending external intr */
- claim_cpu_irqs();
#ifdef CONFIG_SMP
- if (!cpu_eiem)
+ if (!cpu_eiem) {
+ claim_cpu_irqs();
cpu_eiem = EIEM_MASK(IPI_IRQ) | EIEM_MASK(TIMER_IRQ);
+ }
#else
+ claim_cpu_irqs();
cpu_eiem = EIEM_MASK(TIMER_IRQ);
#endif
set_eiem(cpu_eiem); /* EIEM : enable all external intr */
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 5d7218a..ed401dd 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 */
@@ -208,20 +207,46 @@ 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*/
addib,COND(=) -1, %arg3, fioneloop /* Preadjust and test */
movb,<,n %arg3, %r31, fisync /* If loop < 0, do sync */

fimanyloop: /* Loop if LOOP >= 2 */
addib,COND(>) -1, %r31, fimanyloop /* Adjusted inner loop decr */
- fice %r0(%sr1, %arg0)
- fice,m %arg1(%sr1, %arg0) /* Last fice and addr adjust */
+ fice %r0(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0) /* Last fice and addr adjust */
movb,tr %arg3, %r31, fimanyloop /* Re-init inner loop count */
addib,COND(<=),n -1, %arg2, fisync /* Outer loop decr */

fioneloop: /* Loop if LOOP = 1 */
- addib,COND(>) -1, %arg2, fioneloop /* Outer loop count decr */
- fice,m %arg1(%sr1, %arg0) /* Fice for one loop */
+ /* Some implementations may flush with a single fice instruction */
+ cmpib,COND(>>=),n 15, %arg2, fioneloop2
+
+fioneloop1:
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ fice,m %arg1(%sr4, %arg0)
+ addib,COND(>) -16, %arg2, fioneloop1
+ fice,m %arg1(%sr4, %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(%sr4, %arg0) /* Fice for one loop */

fisync:
sync
@@ -240,8 +265,7 @@ ENTRY(flush_data_cache_local)
.callinfo NO_CALLS
.entry

- mtsp %r0, %sr1
- load32 cache_info, %r1
+ load32 cache_info, %r1

/* Flush Data Cache */

@@ -249,20 +273,46 @@ 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*/
addib,COND(=) -1, %arg3, fdoneloop /* Preadjust and test */
movb,<,n %arg3, %r31, fdsync /* If loop < 0, do sync */

fdmanyloop: /* Loop if LOOP >= 2 */
addib,COND(>) -1, %r31, fdmanyloop /* Adjusted inner loop decr */
- fdce %r0(%sr1, %arg0)
- fdce,m %arg1(%sr1, %arg0) /* Last fdce and addr adjust */
+ fdce %r0(%arg0)
+ fdce,m %arg1(%arg0) /* Last fdce and addr adjust */
movb,tr %arg3, %r31, fdmanyloop /* Re-init inner loop count */
addib,COND(<=),n -1, %arg2, fdsync /* Outer loop decr */

fdoneloop: /* Loop if LOOP = 1 */
- addib,COND(>) -1, %arg2, fdoneloop /* Outer loop count decr */
- fdce,m %arg1(%sr1, %arg0) /* Fdce for one loop */
+ /* Some implementations may flush with a single fdce instruction */
+ cmpib,COND(>>=),n 15, %arg2, fdoneloop2
+
+fdoneloop1:
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ fdce,m %arg1(%arg0)
+ addib,COND(>) -16, %arg2, fdoneloop1
+ fdce,m %arg1(%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(%arg0) /* Fdce for one loop */

fdsync:
syncdma
@@ -277,7 +327,104 @@ 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 +432,14 @@ 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 +473,16 @@ 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 +538,7 @@ 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 +561,6 @@ 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 +572,7 @@ 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 +580,21 @@ 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 +609,76 @@ 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

- ldi 64, %r1
+#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.
+ */
+
+ 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 +689,7 @@ 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 +722,10 @@ 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 +733,8 @@ 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 +758,13 @@ 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 +794,7 @@ 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 +819,7 @@ 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 +843,13 @@ 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 +882,17 @@ 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 +920,13 @@ 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 +961,17 @@ 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 +1020,7 @@ 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 +1060,7 @@ 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 ceec85d..6795dc6 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/process.c b/arch/parisc/kernel/process.c
index d4b94b3..2c05a92 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -309,7 +309,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
cregs->ksp = (unsigned long)stack
+ (pregs->gr[21] & (THREAD_SIZE - 1));
cregs->gr[30] = usp;
- if (p->personality == PER_HPUX) {
+ if (personality(p->personality) == PER_HPUX) {
#ifdef CONFIG_HPUX
cregs->kpc = (unsigned long) &hpux_child_return;
#else
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index 594459b..56e0087 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -308,7 +308,7 @@ 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/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index c9b9322..9888765 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -92,11 +92,12 @@ 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;

@@ -225,12 +226,12 @@ long parisc_personality(unsigned long personality)
long err;

if (personality(current->personality) == PER_LINUX32
- && personality == PER_LINUX)
- personality = PER_LINUX32;
+ && personality(personality) == PER_LINUX)
+ personality &= ~PER_LINUX|PER_LINUX32;

err = sys_personality(personality);
- if (err == PER_LINUX32)
- err = PER_LINUX;
+ if (personality(err) == PER_LINUX32)
+ err &= ~PER_LINUX32|PER_LINUX;

return err;
}
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 82a52b2..837c602 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -180,9 +180,10 @@ linux_gateway_entry:

/* Are we being ptraced? */
mfctl %cr30, %r1
- LDREG TI_TASK(%r1),%r1
- ldw TASK_PTRACE(%r1), %r1
- bb,<,n %r1,31,.Ltracesys
+ LDREG TI_FLAGS(%r1),%r1
+ ldi (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | _TIF_BLOCKSTEP), %r19
+ and,COND(=) %r19, %r1, %r0
+ b,n .Ltracesys

/* Note! We cannot use the syscall table that is mapped
nearby since the gateway page is mapped execute-only. */
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 70e105d..4a24ba7 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -77,7 +77,7 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)

cycles_elapsed = now - next_tick;

- if ((cycles_elapsed >> 6) < cpt) {
+ if ((cycles_elapsed >> 7) < cpt) {
/* use "cheap" math (add/subtract) instead
* of the more expensive div/mul method
*/
diff --git a/arch/parisc/math-emu/cnv_float.h b/arch/parisc/math-emu/cnv_float.h
index 9071e09..37299c7 100644
--- a/arch/parisc/math-emu/cnv_float.h
+++ b/arch/parisc/math-emu/cnv_float.h
@@ -347,16 +347,15 @@
Sgl_isinexact_to_fix(sgl_value,exponent)

#define Duint_from_sgl_mantissa(sgl_value,exponent,dresultA,dresultB) \
- {Sall(sgl_value) <<= SGL_EXP_LENGTH; /* left-justify */ \
+ {unsigned int val = Sall(sgl_value) << SGL_EXP_LENGTH; \
if (exponent <= 31) { \
Dintp1(dresultA) = 0; \
- Dintp2(dresultB) = (unsigned)Sall(sgl_value) >> (31 - exponent); \
+ Dintp2(dresultB) = val >> (31 - exponent); \
} \
else { \
- Dintp1(dresultA) = Sall(sgl_value) >> (63 - exponent); \
- Dintp2(dresultB) = Sall(sgl_value) << (exponent - 31); \
+ Dintp1(dresultA) = val >> (63 - exponent); \
+ Dintp2(dresultB) = exponent <= 62 ? val << (exponent - 31) : 0; \
} \
- Sall(sgl_value) >>= SGL_EXP_LENGTH; /* return to original */ \
}

#define Duint_setzero(dresultA,dresultB) \
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 18162ce..524bf5a 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 +221,22 @@ 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;

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index eebd6d5..078a593 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -581,6 +581,7 @@ out_eoi:
void
handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
{
+ struct irqaction *action;
struct irq_chip *chip = irq_desc_get_chip(desc);

kstat_incr_irqs_this_cpu(irq, desc);
@@ -588,7 +589,9 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);

- handle_irq_event_percpu(desc, desc->action);
+ action = desc->action;
+ if (action)
+ handle_irq_event_percpu(desc, action);

if (chip->irq_eoi)
chip->irq_eoi(&desc->irq_data);

Next message: Feng Tang: "Re: linux-next: build failure after merge of the acpi tree"
Previous message: Jon Mason: "Re: [RFC v2 1/2] PCI-Express Non-Transparent Bridge Support"
In reply to: Mikulas Patocka: "Re: Linux 3.4-rc7"
Next in thread: Mikulas Patocka: "Re: Linux 3.4-rc7"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]