kernel_optimize_test/include/asm-parisc/cacheflush.h
Ingo Molnar fb1c8f93d8 [PATCH] spinlock consolidation
This patch (written by me and also containing many suggestions of Arjan van
de Ven) does a major cleanup of the spinlock code.  It does the following
things:

 - consolidates and enhances the spinlock/rwlock debugging code

 - simplifies the asm/spinlock.h files

 - encapsulates the raw spinlock type and moves generic spinlock
   features (such as ->break_lock) into the generic code.

 - cleans up the spinlock code hierarchy to get rid of the spaghetti.

Most notably there's now only a single variant of the debugging code,
located in lib/spinlock_debug.c.  (previously we had one SMP debugging
variant per architecture, plus a separate generic one for UP builds)

Also, i've enhanced the rwlock debugging facility, it will now track
write-owners.  There is new spinlock-owner/CPU-tracking on SMP builds too.
All locks have lockup detection now, which will work for both soft and hard
spin/rwlock lockups.

The arch-level include files now only contain the minimally necessary
subset of the spinlock code - all the rest that can be generalized now
lives in the generic headers:

 include/asm-i386/spinlock_types.h       |   16
 include/asm-x86_64/spinlock_types.h     |   16

I have also split up the various spinlock variants into separate files,
making it easier to see which does what. The new layout is:

   SMP                         |  UP
   ----------------------------|-----------------------------------
   asm/spinlock_types_smp.h    |  linux/spinlock_types_up.h
   linux/spinlock_types.h      |  linux/spinlock_types.h
   asm/spinlock_smp.h          |  linux/spinlock_up.h
   linux/spinlock_api_smp.h    |  linux/spinlock_api_up.h
   linux/spinlock.h            |  linux/spinlock.h

/*
 * here's the role of the various spinlock/rwlock related include files:
 *
 * on SMP builds:
 *
 *  asm/spinlock_types.h: contains the raw_spinlock_t/raw_rwlock_t and the
 *                        initializers
 *
 *  linux/spinlock_types.h:
 *                        defines the generic type and initializers
 *
 *  asm/spinlock.h:       contains the __raw_spin_*()/etc. lowlevel
 *                        implementations, mostly inline assembly code
 *
 *   (also included on UP-debug builds:)
 *
 *  linux/spinlock_api_smp.h:
 *                        contains the prototypes for the _spin_*() APIs.
 *
 *  linux/spinlock.h:     builds the final spin_*() APIs.
 *
 * on UP builds:
 *
 *  linux/spinlock_type_up.h:
 *                        contains the generic, simplified UP spinlock type.
 *                        (which is an empty structure on non-debug builds)
 *
 *  linux/spinlock_types.h:
 *                        defines the generic type and initializers
 *
 *  linux/spinlock_up.h:
 *                        contains the __raw_spin_*()/etc. version of UP
 *                        builds. (which are NOPs on non-debug, non-preempt
 *                        builds)
 *
 *   (included on UP-non-debug builds:)
 *
 *  linux/spinlock_api_up.h:
 *                        builds the _spin_*() APIs.
 *
 *  linux/spinlock.h:     builds the final spin_*() APIs.
 */

All SMP and UP architectures are converted by this patch.

arm, i386, ia64, ppc, ppc64, s390/s390x, x64 was build-tested via
crosscompilers.  m32r, mips, sh, sparc, have not been tested yet, but should
be mostly fine.

From: Grant Grundler <grundler@parisc-linux.org>

  Booted and lightly tested on a500-44 (64-bit, SMP kernel, dual CPU).
  Builds 32-bit SMP kernel (not booted or tested).  I did not try to build
  non-SMP kernels.  That should be trivial to fix up later if necessary.

  I converted bit ops atomic_hash lock to raw_spinlock_t.  Doing so avoids
  some ugly nesting of linux/*.h and asm/*.h files.  Those particular locks
  are well tested and contained entirely inside arch specific code.  I do NOT
  expect any new issues to arise with them.

 If someone does ever need to use debug/metrics with them, then they will
  need to unravel this hairball between spinlocks, atomic ops, and bit ops
  that exist only because parisc has exactly one atomic instruction: LDCW
  (load and clear word).

From: "Luck, Tony" <tony.luck@intel.com>

   ia64 fix

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjanv@infradead.org>
Signed-off-by: Grant Grundler <grundler@parisc-linux.org>
Cc: Matthew Wilcox <willy@debian.org>
Signed-off-by: Hirokazu Takata <takata@linux-m32r.org>
Signed-off-by: Mikael Pettersson <mikpe@csd.uu.se>
Signed-off-by: Benoit Boissinot <benoit.boissinot@ens-lyon.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-10 10:06:21 -07:00

184 lines
4.8 KiB
C

#ifndef _PARISC_CACHEFLUSH_H
#define _PARISC_CACHEFLUSH_H
#include <linux/config.h>
#include <linux/mm.h>
#include <asm/cache.h> /* for flush_user_dcache_range_asm() proto */
/* The usual comment is "Caches aren't brain-dead on the <architecture>".
* Unfortunately, that doesn't apply to PA-RISC. */
/* Cache flush operations */
#ifdef CONFIG_SMP
#define flush_cache_mm(mm) flush_cache_all()
#else
#define flush_cache_mm(mm) flush_cache_all_local()
#endif
#define flush_kernel_dcache_range(start,size) \
flush_kernel_dcache_range_asm((start), (start)+(size));
extern void flush_cache_all_local(void);
static inline void cacheflush_h_tmp_function(void *dummy)
{
flush_cache_all_local();
}
static inline void flush_cache_all(void)
{
on_each_cpu(cacheflush_h_tmp_function, NULL, 1, 1);
}
#define flush_cache_vmap(start, end) flush_cache_all()
#define flush_cache_vunmap(start, end) flush_cache_all()
extern int parisc_cache_flush_threshold;
void parisc_setup_cache_timing(void);
static inline void
flush_user_dcache_range(unsigned long start, unsigned long end)
{
if ((end - start) < parisc_cache_flush_threshold)
flush_user_dcache_range_asm(start,end);
else
flush_data_cache();
}
static inline void
flush_user_icache_range(unsigned long start, unsigned long end)
{
if ((end - start) < parisc_cache_flush_threshold)
flush_user_icache_range_asm(start,end);
else
flush_instruction_cache();
}
extern void flush_dcache_page(struct page *page);
#define flush_dcache_mmap_lock(mapping) \
write_lock_irq(&(mapping)->tree_lock)
#define flush_dcache_mmap_unlock(mapping) \
write_unlock_irq(&(mapping)->tree_lock)
#define flush_icache_page(vma,page) do { flush_kernel_dcache_page(page_address(page)); flush_kernel_icache_page(page_address(page)); } while (0)
#define flush_icache_range(s,e) do { flush_kernel_dcache_range_asm(s,e); flush_kernel_icache_range_asm(s,e); } while (0)
#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
do { \
flush_cache_page(vma, vaddr, page_to_pfn(page)); \
memcpy(dst, src, len); \
flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); \
} while (0)
#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
do { \
flush_cache_page(vma, vaddr, page_to_pfn(page)); \
memcpy(dst, src, len); \
} while (0)
static inline void flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
int sr3;
if (!vma->vm_mm->context) {
BUG();
return;
}
sr3 = mfsp(3);
if (vma->vm_mm->context == sr3) {
flush_user_dcache_range(start,end);
flush_user_icache_range(start,end);
} else {
flush_cache_all();
}
}
/* Simple function to work out if we have an existing address translation
* for a user space vma. */
static inline pte_t *__translation_exists(struct mm_struct *mm,
unsigned long addr)
{
pgd_t *pgd = pgd_offset(mm, addr);
pmd_t *pmd;
pte_t *pte;
if(pgd_none(*pgd))
return NULL;
pmd = pmd_offset(pgd, addr);
if(pmd_none(*pmd) || pmd_bad(*pmd))
return NULL;
pte = pte_offset_map(pmd, addr);
/* The PA flush mappings show up as pte_none, but they're
* valid none the less */
if(pte_none(*pte) && ((pte_val(*pte) & _PAGE_FLUSH) == 0))
return NULL;
return pte;
}
#define translation_exists(vma, addr) __translation_exists((vma)->vm_mm, addr)
/* Private function to flush a page from the cache of a non-current
* process. cr25 contains the Page Directory of the current user
* process; we're going to hijack both it and the user space %sr3 to
* temporarily make the non-current process current. We have to do
* this because cache flushing may cause a non-access tlb miss which
* the handlers have to fill in from the pgd of the non-current
* process. */
static inline void
flush_user_cache_page_non_current(struct vm_area_struct *vma,
unsigned long vmaddr)
{
/* save the current process space and pgd */
unsigned long space = mfsp(3), pgd = mfctl(25);
/* we don't mind taking interrups since they may not
* do anything with user space, but we can't
* be preempted here */
preempt_disable();
/* make us current */
mtctl(__pa(vma->vm_mm->pgd), 25);
mtsp(vma->vm_mm->context, 3);
flush_user_dcache_page(vmaddr);
if(vma->vm_flags & VM_EXEC)
flush_user_icache_page(vmaddr);
/* put the old current process back */
mtsp(space, 3);
mtctl(pgd, 25);
preempt_enable();
}
static inline void
__flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
if (likely(vma->vm_mm->context == mfsp(3))) {
flush_user_dcache_page(vmaddr);
if (vma->vm_flags & VM_EXEC)
flush_user_icache_page(vmaddr);
} else {
flush_user_cache_page_non_current(vma, vmaddr);
}
}
static inline void
flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn)
{
BUG_ON(!vma->vm_mm->context);
if(likely(translation_exists(vma, vmaddr)))
__flush_cache_page(vma, vmaddr);
}
#endif