|
|
|
#ifndef __PARISC_SYSTEM_H
|
|
|
|
#define __PARISC_SYSTEM_H
|
|
|
|
|
|
|
|
#include <asm/psw.h>
|
|
|
|
|
|
|
|
/* The program status word as bitfields. */
|
|
|
|
struct pa_psw {
|
|
|
|
unsigned int y:1;
|
|
|
|
unsigned int z:1;
|
|
|
|
unsigned int rv:2;
|
|
|
|
unsigned int w:1;
|
|
|
|
unsigned int e:1;
|
|
|
|
unsigned int s:1;
|
|
|
|
unsigned int t:1;
|
|
|
|
|
|
|
|
unsigned int h:1;
|
|
|
|
unsigned int l:1;
|
|
|
|
unsigned int n:1;
|
|
|
|
unsigned int x:1;
|
|
|
|
unsigned int b:1;
|
|
|
|
unsigned int c:1;
|
|
|
|
unsigned int v:1;
|
|
|
|
unsigned int m:1;
|
|
|
|
|
|
|
|
unsigned int cb:8;
|
|
|
|
|
|
|
|
unsigned int o:1;
|
|
|
|
unsigned int g:1;
|
|
|
|
unsigned int f:1;
|
|
|
|
unsigned int r:1;
|
|
|
|
unsigned int q:1;
|
|
|
|
unsigned int p:1;
|
|
|
|
unsigned int d:1;
|
|
|
|
unsigned int i:1;
|
|
|
|
};
|
|
|
|
|
|
|
|
#ifdef __LP64__
|
|
|
|
#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW + 4))
|
|
|
|
#else
|
|
|
|
#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW))
|
|
|
|
#endif
|
|
|
|
|
|
|
|
struct task_struct;
|
|
|
|
|
|
|
|
extern struct task_struct *_switch_to(struct task_struct *, struct task_struct *);
|
|
|
|
|
|
|
|
#define switch_to(prev, next, last) do { \
|
|
|
|
(last) = _switch_to(prev, next); \
|
|
|
|
} while(0)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* On SMP systems, when the scheduler does migration-cost autodetection,
|
|
|
|
* it needs a way to flush as much of the CPU's caches as possible.
|
|
|
|
*
|
|
|
|
* TODO: fill this in!
|
|
|
|
*/
|
|
|
|
static inline void sched_cacheflush(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* interrupt control */
|
|
|
|
#define local_save_flags(x) __asm__ __volatile__("ssm 0, %0" : "=r" (x) : : "memory")
|
|
|
|
#define local_irq_disable() __asm__ __volatile__("rsm %0,%%r0\n" : : "i" (PSW_I) : "memory" )
|
|
|
|
#define local_irq_enable() __asm__ __volatile__("ssm %0,%%r0\n" : : "i" (PSW_I) : "memory" )
|
|
|
|
|
|
|
|
#define local_irq_save(x) \
|
|
|
|
__asm__ __volatile__("rsm %1,%0" : "=r" (x) :"i" (PSW_I) : "memory" )
|
|
|
|
#define local_irq_restore(x) \
|
|
|
|
__asm__ __volatile__("mtsm %0" : : "r" (x) : "memory" )
|
|
|
|
|
|
|
|
#define irqs_disabled() \
|
|
|
|
({ \
|
|
|
|
unsigned long flags; \
|
|
|
|
local_save_flags(flags); \
|
|
|
|
(flags & PSW_I) == 0; \
|
|
|
|
})
|
|
|
|
|
|
|
|
#define mfctl(reg) ({ \
|
|
|
|
unsigned long cr; \
|
|
|
|
__asm__ __volatile__( \
|
|
|
|
"mfctl " #reg ",%0" : \
|
|
|
|
"=r" (cr) \
|
|
|
|
); \
|
|
|
|
cr; \
|
|
|
|
})
|
|
|
|
|
|
|
|
#define mtctl(gr, cr) \
|
|
|
|
__asm__ __volatile__("mtctl %0,%1" \
|
|
|
|
: /* no outputs */ \
|
|
|
|
: "r" (gr), "i" (cr) : "memory")
|
|
|
|
|
|
|
|
/* these are here to de-mystefy the calling code, and to provide hooks */
|
|
|
|
/* which I needed for debugging EIEM problems -PB */
|
|
|
|
#define get_eiem() mfctl(15)
|
|
|
|
static inline void set_eiem(unsigned long val)
|
|
|
|
{
|
|
|
|
mtctl(val, 15);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define mfsp(reg) ({ \
|
|
|
|
unsigned long cr; \
|
|
|
|
__asm__ __volatile__( \
|
|
|
|
"mfsp " #reg ",%0" : \
|
|
|
|
"=r" (cr) \
|
|
|
|
); \
|
|
|
|
cr; \
|
|
|
|
})
|
|
|
|
|
|
|
|
#define mtsp(gr, cr) \
|
|
|
|
__asm__ __volatile__("mtsp %0,%1" \
|
|
|
|
: /* no outputs */ \
|
|
|
|
: "r" (gr), "i" (cr) : "memory")
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
** This is simply the barrier() macro from linux/kernel.h but when serial.c
|
|
|
|
** uses tqueue.h uses smp_mb() defined using barrier(), linux/kernel.h
|
|
|
|
** hasn't yet been included yet so it fails, thus repeating the macro here.
|
|
|
|
**
|
|
|
|
** PA-RISC architecture allows for weakly ordered memory accesses although
|
|
|
|
** none of the processors use it. There is a strong ordered bit that is
|
|
|
|
** set in the O-bit of the page directory entry. Operating systems that
|
|
|
|
** can not tolerate out of order accesses should set this bit when mapping
|
|
|
|
** pages. The O-bit of the PSW should also be set to 1 (I don't believe any
|
|
|
|
** of the processor implemented the PSW O-bit). The PCX-W ERS states that
|
|
|
|
** the TLB O-bit is not implemented so the page directory does not need to
|
|
|
|
** have the O-bit set when mapping pages (section 3.1). This section also
|
|
|
|
** states that the PSW Y, Z, G, and O bits are not implemented.
|
|
|
|
** So it looks like nothing needs to be done for parisc-linux (yet).
|
|
|
|
** (thanks to chada for the above comment -ggg)
|
|
|
|
**
|
|
|
|
** The __asm__ op below simple prevents gcc/ld from reordering
|
|
|
|
** instructions across the mb() "call".
|
|
|
|
*/
|
|
|
|
#define mb() __asm__ __volatile__("":::"memory") /* barrier() */
|
|
|
|
#define rmb() mb()
|
|
|
|
#define wmb() mb()
|
|
|
|
#define smp_mb() mb()
|
|
|
|
#define smp_rmb() mb()
|
|
|
|
#define smp_wmb() mb()
|
|
|
|
#define smp_read_barrier_depends() do { } while(0)
|
|
|
|
#define read_barrier_depends() do { } while(0)
|
|
|
|
|
|
|
|
#define set_mb(var, value) do { var = value; mb(); } while (0)
|
|
|
|
|
|
|
|
#ifndef CONFIG_PA20
|
|
|
|
/* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
|
|
|
|
and GCC only guarantees 8-byte alignment for stack locals, we can't
|
|
|
|
be assured of 16-byte alignment for atomic lock data even if we
|
|
|
|
specify "__attribute ((aligned(16)))" in the type declaration. So,
|
|
|
|
we use a struct containing an array of four ints for the atomic lock
|
|
|
|
type and dynamically select the 16-byte aligned int from the array
|
|
|
|
for the semaphore. */
|
|
|
|
|
|
|
|
#define __PA_LDCW_ALIGNMENT 16
|
|
|
|
#define __ldcw_align(a) ({ \
|
|
|
|
unsigned long __ret = (unsigned long) &(a)->lock[0]; \
|
|
|
|
__ret = (__ret + __PA_LDCW_ALIGNMENT - 1) \
|
|
|
|
& ~(__PA_LDCW_ALIGNMENT - 1); \
|
|
|
|
(volatile unsigned int *) __ret; \
|
|
|
|
})
|
|
|
|
#define __LDCW "ldcw"
|
|
|
|
|
|
|
|
#else /*CONFIG_PA20*/
|
|
|
|
/* From: "Jim Hull" <jim.hull of hp.com>
|
|
|
|
I've attached a summary of the change, but basically, for PA 2.0, as
|
|
|
|
long as the ",CO" (coherent operation) completer is specified, then the
|
|
|
|
16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
|
|
|
|
they only require "natural" alignment (4-byte for ldcw, 8-byte for
|
|
|
|
ldcd). */
|
|
|
|
|
|
|
|
#define __PA_LDCW_ALIGNMENT 4
|
|
|
|
#define __ldcw_align(a) ((volatile unsigned int *)a)
|
|
|
|
#define __LDCW "ldcw,co"
|
|
|
|
|
|
|
|
#endif /*!CONFIG_PA20*/
|
|
|
|
|
|
|
|
/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*. */
|
|
|
|
#define __ldcw(a) ({ \
|
|
|
|
unsigned __ret; \
|
|
|
|
__asm__ __volatile__(__LDCW " 0(%1),%0" \
|
|
|
|
: "=r" (__ret) : "r" (a)); \
|
|
|
|
__ret; \
|
|
|
|
})
|
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
[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>
20 years ago
|
|
|
# define __lock_aligned __attribute__((__section__(".data.lock_aligned")))
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#define KERNEL_START (0x10100000 - 0x1000)
|
|
|
|
#define arch_align_stack(x) (x)
|
|
|
|
|
|
|
|
#endif
|