mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-22 18:44:44 +08:00
3a6bfbc91d
The arch_mutex_cpu_relax() function, introduced by 34b133f
, is
hacky and ugly. It was added a few years ago to address the fact
that common cpu_relax() calls include yielding on s390, and thus
impact the optimistic spinning functionality of mutexes. Nowadays
we use this function well beyond mutexes: rwsem, qrwlock, mcs and
lockref. Since the macro that defines the call is in the mutex header,
any users must include mutex.h and the naming is misleading as well.
This patch (i) renames the call to cpu_relax_lowlatency ("relax, but
only if you can do it with very low latency") and (ii) defines it in
each arch's asm/processor.h local header, just like for regular cpu_relax
functions. On all archs, except s390, cpu_relax_lowlatency is simply cpu_relax,
and thus we can take it out of mutex.h. While this can seem redundant,
I believe it is a good choice as it allows us to move out arch specific
logic from generic locking primitives and enables future(?) archs to
transparently define it, similarly to System Z.
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Anton Blanchard <anton@samba.org>
Cc: Aurelien Jacquiot <a-jacquiot@ti.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Bharat Bhushan <r65777@freescale.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chen Liqin <liqin.linux@gmail.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: David Howells <dhowells@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Deepthi Dharwar <deepthi@linux.vnet.ibm.com>
Cc: Dominik Dingel <dingel@linux.vnet.ibm.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: Haavard Skinnemoen <hskinnemoen@gmail.com>
Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James E.J. Bottomley <jejb@parisc-linux.org>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Joe Perches <joe@perches.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Joseph Myers <joseph@codesourcery.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com>
Cc: Lennox Wu <lennox.wu@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Salter <msalter@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Mikael Starvik <starvik@axis.com>
Cc: Nicolas Pitre <nico@linaro.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Qais Yousef <qais.yousef@imgtec.com>
Cc: Qiaowei Ren <qiaowei.ren@intel.com>
Cc: Rafael Wysocki <rafael.j.wysocki@intel.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Richard Kuo <rkuo@codeaurora.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Steven Miao <realmz6@gmail.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: Stratos Karafotis <stratosk@semaphore.gr>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vasily Kulikov <segoon@openwall.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Wolfram Sang <wsa@the-dreams.de>
Cc: adi-buildroot-devel@lists.sourceforge.net
Cc: linux390@de.ibm.com
Cc: linux-alpha@vger.kernel.org
Cc: linux-am33-list@redhat.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-c6x-dev@linux-c6x.org
Cc: linux-cris-kernel@axis.com
Cc: linux-hexagon@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
Cc: linux@lists.openrisc.net
Cc: linux-m32r-ja@ml.linux-m32r.org
Cc: linux-m32r@ml.linux-m32r.org
Cc: linux-m68k@lists.linux-m68k.org
Cc: linux-metag@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: linux-xtensa@linux-xtensa.org
Cc: sparclinux@vger.kernel.org
Link: http://lkml.kernel.org/r/1404079773.2619.4.camel@buesod1.americas.hpqcorp.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
359 lines
11 KiB
C
359 lines
11 KiB
C
/*
|
|
* include/asm-parisc/processor.h
|
|
*
|
|
* Copyright (C) 1994 Linus Torvalds
|
|
* Copyright (C) 2001 Grant Grundler
|
|
*/
|
|
|
|
#ifndef __ASM_PARISC_PROCESSOR_H
|
|
#define __ASM_PARISC_PROCESSOR_H
|
|
|
|
#ifndef __ASSEMBLY__
|
|
#include <linux/threads.h>
|
|
|
|
#include <asm/prefetch.h>
|
|
#include <asm/hardware.h>
|
|
#include <asm/pdc.h>
|
|
#include <asm/ptrace.h>
|
|
#include <asm/types.h>
|
|
#include <asm/percpu.h>
|
|
#endif /* __ASSEMBLY__ */
|
|
|
|
/*
|
|
* Default implementation of macro that returns current
|
|
* instruction pointer ("program counter").
|
|
*/
|
|
#ifdef CONFIG_PA20
|
|
#define current_ia(x) __asm__("mfia %0" : "=r"(x))
|
|
#else /* mfia added in pa2.0 */
|
|
#define current_ia(x) __asm__("blr 0,%0\n\tnop" : "=r"(x))
|
|
#endif
|
|
#define current_text_addr() ({ void *pc; current_ia(pc); pc; })
|
|
|
|
#define HAVE_ARCH_PICK_MMAP_LAYOUT
|
|
|
|
#define TASK_SIZE_OF(tsk) ((tsk)->thread.task_size)
|
|
#define TASK_SIZE TASK_SIZE_OF(current)
|
|
#define TASK_UNMAPPED_BASE (current->thread.map_base)
|
|
|
|
#define DEFAULT_TASK_SIZE32 (0xFFF00000UL)
|
|
#define DEFAULT_MAP_BASE32 (0x40000000UL)
|
|
|
|
#ifdef CONFIG_64BIT
|
|
#define DEFAULT_TASK_SIZE (MAX_ADDRESS-0xf000000)
|
|
#define DEFAULT_MAP_BASE (0x200000000UL)
|
|
#else
|
|
#define DEFAULT_TASK_SIZE DEFAULT_TASK_SIZE32
|
|
#define DEFAULT_MAP_BASE DEFAULT_MAP_BASE32
|
|
#endif
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
/* XXX: STACK_TOP actually should be STACK_BOTTOM for parisc.
|
|
* prumpf */
|
|
|
|
#define STACK_TOP TASK_SIZE
|
|
#define STACK_TOP_MAX DEFAULT_TASK_SIZE
|
|
|
|
/* Allow bigger stacks for 64-bit processes */
|
|
#define STACK_SIZE_MAX (USER_WIDE_MODE \
|
|
? (1 << 30) /* 1 GB */ \
|
|
: (CONFIG_MAX_STACK_SIZE_MB*1024*1024))
|
|
|
|
#endif
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
/*
|
|
* Data detected about CPUs at boot time which is the same for all CPU's.
|
|
* HP boxes are SMP - ie identical processors.
|
|
*
|
|
* FIXME: some CPU rev info may be processor specific...
|
|
*/
|
|
struct system_cpuinfo_parisc {
|
|
unsigned int cpu_count;
|
|
unsigned int cpu_hz;
|
|
unsigned int hversion;
|
|
unsigned int sversion;
|
|
enum cpu_type cpu_type;
|
|
|
|
struct {
|
|
struct pdc_model model;
|
|
unsigned long versions;
|
|
unsigned long cpuid;
|
|
unsigned long capabilities;
|
|
char sys_model_name[81]; /* PDC-ROM returnes this model name */
|
|
} pdc;
|
|
|
|
const char *cpu_name; /* e.g. "PA7300LC (PCX-L2)" */
|
|
const char *family_name; /* e.g. "1.1e" */
|
|
};
|
|
|
|
|
|
/* Per CPU data structure - ie varies per CPU. */
|
|
struct cpuinfo_parisc {
|
|
unsigned long it_value; /* Interval Timer at last timer Intr */
|
|
unsigned long it_delta; /* Interval delta (tic_10ms / HZ * 100) */
|
|
unsigned long irq_count; /* number of IRQ's since boot */
|
|
unsigned long irq_max_cr16; /* longest time to handle a single IRQ */
|
|
unsigned long cpuid; /* aka slot_number or set to NO_PROC_ID */
|
|
unsigned long hpa; /* Host Physical address */
|
|
unsigned long txn_addr; /* MMIO addr of EIR or id_eid */
|
|
#ifdef CONFIG_SMP
|
|
unsigned long pending_ipi; /* bitmap of type ipi_message_type */
|
|
#endif
|
|
unsigned long bh_count; /* number of times bh was invoked */
|
|
unsigned long prof_counter; /* per CPU profiling support */
|
|
unsigned long prof_multiplier; /* per CPU profiling support */
|
|
unsigned long fp_rev;
|
|
unsigned long fp_model;
|
|
unsigned int state;
|
|
struct parisc_device *dev;
|
|
unsigned long loops_per_jiffy;
|
|
};
|
|
|
|
extern struct system_cpuinfo_parisc boot_cpu_data;
|
|
DECLARE_PER_CPU(struct cpuinfo_parisc, cpu_data);
|
|
|
|
#define CPU_HVERSION ((boot_cpu_data.hversion >> 4) & 0x0FFF)
|
|
|
|
typedef struct {
|
|
int seg;
|
|
} mm_segment_t;
|
|
|
|
#define ARCH_MIN_TASKALIGN 8
|
|
|
|
struct thread_struct {
|
|
struct pt_regs regs;
|
|
unsigned long task_size;
|
|
unsigned long map_base;
|
|
unsigned long flags;
|
|
};
|
|
|
|
#define task_pt_regs(tsk) ((struct pt_regs *)&((tsk)->thread.regs))
|
|
|
|
/* Thread struct flags. */
|
|
#define PARISC_UAC_NOPRINT (1UL << 0) /* see prctl and unaligned.c */
|
|
#define PARISC_UAC_SIGBUS (1UL << 1)
|
|
#define PARISC_KERNEL_DEATH (1UL << 31) /* see die_if_kernel()... */
|
|
|
|
#define PARISC_UAC_SHIFT 0
|
|
#define PARISC_UAC_MASK (PARISC_UAC_NOPRINT|PARISC_UAC_SIGBUS)
|
|
|
|
#define SET_UNALIGN_CTL(task,value) \
|
|
({ \
|
|
(task)->thread.flags = (((task)->thread.flags & ~PARISC_UAC_MASK) \
|
|
| (((value) << PARISC_UAC_SHIFT) & \
|
|
PARISC_UAC_MASK)); \
|
|
0; \
|
|
})
|
|
|
|
#define GET_UNALIGN_CTL(task,addr) \
|
|
({ \
|
|
put_user(((task)->thread.flags & PARISC_UAC_MASK) \
|
|
>> PARISC_UAC_SHIFT, (int __user *) (addr)); \
|
|
})
|
|
|
|
#define INIT_THREAD { \
|
|
.regs = { .gr = { 0, }, \
|
|
.fr = { 0, }, \
|
|
.sr = { 0, }, \
|
|
.iasq = { 0, }, \
|
|
.iaoq = { 0, }, \
|
|
.cr27 = 0, \
|
|
}, \
|
|
.task_size = DEFAULT_TASK_SIZE, \
|
|
.map_base = DEFAULT_MAP_BASE, \
|
|
.flags = 0 \
|
|
}
|
|
|
|
/*
|
|
* Return saved PC of a blocked thread. This is used by ps mostly.
|
|
*/
|
|
|
|
struct task_struct;
|
|
unsigned long thread_saved_pc(struct task_struct *t);
|
|
void show_trace(struct task_struct *task, unsigned long *stack);
|
|
|
|
/*
|
|
* Start user thread in another space.
|
|
*
|
|
* Note that we set both the iaoq and r31 to the new pc. When
|
|
* the kernel initially calls execve it will return through an
|
|
* rfi path that will use the values in the iaoq. The execve
|
|
* syscall path will return through the gateway page, and
|
|
* that uses r31 to branch to.
|
|
*
|
|
* For ELF we clear r23, because the dynamic linker uses it to pass
|
|
* the address of the finalizer function.
|
|
*
|
|
* We also initialize sr3 to an illegal value (illegal for our
|
|
* implementation, not for the architecture).
|
|
*/
|
|
typedef unsigned int elf_caddr_t;
|
|
|
|
#define start_thread_som(regs, new_pc, new_sp) do { \
|
|
unsigned long *sp = (unsigned long *)new_sp; \
|
|
__u32 spaceid = (__u32)current->mm->context; \
|
|
unsigned long pc = (unsigned long)new_pc; \
|
|
/* offset pc for priv. level */ \
|
|
pc |= 3; \
|
|
\
|
|
regs->iasq[0] = spaceid; \
|
|
regs->iasq[1] = spaceid; \
|
|
regs->iaoq[0] = pc; \
|
|
regs->iaoq[1] = pc + 4; \
|
|
regs->sr[2] = LINUX_GATEWAY_SPACE; \
|
|
regs->sr[3] = 0xffff; \
|
|
regs->sr[4] = spaceid; \
|
|
regs->sr[5] = spaceid; \
|
|
regs->sr[6] = spaceid; \
|
|
regs->sr[7] = spaceid; \
|
|
regs->gr[ 0] = USER_PSW; \
|
|
regs->gr[30] = ((new_sp)+63)&~63; \
|
|
regs->gr[31] = pc; \
|
|
\
|
|
get_user(regs->gr[26],&sp[0]); \
|
|
get_user(regs->gr[25],&sp[-1]); \
|
|
get_user(regs->gr[24],&sp[-2]); \
|
|
get_user(regs->gr[23],&sp[-3]); \
|
|
} while(0)
|
|
|
|
/* The ELF abi wants things done a "wee bit" differently than
|
|
* som does. Supporting this behavior here avoids
|
|
* having our own version of create_elf_tables.
|
|
*
|
|
* Oh, and yes, that is not a typo, we are really passing argc in r25
|
|
* and argv in r24 (rather than r26 and r25). This is because that's
|
|
* where __libc_start_main wants them.
|
|
*
|
|
* Duplicated from dl-machine.h for the benefit of readers:
|
|
*
|
|
* Our initial stack layout is rather different from everyone else's
|
|
* due to the unique PA-RISC ABI. As far as I know it looks like
|
|
* this:
|
|
|
|
----------------------------------- (user startup code creates this frame)
|
|
| 32 bytes of magic |
|
|
|---------------------------------|
|
|
| 32 bytes argument/sp save area |
|
|
|---------------------------------| (bprm->p)
|
|
| ELF auxiliary info |
|
|
| (up to 28 words) |
|
|
|---------------------------------|
|
|
| NULL |
|
|
|---------------------------------|
|
|
| Environment pointers |
|
|
|---------------------------------|
|
|
| NULL |
|
|
|---------------------------------|
|
|
| Argument pointers |
|
|
|---------------------------------| <- argv
|
|
| argc (1 word) |
|
|
|---------------------------------| <- bprm->exec (HACK!)
|
|
| N bytes of slack |
|
|
|---------------------------------|
|
|
| filename passed to execve |
|
|
|---------------------------------| (mm->env_end)
|
|
| env strings |
|
|
|---------------------------------| (mm->env_start, mm->arg_end)
|
|
| arg strings |
|
|
|---------------------------------|
|
|
| additional faked arg strings if |
|
|
| we're invoked via binfmt_script |
|
|
|---------------------------------| (mm->arg_start)
|
|
stack base is at TASK_SIZE - rlim_max.
|
|
|
|
on downward growing arches, it looks like this:
|
|
stack base at TASK_SIZE
|
|
| filename passed to execve
|
|
| env strings
|
|
| arg strings
|
|
| faked arg strings
|
|
| slack
|
|
| ELF
|
|
| envps
|
|
| argvs
|
|
| argc
|
|
|
|
* The pleasant part of this is that if we need to skip arguments we
|
|
* can just decrement argc and move argv, because the stack pointer
|
|
* is utterly unrelated to the location of the environment and
|
|
* argument vectors.
|
|
*
|
|
* Note that the S/390 people took the easy way out and hacked their
|
|
* GCC to make the stack grow downwards.
|
|
*
|
|
* Final Note: For entry from syscall, the W (wide) bit of the PSW
|
|
* is stuffed into the lowest bit of the user sp (%r30), so we fill
|
|
* it in here from the current->personality
|
|
*/
|
|
|
|
#ifdef CONFIG_64BIT
|
|
#define USER_WIDE_MODE (!test_thread_flag(TIF_32BIT))
|
|
#else
|
|
#define USER_WIDE_MODE 0
|
|
#endif
|
|
|
|
#define start_thread(regs, new_pc, new_sp) do { \
|
|
elf_addr_t *sp = (elf_addr_t *)new_sp; \
|
|
__u32 spaceid = (__u32)current->mm->context; \
|
|
elf_addr_t pc = (elf_addr_t)new_pc | 3; \
|
|
elf_caddr_t *argv = (elf_caddr_t *)bprm->exec + 1; \
|
|
\
|
|
regs->iasq[0] = spaceid; \
|
|
regs->iasq[1] = spaceid; \
|
|
regs->iaoq[0] = pc; \
|
|
regs->iaoq[1] = pc + 4; \
|
|
regs->sr[2] = LINUX_GATEWAY_SPACE; \
|
|
regs->sr[3] = 0xffff; \
|
|
regs->sr[4] = spaceid; \
|
|
regs->sr[5] = spaceid; \
|
|
regs->sr[6] = spaceid; \
|
|
regs->sr[7] = spaceid; \
|
|
regs->gr[ 0] = USER_PSW | (USER_WIDE_MODE ? PSW_W : 0); \
|
|
regs->fr[ 0] = 0LL; \
|
|
regs->fr[ 1] = 0LL; \
|
|
regs->fr[ 2] = 0LL; \
|
|
regs->fr[ 3] = 0LL; \
|
|
regs->gr[30] = (((unsigned long)sp + 63) &~ 63) | (USER_WIDE_MODE ? 1 : 0); \
|
|
regs->gr[31] = pc; \
|
|
\
|
|
get_user(regs->gr[25], (argv - 1)); \
|
|
regs->gr[24] = (long) argv; \
|
|
regs->gr[23] = 0; \
|
|
} while(0)
|
|
|
|
struct task_struct;
|
|
struct mm_struct;
|
|
|
|
/* Free all resources held by a thread. */
|
|
extern void release_thread(struct task_struct *);
|
|
|
|
extern void map_hpux_gateway_page(struct task_struct *tsk, struct mm_struct *mm);
|
|
|
|
extern unsigned long get_wchan(struct task_struct *p);
|
|
|
|
#define KSTK_EIP(tsk) ((tsk)->thread.regs.iaoq[0])
|
|
#define KSTK_ESP(tsk) ((tsk)->thread.regs.gr[30])
|
|
|
|
#define cpu_relax() barrier()
|
|
#define cpu_relax_lowlatency() cpu_relax()
|
|
|
|
/* Used as a macro to identify the combined VIPT/PIPT cached
|
|
* CPUs which require a guarantee of coherency (no inequivalent
|
|
* aliases with different data, whether clean or not) to operate */
|
|
static inline int parisc_requires_coherency(void)
|
|
{
|
|
#ifdef CONFIG_PA8X00
|
|
return (boot_cpu_data.cpu_type == mako) ||
|
|
(boot_cpu_data.cpu_type == mako2);
|
|
#else
|
|
return 0;
|
|
#endif
|
|
}
|
|
|
|
#endif /* __ASSEMBLY__ */
|
|
|
|
#endif /* __ASM_PARISC_PROCESSOR_H */
|