mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
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>
262 lines
7.6 KiB
C
262 lines
7.6 KiB
C
/*
|
|
* include/asm/processor.h
|
|
*
|
|
* Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
|
|
*/
|
|
|
|
#ifndef __ASM_SPARC64_PROCESSOR_H
|
|
#define __ASM_SPARC64_PROCESSOR_H
|
|
|
|
/*
|
|
* Sparc64 implementation of macro that returns current
|
|
* instruction pointer ("program counter").
|
|
*/
|
|
#define current_text_addr() ({ void *pc; __asm__("rd %%pc, %0" : "=r" (pc)); pc; })
|
|
|
|
#include <asm/asi.h>
|
|
#include <asm/pstate.h>
|
|
#include <asm/ptrace.h>
|
|
#include <asm/page.h>
|
|
|
|
/* The sparc has no problems with write protection */
|
|
#define wp_works_ok 1
|
|
#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
|
|
|
|
/*
|
|
* User lives in his very own context, and cannot reference us. Note
|
|
* that TASK_SIZE is a misnomer, it really gives maximum user virtual
|
|
* address that the kernel will allocate out.
|
|
*
|
|
* XXX No longer using virtual page tables, kill this upper limit...
|
|
*/
|
|
#define VA_BITS 44
|
|
#ifndef __ASSEMBLY__
|
|
#define VPTE_SIZE (1UL << (VA_BITS - PAGE_SHIFT + 3))
|
|
#else
|
|
#define VPTE_SIZE (1 << (VA_BITS - PAGE_SHIFT + 3))
|
|
#endif
|
|
|
|
#define TASK_SIZE_OF(tsk) \
|
|
(test_tsk_thread_flag(tsk,TIF_32BIT) ? \
|
|
(1UL << 32UL) : ((unsigned long)-VPTE_SIZE))
|
|
#define TASK_SIZE \
|
|
(test_thread_flag(TIF_32BIT) ? \
|
|
(1UL << 32UL) : ((unsigned long)-VPTE_SIZE))
|
|
#ifdef __KERNEL__
|
|
|
|
#define STACK_TOP32 ((1UL << 32UL) - PAGE_SIZE)
|
|
#define STACK_TOP64 (0x0000080000000000UL - (1UL << 32UL))
|
|
|
|
#define STACK_TOP (test_thread_flag(TIF_32BIT) ? \
|
|
STACK_TOP32 : STACK_TOP64)
|
|
|
|
#define STACK_TOP_MAX STACK_TOP64
|
|
|
|
#endif
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
typedef struct {
|
|
unsigned char seg;
|
|
} mm_segment_t;
|
|
|
|
/* The Sparc processor specific thread struct. */
|
|
/* XXX This should die, everything can go into thread_info now. */
|
|
struct thread_struct {
|
|
#ifdef CONFIG_DEBUG_SPINLOCK
|
|
/* How many spinlocks held by this thread.
|
|
* Used with spin lock debugging to catch tasks
|
|
* sleeping illegally with locks held.
|
|
*/
|
|
int smp_lock_count;
|
|
unsigned int smp_lock_pc;
|
|
#else
|
|
int dummy; /* f'in gcc bug... */
|
|
#endif
|
|
};
|
|
|
|
#endif /* !(__ASSEMBLY__) */
|
|
|
|
#ifndef CONFIG_DEBUG_SPINLOCK
|
|
#define INIT_THREAD { \
|
|
0, \
|
|
}
|
|
#else /* CONFIG_DEBUG_SPINLOCK */
|
|
#define INIT_THREAD { \
|
|
/* smp_lock_count, smp_lock_pc, */ \
|
|
0, 0, \
|
|
}
|
|
#endif /* !(CONFIG_DEBUG_SPINLOCK) */
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#include <linux/types.h>
|
|
#include <asm/fpumacro.h>
|
|
|
|
/* Return saved PC of a blocked thread. */
|
|
struct task_struct;
|
|
unsigned long thread_saved_pc(struct task_struct *);
|
|
|
|
/* On Uniprocessor, even in RMO processes see TSO semantics */
|
|
#ifdef CONFIG_SMP
|
|
#define TSTATE_INITIAL_MM TSTATE_TSO
|
|
#else
|
|
#define TSTATE_INITIAL_MM TSTATE_RMO
|
|
#endif
|
|
|
|
/* Do necessary setup to start up a newly executed thread. */
|
|
#define start_thread(regs, pc, sp) \
|
|
do { \
|
|
unsigned long __asi = ASI_PNF; \
|
|
regs->tstate = (regs->tstate & (TSTATE_CWP)) | (TSTATE_INITIAL_MM|TSTATE_IE) | (__asi << 24UL); \
|
|
regs->tpc = ((pc & (~3)) - 4); \
|
|
regs->tnpc = regs->tpc + 4; \
|
|
regs->y = 0; \
|
|
set_thread_wstate(1 << 3); \
|
|
if (current_thread_info()->utraps) { \
|
|
if (*(current_thread_info()->utraps) < 2) \
|
|
kfree(current_thread_info()->utraps); \
|
|
else \
|
|
(*(current_thread_info()->utraps))--; \
|
|
current_thread_info()->utraps = NULL; \
|
|
} \
|
|
__asm__ __volatile__( \
|
|
"stx %%g0, [%0 + %2 + 0x00]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x08]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x10]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x18]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x20]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x28]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x30]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x38]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x40]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x48]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x50]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x58]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x60]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x68]\n\t" \
|
|
"stx %1, [%0 + %2 + 0x70]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x78]\n\t" \
|
|
"wrpr %%g0, (1 << 3), %%wstate\n\t" \
|
|
: \
|
|
: "r" (regs), "r" (sp - sizeof(struct reg_window) - STACK_BIAS), \
|
|
"i" ((const unsigned long)(&((struct pt_regs *)0)->u_regs[0]))); \
|
|
fprs_write(0); \
|
|
current_thread_info()->xfsr[0] = 0; \
|
|
current_thread_info()->fpsaved[0] = 0; \
|
|
regs->tstate &= ~TSTATE_PEF; \
|
|
} while (0)
|
|
|
|
#define start_thread32(regs, pc, sp) \
|
|
do { \
|
|
unsigned long __asi = ASI_PNF; \
|
|
pc &= 0x00000000ffffffffUL; \
|
|
sp &= 0x00000000ffffffffUL; \
|
|
regs->tstate = (regs->tstate & (TSTATE_CWP))|(TSTATE_INITIAL_MM|TSTATE_IE|TSTATE_AM) | (__asi << 24UL); \
|
|
regs->tpc = ((pc & (~3)) - 4); \
|
|
regs->tnpc = regs->tpc + 4; \
|
|
regs->y = 0; \
|
|
set_thread_wstate(2 << 3); \
|
|
if (current_thread_info()->utraps) { \
|
|
if (*(current_thread_info()->utraps) < 2) \
|
|
kfree(current_thread_info()->utraps); \
|
|
else \
|
|
(*(current_thread_info()->utraps))--; \
|
|
current_thread_info()->utraps = NULL; \
|
|
} \
|
|
__asm__ __volatile__( \
|
|
"stx %%g0, [%0 + %2 + 0x00]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x08]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x10]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x18]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x20]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x28]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x30]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x38]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x40]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x48]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x50]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x58]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x60]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x68]\n\t" \
|
|
"stx %1, [%0 + %2 + 0x70]\n\t" \
|
|
"stx %%g0, [%0 + %2 + 0x78]\n\t" \
|
|
"wrpr %%g0, (2 << 3), %%wstate\n\t" \
|
|
: \
|
|
: "r" (regs), "r" (sp - sizeof(struct reg_window32)), \
|
|
"i" ((const unsigned long)(&((struct pt_regs *)0)->u_regs[0]))); \
|
|
fprs_write(0); \
|
|
current_thread_info()->xfsr[0] = 0; \
|
|
current_thread_info()->fpsaved[0] = 0; \
|
|
regs->tstate &= ~TSTATE_PEF; \
|
|
} while (0)
|
|
|
|
/* Free all resources held by a thread. */
|
|
#define release_thread(tsk) do { } while (0)
|
|
|
|
unsigned long get_wchan(struct task_struct *task);
|
|
|
|
#define task_pt_regs(tsk) (task_thread_info(tsk)->kregs)
|
|
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->tpc)
|
|
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->u_regs[UREG_FP])
|
|
|
|
/* Please see the commentary in asm/backoff.h for a description of
|
|
* what these instructions are doing and how they have been choosen.
|
|
* To make a long story short, we are trying to yield the current cpu
|
|
* strand during busy loops.
|
|
*/
|
|
#define cpu_relax() asm volatile("\n99:\n\t" \
|
|
"rd %%ccr, %%g0\n\t" \
|
|
"rd %%ccr, %%g0\n\t" \
|
|
"rd %%ccr, %%g0\n\t" \
|
|
".section .pause_3insn_patch,\"ax\"\n\t"\
|
|
".word 99b\n\t" \
|
|
"wr %%g0, 128, %%asr27\n\t" \
|
|
"nop\n\t" \
|
|
"nop\n\t" \
|
|
".previous" \
|
|
::: "memory")
|
|
#define cpu_relax_lowlatency() cpu_relax()
|
|
|
|
/* Prefetch support. This is tuned for UltraSPARC-III and later.
|
|
* UltraSPARC-I will treat these as nops, and UltraSPARC-II has
|
|
* a shallower prefetch queue than later chips.
|
|
*/
|
|
#define ARCH_HAS_PREFETCH
|
|
#define ARCH_HAS_PREFETCHW
|
|
#define ARCH_HAS_SPINLOCK_PREFETCH
|
|
|
|
static inline void prefetch(const void *x)
|
|
{
|
|
/* We do not use the read prefetch mnemonic because that
|
|
* prefetches into the prefetch-cache which only is accessible
|
|
* by floating point operations in UltraSPARC-III and later.
|
|
* By contrast, "#one_write" prefetches into the L2 cache
|
|
* in shared state.
|
|
*/
|
|
__asm__ __volatile__("prefetch [%0], #one_write"
|
|
: /* no outputs */
|
|
: "r" (x));
|
|
}
|
|
|
|
static inline void prefetchw(const void *x)
|
|
{
|
|
/* The most optimal prefetch to use for writes is
|
|
* "#n_writes". This brings the cacheline into the
|
|
* L2 cache in "owned" state.
|
|
*/
|
|
__asm__ __volatile__("prefetch [%0], #n_writes"
|
|
: /* no outputs */
|
|
: "r" (x));
|
|
}
|
|
|
|
#define spin_lock_prefetch(x) prefetchw(x)
|
|
|
|
#define HAVE_ARCH_PICK_MMAP_LAYOUT
|
|
|
|
int do_mathemu(struct pt_regs *regs, struct fpustate *f, bool illegal_insn_trap);
|
|
|
|
#endif /* !(__ASSEMBLY__) */
|
|
|
|
#endif /* !(__ASM_SPARC64_PROCESSOR_H) */
|