mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 13:56:53 +07:00
ecd322c9b3
Add cmpxchg/cmpxchg64 support for ARMv6K and ARMv7 systems (original patch from Catalin Marinas <catalin.marinas@arm.com>) The cmpxchg and cmpxchg64 functions can be implemented using the LDREX*/STREX* instructions. Since operand lengths other than 32bit are required, the full implementations are only available if the ARMv6K extensions are present (for the LDREXB, LDREXH and LDREXD instructions). For ARMv6, only 32-bits cmpxchg is available. Mathieu : Make cmpxchg_local always available with best implementation for all type sizes (1, 2, 4 bytes). Make cmpxchg64_local always available. Use "Ir" constraint for "old" operand, like atomic.h atomic_cmpxchg does. Change since v3 : - Add "memory" clobbers (thanks to Nicolas Pitre) - removed __asmeq(), only needed for old compilers, very unlikely on ARMv6+. Note : ARMv7-M should eventually be ifdefed-out of cmpxchg64. But it's not supported by the Linux kernel currently. Put back arm < v6 cmpxchg support. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> CC: Catalin Marinas <catalin.marinas@arm.com> CC: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
515 lines
13 KiB
C
515 lines
13 KiB
C
#ifndef __ASM_ARM_SYSTEM_H
|
|
#define __ASM_ARM_SYSTEM_H
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#define CPU_ARCH_UNKNOWN 0
|
|
#define CPU_ARCH_ARMv3 1
|
|
#define CPU_ARCH_ARMv4 2
|
|
#define CPU_ARCH_ARMv4T 3
|
|
#define CPU_ARCH_ARMv5 4
|
|
#define CPU_ARCH_ARMv5T 5
|
|
#define CPU_ARCH_ARMv5TE 6
|
|
#define CPU_ARCH_ARMv5TEJ 7
|
|
#define CPU_ARCH_ARMv6 8
|
|
#define CPU_ARCH_ARMv7 9
|
|
|
|
/*
|
|
* CR1 bits (CP#15 CR1)
|
|
*/
|
|
#define CR_M (1 << 0) /* MMU enable */
|
|
#define CR_A (1 << 1) /* Alignment abort enable */
|
|
#define CR_C (1 << 2) /* Dcache enable */
|
|
#define CR_W (1 << 3) /* Write buffer enable */
|
|
#define CR_P (1 << 4) /* 32-bit exception handler */
|
|
#define CR_D (1 << 5) /* 32-bit data address range */
|
|
#define CR_L (1 << 6) /* Implementation defined */
|
|
#define CR_B (1 << 7) /* Big endian */
|
|
#define CR_S (1 << 8) /* System MMU protection */
|
|
#define CR_R (1 << 9) /* ROM MMU protection */
|
|
#define CR_F (1 << 10) /* Implementation defined */
|
|
#define CR_Z (1 << 11) /* Implementation defined */
|
|
#define CR_I (1 << 12) /* Icache enable */
|
|
#define CR_V (1 << 13) /* Vectors relocated to 0xffff0000 */
|
|
#define CR_RR (1 << 14) /* Round Robin cache replacement */
|
|
#define CR_L4 (1 << 15) /* LDR pc can set T bit */
|
|
#define CR_DT (1 << 16)
|
|
#define CR_IT (1 << 18)
|
|
#define CR_ST (1 << 19)
|
|
#define CR_FI (1 << 21) /* Fast interrupt (lower latency mode) */
|
|
#define CR_U (1 << 22) /* Unaligned access operation */
|
|
#define CR_XP (1 << 23) /* Extended page tables */
|
|
#define CR_VE (1 << 24) /* Vectored interrupts */
|
|
#define CR_EE (1 << 25) /* Exception (Big) Endian */
|
|
#define CR_TRE (1 << 28) /* TEX remap enable */
|
|
#define CR_AFE (1 << 29) /* Access flag enable */
|
|
#define CR_TE (1 << 30) /* Thumb exception enable */
|
|
|
|
/*
|
|
* This is used to ensure the compiler did actually allocate the register we
|
|
* asked it for some inline assembly sequences. Apparently we can't trust
|
|
* the compiler from one version to another so a bit of paranoia won't hurt.
|
|
* This string is meant to be concatenated with the inline asm string and
|
|
* will cause compilation to stop on mismatch.
|
|
* (for details, see gcc PR 15089)
|
|
*/
|
|
#define __asmeq(x, y) ".ifnc " x "," y " ; .err ; .endif\n\t"
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#include <linux/linkage.h>
|
|
#include <linux/irqflags.h>
|
|
|
|
#define __exception __attribute__((section(".exception.text")))
|
|
|
|
struct thread_info;
|
|
struct task_struct;
|
|
|
|
/* information about the system we're running on */
|
|
extern unsigned int system_rev;
|
|
extern unsigned int system_serial_low;
|
|
extern unsigned int system_serial_high;
|
|
extern unsigned int mem_fclk_21285;
|
|
|
|
struct pt_regs;
|
|
|
|
void die(const char *msg, struct pt_regs *regs, int err)
|
|
__attribute__((noreturn));
|
|
|
|
struct siginfo;
|
|
void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
|
|
unsigned long err, unsigned long trap);
|
|
|
|
void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
|
|
struct pt_regs *),
|
|
int sig, const char *name);
|
|
|
|
#define xchg(ptr,x) \
|
|
((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
|
|
|
|
extern asmlinkage void __backtrace(void);
|
|
extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
|
|
|
|
struct mm_struct;
|
|
extern void show_pte(struct mm_struct *mm, unsigned long addr);
|
|
extern void __show_regs(struct pt_regs *);
|
|
|
|
extern int cpu_architecture(void);
|
|
extern void cpu_init(void);
|
|
|
|
void arm_machine_restart(char mode, const char *cmd);
|
|
extern void (*arm_pm_restart)(char str, const char *cmd);
|
|
|
|
#define UDBG_UNDEFINED (1 << 0)
|
|
#define UDBG_SYSCALL (1 << 1)
|
|
#define UDBG_BADABORT (1 << 2)
|
|
#define UDBG_SEGV (1 << 3)
|
|
#define UDBG_BUS (1 << 4)
|
|
|
|
extern unsigned int user_debug;
|
|
|
|
#if __LINUX_ARM_ARCH__ >= 4
|
|
#define vectors_high() (cr_alignment & CR_V)
|
|
#else
|
|
#define vectors_high() (0)
|
|
#endif
|
|
|
|
#if __LINUX_ARM_ARCH__ >= 7
|
|
#define isb() __asm__ __volatile__ ("isb" : : : "memory")
|
|
#define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
|
|
#define dmb() __asm__ __volatile__ ("dmb" : : : "memory")
|
|
#elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
|
|
#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
|
|
: : "r" (0) : "memory")
|
|
#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
|
|
: : "r" (0) : "memory")
|
|
#define dmb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
|
|
: : "r" (0) : "memory")
|
|
#elif defined(CONFIG_CPU_FA526)
|
|
#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
|
|
: : "r" (0) : "memory")
|
|
#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
|
|
: : "r" (0) : "memory")
|
|
#define dmb() __asm__ __volatile__ ("" : : : "memory")
|
|
#else
|
|
#define isb() __asm__ __volatile__ ("" : : : "memory")
|
|
#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
|
|
: : "r" (0) : "memory")
|
|
#define dmb() __asm__ __volatile__ ("" : : : "memory")
|
|
#endif
|
|
|
|
#ifndef CONFIG_SMP
|
|
#define mb() do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
|
|
#define rmb() do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
|
|
#define wmb() do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
|
|
#define smp_mb() barrier()
|
|
#define smp_rmb() barrier()
|
|
#define smp_wmb() barrier()
|
|
#else
|
|
#define mb() dmb()
|
|
#define rmb() dmb()
|
|
#define wmb() dmb()
|
|
#define smp_mb() dmb()
|
|
#define smp_rmb() dmb()
|
|
#define smp_wmb() dmb()
|
|
#endif
|
|
#define read_barrier_depends() do { } while(0)
|
|
#define smp_read_barrier_depends() do { } while(0)
|
|
|
|
#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
|
|
#define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");
|
|
|
|
extern unsigned long cr_no_alignment; /* defined in entry-armv.S */
|
|
extern unsigned long cr_alignment; /* defined in entry-armv.S */
|
|
|
|
static inline unsigned int get_cr(void)
|
|
{
|
|
unsigned int val;
|
|
asm("mrc p15, 0, %0, c1, c0, 0 @ get CR" : "=r" (val) : : "cc");
|
|
return val;
|
|
}
|
|
|
|
static inline void set_cr(unsigned int val)
|
|
{
|
|
asm volatile("mcr p15, 0, %0, c1, c0, 0 @ set CR"
|
|
: : "r" (val) : "cc");
|
|
isb();
|
|
}
|
|
|
|
#ifndef CONFIG_SMP
|
|
extern void adjust_cr(unsigned long mask, unsigned long set);
|
|
#endif
|
|
|
|
#define CPACC_FULL(n) (3 << (n * 2))
|
|
#define CPACC_SVC(n) (1 << (n * 2))
|
|
#define CPACC_DISABLE(n) (0 << (n * 2))
|
|
|
|
static inline unsigned int get_copro_access(void)
|
|
{
|
|
unsigned int val;
|
|
asm("mrc p15, 0, %0, c1, c0, 2 @ get copro access"
|
|
: "=r" (val) : : "cc");
|
|
return val;
|
|
}
|
|
|
|
static inline void set_copro_access(unsigned int val)
|
|
{
|
|
asm volatile("mcr p15, 0, %0, c1, c0, 2 @ set copro access"
|
|
: : "r" (val) : "cc");
|
|
isb();
|
|
}
|
|
|
|
/*
|
|
* switch_mm() may do a full cache flush over the context switch,
|
|
* so enable interrupts over the context switch to avoid high
|
|
* latency.
|
|
*/
|
|
#define __ARCH_WANT_INTERRUPTS_ON_CTXSW
|
|
|
|
/*
|
|
* switch_to(prev, next) should switch from task `prev' to `next'
|
|
* `prev' will never be the same as `next'. schedule() itself
|
|
* contains the memory barrier to tell GCC not to cache `current'.
|
|
*/
|
|
extern struct task_struct *__switch_to(struct task_struct *, struct thread_info *, struct thread_info *);
|
|
|
|
#define switch_to(prev,next,last) \
|
|
do { \
|
|
last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \
|
|
} while (0)
|
|
|
|
#if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
|
|
/*
|
|
* On the StrongARM, "swp" is terminally broken since it bypasses the
|
|
* cache totally. This means that the cache becomes inconsistent, and,
|
|
* since we use normal loads/stores as well, this is really bad.
|
|
* Typically, this causes oopsen in filp_close, but could have other,
|
|
* more disasterous effects. There are two work-arounds:
|
|
* 1. Disable interrupts and emulate the atomic swap
|
|
* 2. Clean the cache, perform atomic swap, flush the cache
|
|
*
|
|
* We choose (1) since its the "easiest" to achieve here and is not
|
|
* dependent on the processor type.
|
|
*
|
|
* NOTE that this solution won't work on an SMP system, so explcitly
|
|
* forbid it here.
|
|
*/
|
|
#define swp_is_buggy
|
|
#endif
|
|
|
|
static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
|
|
{
|
|
extern void __bad_xchg(volatile void *, int);
|
|
unsigned long ret;
|
|
#ifdef swp_is_buggy
|
|
unsigned long flags;
|
|
#endif
|
|
#if __LINUX_ARM_ARCH__ >= 6
|
|
unsigned int tmp;
|
|
#endif
|
|
|
|
smp_mb();
|
|
|
|
switch (size) {
|
|
#if __LINUX_ARM_ARCH__ >= 6
|
|
case 1:
|
|
asm volatile("@ __xchg1\n"
|
|
"1: ldrexb %0, [%3]\n"
|
|
" strexb %1, %2, [%3]\n"
|
|
" teq %1, #0\n"
|
|
" bne 1b"
|
|
: "=&r" (ret), "=&r" (tmp)
|
|
: "r" (x), "r" (ptr)
|
|
: "memory", "cc");
|
|
break;
|
|
case 4:
|
|
asm volatile("@ __xchg4\n"
|
|
"1: ldrex %0, [%3]\n"
|
|
" strex %1, %2, [%3]\n"
|
|
" teq %1, #0\n"
|
|
" bne 1b"
|
|
: "=&r" (ret), "=&r" (tmp)
|
|
: "r" (x), "r" (ptr)
|
|
: "memory", "cc");
|
|
break;
|
|
#elif defined(swp_is_buggy)
|
|
#ifdef CONFIG_SMP
|
|
#error SMP is not supported on this platform
|
|
#endif
|
|
case 1:
|
|
raw_local_irq_save(flags);
|
|
ret = *(volatile unsigned char *)ptr;
|
|
*(volatile unsigned char *)ptr = x;
|
|
raw_local_irq_restore(flags);
|
|
break;
|
|
|
|
case 4:
|
|
raw_local_irq_save(flags);
|
|
ret = *(volatile unsigned long *)ptr;
|
|
*(volatile unsigned long *)ptr = x;
|
|
raw_local_irq_restore(flags);
|
|
break;
|
|
#else
|
|
case 1:
|
|
asm volatile("@ __xchg1\n"
|
|
" swpb %0, %1, [%2]"
|
|
: "=&r" (ret)
|
|
: "r" (x), "r" (ptr)
|
|
: "memory", "cc");
|
|
break;
|
|
case 4:
|
|
asm volatile("@ __xchg4\n"
|
|
" swp %0, %1, [%2]"
|
|
: "=&r" (ret)
|
|
: "r" (x), "r" (ptr)
|
|
: "memory", "cc");
|
|
break;
|
|
#endif
|
|
default:
|
|
__bad_xchg(ptr, size), ret = 0;
|
|
break;
|
|
}
|
|
smp_mb();
|
|
|
|
return ret;
|
|
}
|
|
|
|
extern void disable_hlt(void);
|
|
extern void enable_hlt(void);
|
|
|
|
#include <asm-generic/cmpxchg-local.h>
|
|
|
|
#if __LINUX_ARM_ARCH__ < 6
|
|
|
|
#ifdef CONFIG_SMP
|
|
#error "SMP is not supported on this platform"
|
|
#endif
|
|
|
|
/*
|
|
* cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
|
|
* them available.
|
|
*/
|
|
#define cmpxchg_local(ptr, o, n) \
|
|
((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
|
|
(unsigned long)(n), sizeof(*(ptr))))
|
|
#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
|
|
|
|
#ifndef CONFIG_SMP
|
|
#include <asm-generic/cmpxchg.h>
|
|
#endif
|
|
|
|
#else /* __LINUX_ARM_ARCH__ >= 6 */
|
|
|
|
extern void __bad_cmpxchg(volatile void *ptr, int size);
|
|
|
|
/*
|
|
* cmpxchg only support 32-bits operands on ARMv6.
|
|
*/
|
|
|
|
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
|
|
unsigned long new, int size)
|
|
{
|
|
unsigned long oldval, res;
|
|
|
|
switch (size) {
|
|
#ifdef CONFIG_CPU_32v6K
|
|
case 1:
|
|
do {
|
|
asm volatile("@ __cmpxchg1\n"
|
|
" ldrexb %1, [%2]\n"
|
|
" mov %0, #0\n"
|
|
" teq %1, %3\n"
|
|
" strexbeq %0, %4, [%2]\n"
|
|
: "=&r" (res), "=&r" (oldval)
|
|
: "r" (ptr), "Ir" (old), "r" (new)
|
|
: "memory", "cc");
|
|
} while (res);
|
|
break;
|
|
case 2:
|
|
do {
|
|
asm volatile("@ __cmpxchg1\n"
|
|
" ldrexh %1, [%2]\n"
|
|
" mov %0, #0\n"
|
|
" teq %1, %3\n"
|
|
" strexheq %0, %4, [%2]\n"
|
|
: "=&r" (res), "=&r" (oldval)
|
|
: "r" (ptr), "Ir" (old), "r" (new)
|
|
: "memory", "cc");
|
|
} while (res);
|
|
break;
|
|
#endif /* CONFIG_CPU_32v6K */
|
|
case 4:
|
|
do {
|
|
asm volatile("@ __cmpxchg4\n"
|
|
" ldrex %1, [%2]\n"
|
|
" mov %0, #0\n"
|
|
" teq %1, %3\n"
|
|
" strexeq %0, %4, [%2]\n"
|
|
: "=&r" (res), "=&r" (oldval)
|
|
: "r" (ptr), "Ir" (old), "r" (new)
|
|
: "memory", "cc");
|
|
} while (res);
|
|
break;
|
|
default:
|
|
__bad_cmpxchg(ptr, size);
|
|
oldval = 0;
|
|
}
|
|
|
|
return oldval;
|
|
}
|
|
|
|
static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
|
|
unsigned long new, int size)
|
|
{
|
|
unsigned long ret;
|
|
|
|
smp_mb();
|
|
ret = __cmpxchg(ptr, old, new, size);
|
|
smp_mb();
|
|
|
|
return ret;
|
|
}
|
|
|
|
#define cmpxchg(ptr,o,n) \
|
|
((__typeof__(*(ptr)))__cmpxchg_mb((ptr), \
|
|
(unsigned long)(o), \
|
|
(unsigned long)(n), \
|
|
sizeof(*(ptr))))
|
|
|
|
static inline unsigned long __cmpxchg_local(volatile void *ptr,
|
|
unsigned long old,
|
|
unsigned long new, int size)
|
|
{
|
|
unsigned long ret;
|
|
|
|
switch (size) {
|
|
#ifndef CONFIG_CPU_32v6K
|
|
case 1:
|
|
case 2:
|
|
ret = __cmpxchg_local_generic(ptr, old, new, size);
|
|
break;
|
|
#endif /* !CONFIG_CPU_32v6K */
|
|
default:
|
|
ret = __cmpxchg(ptr, old, new, size);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
#define cmpxchg_local(ptr,o,n) \
|
|
((__typeof__(*(ptr)))__cmpxchg_local((ptr), \
|
|
(unsigned long)(o), \
|
|
(unsigned long)(n), \
|
|
sizeof(*(ptr))))
|
|
|
|
#ifdef CONFIG_CPU_32v6K
|
|
|
|
/*
|
|
* Note : ARMv7-M (currently unsupported by Linux) does not support
|
|
* ldrexd/strexd. If ARMv7-M is ever supported by the Linux kernel, it should
|
|
* not be allowed to use __cmpxchg64.
|
|
*/
|
|
static inline unsigned long long __cmpxchg64(volatile void *ptr,
|
|
unsigned long long old,
|
|
unsigned long long new)
|
|
{
|
|
register unsigned long long oldval asm("r0");
|
|
register unsigned long long __old asm("r2") = old;
|
|
register unsigned long long __new asm("r4") = new;
|
|
unsigned long res;
|
|
|
|
do {
|
|
asm volatile(
|
|
" @ __cmpxchg8\n"
|
|
" ldrexd %1, %H1, [%2]\n"
|
|
" mov %0, #0\n"
|
|
" teq %1, %3\n"
|
|
" teqeq %H1, %H3\n"
|
|
" strexdeq %0, %4, %H4, [%2]\n"
|
|
: "=&r" (res), "=&r" (oldval)
|
|
: "r" (ptr), "Ir" (__old), "r" (__new)
|
|
: "memory", "cc");
|
|
} while (res);
|
|
|
|
return oldval;
|
|
}
|
|
|
|
static inline unsigned long long __cmpxchg64_mb(volatile void *ptr,
|
|
unsigned long long old,
|
|
unsigned long long new)
|
|
{
|
|
unsigned long long ret;
|
|
|
|
smp_mb();
|
|
ret = __cmpxchg64(ptr, old, new);
|
|
smp_mb();
|
|
|
|
return ret;
|
|
}
|
|
|
|
#define cmpxchg64(ptr,o,n) \
|
|
((__typeof__(*(ptr)))__cmpxchg64_mb((ptr), \
|
|
(unsigned long long)(o), \
|
|
(unsigned long long)(n)))
|
|
|
|
#define cmpxchg64_local(ptr,o,n) \
|
|
((__typeof__(*(ptr)))__cmpxchg64((ptr), \
|
|
(unsigned long long)(o), \
|
|
(unsigned long long)(n)))
|
|
|
|
#else /* !CONFIG_CPU_32v6K */
|
|
|
|
#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
|
|
|
|
#endif /* CONFIG_CPU_32v6K */
|
|
|
|
#endif /* __LINUX_ARM_ARCH__ >= 6 */
|
|
|
|
#endif /* __ASSEMBLY__ */
|
|
|
|
#define arch_align_stack(x) (x)
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif
|