mirror of
https://github.com/torvalds/linux.git
synced 2024-12-23 11:21:33 +00:00
687413d34d
When compiling with __KVM_NVHE_HYPERVISOR__, redefine per_cpu_offset() to __hyp_per_cpu_offset() which looks up the base of the nVHE per-CPU region of the given cpu and computes its offset from the .hyp.data..percpu section. This enables use of per_cpu_ptr() helpers in nVHE hyp code. Until now only this_cpu_ptr() was supported by setting TPIDR_EL2. Signed-off-by: David Brazdil <dbrazdil@google.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20201202184122.26046-14-dbrazdil@google.com
261 lines
8.0 KiB
C
261 lines
8.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Copyright (C) 2013 ARM Ltd.
|
|
*/
|
|
#ifndef __ASM_PERCPU_H
|
|
#define __ASM_PERCPU_H
|
|
|
|
#include <linux/preempt.h>
|
|
|
|
#include <asm/alternative.h>
|
|
#include <asm/cmpxchg.h>
|
|
#include <asm/stack_pointer.h>
|
|
|
|
static inline void set_my_cpu_offset(unsigned long off)
|
|
{
|
|
asm volatile(ALTERNATIVE("msr tpidr_el1, %0",
|
|
"msr tpidr_el2, %0",
|
|
ARM64_HAS_VIRT_HOST_EXTN)
|
|
:: "r" (off) : "memory");
|
|
}
|
|
|
|
static inline unsigned long __hyp_my_cpu_offset(void)
|
|
{
|
|
/*
|
|
* Non-VHE hyp code runs with preemption disabled. No need to hazard
|
|
* the register access against barrier() as in __kern_my_cpu_offset.
|
|
*/
|
|
return read_sysreg(tpidr_el2);
|
|
}
|
|
|
|
static inline unsigned long __kern_my_cpu_offset(void)
|
|
{
|
|
unsigned long off;
|
|
|
|
/*
|
|
* We want to allow caching the value, so avoid using volatile and
|
|
* instead use a fake stack read to hazard against barrier().
|
|
*/
|
|
asm(ALTERNATIVE("mrs %0, tpidr_el1",
|
|
"mrs %0, tpidr_el2",
|
|
ARM64_HAS_VIRT_HOST_EXTN)
|
|
: "=r" (off) :
|
|
"Q" (*(const unsigned long *)current_stack_pointer));
|
|
|
|
return off;
|
|
}
|
|
|
|
#ifdef __KVM_NVHE_HYPERVISOR__
|
|
#define __my_cpu_offset __hyp_my_cpu_offset()
|
|
#else
|
|
#define __my_cpu_offset __kern_my_cpu_offset()
|
|
#endif
|
|
|
|
#define PERCPU_RW_OPS(sz) \
|
|
static inline unsigned long __percpu_read_##sz(void *ptr) \
|
|
{ \
|
|
return READ_ONCE(*(u##sz *)ptr); \
|
|
} \
|
|
\
|
|
static inline void __percpu_write_##sz(void *ptr, unsigned long val) \
|
|
{ \
|
|
WRITE_ONCE(*(u##sz *)ptr, (u##sz)val); \
|
|
}
|
|
|
|
#define __PERCPU_OP_CASE(w, sfx, name, sz, op_llsc, op_lse) \
|
|
static inline void \
|
|
__percpu_##name##_case_##sz(void *ptr, unsigned long val) \
|
|
{ \
|
|
unsigned int loop; \
|
|
u##sz tmp; \
|
|
\
|
|
asm volatile (ARM64_LSE_ATOMIC_INSN( \
|
|
/* LL/SC */ \
|
|
"1: ldxr" #sfx "\t%" #w "[tmp], %[ptr]\n" \
|
|
#op_llsc "\t%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \
|
|
" stxr" #sfx "\t%w[loop], %" #w "[tmp], %[ptr]\n" \
|
|
" cbnz %w[loop], 1b", \
|
|
/* LSE atomics */ \
|
|
#op_lse "\t%" #w "[val], %[ptr]\n" \
|
|
__nops(3)) \
|
|
: [loop] "=&r" (loop), [tmp] "=&r" (tmp), \
|
|
[ptr] "+Q"(*(u##sz *)ptr) \
|
|
: [val] "r" ((u##sz)(val))); \
|
|
}
|
|
|
|
#define __PERCPU_RET_OP_CASE(w, sfx, name, sz, op_llsc, op_lse) \
|
|
static inline u##sz \
|
|
__percpu_##name##_return_case_##sz(void *ptr, unsigned long val) \
|
|
{ \
|
|
unsigned int loop; \
|
|
u##sz ret; \
|
|
\
|
|
asm volatile (ARM64_LSE_ATOMIC_INSN( \
|
|
/* LL/SC */ \
|
|
"1: ldxr" #sfx "\t%" #w "[ret], %[ptr]\n" \
|
|
#op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n" \
|
|
" stxr" #sfx "\t%w[loop], %" #w "[ret], %[ptr]\n" \
|
|
" cbnz %w[loop], 1b", \
|
|
/* LSE atomics */ \
|
|
#op_lse "\t%" #w "[val], %" #w "[ret], %[ptr]\n" \
|
|
#op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n" \
|
|
__nops(2)) \
|
|
: [loop] "=&r" (loop), [ret] "=&r" (ret), \
|
|
[ptr] "+Q"(*(u##sz *)ptr) \
|
|
: [val] "r" ((u##sz)(val))); \
|
|
\
|
|
return ret; \
|
|
}
|
|
|
|
#define PERCPU_OP(name, op_llsc, op_lse) \
|
|
__PERCPU_OP_CASE(w, b, name, 8, op_llsc, op_lse) \
|
|
__PERCPU_OP_CASE(w, h, name, 16, op_llsc, op_lse) \
|
|
__PERCPU_OP_CASE(w, , name, 32, op_llsc, op_lse) \
|
|
__PERCPU_OP_CASE( , , name, 64, op_llsc, op_lse)
|
|
|
|
#define PERCPU_RET_OP(name, op_llsc, op_lse) \
|
|
__PERCPU_RET_OP_CASE(w, b, name, 8, op_llsc, op_lse) \
|
|
__PERCPU_RET_OP_CASE(w, h, name, 16, op_llsc, op_lse) \
|
|
__PERCPU_RET_OP_CASE(w, , name, 32, op_llsc, op_lse) \
|
|
__PERCPU_RET_OP_CASE( , , name, 64, op_llsc, op_lse)
|
|
|
|
PERCPU_RW_OPS(8)
|
|
PERCPU_RW_OPS(16)
|
|
PERCPU_RW_OPS(32)
|
|
PERCPU_RW_OPS(64)
|
|
PERCPU_OP(add, add, stadd)
|
|
PERCPU_OP(andnot, bic, stclr)
|
|
PERCPU_OP(or, orr, stset)
|
|
PERCPU_RET_OP(add, add, ldadd)
|
|
|
|
#undef PERCPU_RW_OPS
|
|
#undef __PERCPU_OP_CASE
|
|
#undef __PERCPU_RET_OP_CASE
|
|
#undef PERCPU_OP
|
|
#undef PERCPU_RET_OP
|
|
|
|
/*
|
|
* It would be nice to avoid the conditional call into the scheduler when
|
|
* re-enabling preemption for preemptible kernels, but doing that in a way
|
|
* which builds inside a module would mean messing directly with the preempt
|
|
* count. If you do this, peterz and tglx will hunt you down.
|
|
*/
|
|
#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \
|
|
({ \
|
|
int __ret; \
|
|
preempt_disable_notrace(); \
|
|
__ret = cmpxchg_double_local( raw_cpu_ptr(&(ptr1)), \
|
|
raw_cpu_ptr(&(ptr2)), \
|
|
o1, o2, n1, n2); \
|
|
preempt_enable_notrace(); \
|
|
__ret; \
|
|
})
|
|
|
|
#define _pcp_protect(op, pcp, ...) \
|
|
({ \
|
|
preempt_disable_notrace(); \
|
|
op(raw_cpu_ptr(&(pcp)), __VA_ARGS__); \
|
|
preempt_enable_notrace(); \
|
|
})
|
|
|
|
#define _pcp_protect_return(op, pcp, args...) \
|
|
({ \
|
|
typeof(pcp) __retval; \
|
|
preempt_disable_notrace(); \
|
|
__retval = (typeof(pcp))op(raw_cpu_ptr(&(pcp)), ##args); \
|
|
preempt_enable_notrace(); \
|
|
__retval; \
|
|
})
|
|
|
|
#define this_cpu_read_1(pcp) \
|
|
_pcp_protect_return(__percpu_read_8, pcp)
|
|
#define this_cpu_read_2(pcp) \
|
|
_pcp_protect_return(__percpu_read_16, pcp)
|
|
#define this_cpu_read_4(pcp) \
|
|
_pcp_protect_return(__percpu_read_32, pcp)
|
|
#define this_cpu_read_8(pcp) \
|
|
_pcp_protect_return(__percpu_read_64, pcp)
|
|
|
|
#define this_cpu_write_1(pcp, val) \
|
|
_pcp_protect(__percpu_write_8, pcp, (unsigned long)val)
|
|
#define this_cpu_write_2(pcp, val) \
|
|
_pcp_protect(__percpu_write_16, pcp, (unsigned long)val)
|
|
#define this_cpu_write_4(pcp, val) \
|
|
_pcp_protect(__percpu_write_32, pcp, (unsigned long)val)
|
|
#define this_cpu_write_8(pcp, val) \
|
|
_pcp_protect(__percpu_write_64, pcp, (unsigned long)val)
|
|
|
|
#define this_cpu_add_1(pcp, val) \
|
|
_pcp_protect(__percpu_add_case_8, pcp, val)
|
|
#define this_cpu_add_2(pcp, val) \
|
|
_pcp_protect(__percpu_add_case_16, pcp, val)
|
|
#define this_cpu_add_4(pcp, val) \
|
|
_pcp_protect(__percpu_add_case_32, pcp, val)
|
|
#define this_cpu_add_8(pcp, val) \
|
|
_pcp_protect(__percpu_add_case_64, pcp, val)
|
|
|
|
#define this_cpu_add_return_1(pcp, val) \
|
|
_pcp_protect_return(__percpu_add_return_case_8, pcp, val)
|
|
#define this_cpu_add_return_2(pcp, val) \
|
|
_pcp_protect_return(__percpu_add_return_case_16, pcp, val)
|
|
#define this_cpu_add_return_4(pcp, val) \
|
|
_pcp_protect_return(__percpu_add_return_case_32, pcp, val)
|
|
#define this_cpu_add_return_8(pcp, val) \
|
|
_pcp_protect_return(__percpu_add_return_case_64, pcp, val)
|
|
|
|
#define this_cpu_and_1(pcp, val) \
|
|
_pcp_protect(__percpu_andnot_case_8, pcp, ~val)
|
|
#define this_cpu_and_2(pcp, val) \
|
|
_pcp_protect(__percpu_andnot_case_16, pcp, ~val)
|
|
#define this_cpu_and_4(pcp, val) \
|
|
_pcp_protect(__percpu_andnot_case_32, pcp, ~val)
|
|
#define this_cpu_and_8(pcp, val) \
|
|
_pcp_protect(__percpu_andnot_case_64, pcp, ~val)
|
|
|
|
#define this_cpu_or_1(pcp, val) \
|
|
_pcp_protect(__percpu_or_case_8, pcp, val)
|
|
#define this_cpu_or_2(pcp, val) \
|
|
_pcp_protect(__percpu_or_case_16, pcp, val)
|
|
#define this_cpu_or_4(pcp, val) \
|
|
_pcp_protect(__percpu_or_case_32, pcp, val)
|
|
#define this_cpu_or_8(pcp, val) \
|
|
_pcp_protect(__percpu_or_case_64, pcp, val)
|
|
|
|
#define this_cpu_xchg_1(pcp, val) \
|
|
_pcp_protect_return(xchg_relaxed, pcp, val)
|
|
#define this_cpu_xchg_2(pcp, val) \
|
|
_pcp_protect_return(xchg_relaxed, pcp, val)
|
|
#define this_cpu_xchg_4(pcp, val) \
|
|
_pcp_protect_return(xchg_relaxed, pcp, val)
|
|
#define this_cpu_xchg_8(pcp, val) \
|
|
_pcp_protect_return(xchg_relaxed, pcp, val)
|
|
|
|
#define this_cpu_cmpxchg_1(pcp, o, n) \
|
|
_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
|
|
#define this_cpu_cmpxchg_2(pcp, o, n) \
|
|
_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
|
|
#define this_cpu_cmpxchg_4(pcp, o, n) \
|
|
_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
|
|
#define this_cpu_cmpxchg_8(pcp, o, n) \
|
|
_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
|
|
|
|
#ifdef __KVM_NVHE_HYPERVISOR__
|
|
extern unsigned long __hyp_per_cpu_offset(unsigned int cpu);
|
|
#define __per_cpu_offset
|
|
#define per_cpu_offset(cpu) __hyp_per_cpu_offset((cpu))
|
|
#endif
|
|
|
|
#include <asm-generic/percpu.h>
|
|
|
|
/* Redefine macros for nVHE hyp under DEBUG_PREEMPT to avoid its dependencies. */
|
|
#if defined(__KVM_NVHE_HYPERVISOR__) && defined(CONFIG_DEBUG_PREEMPT)
|
|
#undef this_cpu_ptr
|
|
#define this_cpu_ptr raw_cpu_ptr
|
|
#undef __this_cpu_read
|
|
#define __this_cpu_read raw_cpu_read
|
|
#undef __this_cpu_write
|
|
#define __this_cpu_write raw_cpu_write
|
|
#endif
|
|
|
|
#endif /* __ASM_PERCPU_H */
|