linux_dsm_epyc7002/arch/powerpc/include/asm/spinlock.h
Christopher M. Riedl 405efc5980 powerpc/spinlocks: Fix oops in __spin_yield() on bare metal
Booting w/ppc64le_defconfig + CONFIG_PREEMPT on bare metal results in
the oops below due to calling into __spin_yield() when not running in
an SPLPAR, which means lppaca pointers are NULL.

We fixed a similar case previously in commit a6201da34f ("powerpc:
Fix oops due to bad access of lppaca on bare metal"), by adding SPLPAR
checks in lppaca_shared_proc(). However when PREEMPT is enabled we can
call __spin_yield() directly from arch_spin_yield().

To fix it add spin_yield() and rw_yield() which check that
shared-processor LPAR is enabled before calling the SPLPAR-only
implementation of each.

  BUG: Kernel NULL pointer dereference at 0x00000100
  Faulting instruction address: 0xc000000000097f88
  Oops: Kernel access of bad area, sig: 7 [#1]
  LE PAGE_SIZE=64K MMU=Radix MMU=Hash PREEMPT SMP NR_CPUS=2048 NUMA PowerNV
  Modules linked in:
  CPU: 0 PID: 2 Comm: kthreadd Not tainted 5.2.0-rc6-00491-g249155c20f9b #28
  NIP:  c000000000097f88 LR: c000000000c07a88 CTR: c00000000015ca10
  REGS: c0000000727079f0 TRAP: 0300   Not tainted  (5.2.0-rc6-00491-g249155c20f9b)
  MSR:  9000000002009033 <SF,HV,VEC,EE,ME,IR,DR,RI,LE>  CR: 84000424  XER: 20040000
  CFAR: c000000000c07a84 DAR: 0000000000000100 DSISR: 00080000 IRQMASK: 1
  GPR00: c000000000c07a88 c000000072707c80 c000000001546300 c00000007be38a80
  GPR04: c0000000726f0c00 0000000000000002 c00000007279c980 0000000000000100
  GPR08: c000000001581b78 0000000080000001 0000000000000008 c00000007279c9b0
  GPR12: 0000000000000000 c000000001730000 c000000000142558 0000000000000000
  GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
  GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
  GPR24: c00000007be38a80 c000000000c002f4 0000000000000000 0000000000000000
  GPR28: c000000072221a00 c0000000726c2600 c00000007be38a80 c00000007be38a80
  NIP [c000000000097f88] __spin_yield+0x48/0xa0
  LR [c000000000c07a88] __raw_spin_lock+0xb8/0xc0
  Call Trace:
  [c000000072707c80] [c000000072221a00] 0xc000000072221a00 (unreliable)
  [c000000072707cb0] [c000000000bffb0c] __schedule+0xbc/0x850
  [c000000072707d70] [c000000000c002f4] schedule+0x54/0x130
  [c000000072707da0] [c0000000001427dc] kthreadd+0x28c/0x2b0
  [c000000072707e20] [c00000000000c1cc] ret_from_kernel_thread+0x5c/0x70
  Instruction dump:
  4d9e0020 552a043e 210a07ff 79080fe0 0b080000 3d020004 3908b878 794a1f24
  e8e80000 7ce7502a e8e70000 38e70100 <7ca03c2c> 70a70001 78a50020 4d820020
  ---[ end trace 474d6b2b8fc5cb7e ]---

Fixes: 499dcd4137 ("powerpc/64s: Allocate LPPACAs individually")
Signed-off-by: Christopher M. Riedl <cmr@informatik.wtf>
[mpe: Reword change log a bit]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190813031314.1828-4-cmr@informatik.wtf
2019-08-27 21:34:34 +10:00

321 lines
7.1 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef __ASM_SPINLOCK_H
#define __ASM_SPINLOCK_H
#ifdef __KERNEL__
/*
* Simple spin lock operations.
*
* Copyright (C) 2001-2004 Paul Mackerras <paulus@au.ibm.com>, IBM
* Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
* Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM
* Rework to support virtual processors
*
* Type of int is used as a full 64b word is not necessary.
*
* (the type definitions are in asm/spinlock_types.h)
*/
#include <linux/irqflags.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#include <asm/hvcall.h>
#endif
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#include <asm/asm-405.h>
#ifdef CONFIG_PPC64
/* use 0x800000yy when locked, where yy == CPU number */
#ifdef __BIG_ENDIAN__
#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token))
#else
#define LOCK_TOKEN (*(u32 *)(&get_paca()->paca_index))
#endif
#else
#define LOCK_TOKEN 1
#endif
#ifdef CONFIG_PPC_PSERIES
#define vcpu_is_preempted vcpu_is_preempted
static inline bool vcpu_is_preempted(int cpu)
{
if (!firmware_has_feature(FW_FEATURE_SPLPAR))
return false;
return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
}
#endif
static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
return lock.slock == 0;
}
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
smp_mb();
return !arch_spin_value_unlocked(*lock);
}
/*
* This returns the old value in the lock, so we succeeded
* in getting the lock if the return value is 0.
*/
static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock)
{
unsigned long tmp, token;
token = LOCK_TOKEN;
__asm__ __volatile__(
"1: " PPC_LWARX(%0,0,%2,1) "\n\
cmpwi 0,%0,0\n\
bne- 2f\n\
stwcx. %1,0,%2\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"2:"
: "=&r" (tmp)
: "r" (token), "r" (&lock->slock)
: "cr0", "memory");
return tmp;
}
static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
return __arch_spin_trylock(lock) == 0;
}
/*
* On a system with shared processors (that is, where a physical
* processor is multiplexed between several virtual processors),
* there is no point spinning on a lock if the holder of the lock
* isn't currently scheduled on a physical processor. Instead
* we detect this situation and ask the hypervisor to give the
* rest of our timeslice to the lock holder.
*
* So that we can tell which virtual processor is holding a lock,
* we put 0x80000000 | smp_processor_id() in the lock when it is
* held. Conveniently, we have a word in the paca that holds this
* value.
*/
#if defined(CONFIG_PPC_SPLPAR)
/* We only yield to the hypervisor if we are in shared processor mode */
void splpar_spin_yield(arch_spinlock_t *lock);
void splpar_rw_yield(arch_rwlock_t *lock);
#else /* SPLPAR */
static inline void splpar_spin_yield(arch_spinlock_t *lock) {};
static inline void splpar_rw_yield(arch_rwlock_t *lock) {};
#endif
static inline bool is_shared_processor(void)
{
/*
* LPPACA is only available on Pseries so guard anything LPPACA related to
* allow other platforms (which include this common header) to compile.
*/
#ifdef CONFIG_PPC_PSERIES
return (IS_ENABLED(CONFIG_PPC_SPLPAR) &&
lppaca_shared_proc(local_paca->lppaca_ptr));
#else
return false;
#endif
}
static inline void spin_yield(arch_spinlock_t *lock)
{
if (is_shared_processor())
splpar_spin_yield(lock);
else
barrier();
}
static inline void rw_yield(arch_rwlock_t *lock)
{
if (is_shared_processor())
splpar_rw_yield(lock);
else
barrier();
}
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
while (1) {
if (likely(__arch_spin_trylock(lock) == 0))
break;
do {
HMT_low();
if (is_shared_processor())
splpar_spin_yield(lock);
} while (unlikely(lock->slock != 0));
HMT_medium();
}
}
static inline
void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
{
unsigned long flags_dis;
while (1) {
if (likely(__arch_spin_trylock(lock) == 0))
break;
local_save_flags(flags_dis);
local_irq_restore(flags);
do {
HMT_low();
if (is_shared_processor())
splpar_spin_yield(lock);
} while (unlikely(lock->slock != 0));
HMT_medium();
local_irq_restore(flags_dis);
}
}
#define arch_spin_lock_flags arch_spin_lock_flags
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
__asm__ __volatile__("# arch_spin_unlock\n\t"
PPC_RELEASE_BARRIER: : :"memory");
lock->slock = 0;
}
/*
* Read-write spinlocks, allowing multiple readers
* but only one writer.
*
* NOTE! it is quite common to have readers in interrupts
* but no interrupt writers. For those circumstances we
* can "mix" irq-safe locks - any writer needs to get a
* irq-safe write-lock, but readers can get non-irqsafe
* read-locks.
*/
#ifdef CONFIG_PPC64
#define __DO_SIGN_EXTEND "extsw %0,%0\n"
#define WRLOCK_TOKEN LOCK_TOKEN /* it's negative */
#else
#define __DO_SIGN_EXTEND
#define WRLOCK_TOKEN (-1)
#endif
/*
* This returns the old value in the lock + 1,
* so we got a read lock if the return value is > 0.
*/
static inline long __arch_read_trylock(arch_rwlock_t *rw)
{
long tmp;
__asm__ __volatile__(
"1: " PPC_LWARX(%0,0,%1,1) "\n"
__DO_SIGN_EXTEND
" addic. %0,%0,1\n\
ble- 2f\n"
PPC405_ERR77(0,%1)
" stwcx. %0,0,%1\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"2:" : "=&r" (tmp)
: "r" (&rw->lock)
: "cr0", "xer", "memory");
return tmp;
}
/*
* This returns the old value in the lock,
* so we got the write lock if the return value is 0.
*/
static inline long __arch_write_trylock(arch_rwlock_t *rw)
{
long tmp, token;
token = WRLOCK_TOKEN;
__asm__ __volatile__(
"1: " PPC_LWARX(%0,0,%2,1) "\n\
cmpwi 0,%0,0\n\
bne- 2f\n"
PPC405_ERR77(0,%1)
" stwcx. %1,0,%2\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"2:" : "=&r" (tmp)
: "r" (token), "r" (&rw->lock)
: "cr0", "memory");
return tmp;
}
static inline void arch_read_lock(arch_rwlock_t *rw)
{
while (1) {
if (likely(__arch_read_trylock(rw) > 0))
break;
do {
HMT_low();
if (is_shared_processor())
splpar_rw_yield(rw);
} while (unlikely(rw->lock < 0));
HMT_medium();
}
}
static inline void arch_write_lock(arch_rwlock_t *rw)
{
while (1) {
if (likely(__arch_write_trylock(rw) == 0))
break;
do {
HMT_low();
if (is_shared_processor())
splpar_rw_yield(rw);
} while (unlikely(rw->lock != 0));
HMT_medium();
}
}
static inline int arch_read_trylock(arch_rwlock_t *rw)
{
return __arch_read_trylock(rw) > 0;
}
static inline int arch_write_trylock(arch_rwlock_t *rw)
{
return __arch_write_trylock(rw) == 0;
}
static inline void arch_read_unlock(arch_rwlock_t *rw)
{
long tmp;
__asm__ __volatile__(
"# read_unlock\n\t"
PPC_RELEASE_BARRIER
"1: lwarx %0,0,%1\n\
addic %0,%0,-1\n"
PPC405_ERR77(0,%1)
" stwcx. %0,0,%1\n\
bne- 1b"
: "=&r"(tmp)
: "r"(&rw->lock)
: "cr0", "xer", "memory");
}
static inline void arch_write_unlock(arch_rwlock_t *rw)
{
__asm__ __volatile__("# write_unlock\n\t"
PPC_RELEASE_BARRIER: : :"memory");
rw->lock = 0;
}
#define arch_spin_relax(lock) spin_yield(lock)
#define arch_read_relax(lock) rw_yield(lock)
#define arch_write_relax(lock) rw_yield(lock)
/* See include/linux/spinlock.h */
#define smp_mb__after_spinlock() smp_mb()
#endif /* __KERNEL__ */
#endif /* __ASM_SPINLOCK_H */