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 a6201da3 ("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-g249155c2 #28
  NIP:  c000000000097f88 LR: c000000000c07a88 CTR: c00000000015ca10
  REGS: c0000000727079f0 TRAP: 0300   Not tainted  (5.2.0-rc6-00491-g249155c2)
  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: 499dcd41 ("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

arch/powerpc/include/asm/spinlock.h

@@ -103,11 +103,9 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 /* 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);
-#define __spin_yield(x) splpar_spin_yield(x)
-#define __rw_yield(x) splpar_rw_yield(x)
 #else /* SPLPAR */
-#define __spin_yield(x)	barrier()
-#define __rw_yield(x)	barrier()
+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)
@@ -124,6 +122,22 @@ static inline bool is_shared_processor(void)
 #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) {
@@ -132,7 +146,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 		do {
 			HMT_low();
 			if (is_shared_processor())
-				__spin_yield(lock);
+				splpar_spin_yield(lock);
 		} while (unlikely(lock->slock != 0));
 		HMT_medium();
 	}
@@ -151,7 +165,7 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
 		do {
 			HMT_low();
 			if (is_shared_processor())
-				__spin_yield(lock);
+				splpar_spin_yield(lock);
 		} while (unlikely(lock->slock != 0));
 		HMT_medium();
 		local_irq_restore(flags_dis);
@@ -241,7 +255,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 		do {
 			HMT_low();
 			if (is_shared_processor())
-				__rw_yield(rw);
+				splpar_rw_yield(rw);
 		} while (unlikely(rw->lock < 0));
 		HMT_medium();
 	}
@@ -255,7 +269,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 		do {
 			HMT_low();
 			if (is_shared_processor())
-				__rw_yield(rw);
+				splpar_rw_yield(rw);
 		} while (unlikely(rw->lock != 0));
 		HMT_medium();
 	}
@@ -295,9 +309,9 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	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)
+#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()