4 files changed, 87 insertions, 14 deletions

diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
index f69f69c..da84645 100644
--- a/arch/arm64/include/asm/kgdb.h
+++ b/arch/arm64/include/asm/kgdb.h
@@ -38,25 +38,54 @@ extern int kgdb_fault_expected;
 #endif /* !__ASSEMBLY__ */
 
 /*
- * gdb is expecting the following registers layout.
+ * gdb remote procotol (well most versions of it) expects the following
+ * register layout.
  *
  * General purpose regs:
  *     r0-r30: 64 bit
  *     sp,pc : 64 bit
- *     pstate  : 64 bit
- *     Total: 34
+ *     pstate  : 32 bit
+ *     Total: 33 + 1
  * FPU regs:
  *     f0-f31: 128 bit
- *     Total: 32
- * Extra regs
  *     fpsr & fpcr: 32 bit
- *     Total: 2
+ *     Total: 32 + 2
  *
+ * To expand a little on the "most versions of it"... when the gdb remote
+ * protocol for AArch64 was developed it depended on a statement in the
+ * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register".
+ * and, as a result, allocated only 32-bits for the PSTATE in the remote
+ * protocol. In fact this statement is still present in ARM DDI 0487A.i.
+ *
+ * Unfortunately "is a 32-bit register" has a very special meaning for
+ * system registers. It means that "the upper bits, bits[63:32], are
+ * RES0.". RES0 is heavily used in the ARM architecture documents as a
+ * way to leave space for future architecture changes. So to translate a
+ * little for people who don't spend their spare time reading ARM architecture
+ * manuals, what "is a 32-bit register" actually means in this context is
+ * "is a 64-bit register but one with no meaning allocated to any of the
+ * upper 32-bits... *yet*".
+ *
+ * Perhaps then we should not be surprised that this has led to some
+ * confusion. Specifically a patch, influenced by the above translation,
+ * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch
+ * was reverted in gdb-7.8.1 and all later releases, when this was
+ * discovered to be an undocumented protocol change.
+ *
+ * So... it is *not* wrong for us to only allocate 32-bits to PSTATE
+ * here even though the kernel itself allocates 64-bits for the same
+ * state. That is because this bit of code tells the kernel how the gdb
+ * remote protocol (well most versions of it) describes the register state.
+ *
+ * Note that if you are using one of the versions of gdb that supports
+ * the gdb-7.7 version of the protocol you cannot use kgdb directly
+ * without providing a custom register description (gdb can load new
+ * protocol descriptions at runtime).
  */
 
-#define _GP_REGS		34
+#define _GP_REGS		33
 #define _FP_REGS		32
-#define _EXTRA_REGS		2
+#define _EXTRA_REGS		3
 /*
  * general purpose registers size in bytes.
  * pstate is only 4 bytes. subtract 4 bytes
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index ff98585..d25f4f1 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
 
 #define check_pgt_cache()		do { } while (0)
 
-#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 #define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
 
 #if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 433e504..0226447 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void)
 	cpu_park_loop();
 }
 
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
 #endif /* ifndef __ASSEMBLY__ */
 
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index fc9682b..e875a5a 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -30,22 +30,53 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
 	arch_spinlock_t lockval;
+	u32 owner;
+
+	/*
+	 * Ensure prior spin_lock operations to other locks have completed
+	 * on this CPU before we test whether "lock" is locked.
+	 */
+	smp_mb();
+	owner = READ_ONCE(lock->owner) << 16;
 
 	asm volatile(
 "	sevl\n"
 "1:	wfe\n"
 "2:	ldaxr	%w0, %2\n"
+	/* Is the lock free? */
 "	eor	%w1, %w0, %w0, ror #16\n"
-"	cbnz	%w1, 1b\n"
+"	cbz	%w1, 3f\n"
+	/* Lock taken -- has there been a subsequent unlock->lock transition? */
+"	eor	%w1, %w3, %w0, lsl #16\n"
+"	cbz	%w1, 1b\n"
+	/*
+	 * The owner has been updated, so there was an unlock->lock
+	 * transition that we missed. That means we can rely on the
+	 * store-release of the unlock operation paired with the
+	 * load-acquire of the lock operation to publish any of our
+	 * previous stores to the new lock owner and therefore don't
+	 * need to bother with the writeback below.
+	 */
+"	b	4f\n"
+"3:\n"
+	/*
+	 * Serialise against any concurrent lockers by writing back the
+	 * unlocked lock value
+	 */
 	ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
 "	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 2b\n", /* Serialise against any concurrent lockers */
-	/* LSE atomics */
 "	nop\n"
-"	nop\n")
+"	nop\n",
+	/* LSE atomics */
+"	mov	%w1, %w0\n"
+"	cas	%w0, %w0, %2\n"
+"	eor	%w1, %w1, %w0\n")
+	/* Somebody else wrote to the lock, GOTO 10 and reload the value */
+"	cbnz	%w1, 2b\n"
+"4:"
 	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
-	:
+	: "r" (owner)
 	: "memory");
 }
 
@@ -148,6 +179,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
+	smp_mb(); /* See arch_spin_unlock_wait */
 	return !arch_spin_value_unlocked(READ_ONCE(*lock));
 }