arm64/boot: Disable trapping of PMZR_EL0 writes to EL2grafted

__init_el2_fgt2() writes one mask to both HDFGRTR2_EL2 and HDFGWTR2_EL2.
PMZR_EL0 is write-only, so its trap bit, nPMZR_EL0, exists only in
HDFGWTR2_EL2 and is therefore never set: a PMZR_EL0 write from the host
traps to EL2, where the nVHE hypervisor has no handler and BUG()s. The
kernel never writes PMZR_EL0, but kernel.perf_user_access=1 has the PMU
driver set PMUSERENR_EL0.UEN for a task with a user-read event, so a
write from EL0 reaches the trap and takes the host down without a panic
message.

Accumulate the HDFGWTR2_EL2 bits separately, as __init_el2_fgt() already
does for HDFGWTR_EL2, and set nPMZR_EL0 with the other FEAT_PMUv3p9
bits.

Fixes: 858c7bfcb35e1 ("arm64/boot: Enable EL2 requirements for FEAT_PMUv3p9")
Cc: stable@vger.kernel.org
Signed-off-by: Fuad Tabba <fuad.tabba@linux.dev>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Oliver Upton <oupton@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 306 insertions, 0 deletions

diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
new file mode 100644
index 000000000..b99cb57df
--- /dev/null
+++ b/include/asm-generic/barrier.h
@@ -0,0 +1,306 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic barrier definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#ifndef __ASM_GENERIC_BARRIER_H
+#define __ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+#include <linux/kcsan-checks.h>
+#include <asm/rwonce.h>
+
+#ifndef nop
+#define nop()	asm volatile ("nop")
+#endif
+
+/*
+ * Architectures that want generic instrumentation can define __ prefixed
+ * variants of all barriers.
+ */
+
+#ifdef __mb
+#define mb()	do { kcsan_mb(); __mb(); } while (0)
+#endif
+
+#ifdef __rmb
+#define rmb()	do { kcsan_rmb(); __rmb(); } while (0)
+#endif
+
+#ifdef __wmb
+#define wmb()	do { kcsan_wmb(); __wmb(); } while (0)
+#endif
+
+#ifdef __dma_mb
+#define dma_mb()	do { kcsan_mb(); __dma_mb(); } while (0)
+#endif
+
+#ifdef __dma_rmb
+#define dma_rmb()	do { kcsan_rmb(); __dma_rmb(); } while (0)
+#endif
+
+#ifdef __dma_wmb
+#define dma_wmb()	do { kcsan_wmb(); __dma_wmb(); } while (0)
+#endif
+
+/*
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
+ *
+ * Fall back to compiler barriers if nothing better is provided.
+ */
+
+#ifndef mb
+#define mb()	barrier()
+#endif
+
+#ifndef rmb
+#define rmb()	mb()
+#endif
+
+#ifndef wmb
+#define wmb()	mb()
+#endif
+
+#ifndef dma_mb
+#define dma_mb()	mb()
+#endif
+
+#ifndef dma_rmb
+#define dma_rmb()	rmb()
+#endif
+
+#ifndef dma_wmb
+#define dma_wmb()	wmb()
+#endif
+
+#ifndef __smp_mb
+#define __smp_mb()	mb()
+#endif
+
+#ifndef __smp_rmb
+#define __smp_rmb()	rmb()
+#endif
+
+#ifndef __smp_wmb
+#define __smp_wmb()	wmb()
+#endif
+
+#ifdef CONFIG_SMP
+
+#ifndef smp_mb
+#define smp_mb()	do { kcsan_mb(); __smp_mb(); } while (0)
+#endif
+
+#ifndef smp_rmb
+#define smp_rmb()	do { kcsan_rmb(); __smp_rmb(); } while (0)
+#endif
+
+#ifndef smp_wmb
+#define smp_wmb()	do { kcsan_wmb(); __smp_wmb(); } while (0)
+#endif
+
+#else	/* !CONFIG_SMP */
+
+#ifndef smp_mb
+#define smp_mb()	barrier()
+#endif
+
+#ifndef smp_rmb
+#define smp_rmb()	barrier()
+#endif
+
+#ifndef smp_wmb
+#define smp_wmb()	barrier()
+#endif
+
+#endif	/* CONFIG_SMP */
+
+#ifndef __smp_store_mb
+#define __smp_store_mb(var, value)  do { WRITE_ONCE(var, value); __smp_mb(); } while (0)
+#endif
+
+#ifndef __smp_mb__before_atomic
+#define __smp_mb__before_atomic()	__smp_mb()
+#endif
+
+#ifndef __smp_mb__after_atomic
+#define __smp_mb__after_atomic()	__smp_mb()
+#endif
+
+#ifndef __smp_store_release
+#define __smp_store_release(p, v)					\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	__smp_mb();							\
+	WRITE_ONCE(*p, v);						\
+} while (0)
+#endif
+
+#ifndef __smp_load_acquire
+#define __smp_load_acquire(p)						\
+({									\
+	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
+	compiletime_assert_atomic_type(*p);				\
+	__smp_mb();							\
+	(typeof(*p))___p1;						\
+})
+#endif
+
+#ifdef CONFIG_SMP
+
+#ifndef smp_store_mb
+#define smp_store_mb(var, value)  do { kcsan_mb(); __smp_store_mb(var, value); } while (0)
+#endif
+
+#ifndef smp_mb__before_atomic
+#define smp_mb__before_atomic()	do { kcsan_mb(); __smp_mb__before_atomic(); } while (0)
+#endif
+
+#ifndef smp_mb__after_atomic
+#define smp_mb__after_atomic()	do { kcsan_mb(); __smp_mb__after_atomic(); } while (0)
+#endif
+
+#ifndef smp_store_release
+#define smp_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0)
+#endif
+
+#ifndef smp_load_acquire
+#define smp_load_acquire(p) __smp_load_acquire(p)
+#endif
+
+#else	/* !CONFIG_SMP */
+
+#ifndef smp_store_mb
+#define smp_store_mb(var, value)  do { WRITE_ONCE(var, value); barrier(); } while (0)
+#endif
+
+#ifndef smp_mb__before_atomic
+#define smp_mb__before_atomic()	barrier()
+#endif
+
+#ifndef smp_mb__after_atomic
+#define smp_mb__after_atomic()	barrier()
+#endif
+
+#ifndef smp_store_release
+#define smp_store_release(p, v)						\
+do {									\
+	barrier();							\
+	WRITE_ONCE(*p, v);						\
+} while (0)
+#endif
+
+#ifndef smp_load_acquire
+#define smp_load_acquire(p)						\
+({									\
+	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
+	barrier();							\
+	(typeof(*p))___p1;						\
+})
+#endif
+
+#endif	/* CONFIG_SMP */
+
+/* Barriers for virtual machine guests when talking to an SMP host */
+#define virt_mb() do { kcsan_mb(); __smp_mb(); } while (0)
+#define virt_rmb() do { kcsan_rmb(); __smp_rmb(); } while (0)
+#define virt_wmb() do { kcsan_wmb(); __smp_wmb(); } while (0)
+#define virt_store_mb(var, value) do { kcsan_mb(); __smp_store_mb(var, value); } while (0)
+#define virt_mb__before_atomic() do { kcsan_mb(); __smp_mb__before_atomic(); } while (0)
+#define virt_mb__after_atomic()	do { kcsan_mb(); __smp_mb__after_atomic(); } while (0)
+#define virt_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0)
+#define virt_load_acquire(p) __smp_load_acquire(p)
+
+/**
+ * smp_acquire__after_ctrl_dep() - Provide ACQUIRE ordering after a control dependency
+ *
+ * A control dependency provides a LOAD->STORE order, the additional RMB
+ * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
+ * aka. (load)-ACQUIRE.
+ *
+ * Architectures that do not do load speculation can have this be barrier().
+ */
+#ifndef smp_acquire__after_ctrl_dep
+#define smp_acquire__after_ctrl_dep()		smp_rmb()
+#endif
+
+/**
+ * smp_cond_load_relaxed() - (Spin) wait for cond with no ordering guarantees
+ * @ptr: pointer to the variable to wait on
+ * @cond_expr: boolean expression to wait for
+ *
+ * Equivalent to using READ_ONCE() on the condition variable.
+ *
+ * Due to C lacking lambda expressions we load the value of *ptr into a
+ * pre-named variable @VAL to be used in @cond.
+ */
+#ifndef smp_cond_load_relaxed
+#define smp_cond_load_relaxed(ptr, cond_expr) ({		\
+	typeof(ptr) __PTR = (ptr);				\
+	__unqual_scalar_typeof(*ptr) VAL;			\
+	for (;;) {						\
+		VAL = READ_ONCE(*__PTR);			\
+		if (cond_expr)					\
+			break;					\
+		cpu_relax();					\
+	}							\
+	(typeof(*ptr))VAL;					\
+})
+#endif
+
+/**
+ * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
+ * @ptr: pointer to the variable to wait on
+ * @cond_expr: boolean expression to wait for
+ *
+ * Equivalent to using smp_load_acquire() on the condition variable but employs
+ * the control dependency of the wait to reduce the barrier on many platforms.
+ */
+#ifndef smp_cond_load_acquire
+#define smp_cond_load_acquire(ptr, cond_expr) ({		\
+	__unqual_scalar_typeof(*ptr) _val;			\
+	_val = smp_cond_load_relaxed(ptr, cond_expr);		\
+	smp_acquire__after_ctrl_dep();				\
+	(typeof(*ptr))_val;					\
+})
+#endif
+
+/*
+ * pmem_wmb() ensures that all stores for which the modification
+ * are written to persistent storage by preceding instructions have
+ * updated persistent storage before any data  access or data transfer
+ * caused by subsequent instructions is initiated.
+ */
+#ifndef pmem_wmb
+#define pmem_wmb()	wmb()
+#endif
+
+/*
+ * ioremap_wc() maps I/O memory as memory with write-combining attributes. For
+ * this kind of memory accesses, the CPU may wait for prior accesses to be
+ * merged with subsequent ones. In some situation, such wait is bad for the
+ * performance. io_stop_wc() can be used to prevent the merging of
+ * write-combining memory accesses before this macro with those after it.
+ */
+#ifndef io_stop_wc
+#define io_stop_wc() do { } while (0)
+#endif
+
+/*
+ * Architectures that guarantee an implicit smp_mb() in switch_mm()
+ * can override smp_mb__after_switch_mm.
+ */
+#ifndef smp_mb__after_switch_mm
+# define smp_mb__after_switch_mm()	smp_mb()
+#endif
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_GENERIC_BARRIER_H */