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, 81 insertions, 0 deletions

diff --git a/include/rdma/ib.h b/include/rdma/ib.h
new file mode 100644
index 000000000..f7c185ff7
--- /dev/null
+++ b/include/rdma/ib.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2010 Intel Corporation.  All rights reserved.
+ */
+
+#ifndef _RDMA_IB_H
+#define _RDMA_IB_H
+
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/uaccess.h>
+#include <linux/fs.h>
+
+struct ib_addr {
+	union {
+		__u8		uib_addr8[16];
+		__be16		uib_addr16[8];
+		__be32		uib_addr32[4];
+		__be64		uib_addr64[2];
+	} ib_u;
+#define sib_addr8		ib_u.uib_addr8
+#define sib_addr16		ib_u.uib_addr16
+#define sib_addr32		ib_u.uib_addr32
+#define sib_addr64		ib_u.uib_addr64
+#define sib_raw			ib_u.uib_addr8
+#define sib_subnet_prefix	ib_u.uib_addr64[0]
+#define sib_interface_id	ib_u.uib_addr64[1]
+};
+
+static inline bool ib_addr_any(const struct ib_addr *a)
+{
+	return ((a->sib_addr64[0] | a->sib_addr64[1]) == 0);
+}
+
+static inline bool ib_addr_loopback(const struct ib_addr *a)
+{
+	return ((a->sib_addr32[0] | a->sib_addr32[1] |
+		 a->sib_addr32[2] | (a->sib_addr32[3] ^ htonl(1))) == 0);
+}
+
+static inline void ib_addr_set(struct ib_addr *addr,
+			       __be32 w1, __be32 w2, __be32 w3, __be32 w4)
+{
+	addr->sib_addr32[0] = w1;
+	addr->sib_addr32[1] = w2;
+	addr->sib_addr32[2] = w3;
+	addr->sib_addr32[3] = w4;
+}
+
+static inline int ib_addr_cmp(const struct ib_addr *a1, const struct ib_addr *a2)
+{
+	return memcmp(a1, a2, sizeof(struct ib_addr));
+}
+
+struct sockaddr_ib {
+	unsigned short int	sib_family;	/* AF_IB */
+	__be16			sib_pkey;
+	__be32			sib_flowinfo;
+	struct ib_addr		sib_addr;
+	__be64			sib_sid;
+	__be64			sib_sid_mask;
+	__u64			sib_scope_id;
+};
+
+/*
+ * The IB interfaces that use write() as bi-directional ioctl() are
+ * fundamentally unsafe, since there are lots of ways to trigger "write()"
+ * calls from various contexts with elevated privileges. That includes the
+ * traditional suid executable error message writes, but also various kernel
+ * interfaces that can write to file descriptors.
+ *
+ * This function provides protection for the legacy API by restricting the
+ * calling context.
+ */
+static inline bool ib_safe_file_access(struct file *filp)
+{
+	return filp->f_cred == current_cred();
+}
+
+#endif /* _RDMA_IB_H */