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, 66 insertions, 0 deletions

diff --git a/include/uapi/rdma/rvt-abi.h b/include/uapi/rdma/rvt-abi.h
new file mode 100644
index 000000000..7c05a02d2
--- /dev/null
+++ b/include/uapi/rdma/rvt-abi.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+
+/*
+ * This file contains defines, structures, etc. that are used
+ * to communicate between kernel and user code.
+ */
+
+#ifndef RVT_ABI_USER_H
+#define RVT_ABI_USER_H
+
+#include <linux/types.h>
+#include <rdma/ib_user_verbs.h>
+#ifndef RDMA_ATOMIC_UAPI
+#define RDMA_ATOMIC_UAPI(_type, _name) struct{ _type val; } _name
+#endif
+
+struct rvt_wqe_sge {
+	__aligned_u64 addr;
+	__u32 length;
+	__u32 lkey;
+};
+
+/*
+ * This structure is used to contain the head pointer, tail pointer,
+ * and completion queue entries as a single memory allocation so
+ * it can be mmap'ed into user space.
+ */
+struct rvt_cq_wc {
+	/* index of next entry to fill */
+	RDMA_ATOMIC_UAPI(__u32, head);
+	/* index of next ib_poll_cq() entry */
+	RDMA_ATOMIC_UAPI(__u32, tail);
+
+	/* these are actually size ibcq.cqe + 1 */
+	struct ib_uverbs_wc uqueue[];
+};
+
+/*
+ * Receive work request queue entry.
+ * The size of the sg_list is determined when the QP (or SRQ) is created
+ * and stored in qp->r_rq.max_sge (or srq->rq.max_sge).
+ */
+struct rvt_rwqe {
+	__u64 wr_id;
+	__u8 num_sge;
+	__u8 padding[7];
+	struct rvt_wqe_sge sg_list[];
+};
+
+/*
+ * This structure is used to contain the head pointer, tail pointer,
+ * and receive work queue entries as a single memory allocation so
+ * it can be mmap'ed into user space.
+ * Note that the wq array elements are variable size so you can't
+ * just index into the array to get the N'th element;
+ * use get_rwqe_ptr() for user space and rvt_get_rwqe_ptr()
+ * for kernel space.
+ */
+struct rvt_rwq {
+	/* new work requests posted to the head */
+	RDMA_ATOMIC_UAPI(__u32, head);
+	/* receives pull requests from here. */
+	RDMA_ATOMIC_UAPI(__u32, tail);
+	struct rvt_rwqe wq[];
+};
+#endif /* RVT_ABI_USER_H */