Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

2 files changed, 442 insertions, 0 deletions

diff --git a/include/uapi/rdma/hfi/hfi1_ioctl.h b/include/uapi/rdma/hfi/hfi1_ioctl.h
new file mode 100644
index 000000000..8f3d9fe7b
--- /dev/null
+++ b/include/uapi/rdma/hfi/hfi1_ioctl.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/*
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2015 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2015 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  - Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  - Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#ifndef _LINUX__HFI1_IOCTL_H
+#define _LINUX__HFI1_IOCTL_H
+#include <linux/types.h>
+
+/*
+ * This structure is passed to the driver to tell it where
+ * user code buffers are, sizes, etc.   The offsets and sizes of the
+ * fields must remain unchanged, for binary compatibility.  It can
+ * be extended, if userversion is changed so user code can tell, if needed
+ */
+struct hfi1_user_info {
+	/*
+	 * version of user software, to detect compatibility issues.
+	 * Should be set to HFI1_USER_SWVERSION.
+	 */
+	__u32 userversion;
+	__u32 pad;
+	/*
+	 * If two or more processes wish to share a context, each process
+	 * must set the subcontext_cnt and subcontext_id to the same
+	 * values.  The only restriction on the subcontext_id is that
+	 * it be unique for a given node.
+	 */
+	__u16 subctxt_cnt;
+	__u16 subctxt_id;
+	/* 128bit UUID passed in by PSM. */
+	__u8 uuid[16];
+};
+
+struct hfi1_ctxt_info {
+	__aligned_u64 runtime_flags;    /* chip/drv runtime flags (HFI1_CAP_*) */
+	__u32 rcvegr_size;      /* size of each eager buffer */
+	__u16 num_active;       /* number of active units */
+	__u16 unit;             /* unit (chip) assigned to caller */
+	__u16 ctxt;             /* ctxt on unit assigned to caller */
+	__u16 subctxt;          /* subctxt on unit assigned to caller */
+	__u16 rcvtids;          /* number of Rcv TIDs for this context */
+	__u16 credits;          /* number of PIO credits for this context */
+	__u16 numa_node;        /* NUMA node of the assigned device */
+	__u16 rec_cpu;          /* cpu # for affinity (0xffff if none) */
+	__u16 send_ctxt;        /* send context in use by this user context */
+	__u16 egrtids;          /* number of RcvArray entries for Eager Rcvs */
+	__u16 rcvhdrq_cnt;      /* number of RcvHdrQ entries */
+	__u16 rcvhdrq_entsize;  /* size (in bytes) for each RcvHdrQ entry */
+	__u16 sdma_ring_size;   /* number of entries in SDMA request ring */
+};
+
+struct hfi1_tid_info {
+	/* virtual address of first page in transfer */
+	__aligned_u64 vaddr;
+	/* pointer to tid array. this array is big enough */
+	__aligned_u64 tidlist;
+	/* number of tids programmed by this request */
+	__u32 tidcnt;
+	/* length of transfer buffer programmed by this request */
+	__u32 length;
+};
+
+/*
+ * This structure is returned by the driver immediately after
+ * open to get implementation-specific info, and info specific to this
+ * instance.
+ *
+ * This struct must have explicit pad fields where type sizes
+ * may result in different alignments between 32 and 64 bit
+ * programs, since the 64 bit * bit kernel requires the user code
+ * to have matching offsets
+ */
+struct hfi1_base_info {
+	/* version of hardware, for feature checking. */
+	__u32 hw_version;
+	/* version of software, for feature checking. */
+	__u32 sw_version;
+	/* Job key */
+	__u16 jkey;
+	__u16 padding1;
+	/*
+	 * The special QP (queue pair) value that identifies PSM
+	 * protocol packet from standard IB packets.
+	 */
+	__u32 bthqp;
+	/* PIO credit return address, */
+	__aligned_u64 sc_credits_addr;
+	/*
+	 * Base address of write-only pio buffers for this process.
+	 * Each buffer has sendpio_credits*64 bytes.
+	 */
+	__aligned_u64 pio_bufbase_sop;
+	/*
+	 * Base address of write-only pio buffers for this process.
+	 * Each buffer has sendpio_credits*64 bytes.
+	 */
+	__aligned_u64 pio_bufbase;
+	/* address where receive buffer queue is mapped into */
+	__aligned_u64 rcvhdr_bufbase;
+	/* base address of Eager receive buffers. */
+	__aligned_u64 rcvegr_bufbase;
+	/* base address of SDMA completion ring */
+	__aligned_u64 sdma_comp_bufbase;
+	/*
+	 * User register base for init code, not to be used directly by
+	 * protocol or applications.  Always maps real chip register space.
+	 * the register addresses are:
+	 * ur_rcvhdrhead, ur_rcvhdrtail, ur_rcvegrhead, ur_rcvegrtail,
+	 * ur_rcvtidflow
+	 */
+	__aligned_u64 user_regbase;
+	/* notification events */
+	__aligned_u64 events_bufbase;
+	/* status page */
+	__aligned_u64 status_bufbase;
+	/* rcvhdrtail update */
+	__aligned_u64 rcvhdrtail_base;
+	/*
+	 * shared memory pages for subctxts if ctxt is shared; these cover
+	 * all the processes in the group sharing a single context.
+	 * all have enough space for the num_subcontexts value on this job.
+	 */
+	__aligned_u64 subctxt_uregbase;
+	__aligned_u64 subctxt_rcvegrbuf;
+	__aligned_u64 subctxt_rcvhdrbuf;
+};
+#endif /* _LINIUX__HFI1_IOCTL_H */
diff --git a/include/uapi/rdma/hfi/hfi1_user.h b/include/uapi/rdma/hfi/hfi1_user.h
new file mode 100644
index 000000000..1106a7c90
--- /dev/null
+++ b/include/uapi/rdma/hfi/hfi1_user.h
@@ -0,0 +1,268 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/*
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2015 - 2020 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2015 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  - Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  - Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+/*
+ * This file contains defines, structures, etc. that are used
+ * to communicate between kernel and user code.
+ */
+
+#ifndef _LINUX__HFI1_USER_H
+#define _LINUX__HFI1_USER_H
+
+#include <linux/types.h>
+#include <rdma/rdma_user_ioctl.h>
+
+/*
+ * This version number is given to the driver by the user code during
+ * initialization in the spu_userversion field of hfi1_user_info, so
+ * the driver can check for compatibility with user code.
+ *
+ * The major version changes when data structures change in an incompatible
+ * way. The driver must be the same for initialization to succeed.
+ */
+#define HFI1_USER_SWMAJOR 6
+
+/*
+ * Minor version differences are always compatible
+ * a within a major version, however if user software is larger
+ * than driver software, some new features and/or structure fields
+ * may not be implemented; the user code must deal with this if it
+ * cares, or it must abort after initialization reports the difference.
+ */
+#define HFI1_USER_SWMINOR 3
+
+/*
+ * We will encode the major/minor inside a single 32bit version number.
+ */
+#define HFI1_SWMAJOR_SHIFT 16
+
+/*
+ * Set of HW and driver capability/feature bits.
+ * These bit values are used to configure enabled/disabled HW and
+ * driver features. The same set of bits are communicated to user
+ * space.
+ */
+#define HFI1_CAP_DMA_RTAIL        (1UL <<  0) /* Use DMA'ed RTail value */
+#define HFI1_CAP_SDMA             (1UL <<  1) /* Enable SDMA support */
+#define HFI1_CAP_SDMA_AHG         (1UL <<  2) /* Enable SDMA AHG support */
+#define HFI1_CAP_EXTENDED_PSN     (1UL <<  3) /* Enable Extended PSN support */
+#define HFI1_CAP_HDRSUPP          (1UL <<  4) /* Enable Header Suppression */
+#define HFI1_CAP_TID_RDMA         (1UL <<  5) /* Enable TID RDMA operations */
+#define HFI1_CAP_USE_SDMA_HEAD    (1UL <<  6) /* DMA Hdr Q tail vs. use CSR */
+#define HFI1_CAP_MULTI_PKT_EGR    (1UL <<  7) /* Enable multi-packet Egr buffs*/
+#define HFI1_CAP_NODROP_RHQ_FULL  (1UL <<  8) /* Don't drop on Hdr Q full */
+#define HFI1_CAP_NODROP_EGR_FULL  (1UL <<  9) /* Don't drop on EGR buffs full */
+#define HFI1_CAP_TID_UNMAP        (1UL << 10) /* Disable Expected TID caching */
+#define HFI1_CAP_PRINT_UNIMPL     (1UL << 11) /* Show for unimplemented feats */
+#define HFI1_CAP_ALLOW_PERM_JKEY  (1UL << 12) /* Allow use of permissive JKEY */
+#define HFI1_CAP_NO_INTEGRITY     (1UL << 13) /* Enable ctxt integrity checks */
+#define HFI1_CAP_PKEY_CHECK       (1UL << 14) /* Enable ctxt PKey checking */
+#define HFI1_CAP_STATIC_RATE_CTRL (1UL << 15) /* Allow PBC.StaticRateControl */
+#define HFI1_CAP_OPFN             (1UL << 16) /* Enable the OPFN protocol */
+#define HFI1_CAP_SDMA_HEAD_CHECK  (1UL << 17) /* SDMA head checking */
+#define HFI1_CAP_EARLY_CREDIT_RETURN (1UL << 18) /* early credit return */
+#define HFI1_CAP_AIP              (1UL << 19) /* Enable accelerated IP */
+
+#define HFI1_RCVHDR_ENTSIZE_2    (1UL << 0)
+#define HFI1_RCVHDR_ENTSIZE_16   (1UL << 1)
+#define HFI1_RCVDHR_ENTSIZE_32   (1UL << 2)
+
+#define _HFI1_EVENT_FROZEN_BIT         0
+#define _HFI1_EVENT_LINKDOWN_BIT       1
+#define _HFI1_EVENT_LID_CHANGE_BIT     2
+#define _HFI1_EVENT_LMC_CHANGE_BIT     3
+#define _HFI1_EVENT_SL2VL_CHANGE_BIT   4
+#define _HFI1_EVENT_TID_MMU_NOTIFY_BIT 5
+#define _HFI1_MAX_EVENT_BIT _HFI1_EVENT_TID_MMU_NOTIFY_BIT
+
+#define HFI1_EVENT_FROZEN            (1UL << _HFI1_EVENT_FROZEN_BIT)
+#define HFI1_EVENT_LINKDOWN          (1UL << _HFI1_EVENT_LINKDOWN_BIT)
+#define HFI1_EVENT_LID_CHANGE        (1UL << _HFI1_EVENT_LID_CHANGE_BIT)
+#define HFI1_EVENT_LMC_CHANGE        (1UL << _HFI1_EVENT_LMC_CHANGE_BIT)
+#define HFI1_EVENT_SL2VL_CHANGE      (1UL << _HFI1_EVENT_SL2VL_CHANGE_BIT)
+#define HFI1_EVENT_TID_MMU_NOTIFY    (1UL << _HFI1_EVENT_TID_MMU_NOTIFY_BIT)
+
+/*
+ * These are the status bits readable (in ASCII form, 64bit value)
+ * from the "status" sysfs file.  For binary compatibility, values
+ * must remain as is; removed states can be reused for different
+ * purposes.
+ */
+#define HFI1_STATUS_INITTED       0x1    /* basic initialization done */
+/* Chip has been found and initialized */
+#define HFI1_STATUS_CHIP_PRESENT 0x20
+/* IB link is at ACTIVE, usable for data traffic */
+#define HFI1_STATUS_IB_READY     0x40
+/* link is configured, LID, MTU, etc. have been set */
+#define HFI1_STATUS_IB_CONF      0x80
+/* A Fatal hardware error has occurred. */
+#define HFI1_STATUS_HWERROR     0x200
+
+/*
+ * Number of supported shared contexts.
+ * This is the maximum number of software contexts that can share
+ * a hardware send/receive context.
+ */
+#define HFI1_MAX_SHARED_CTXTS 8
+
+/*
+ * Poll types
+ */
+#define HFI1_POLL_TYPE_ANYRCV     0x0
+#define HFI1_POLL_TYPE_URGENT     0x1
+
+enum hfi1_sdma_comp_state {
+	FREE = 0,
+	QUEUED,
+	COMPLETE,
+	ERROR
+};
+
+/*
+ * SDMA completion ring entry
+ */
+struct hfi1_sdma_comp_entry {
+	__u32 status;
+	__u32 errcode;
+};
+
+/*
+ * Device status and notifications from driver to user-space.
+ */
+struct hfi1_status {
+	__aligned_u64 dev;      /* device/hw status bits */
+	__aligned_u64 port;     /* port state and status bits */
+	char freezemsg[];
+};
+
+enum sdma_req_opcode {
+	EXPECTED = 0,
+	EAGER
+};
+
+#define HFI1_SDMA_REQ_VERSION_MASK 0xF
+#define HFI1_SDMA_REQ_VERSION_SHIFT 0x0
+#define HFI1_SDMA_REQ_OPCODE_MASK 0xF
+#define HFI1_SDMA_REQ_OPCODE_SHIFT 0x4
+#define HFI1_SDMA_REQ_IOVCNT_MASK 0xFF
+#define HFI1_SDMA_REQ_IOVCNT_SHIFT 0x8
+
+struct sdma_req_info {
+	/*
+	 * bits 0-3 - version (currently unused)
+	 * bits 4-7 - opcode (enum sdma_req_opcode)
+	 * bits 8-15 - io vector count
+	 */
+	__u16 ctrl;
+	/*
+	 * Number of fragments contained in this request.
+	 * User-space has already computed how many
+	 * fragment-sized packet the user buffer will be
+	 * split into.
+	 */
+	__u16 npkts;
+	/*
+	 * Size of each fragment the user buffer will be
+	 * split into.
+	 */
+	__u16 fragsize;
+	/*
+	 * Index of the slot in the SDMA completion ring
+	 * this request should be using. User-space is
+	 * in charge of managing its own ring.
+	 */
+	__u16 comp_idx;
+} __attribute__((__packed__));
+
+/*
+ * SW KDETH header.
+ * swdata is SW defined portion.
+ */
+struct hfi1_kdeth_header {
+	__le32 ver_tid_offset;
+	__le16 jkey;
+	__le16 hcrc;
+	__le32 swdata[7];
+}  __attribute__((__packed__));
+
+/*
+ * Structure describing the headers that User space uses. The
+ * structure above is a subset of this one.
+ */
+struct hfi1_pkt_header {
+	__le16 pbc[4];
+	__be16 lrh[4];
+	__be32 bth[3];
+	struct hfi1_kdeth_header kdeth;
+}  __attribute__((__packed__));
+
+
+/*
+ * The list of usermode accessible registers.
+ */
+enum hfi1_ureg {
+	/* (RO)  DMA RcvHdr to be used next. */
+	ur_rcvhdrtail = 0,
+	/* (RW)  RcvHdr entry to be processed next by host. */
+	ur_rcvhdrhead = 1,
+	/* (RO)  Index of next Eager index to use. */
+	ur_rcvegrindextail = 2,
+	/* (RW)  Eager TID to be processed next */
+	ur_rcvegrindexhead = 3,
+	/* (RO)  Receive Eager Offset Tail */
+	ur_rcvegroffsettail = 4,
+	/* For internal use only; max register number. */
+	ur_maxreg,
+	/* (RW)  Receive TID flow table */
+	ur_rcvtidflowtable = 256
+};
+
+#endif /* _LINIUX__HFI1_USER_H */