diff --git a/contrib/plugins/Makefile b/contrib/plugins/Makefile
index 7801b08b0d..b9d7935e5e 100644
--- a/contrib/plugins/Makefile
+++ b/contrib/plugins/Makefile
@@ -17,6 +17,7 @@ NAMES += hotblocks
 NAMES += hotpages
 NAMES += howvec
 NAMES += lockstep
+NAMES += hwprofile
 
 SONAMES := $(addsuffix .so,$(addprefix lib,$(NAMES)))
 
diff --git a/contrib/plugins/hwprofile.c b/contrib/plugins/hwprofile.c
new file mode 100644
index 0000000000..6dac1d5f85
--- /dev/null
+++ b/contrib/plugins/hwprofile.c
@@ -0,0 +1,305 @@
+/*
+ * Copyright (C) 2020, Alex Bennée <alex.bennee@linaro.org>
+ *
+ * HW Profile - breakdown access patterns for IO to devices
+ *
+ * License: GNU GPL, version 2 or later.
+ *   See the COPYING file in the top-level directory.
+ */
+
+#include <inttypes.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <glib.h>
+
+#include <qemu-plugin.h>
+
+QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION;
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+typedef struct {
+    uint64_t cpu_read;
+    uint64_t cpu_write;
+    uint64_t reads;
+    uint64_t writes;
+} IOCounts;
+
+typedef struct {
+    uint64_t off_or_pc;
+    IOCounts counts;
+} IOLocationCounts;
+
+typedef struct {
+    const char *name;
+    uint64_t   base;
+    IOCounts   totals;
+    GHashTable *detail;
+} DeviceCounts;
+
+static GMutex lock;
+static GHashTable *devices;
+
+/* track the access pattern to a piece of HW */
+static bool pattern;
+/* track the source address of access to HW */
+static bool source;
+/* track only matched regions of HW */
+static bool check_match;
+static gchar **matches;
+
+static enum qemu_plugin_mem_rw rw = QEMU_PLUGIN_MEM_RW;
+
+static inline bool track_reads(void)
+{
+    return rw == QEMU_PLUGIN_MEM_RW || rw == QEMU_PLUGIN_MEM_R;
+}
+
+static inline bool track_writes(void)
+{
+    return rw == QEMU_PLUGIN_MEM_RW || rw == QEMU_PLUGIN_MEM_W;
+}
+
+static void plugin_init(void)
+{
+    devices = g_hash_table_new(NULL, NULL);
+}
+
+static gint sort_cmp(gconstpointer a, gconstpointer b)
+{
+    DeviceCounts *ea = (DeviceCounts *) a;
+    DeviceCounts *eb = (DeviceCounts *) b;
+    return ea->totals.reads + ea->totals.writes >
+           eb->totals.reads + eb->totals.writes ? -1 : 1;
+}
+
+static gint sort_loc(gconstpointer a, gconstpointer b)
+{
+    IOLocationCounts *ea = (IOLocationCounts *) a;
+    IOLocationCounts *eb = (IOLocationCounts *) b;
+    return ea->off_or_pc > eb->off_or_pc;
+}
+
+static void fmt_iocount_record(GString *s, IOCounts *rec)
+{
+    if (track_reads()) {
+        g_string_append_printf(s, ", %"PRIx64", %"PRId64,
+                               rec->cpu_read, rec->reads);
+    }
+    if (track_writes()) {
+        g_string_append_printf(s, ", %"PRIx64", %"PRId64,
+                               rec->cpu_write, rec->writes);
+    }
+}
+
+static void fmt_dev_record(GString *s, DeviceCounts *rec)
+{
+    g_string_append_printf(s, "%s, 0x%"PRIx64,
+                           rec->name, rec->base);
+    fmt_iocount_record(s, &rec->totals);
+    g_string_append_c(s, '\n');
+}
+
+static void plugin_exit(qemu_plugin_id_t id, void *p)
+{
+    g_autoptr(GString) report = g_string_new("");
+    GList *counts;
+
+    if (!(pattern || source)) {
+        g_string_printf(report, "Device, Address");
+        if (track_reads()) {
+            g_string_append_printf(report, ", RCPUs, Reads");
+        }
+        if (track_writes()) {
+            g_string_append_printf(report, ",  WCPUs, Writes");
+        }
+        g_string_append_c(report, '\n');
+    }
+
+    counts = g_hash_table_get_values(devices);
+    if (counts && g_list_next(counts)) {
+        GList *it;
+
+        it = g_list_sort(counts, sort_cmp);
+
+        while (it) {
+            DeviceCounts *rec = (DeviceCounts *) it->data;
+            if (rec->detail) {
+                GList *accesses = g_hash_table_get_values(rec->detail);
+                GList *io_it = g_list_sort(accesses, sort_loc);
+                const char *prefix = pattern ? "off" : "pc";
+                g_string_append_printf(report, "%s @ 0x%"PRIx64"\n",
+                                       rec->name, rec->base);
+                while (io_it) {
+                    IOLocationCounts *loc = (IOLocationCounts *) io_it->data;
+                    g_string_append_printf(report, "  %s:%08"PRIx64,
+                                           prefix, loc->off_or_pc);
+                    fmt_iocount_record(report, &loc->counts);
+                    g_string_append_c(report, '\n');
+                    io_it = io_it->next;
+                }
+            } else {
+                fmt_dev_record(report, rec);
+            }
+            it = it->next;
+        };
+        g_list_free(it);
+    }
+
+    qemu_plugin_outs(report->str);
+}
+
+static DeviceCounts *new_count(const char *name, uint64_t base)
+{
+    DeviceCounts *count = g_new0(DeviceCounts, 1);
+    count->name = name;
+    count->base = base;
+    if (pattern || source) {
+        count->detail = g_hash_table_new(NULL, NULL);
+    }
+    g_hash_table_insert(devices, (gpointer) name, count);
+    return count;
+}
+
+static IOLocationCounts *new_location(GHashTable *table, uint64_t off_or_pc)
+{
+    IOLocationCounts *loc = g_new0(IOLocationCounts, 1);
+    loc->off_or_pc = off_or_pc;
+    g_hash_table_insert(table, (gpointer) off_or_pc, loc);
+    return loc;
+}
+
+static void hwprofile_match_hit(DeviceCounts *rec, uint64_t off)
+{
+    g_autoptr(GString) report = g_string_new("hwprofile: match @ offset");
+    g_string_append_printf(report, "%"PRIx64", previous hits\n", off);
+    fmt_dev_record(report, rec);
+    qemu_plugin_outs(report->str);
+}
+
+static void inc_count(IOCounts *count, bool is_write, unsigned int cpu_index)
+{
+    if (is_write) {
+        count->writes++;
+        count->cpu_write |= (1 << cpu_index);
+    } else {
+        count->reads++;
+        count->cpu_read |= (1 << cpu_index);
+    }
+}
+
+static void vcpu_haddr(unsigned int cpu_index, qemu_plugin_meminfo_t meminfo,
+                       uint64_t vaddr, void *udata)
+{
+    struct qemu_plugin_hwaddr *hwaddr = qemu_plugin_get_hwaddr(meminfo, vaddr);
+
+    if (!hwaddr || !qemu_plugin_hwaddr_is_io(hwaddr)) {
+        return;
+    } else {
+        const char *name = qemu_plugin_hwaddr_device_name(hwaddr);
+        uint64_t off = qemu_plugin_hwaddr_device_offset(hwaddr);
+        bool is_write = qemu_plugin_mem_is_store(meminfo);
+        DeviceCounts *counts;
+
+        g_mutex_lock(&lock);
+        counts = (DeviceCounts *) g_hash_table_lookup(devices, name);
+
+        if (!counts) {
+            uint64_t base = vaddr - off;
+            counts = new_count(name, base);
+        }
+
+        if (check_match) {
+            if (g_strv_contains((const char * const *)matches, counts->name)) {
+                hwprofile_match_hit(counts, off);
+                inc_count(&counts->totals, is_write, cpu_index);
+            }
+        } else {
+            inc_count(&counts->totals, is_write, cpu_index);
+        }
+
+        /* either track offsets or source of access */
+        if (source) {
+            off = (uint64_t) udata;
+        }
+
+        if (pattern || source) {
+            IOLocationCounts *io_count = g_hash_table_lookup(counts->detail,
+                                                             (gpointer) off);
+            if (!io_count) {
+                io_count = new_location(counts->detail, off);
+            }
+            inc_count(&io_count->counts, is_write, cpu_index);
+        }
+
+        g_mutex_unlock(&lock);
+    }
+}
+
+static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
+{
+    size_t n = qemu_plugin_tb_n_insns(tb);
+    size_t i;
+
+    for (i = 0; i < n; i++) {
+        struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i);
+        gpointer udata = (gpointer) (source ? qemu_plugin_insn_vaddr(insn) : 0);
+        qemu_plugin_register_vcpu_mem_cb(insn, vcpu_haddr,
+                                         QEMU_PLUGIN_CB_NO_REGS,
+                                         rw, udata);
+    }
+}
+
+QEMU_PLUGIN_EXPORT
+int qemu_plugin_install(qemu_plugin_id_t id, const qemu_info_t *info,
+                        int argc, char **argv)
+{
+    int i;
+
+    for (i = 0; i < argc; i++) {
+        char *opt = argv[i];
+        if (g_strcmp0(opt, "read") == 0) {
+            rw = QEMU_PLUGIN_MEM_R;
+        } else if (g_strcmp0(opt, "write") == 0) {
+            rw = QEMU_PLUGIN_MEM_W;
+        } else if (g_strcmp0(opt, "pattern") == 0) {
+            pattern = true;
+        } else if (g_strcmp0(opt, "source") == 0) {
+            source = true;
+        } else if (g_str_has_prefix(opt, "match")) {
+            gchar **parts = g_strsplit(opt, "=", 2);
+            check_match = true;
+            matches = g_strsplit(parts[1], ",", -1);
+            g_strfreev(parts);
+        } else {
+            fprintf(stderr, "option parsing failed: %s\n", opt);
+            return -1;
+        }
+    }
+
+    if (source && pattern) {
+        fprintf(stderr, "can only currently track either source or pattern.\n");
+        return -1;
+    }
+
+    if (!info->system_emulation) {
+        fprintf(stderr, "hwprofile: plugin only useful for system emulation\n");
+        return -1;
+    }
+
+    /* Just warn about overflow */
+    if (info->system.smp_vcpus > 64 ||
+        info->system.max_vcpus > 64) {
+        fprintf(stderr, "hwprofile: can only track up to 64 CPUs\n");
+    }
+
+    plugin_init();
+
+    qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
+    qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);
+    return 0;
+}
diff --git a/docs/devel/tcg-plugins.rst b/docs/devel/tcg-plugins.rst
index 0568dfa6a4..39ce86ed96 100644
--- a/docs/devel/tcg-plugins.rst
+++ b/docs/devel/tcg-plugins.rst
@@ -280,3 +280,37 @@ which will eventually report::
     previously @ 0x000000ffd08098/5 (809900593 insns)
     previously @ 0x000000ffd080c0/1 (809900588 insns)
 
+- contrib/plugins/hwprofile
+
+The hwprofile tool can only be used with system emulation and allows
+the user to see what hardware is accessed how often. It has a number of options:
+
+ * arg=read or arg=write
+
+ By default the plugin tracks both reads and writes. You can use one
+ of these options to limit the tracking to just one class of accesses.
+
+ * arg=source
+
+ Will include a detailed break down of what the guest PC that made the
+ access was. Not compatible with arg=pattern. Example output::
+
+   cirrus-low-memory @ 0xfffffd00000a0000
+    pc:fffffc0000005cdc, 1, 256
+    pc:fffffc0000005ce8, 1, 256
+    pc:fffffc0000005cec, 1, 256
+
+ * arg=pattern
+
+ Instead break down the accesses based on the offset into the HW
+ region. This can be useful for seeing the most used registers of a
+ device. Example output::
+
+    pci0-conf @ 0xfffffd01fe000000
+      off:00000004, 1, 1
+      off:00000010, 1, 3
+      off:00000014, 1, 3
+      off:00000018, 1, 2
+      off:0000001c, 1, 2
+      off:00000020, 1, 2
+      ...