summaryrefslogtreecommitdiffstats
path: root/hw/block
diff options
context:
space:
mode:
Diffstat (limited to 'hw/block')
-rw-r--r--hw/block/Kconfig46
-rw-r--r--hw/block/block.c239
-rw-r--r--hw/block/cdrom.c155
-rw-r--r--hw/block/dataplane/meson.build2
-rw-r--r--hw/block/dataplane/trace-events5
-rw-r--r--hw/block/dataplane/trace.h1
-rw-r--r--hw/block/dataplane/virtio-blk.c362
-rw-r--r--hw/block/dataplane/virtio-blk.h31
-rw-r--r--hw/block/dataplane/xen-block.c829
-rw-r--r--hw/block/dataplane/xen-block.h30
-rw-r--r--hw/block/ecc.c91
-rw-r--r--hw/block/fdc-internal.h158
-rw-r--r--hw/block/fdc-isa.c327
-rw-r--r--hw/block/fdc-sysbus.c257
-rw-r--r--hw/block/fdc.c2393
-rw-r--r--hw/block/hd-geometry.c168
-rw-r--r--hw/block/m25p80.c1831
-rw-r--r--hw/block/m25p80_sfdp.c332
-rw-r--r--hw/block/m25p80_sfdp.h29
-rw-r--r--hw/block/meson.build23
-rw-r--r--hw/block/nand.c815
-rw-r--r--hw/block/onenand.c872
-rw-r--r--hw/block/pflash_cfi01.c1043
-rw-r--r--hw/block/pflash_cfi02.c1031
-rw-r--r--hw/block/swim.c491
-rw-r--r--hw/block/tc58128.c208
-rw-r--r--hw/block/trace-events85
-rw-r--r--hw/block/trace.h1
-rw-r--r--hw/block/vhost-user-blk.c612
-rw-r--r--hw/block/virtio-blk-common.c39
-rw-r--r--hw/block/virtio-blk.c1336
-rw-r--r--hw/block/xen-block.c1023
-rw-r--r--hw/block/xen_blkif.h147
33 files changed, 15012 insertions, 0 deletions
diff --git a/hw/block/Kconfig b/hw/block/Kconfig
new file mode 100644
index 00000000..9e8f28f9
--- /dev/null
+++ b/hw/block/Kconfig
@@ -0,0 +1,46 @@
+config FDC
+ bool
+
+config FDC_ISA
+ bool
+ depends on ISA_BUS
+ select FDC
+
+config FDC_SYSBUS
+ bool
+ select FDC
+
+config SSI_M25P80
+ bool
+
+config NAND
+ bool
+
+config PFLASH_CFI01
+ bool
+
+config PFLASH_CFI02
+ bool
+
+config ECC
+ bool
+
+config ONENAND
+ bool
+
+config TC58128
+ bool
+
+config VIRTIO_BLK
+ bool
+ default y
+ depends on VIRTIO
+
+config VHOST_USER_BLK
+ bool
+ # Only PCI devices are provided for now
+ default y if VIRTIO_PCI
+ depends on VIRTIO && VHOST_USER && LINUX
+
+config SWIM
+ bool
diff --git a/hw/block/block.c b/hw/block/block.c
new file mode 100644
index 00000000..f9c4fe67
--- /dev/null
+++ b/hw/block/block.c
@@ -0,0 +1,239 @@
+/*
+ * Common code for block device models
+ *
+ * Copyright (C) 2012 Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later. See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "sysemu/blockdev.h"
+#include "sysemu/block-backend.h"
+#include "hw/block/block.h"
+#include "qapi/error.h"
+#include "qapi/qapi-types-block.h"
+
+/*
+ * Read the entire contents of @blk into @buf.
+ * @blk's contents must be @size bytes, and @size must be at most
+ * BDRV_REQUEST_MAX_BYTES.
+ * On success, return true.
+ * On failure, store an error through @errp and return false.
+ * Note that the error messages do not identify the block backend.
+ * TODO Since callers don't either, this can result in confusing
+ * errors.
+ * This function not intended for actual block devices, which read on
+ * demand. It's for things like memory devices that (ab)use a block
+ * backend to provide persistence.
+ */
+bool blk_check_size_and_read_all(BlockBackend *blk, void *buf, hwaddr size,
+ Error **errp)
+{
+ int64_t blk_len;
+ int ret;
+
+ blk_len = blk_getlength(blk);
+ if (blk_len < 0) {
+ error_setg_errno(errp, -blk_len,
+ "can't get size of block backend");
+ return false;
+ }
+ if (blk_len != size) {
+ error_setg(errp, "device requires %" HWADDR_PRIu " bytes, "
+ "block backend provides %" PRIu64 " bytes",
+ size, blk_len);
+ return false;
+ }
+
+ /*
+ * We could loop for @size > BDRV_REQUEST_MAX_BYTES, but if we
+ * ever get to the point we want to read *gigabytes* here, we
+ * should probably rework the device to be more like an actual
+ * block device and read only on demand.
+ */
+ assert(size <= BDRV_REQUEST_MAX_BYTES);
+ ret = blk_pread(blk, 0, size, buf, 0);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "can't read block backend");
+ return false;
+ }
+ return true;
+}
+
+bool blkconf_blocksizes(BlockConf *conf, Error **errp)
+{
+ BlockBackend *blk = conf->blk;
+ BlockSizes blocksizes;
+ BlockDriverState *bs;
+ bool use_blocksizes;
+ bool use_bs;
+
+ switch (conf->backend_defaults) {
+ case ON_OFF_AUTO_AUTO:
+ use_blocksizes = !blk_probe_blocksizes(blk, &blocksizes);
+ use_bs = false;
+ break;
+
+ case ON_OFF_AUTO_ON:
+ use_blocksizes = !blk_probe_blocksizes(blk, &blocksizes);
+ bs = blk_bs(blk);
+ use_bs = bs;
+ break;
+
+ case ON_OFF_AUTO_OFF:
+ use_blocksizes = false;
+ use_bs = false;
+ break;
+
+ default:
+ abort();
+ }
+
+ /* fill in detected values if they are not defined via qemu command line */
+ if (!conf->physical_block_size) {
+ if (use_blocksizes) {
+ conf->physical_block_size = blocksizes.phys;
+ } else {
+ conf->physical_block_size = BDRV_SECTOR_SIZE;
+ }
+ }
+ if (!conf->logical_block_size) {
+ if (use_blocksizes) {
+ conf->logical_block_size = blocksizes.log;
+ } else {
+ conf->logical_block_size = BDRV_SECTOR_SIZE;
+ }
+ }
+ if (use_bs) {
+ if (!conf->opt_io_size) {
+ conf->opt_io_size = bs->bl.opt_transfer;
+ }
+ if (conf->discard_granularity == -1) {
+ if (bs->bl.pdiscard_alignment) {
+ conf->discard_granularity = bs->bl.pdiscard_alignment;
+ } else if (bs->bl.request_alignment != 1) {
+ conf->discard_granularity = bs->bl.request_alignment;
+ }
+ }
+ }
+
+ if (conf->logical_block_size > conf->physical_block_size) {
+ error_setg(errp,
+ "logical_block_size > physical_block_size not supported");
+ return false;
+ }
+
+ if (!QEMU_IS_ALIGNED(conf->min_io_size, conf->logical_block_size)) {
+ error_setg(errp,
+ "min_io_size must be a multiple of logical_block_size");
+ return false;
+ }
+
+ /*
+ * all devices which support min_io_size (scsi and virtio-blk) expose it to
+ * the guest as a uint16_t in units of logical blocks
+ */
+ if (conf->min_io_size / conf->logical_block_size > UINT16_MAX) {
+ error_setg(errp, "min_io_size must not exceed %u logical blocks",
+ UINT16_MAX);
+ return false;
+ }
+
+ if (!QEMU_IS_ALIGNED(conf->opt_io_size, conf->logical_block_size)) {
+ error_setg(errp,
+ "opt_io_size must be a multiple of logical_block_size");
+ return false;
+ }
+
+ if (conf->discard_granularity != -1 &&
+ !QEMU_IS_ALIGNED(conf->discard_granularity,
+ conf->logical_block_size)) {
+ error_setg(errp, "discard_granularity must be "
+ "a multiple of logical_block_size");
+ return false;
+ }
+
+ return true;
+}
+
+bool blkconf_apply_backend_options(BlockConf *conf, bool readonly,
+ bool resizable, Error **errp)
+{
+ BlockBackend *blk = conf->blk;
+ BlockdevOnError rerror, werror;
+ uint64_t perm, shared_perm;
+ bool wce;
+ int ret;
+
+ perm = BLK_PERM_CONSISTENT_READ;
+ if (!readonly) {
+ perm |= BLK_PERM_WRITE;
+ }
+
+ shared_perm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED;
+ if (resizable) {
+ shared_perm |= BLK_PERM_RESIZE;
+ }
+ if (conf->share_rw) {
+ shared_perm |= BLK_PERM_WRITE;
+ }
+
+ ret = blk_set_perm(blk, perm, shared_perm, errp);
+ if (ret < 0) {
+ return false;
+ }
+
+ switch (conf->wce) {
+ case ON_OFF_AUTO_ON: wce = true; break;
+ case ON_OFF_AUTO_OFF: wce = false; break;
+ case ON_OFF_AUTO_AUTO: wce = blk_enable_write_cache(blk); break;
+ default:
+ abort();
+ }
+
+ rerror = conf->rerror;
+ if (rerror == BLOCKDEV_ON_ERROR_AUTO) {
+ rerror = blk_get_on_error(blk, true);
+ }
+
+ werror = conf->werror;
+ if (werror == BLOCKDEV_ON_ERROR_AUTO) {
+ werror = blk_get_on_error(blk, false);
+ }
+
+ blk_set_enable_write_cache(blk, wce);
+ blk_set_on_error(blk, rerror, werror);
+
+ block_acct_setup(blk_get_stats(blk), conf->account_invalid,
+ conf->account_failed);
+ return true;
+}
+
+bool blkconf_geometry(BlockConf *conf, int *ptrans,
+ unsigned cyls_max, unsigned heads_max, unsigned secs_max,
+ Error **errp)
+{
+ if (!conf->cyls && !conf->heads && !conf->secs) {
+ hd_geometry_guess(conf->blk,
+ &conf->cyls, &conf->heads, &conf->secs,
+ ptrans);
+ } else if (ptrans && *ptrans == BIOS_ATA_TRANSLATION_AUTO) {
+ *ptrans = hd_bios_chs_auto_trans(conf->cyls, conf->heads, conf->secs);
+ }
+ if (conf->cyls || conf->heads || conf->secs) {
+ if (conf->cyls < 1 || conf->cyls > cyls_max) {
+ error_setg(errp, "cyls must be between 1 and %u", cyls_max);
+ return false;
+ }
+ if (conf->heads < 1 || conf->heads > heads_max) {
+ error_setg(errp, "heads must be between 1 and %u", heads_max);
+ return false;
+ }
+ if (conf->secs < 1 || conf->secs > secs_max) {
+ error_setg(errp, "secs must be between 1 and %u", secs_max);
+ return false;
+ }
+ }
+ return true;
+}
diff --git a/hw/block/cdrom.c b/hw/block/cdrom.c
new file mode 100644
index 00000000..c6bfa50a
--- /dev/null
+++ b/hw/block/cdrom.c
@@ -0,0 +1,155 @@
+/*
+ * QEMU ATAPI CD-ROM Emulator
+ *
+ * Copyright (c) 2006 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+/* ??? Most of the ATAPI emulation is still in ide.c. It should be moved
+ here. */
+
+#include "qemu/osdep.h"
+#include "hw/scsi/scsi.h"
+
+static void lba_to_msf(uint8_t *buf, int lba)
+{
+ lba += 150;
+ buf[0] = (lba / 75) / 60;
+ buf[1] = (lba / 75) % 60;
+ buf[2] = lba % 75;
+}
+
+/* same toc as bochs. Return -1 if error or the toc length */
+/* XXX: check this */
+int cdrom_read_toc(int nb_sectors, uint8_t *buf, int msf, int start_track)
+{
+ uint8_t *q;
+ int len;
+
+ if (start_track > 1 && start_track != 0xaa)
+ return -1;
+ q = buf + 2;
+ *q++ = 1; /* first session */
+ *q++ = 1; /* last session */
+ if (start_track <= 1) {
+ *q++ = 0; /* reserved */
+ *q++ = 0x14; /* ADR, control */
+ *q++ = 1; /* track number */
+ *q++ = 0; /* reserved */
+ if (msf) {
+ *q++ = 0; /* reserved */
+ lba_to_msf(q, 0);
+ q += 3;
+ } else {
+ /* sector 0 */
+ stl_be_p(q, 0);
+ q += 4;
+ }
+ }
+ /* lead out track */
+ *q++ = 0; /* reserved */
+ *q++ = 0x16; /* ADR, control */
+ *q++ = 0xaa; /* track number */
+ *q++ = 0; /* reserved */
+ if (msf) {
+ *q++ = 0; /* reserved */
+ lba_to_msf(q, nb_sectors);
+ q += 3;
+ } else {
+ stl_be_p(q, nb_sectors);
+ q += 4;
+ }
+ len = q - buf;
+ stw_be_p(buf, len - 2);
+ return len;
+}
+
+/* mostly same info as PearPc */
+int cdrom_read_toc_raw(int nb_sectors, uint8_t *buf, int msf, int session_num)
+{
+ uint8_t *q;
+ int len;
+
+ q = buf + 2;
+ *q++ = 1; /* first session */
+ *q++ = 1; /* last session */
+
+ *q++ = 1; /* session number */
+ *q++ = 0x14; /* data track */
+ *q++ = 0; /* track number */
+ *q++ = 0xa0; /* lead-in */
+ *q++ = 0; /* min */
+ *q++ = 0; /* sec */
+ *q++ = 0; /* frame */
+ *q++ = 0;
+ *q++ = 1; /* first track */
+ *q++ = 0x00; /* disk type */
+ *q++ = 0x00;
+
+ *q++ = 1; /* session number */
+ *q++ = 0x14; /* data track */
+ *q++ = 0; /* track number */
+ *q++ = 0xa1;
+ *q++ = 0; /* min */
+ *q++ = 0; /* sec */
+ *q++ = 0; /* frame */
+ *q++ = 0;
+ *q++ = 1; /* last track */
+ *q++ = 0x00;
+ *q++ = 0x00;
+
+ *q++ = 1; /* session number */
+ *q++ = 0x14; /* data track */
+ *q++ = 0; /* track number */
+ *q++ = 0xa2; /* lead-out */
+ *q++ = 0; /* min */
+ *q++ = 0; /* sec */
+ *q++ = 0; /* frame */
+ if (msf) {
+ *q++ = 0; /* reserved */
+ lba_to_msf(q, nb_sectors);
+ q += 3;
+ } else {
+ stl_be_p(q, nb_sectors);
+ q += 4;
+ }
+
+ *q++ = 1; /* session number */
+ *q++ = 0x14; /* ADR, control */
+ *q++ = 0; /* track number */
+ *q++ = 1; /* point */
+ *q++ = 0; /* min */
+ *q++ = 0; /* sec */
+ *q++ = 0; /* frame */
+ if (msf) {
+ *q++ = 0;
+ lba_to_msf(q, 0);
+ q += 3;
+ } else {
+ *q++ = 0;
+ *q++ = 0;
+ *q++ = 0;
+ *q++ = 0;
+ }
+
+ len = q - buf;
+ stw_be_p(buf, len - 2);
+ return len;
+}
diff --git a/hw/block/dataplane/meson.build b/hw/block/dataplane/meson.build
new file mode 100644
index 00000000..12c6a264
--- /dev/null
+++ b/hw/block/dataplane/meson.build
@@ -0,0 +1,2 @@
+specific_ss.add(when: 'CONFIG_VIRTIO_BLK', if_true: files('virtio-blk.c'))
+specific_ss.add(when: 'CONFIG_XEN', if_true: files('xen-block.c'))
diff --git a/hw/block/dataplane/trace-events b/hw/block/dataplane/trace-events
new file mode 100644
index 00000000..38fc3e75
--- /dev/null
+++ b/hw/block/dataplane/trace-events
@@ -0,0 +1,5 @@
+# See docs/devel/tracing.rst for syntax documentation.
+
+# virtio-blk.c
+virtio_blk_data_plane_start(void *s) "dataplane %p"
+virtio_blk_data_plane_stop(void *s) "dataplane %p"
diff --git a/hw/block/dataplane/trace.h b/hw/block/dataplane/trace.h
new file mode 100644
index 00000000..240cc598
--- /dev/null
+++ b/hw/block/dataplane/trace.h
@@ -0,0 +1 @@
+#include "trace/trace-hw_block_dataplane.h"
diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
new file mode 100644
index 00000000..26f965ca
--- /dev/null
+++ b/hw/block/dataplane/virtio-blk.c
@@ -0,0 +1,362 @@
+/*
+ * Dedicated thread for virtio-blk I/O processing
+ *
+ * Copyright 2012 IBM, Corp.
+ * Copyright 2012 Red Hat, Inc. and/or its affiliates
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "trace.h"
+#include "qemu/iov.h"
+#include "qemu/main-loop.h"
+#include "qemu/thread.h"
+#include "qemu/error-report.h"
+#include "hw/virtio/virtio-access.h"
+#include "hw/virtio/virtio-blk.h"
+#include "virtio-blk.h"
+#include "block/aio.h"
+#include "hw/virtio/virtio-bus.h"
+#include "qom/object_interfaces.h"
+
+struct VirtIOBlockDataPlane {
+ bool starting;
+ bool stopping;
+
+ VirtIOBlkConf *conf;
+ VirtIODevice *vdev;
+ QEMUBH *bh; /* bh for guest notification */
+ unsigned long *batch_notify_vqs;
+ bool batch_notifications;
+
+ /* Note that these EventNotifiers are assigned by value. This is
+ * fine as long as you do not call event_notifier_cleanup on them
+ * (because you don't own the file descriptor or handle; you just
+ * use it).
+ */
+ IOThread *iothread;
+ AioContext *ctx;
+};
+
+/* Raise an interrupt to signal guest, if necessary */
+void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s, VirtQueue *vq)
+{
+ if (s->batch_notifications) {
+ set_bit(virtio_get_queue_index(vq), s->batch_notify_vqs);
+ qemu_bh_schedule(s->bh);
+ } else {
+ virtio_notify_irqfd(s->vdev, vq);
+ }
+}
+
+static void notify_guest_bh(void *opaque)
+{
+ VirtIOBlockDataPlane *s = opaque;
+ unsigned nvqs = s->conf->num_queues;
+ unsigned long bitmap[BITS_TO_LONGS(nvqs)];
+ unsigned j;
+
+ memcpy(bitmap, s->batch_notify_vqs, sizeof(bitmap));
+ memset(s->batch_notify_vqs, 0, sizeof(bitmap));
+
+ for (j = 0; j < nvqs; j += BITS_PER_LONG) {
+ unsigned long bits = bitmap[j / BITS_PER_LONG];
+
+ while (bits != 0) {
+ unsigned i = j + ctzl(bits);
+ VirtQueue *vq = virtio_get_queue(s->vdev, i);
+
+ virtio_notify_irqfd(s->vdev, vq);
+
+ bits &= bits - 1; /* clear right-most bit */
+ }
+ }
+}
+
+/* Context: QEMU global mutex held */
+bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
+ VirtIOBlockDataPlane **dataplane,
+ Error **errp)
+{
+ VirtIOBlockDataPlane *s;
+ BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+ VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+
+ *dataplane = NULL;
+
+ if (conf->iothread) {
+ if (!k->set_guest_notifiers || !k->ioeventfd_assign) {
+ error_setg(errp,
+ "device is incompatible with iothread "
+ "(transport does not support notifiers)");
+ return false;
+ }
+ if (!virtio_device_ioeventfd_enabled(vdev)) {
+ error_setg(errp, "ioeventfd is required for iothread");
+ return false;
+ }
+
+ /* If dataplane is (re-)enabled while the guest is running there could
+ * be block jobs that can conflict.
+ */
+ if (blk_op_is_blocked(conf->conf.blk, BLOCK_OP_TYPE_DATAPLANE, errp)) {
+ error_prepend(errp, "cannot start virtio-blk dataplane: ");
+ return false;
+ }
+ }
+ /* Don't try if transport does not support notifiers. */
+ if (!virtio_device_ioeventfd_enabled(vdev)) {
+ return false;
+ }
+
+ s = g_new0(VirtIOBlockDataPlane, 1);
+ s->vdev = vdev;
+ s->conf = conf;
+
+ if (conf->iothread) {
+ s->iothread = conf->iothread;
+ object_ref(OBJECT(s->iothread));
+ s->ctx = iothread_get_aio_context(s->iothread);
+ } else {
+ s->ctx = qemu_get_aio_context();
+ }
+ s->bh = aio_bh_new(s->ctx, notify_guest_bh, s);
+ s->batch_notify_vqs = bitmap_new(conf->num_queues);
+
+ *dataplane = s;
+
+ return true;
+}
+
+/* Context: QEMU global mutex held */
+void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
+{
+ VirtIOBlock *vblk;
+
+ if (!s) {
+ return;
+ }
+
+ vblk = VIRTIO_BLK(s->vdev);
+ assert(!vblk->dataplane_started);
+ g_free(s->batch_notify_vqs);
+ qemu_bh_delete(s->bh);
+ if (s->iothread) {
+ object_unref(OBJECT(s->iothread));
+ }
+ g_free(s);
+}
+
+/* Context: QEMU global mutex held */
+int virtio_blk_data_plane_start(VirtIODevice *vdev)
+{
+ VirtIOBlock *vblk = VIRTIO_BLK(vdev);
+ VirtIOBlockDataPlane *s = vblk->dataplane;
+ BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vblk)));
+ VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+ AioContext *old_context;
+ unsigned i;
+ unsigned nvqs = s->conf->num_queues;
+ Error *local_err = NULL;
+ int r;
+
+ if (vblk->dataplane_started || s->starting) {
+ return 0;
+ }
+
+ s->starting = true;
+
+ if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
+ s->batch_notifications = true;
+ } else {
+ s->batch_notifications = false;
+ }
+
+ /* Set up guest notifier (irq) */
+ r = k->set_guest_notifiers(qbus->parent, nvqs, true);
+ if (r != 0) {
+ error_report("virtio-blk failed to set guest notifier (%d), "
+ "ensure -accel kvm is set.", r);
+ goto fail_guest_notifiers;
+ }
+
+ /*
+ * Batch all the host notifiers in a single transaction to avoid
+ * quadratic time complexity in address_space_update_ioeventfds().
+ */
+ memory_region_transaction_begin();
+
+ /* Set up virtqueue notify */
+ for (i = 0; i < nvqs; i++) {
+ r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, true);
+ if (r != 0) {
+ int j = i;
+
+ fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r);
+ while (i--) {
+ virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
+ }
+
+ /*
+ * The transaction expects the ioeventfds to be open when it
+ * commits. Do it now, before the cleanup loop.
+ */
+ memory_region_transaction_commit();
+
+ while (j--) {
+ virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), j);
+ }
+ goto fail_host_notifiers;
+ }
+ }
+
+ memory_region_transaction_commit();
+
+ /*
+ * These fields are visible to the IOThread so we rely on implicit barriers
+ * in aio_context_acquire() on the write side and aio_notify_accept() on
+ * the read side.
+ */
+ s->starting = false;
+ vblk->dataplane_started = true;
+ trace_virtio_blk_data_plane_start(s);
+
+ old_context = blk_get_aio_context(s->conf->conf.blk);
+ aio_context_acquire(old_context);
+ r = blk_set_aio_context(s->conf->conf.blk, s->ctx, &local_err);
+ aio_context_release(old_context);
+ if (r < 0) {
+ error_report_err(local_err);
+ goto fail_aio_context;
+ }
+
+ /* Process queued requests before the ones in vring */
+ virtio_blk_process_queued_requests(vblk, false);
+
+ /* Kick right away to begin processing requests already in vring */
+ for (i = 0; i < nvqs; i++) {
+ VirtQueue *vq = virtio_get_queue(s->vdev, i);
+
+ event_notifier_set(virtio_queue_get_host_notifier(vq));
+ }
+
+ /* Get this show started by hooking up our callbacks */
+ aio_context_acquire(s->ctx);
+ for (i = 0; i < nvqs; i++) {
+ VirtQueue *vq = virtio_get_queue(s->vdev, i);
+
+ virtio_queue_aio_attach_host_notifier(vq, s->ctx);
+ }
+ aio_context_release(s->ctx);
+ return 0;
+
+ fail_aio_context:
+ memory_region_transaction_begin();
+
+ for (i = 0; i < nvqs; i++) {
+ virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
+ }
+
+ memory_region_transaction_commit();
+
+ for (i = 0; i < nvqs; i++) {
+ virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i);
+ }
+ fail_host_notifiers:
+ k->set_guest_notifiers(qbus->parent, nvqs, false);
+ fail_guest_notifiers:
+ /*
+ * If we failed to set up the guest notifiers queued requests will be
+ * processed on the main context.
+ */
+ virtio_blk_process_queued_requests(vblk, false);
+ vblk->dataplane_disabled = true;
+ s->starting = false;
+ vblk->dataplane_started = true;
+ return -ENOSYS;
+}
+
+/* Stop notifications for new requests from guest.
+ *
+ * Context: BH in IOThread
+ */
+static void virtio_blk_data_plane_stop_bh(void *opaque)
+{
+ VirtIOBlockDataPlane *s = opaque;
+ unsigned i;
+
+ for (i = 0; i < s->conf->num_queues; i++) {
+ VirtQueue *vq = virtio_get_queue(s->vdev, i);
+
+ virtio_queue_aio_detach_host_notifier(vq, s->ctx);
+ }
+}
+
+/* Context: QEMU global mutex held */
+void virtio_blk_data_plane_stop(VirtIODevice *vdev)
+{
+ VirtIOBlock *vblk = VIRTIO_BLK(vdev);
+ VirtIOBlockDataPlane *s = vblk->dataplane;
+ BusState *qbus = qdev_get_parent_bus(DEVICE(vblk));
+ VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+ unsigned i;
+ unsigned nvqs = s->conf->num_queues;
+
+ if (!vblk->dataplane_started || s->stopping) {
+ return;
+ }
+
+ /* Better luck next time. */
+ if (vblk->dataplane_disabled) {
+ vblk->dataplane_disabled = false;
+ vblk->dataplane_started = false;
+ return;
+ }
+ s->stopping = true;
+ trace_virtio_blk_data_plane_stop(s);
+
+ aio_context_acquire(s->ctx);
+ aio_wait_bh_oneshot(s->ctx, virtio_blk_data_plane_stop_bh, s);
+
+ /* Drain and try to switch bs back to the QEMU main loop. If other users
+ * keep the BlockBackend in the iothread, that's ok */
+ blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context(), NULL);
+
+ aio_context_release(s->ctx);
+
+ /*
+ * Batch all the host notifiers in a single transaction to avoid
+ * quadratic time complexity in address_space_update_ioeventfds().
+ */
+ memory_region_transaction_begin();
+
+ for (i = 0; i < nvqs; i++) {
+ virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
+ }
+
+ /*
+ * The transaction expects the ioeventfds to be open when it
+ * commits. Do it now, before the cleanup loop.
+ */
+ memory_region_transaction_commit();
+
+ for (i = 0; i < nvqs; i++) {
+ virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i);
+ }
+
+ qemu_bh_cancel(s->bh);
+ notify_guest_bh(s); /* final chance to notify guest */
+
+ /* Clean up guest notifier (irq) */
+ k->set_guest_notifiers(qbus->parent, nvqs, false);
+
+ vblk->dataplane_started = false;
+ s->stopping = false;
+}
diff --git a/hw/block/dataplane/virtio-blk.h b/hw/block/dataplane/virtio-blk.h
new file mode 100644
index 00000000..5e18bb99
--- /dev/null
+++ b/hw/block/dataplane/virtio-blk.h
@@ -0,0 +1,31 @@
+/*
+ * Dedicated thread for virtio-blk I/O processing
+ *
+ * Copyright 2012 IBM, Corp.
+ * Copyright 2012 Red Hat, Inc. and/or its affiliates
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef HW_DATAPLANE_VIRTIO_BLK_H
+#define HW_DATAPLANE_VIRTIO_BLK_H
+
+#include "hw/virtio/virtio.h"
+
+typedef struct VirtIOBlockDataPlane VirtIOBlockDataPlane;
+
+bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
+ VirtIOBlockDataPlane **dataplane,
+ Error **errp);
+void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s);
+void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s, VirtQueue *vq);
+
+int virtio_blk_data_plane_start(VirtIODevice *vdev);
+void virtio_blk_data_plane_stop(VirtIODevice *vdev);
+
+#endif /* HW_DATAPLANE_VIRTIO_BLK_H */
diff --git a/hw/block/dataplane/xen-block.c b/hw/block/dataplane/xen-block.c
new file mode 100644
index 00000000..2785b9e8
--- /dev/null
+++ b/hw/block/dataplane/xen-block.c
@@ -0,0 +1,829 @@
+/*
+ * Copyright (c) 2018 Citrix Systems Inc.
+ * (c) Gerd Hoffmann <kraxel@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; under version 2 of the License.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/error-report.h"
+#include "qemu/main-loop.h"
+#include "qemu/memalign.h"
+#include "qapi/error.h"
+#include "hw/xen/xen_common.h"
+#include "hw/block/xen_blkif.h"
+#include "sysemu/block-backend.h"
+#include "sysemu/iothread.h"
+#include "xen-block.h"
+
+typedef struct XenBlockRequest {
+ blkif_request_t req;
+ int16_t status;
+ off_t start;
+ QEMUIOVector v;
+ void *buf;
+ size_t size;
+ int presync;
+ int aio_inflight;
+ int aio_errors;
+ XenBlockDataPlane *dataplane;
+ QLIST_ENTRY(XenBlockRequest) list;
+ BlockAcctCookie acct;
+} XenBlockRequest;
+
+struct XenBlockDataPlane {
+ XenDevice *xendev;
+ XenEventChannel *event_channel;
+ unsigned int *ring_ref;
+ unsigned int nr_ring_ref;
+ void *sring;
+ int protocol;
+ blkif_back_rings_t rings;
+ int more_work;
+ QLIST_HEAD(inflight_head, XenBlockRequest) inflight;
+ QLIST_HEAD(freelist_head, XenBlockRequest) freelist;
+ int requests_total;
+ int requests_inflight;
+ unsigned int max_requests;
+ BlockBackend *blk;
+ unsigned int sector_size;
+ QEMUBH *bh;
+ IOThread *iothread;
+ AioContext *ctx;
+};
+
+static int xen_block_send_response(XenBlockRequest *request);
+
+static void reset_request(XenBlockRequest *request)
+{
+ memset(&request->req, 0, sizeof(request->req));
+ request->status = 0;
+ request->start = 0;
+ request->size = 0;
+ request->presync = 0;
+
+ request->aio_inflight = 0;
+ request->aio_errors = 0;
+
+ request->dataplane = NULL;
+ memset(&request->list, 0, sizeof(request->list));
+ memset(&request->acct, 0, sizeof(request->acct));
+
+ qemu_iovec_reset(&request->v);
+}
+
+static XenBlockRequest *xen_block_start_request(XenBlockDataPlane *dataplane)
+{
+ XenBlockRequest *request = NULL;
+
+ if (QLIST_EMPTY(&dataplane->freelist)) {
+ if (dataplane->requests_total >= dataplane->max_requests) {
+ goto out;
+ }
+ /* allocate new struct */
+ request = g_malloc0(sizeof(*request));
+ request->dataplane = dataplane;
+ /*
+ * We cannot need more pages per requests than this, and since we
+ * re-use requests, allocate the memory once here. It will be freed
+ * xen_block_dataplane_destroy() when the request list is freed.
+ */
+ request->buf = qemu_memalign(XC_PAGE_SIZE,
+ BLKIF_MAX_SEGMENTS_PER_REQUEST *
+ XC_PAGE_SIZE);
+ dataplane->requests_total++;
+ qemu_iovec_init(&request->v, 1);
+ } else {
+ /* get one from freelist */
+ request = QLIST_FIRST(&dataplane->freelist);
+ QLIST_REMOVE(request, list);
+ }
+ QLIST_INSERT_HEAD(&dataplane->inflight, request, list);
+ dataplane->requests_inflight++;
+
+out:
+ return request;
+}
+
+static void xen_block_complete_request(XenBlockRequest *request)
+{
+ XenBlockDataPlane *dataplane = request->dataplane;
+
+ if (xen_block_send_response(request)) {
+ Error *local_err = NULL;
+
+ xen_device_notify_event_channel(dataplane->xendev,
+ dataplane->event_channel,
+ &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ }
+ }
+
+ QLIST_REMOVE(request, list);
+ dataplane->requests_inflight--;
+ reset_request(request);
+ request->dataplane = dataplane;
+ QLIST_INSERT_HEAD(&dataplane->freelist, request, list);
+}
+
+/*
+ * translate request into iovec + start offset
+ * do sanity checks along the way
+ */
+static int xen_block_parse_request(XenBlockRequest *request)
+{
+ XenBlockDataPlane *dataplane = request->dataplane;
+ size_t len;
+ int i;
+
+ switch (request->req.operation) {
+ case BLKIF_OP_READ:
+ break;
+ case BLKIF_OP_FLUSH_DISKCACHE:
+ request->presync = 1;
+ if (!request->req.nr_segments) {
+ return 0;
+ }
+ /* fall through */
+ case BLKIF_OP_WRITE:
+ break;
+ case BLKIF_OP_DISCARD:
+ return 0;
+ default:
+ error_report("error: unknown operation (%d)", request->req.operation);
+ goto err;
+ };
+
+ if (request->req.operation != BLKIF_OP_READ &&
+ !blk_is_writable(dataplane->blk)) {
+ error_report("error: write req for ro device");
+ goto err;
+ }
+
+ request->start = request->req.sector_number * dataplane->sector_size;
+ for (i = 0; i < request->req.nr_segments; i++) {
+ if (i == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+ error_report("error: nr_segments too big");
+ goto err;
+ }
+ if (request->req.seg[i].first_sect > request->req.seg[i].last_sect) {
+ error_report("error: first > last sector");
+ goto err;
+ }
+ if (request->req.seg[i].last_sect * dataplane->sector_size >=
+ XC_PAGE_SIZE) {
+ error_report("error: page crossing");
+ goto err;
+ }
+
+ len = (request->req.seg[i].last_sect -
+ request->req.seg[i].first_sect + 1) * dataplane->sector_size;
+ request->size += len;
+ }
+ if (request->start + request->size > blk_getlength(dataplane->blk)) {
+ error_report("error: access beyond end of file");
+ goto err;
+ }
+ return 0;
+
+err:
+ request->status = BLKIF_RSP_ERROR;
+ return -1;
+}
+
+static int xen_block_copy_request(XenBlockRequest *request)
+{
+ XenBlockDataPlane *dataplane = request->dataplane;
+ XenDevice *xendev = dataplane->xendev;
+ XenDeviceGrantCopySegment segs[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ int i, count;
+ bool to_domain = (request->req.operation == BLKIF_OP_READ);
+ void *virt = request->buf;
+ Error *local_err = NULL;
+
+ if (request->req.nr_segments == 0) {
+ return 0;
+ }
+
+ count = request->req.nr_segments;
+
+ for (i = 0; i < count; i++) {
+ if (to_domain) {
+ segs[i].dest.foreign.ref = request->req.seg[i].gref;
+ segs[i].dest.foreign.offset = request->req.seg[i].first_sect *
+ dataplane->sector_size;
+ segs[i].source.virt = virt;
+ } else {
+ segs[i].source.foreign.ref = request->req.seg[i].gref;
+ segs[i].source.foreign.offset = request->req.seg[i].first_sect *
+ dataplane->sector_size;
+ segs[i].dest.virt = virt;
+ }
+ segs[i].len = (request->req.seg[i].last_sect -
+ request->req.seg[i].first_sect + 1) *
+ dataplane->sector_size;
+ virt += segs[i].len;
+ }
+
+ xen_device_copy_grant_refs(xendev, to_domain, segs, count, &local_err);
+
+ if (local_err) {
+ error_reportf_err(local_err, "failed to copy data: ");
+
+ request->aio_errors++;
+ return -1;
+ }
+
+ return 0;
+}
+
+static int xen_block_do_aio(XenBlockRequest *request);
+
+static void xen_block_complete_aio(void *opaque, int ret)
+{
+ XenBlockRequest *request = opaque;
+ XenBlockDataPlane *dataplane = request->dataplane;
+
+ aio_context_acquire(dataplane->ctx);
+
+ if (ret != 0) {
+ error_report("%s I/O error",
+ request->req.operation == BLKIF_OP_READ ?
+ "read" : "write");
+ request->aio_errors++;
+ }
+
+ request->aio_inflight--;
+ if (request->presync) {
+ request->presync = 0;
+ xen_block_do_aio(request);
+ goto done;
+ }
+ if (request->aio_inflight > 0) {
+ goto done;
+ }
+
+ switch (request->req.operation) {
+ case BLKIF_OP_READ:
+ /* in case of failure request->aio_errors is increased */
+ if (ret == 0) {
+ xen_block_copy_request(request);
+ }
+ break;
+ case BLKIF_OP_WRITE:
+ case BLKIF_OP_FLUSH_DISKCACHE:
+ default:
+ break;
+ }
+
+ request->status = request->aio_errors ? BLKIF_RSP_ERROR : BLKIF_RSP_OKAY;
+
+ switch (request->req.operation) {
+ case BLKIF_OP_WRITE:
+ case BLKIF_OP_FLUSH_DISKCACHE:
+ if (!request->req.nr_segments) {
+ break;
+ }
+ /* fall through */
+ case BLKIF_OP_READ:
+ if (request->status == BLKIF_RSP_OKAY) {
+ block_acct_done(blk_get_stats(dataplane->blk), &request->acct);
+ } else {
+ block_acct_failed(blk_get_stats(dataplane->blk), &request->acct);
+ }
+ break;
+ case BLKIF_OP_DISCARD:
+ default:
+ break;
+ }
+
+ xen_block_complete_request(request);
+
+ if (dataplane->more_work) {
+ qemu_bh_schedule(dataplane->bh);
+ }
+
+done:
+ aio_context_release(dataplane->ctx);
+}
+
+static bool xen_block_split_discard(XenBlockRequest *request,
+ blkif_sector_t sector_number,
+ uint64_t nr_sectors)
+{
+ XenBlockDataPlane *dataplane = request->dataplane;
+ int64_t byte_offset;
+ int byte_chunk;
+ uint64_t byte_remaining;
+ uint64_t sec_start = sector_number;
+ uint64_t sec_count = nr_sectors;
+
+ /* Wrap around, or overflowing byte limit? */
+ if (sec_start + sec_count < sec_count ||
+ sec_start + sec_count > INT64_MAX / dataplane->sector_size) {
+ return false;
+ }
+
+ byte_offset = sec_start * dataplane->sector_size;
+ byte_remaining = sec_count * dataplane->sector_size;
+
+ do {
+ byte_chunk = byte_remaining > BDRV_REQUEST_MAX_BYTES ?
+ BDRV_REQUEST_MAX_BYTES : byte_remaining;
+ request->aio_inflight++;
+ blk_aio_pdiscard(dataplane->blk, byte_offset, byte_chunk,
+ xen_block_complete_aio, request);
+ byte_remaining -= byte_chunk;
+ byte_offset += byte_chunk;
+ } while (byte_remaining > 0);
+
+ return true;
+}
+
+static int xen_block_do_aio(XenBlockRequest *request)
+{
+ XenBlockDataPlane *dataplane = request->dataplane;
+
+ if (request->req.nr_segments &&
+ (request->req.operation == BLKIF_OP_WRITE ||
+ request->req.operation == BLKIF_OP_FLUSH_DISKCACHE) &&
+ xen_block_copy_request(request)) {
+ goto err;
+ }
+
+ request->aio_inflight++;
+ if (request->presync) {
+ blk_aio_flush(request->dataplane->blk, xen_block_complete_aio,
+ request);
+ return 0;
+ }
+
+ switch (request->req.operation) {
+ case BLKIF_OP_READ:
+ qemu_iovec_add(&request->v, request->buf, request->size);
+ block_acct_start(blk_get_stats(dataplane->blk), &request->acct,
+ request->v.size, BLOCK_ACCT_READ);
+ request->aio_inflight++;
+ blk_aio_preadv(dataplane->blk, request->start, &request->v, 0,
+ xen_block_complete_aio, request);
+ break;
+ case BLKIF_OP_WRITE:
+ case BLKIF_OP_FLUSH_DISKCACHE:
+ if (!request->req.nr_segments) {
+ break;
+ }
+
+ qemu_iovec_add(&request->v, request->buf, request->size);
+ block_acct_start(blk_get_stats(dataplane->blk), &request->acct,
+ request->v.size,
+ request->req.operation == BLKIF_OP_WRITE ?
+ BLOCK_ACCT_WRITE : BLOCK_ACCT_FLUSH);
+ request->aio_inflight++;
+ blk_aio_pwritev(dataplane->blk, request->start, &request->v, 0,
+ xen_block_complete_aio, request);
+ break;
+ case BLKIF_OP_DISCARD:
+ {
+ struct blkif_request_discard *req = (void *)&request->req;
+ if (!xen_block_split_discard(request, req->sector_number,
+ req->nr_sectors)) {
+ goto err;
+ }
+ break;
+ }
+ default:
+ /* unknown operation (shouldn't happen -- parse catches this) */
+ goto err;
+ }
+
+ xen_block_complete_aio(request, 0);
+
+ return 0;
+
+err:
+ request->status = BLKIF_RSP_ERROR;
+ xen_block_complete_request(request);
+ return -1;
+}
+
+static int xen_block_send_response(XenBlockRequest *request)
+{
+ XenBlockDataPlane *dataplane = request->dataplane;
+ int send_notify = 0;
+ int have_requests = 0;
+ blkif_response_t *resp;
+
+ /* Place on the response ring for the relevant domain. */
+ switch (dataplane->protocol) {
+ case BLKIF_PROTOCOL_NATIVE:
+ resp = (blkif_response_t *)RING_GET_RESPONSE(
+ &dataplane->rings.native,
+ dataplane->rings.native.rsp_prod_pvt);
+ break;
+ case BLKIF_PROTOCOL_X86_32:
+ resp = (blkif_response_t *)RING_GET_RESPONSE(
+ &dataplane->rings.x86_32_part,
+ dataplane->rings.x86_32_part.rsp_prod_pvt);
+ break;
+ case BLKIF_PROTOCOL_X86_64:
+ resp = (blkif_response_t *)RING_GET_RESPONSE(
+ &dataplane->rings.x86_64_part,
+ dataplane->rings.x86_64_part.rsp_prod_pvt);
+ break;
+ default:
+ return 0;
+ }
+
+ resp->id = request->req.id;
+ resp->operation = request->req.operation;
+ resp->status = request->status;
+
+ dataplane->rings.common.rsp_prod_pvt++;
+
+ RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&dataplane->rings.common,
+ send_notify);
+ if (dataplane->rings.common.rsp_prod_pvt ==
+ dataplane->rings.common.req_cons) {
+ /*
+ * Tail check for pending requests. Allows frontend to avoid
+ * notifications if requests are already in flight (lower
+ * overheads and promotes batching).
+ */
+ RING_FINAL_CHECK_FOR_REQUESTS(&dataplane->rings.common,
+ have_requests);
+ } else if (RING_HAS_UNCONSUMED_REQUESTS(&dataplane->rings.common)) {
+ have_requests = 1;
+ }
+
+ if (have_requests) {
+ dataplane->more_work++;
+ }
+ return send_notify;
+}
+
+static int xen_block_get_request(XenBlockDataPlane *dataplane,
+ XenBlockRequest *request, RING_IDX rc)
+{
+ switch (dataplane->protocol) {
+ case BLKIF_PROTOCOL_NATIVE: {
+ blkif_request_t *req =
+ RING_GET_REQUEST(&dataplane->rings.native, rc);
+
+ memcpy(&request->req, req, sizeof(request->req));
+ break;
+ }
+ case BLKIF_PROTOCOL_X86_32: {
+ blkif_x86_32_request_t *req =
+ RING_GET_REQUEST(&dataplane->rings.x86_32_part, rc);
+
+ blkif_get_x86_32_req(&request->req, req);
+ break;
+ }
+ case BLKIF_PROTOCOL_X86_64: {
+ blkif_x86_64_request_t *req =
+ RING_GET_REQUEST(&dataplane->rings.x86_64_part, rc);
+
+ blkif_get_x86_64_req(&request->req, req);
+ break;
+ }
+ }
+ /* Prevent the compiler from accessing the on-ring fields instead. */
+ barrier();
+ return 0;
+}
+
+/*
+ * Threshold of in-flight requests above which we will start using
+ * blk_io_plug()/blk_io_unplug() to batch requests.
+ */
+#define IO_PLUG_THRESHOLD 1
+
+static bool xen_block_handle_requests(XenBlockDataPlane *dataplane)
+{
+ RING_IDX rc, rp;
+ XenBlockRequest *request;
+ int inflight_atstart = dataplane->requests_inflight;
+ int batched = 0;
+ bool done_something = false;
+
+ dataplane->more_work = 0;
+
+ rc = dataplane->rings.common.req_cons;
+ rp = dataplane->rings.common.sring->req_prod;
+ xen_rmb(); /* Ensure we see queued requests up to 'rp'. */
+
+ /*
+ * If there was more than IO_PLUG_THRESHOLD requests in flight
+ * when we got here, this is an indication that there the bottleneck
+ * is below us, so it's worth beginning to batch up I/O requests
+ * rather than submitting them immediately. The maximum number
+ * of requests we're willing to batch is the number already in
+ * flight, so it can grow up to max_requests when the bottleneck
+ * is below us.
+ */
+ if (inflight_atstart > IO_PLUG_THRESHOLD) {
+ blk_io_plug(dataplane->blk);
+ }
+ while (rc != rp) {
+ /* pull request from ring */
+ if (RING_REQUEST_CONS_OVERFLOW(&dataplane->rings.common, rc)) {
+ break;
+ }
+ request = xen_block_start_request(dataplane);
+ if (request == NULL) {
+ dataplane->more_work++;
+ break;
+ }
+ xen_block_get_request(dataplane, request, rc);
+ dataplane->rings.common.req_cons = ++rc;
+ done_something = true;
+
+ /* parse them */
+ if (xen_block_parse_request(request) != 0) {
+ switch (request->req.operation) {
+ case BLKIF_OP_READ:
+ block_acct_invalid(blk_get_stats(dataplane->blk),
+ BLOCK_ACCT_READ);
+ break;
+ case BLKIF_OP_WRITE:
+ block_acct_invalid(blk_get_stats(dataplane->blk),
+ BLOCK_ACCT_WRITE);
+ break;
+ case BLKIF_OP_FLUSH_DISKCACHE:
+ block_acct_invalid(blk_get_stats(dataplane->blk),
+ BLOCK_ACCT_FLUSH);
+ default:
+ break;
+ };
+
+ xen_block_complete_request(request);
+ continue;
+ }
+
+ if (inflight_atstart > IO_PLUG_THRESHOLD &&
+ batched >= inflight_atstart) {
+ blk_io_unplug(dataplane->blk);
+ }
+ xen_block_do_aio(request);
+ if (inflight_atstart > IO_PLUG_THRESHOLD) {
+ if (batched >= inflight_atstart) {
+ blk_io_plug(dataplane->blk);
+ batched = 0;
+ } else {
+ batched++;
+ }
+ }
+ }
+ if (inflight_atstart > IO_PLUG_THRESHOLD) {
+ blk_io_unplug(dataplane->blk);
+ }
+
+ return done_something;
+}
+
+static void xen_block_dataplane_bh(void *opaque)
+{
+ XenBlockDataPlane *dataplane = opaque;
+
+ aio_context_acquire(dataplane->ctx);
+ xen_block_handle_requests(dataplane);
+ aio_context_release(dataplane->ctx);
+}
+
+static bool xen_block_dataplane_event(void *opaque)
+{
+ XenBlockDataPlane *dataplane = opaque;
+
+ return xen_block_handle_requests(dataplane);
+}
+
+XenBlockDataPlane *xen_block_dataplane_create(XenDevice *xendev,
+ BlockBackend *blk,
+ unsigned int sector_size,
+ IOThread *iothread)
+{
+ XenBlockDataPlane *dataplane = g_new0(XenBlockDataPlane, 1);
+
+ dataplane->xendev = xendev;
+ dataplane->blk = blk;
+ dataplane->sector_size = sector_size;
+
+ QLIST_INIT(&dataplane->inflight);
+ QLIST_INIT(&dataplane->freelist);
+
+ if (iothread) {
+ dataplane->iothread = iothread;
+ object_ref(OBJECT(dataplane->iothread));
+ dataplane->ctx = iothread_get_aio_context(dataplane->iothread);
+ } else {
+ dataplane->ctx = qemu_get_aio_context();
+ }
+ dataplane->bh = aio_bh_new(dataplane->ctx, xen_block_dataplane_bh,
+ dataplane);
+
+ return dataplane;
+}
+
+void xen_block_dataplane_destroy(XenBlockDataPlane *dataplane)
+{
+ XenBlockRequest *request;
+
+ if (!dataplane) {
+ return;
+ }
+
+ while (!QLIST_EMPTY(&dataplane->freelist)) {
+ request = QLIST_FIRST(&dataplane->freelist);
+ QLIST_REMOVE(request, list);
+ qemu_iovec_destroy(&request->v);
+ qemu_vfree(request->buf);
+ g_free(request);
+ }
+
+ qemu_bh_delete(dataplane->bh);
+ if (dataplane->iothread) {
+ object_unref(OBJECT(dataplane->iothread));
+ }
+
+ g_free(dataplane);
+}
+
+void xen_block_dataplane_stop(XenBlockDataPlane *dataplane)
+{
+ XenDevice *xendev;
+
+ if (!dataplane) {
+ return;
+ }
+
+ xendev = dataplane->xendev;
+
+ aio_context_acquire(dataplane->ctx);
+ if (dataplane->event_channel) {
+ /* Only reason for failure is a NULL channel */
+ xen_device_set_event_channel_context(xendev, dataplane->event_channel,
+ qemu_get_aio_context(),
+ &error_abort);
+ }
+ /* Xen doesn't have multiple users for nodes, so this can't fail */
+ blk_set_aio_context(dataplane->blk, qemu_get_aio_context(), &error_abort);
+ aio_context_release(dataplane->ctx);
+
+ /*
+ * Now that the context has been moved onto the main thread, cancel
+ * further processing.
+ */
+ qemu_bh_cancel(dataplane->bh);
+
+ if (dataplane->event_channel) {
+ Error *local_err = NULL;
+
+ xen_device_unbind_event_channel(xendev, dataplane->event_channel,
+ &local_err);
+ dataplane->event_channel = NULL;
+
+ if (local_err) {
+ error_report_err(local_err);
+ }
+ }
+
+ if (dataplane->sring) {
+ Error *local_err = NULL;
+
+ xen_device_unmap_grant_refs(xendev, dataplane->sring,
+ dataplane->nr_ring_ref, &local_err);
+ dataplane->sring = NULL;
+
+ if (local_err) {
+ error_report_err(local_err);
+ }
+ }
+
+ g_free(dataplane->ring_ref);
+ dataplane->ring_ref = NULL;
+}
+
+void xen_block_dataplane_start(XenBlockDataPlane *dataplane,
+ const unsigned int ring_ref[],
+ unsigned int nr_ring_ref,
+ unsigned int event_channel,
+ unsigned int protocol,
+ Error **errp)
+{
+ ERRP_GUARD();
+ XenDevice *xendev = dataplane->xendev;
+ AioContext *old_context;
+ unsigned int ring_size;
+ unsigned int i;
+
+ dataplane->nr_ring_ref = nr_ring_ref;
+ dataplane->ring_ref = g_new(unsigned int, nr_ring_ref);
+
+ for (i = 0; i < nr_ring_ref; i++) {
+ dataplane->ring_ref[i] = ring_ref[i];
+ }
+
+ dataplane->protocol = protocol;
+
+ ring_size = XC_PAGE_SIZE * dataplane->nr_ring_ref;
+ switch (dataplane->protocol) {
+ case BLKIF_PROTOCOL_NATIVE:
+ {
+ dataplane->max_requests = __CONST_RING_SIZE(blkif, ring_size);
+ break;
+ }
+ case BLKIF_PROTOCOL_X86_32:
+ {
+ dataplane->max_requests = __CONST_RING_SIZE(blkif_x86_32, ring_size);
+ break;
+ }
+ case BLKIF_PROTOCOL_X86_64:
+ {
+ dataplane->max_requests = __CONST_RING_SIZE(blkif_x86_64, ring_size);
+ break;
+ }
+ default:
+ error_setg(errp, "unknown protocol %u", dataplane->protocol);
+ return;
+ }
+
+ xen_device_set_max_grant_refs(xendev, dataplane->nr_ring_ref,
+ errp);
+ if (*errp) {
+ goto stop;
+ }
+
+ dataplane->sring = xen_device_map_grant_refs(xendev,
+ dataplane->ring_ref,
+ dataplane->nr_ring_ref,
+ PROT_READ | PROT_WRITE,
+ errp);
+ if (*errp) {
+ goto stop;
+ }
+
+ switch (dataplane->protocol) {
+ case BLKIF_PROTOCOL_NATIVE:
+ {
+ blkif_sring_t *sring_native = dataplane->sring;
+
+ BACK_RING_INIT(&dataplane->rings.native, sring_native, ring_size);
+ break;
+ }
+ case BLKIF_PROTOCOL_X86_32:
+ {
+ blkif_x86_32_sring_t *sring_x86_32 = dataplane->sring;
+
+ BACK_RING_INIT(&dataplane->rings.x86_32_part, sring_x86_32,
+ ring_size);
+ break;
+ }
+ case BLKIF_PROTOCOL_X86_64:
+ {
+ blkif_x86_64_sring_t *sring_x86_64 = dataplane->sring;
+
+ BACK_RING_INIT(&dataplane->rings.x86_64_part, sring_x86_64,
+ ring_size);
+ break;
+ }
+ }
+
+ dataplane->event_channel =
+ xen_device_bind_event_channel(xendev, event_channel,
+ xen_block_dataplane_event, dataplane,
+ errp);
+ if (*errp) {
+ goto stop;
+ }
+
+ old_context = blk_get_aio_context(dataplane->blk);
+ aio_context_acquire(old_context);
+ /* If other users keep the BlockBackend in the iothread, that's ok */
+ blk_set_aio_context(dataplane->blk, dataplane->ctx, NULL);
+ aio_context_release(old_context);
+
+ /* Only reason for failure is a NULL channel */
+ aio_context_acquire(dataplane->ctx);
+ xen_device_set_event_channel_context(xendev, dataplane->event_channel,
+ dataplane->ctx, &error_abort);
+ aio_context_release(dataplane->ctx);
+
+ return;
+
+stop:
+ xen_block_dataplane_stop(dataplane);
+}
diff --git a/hw/block/dataplane/xen-block.h b/hw/block/dataplane/xen-block.h
new file mode 100644
index 00000000..76dcd51c
--- /dev/null
+++ b/hw/block/dataplane/xen-block.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (c) 2018 Citrix Systems Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef HW_BLOCK_DATAPLANE_XEN_BLOCK_H
+#define HW_BLOCK_DATAPLANE_XEN_BLOCK_H
+
+#include "hw/block/block.h"
+#include "hw/xen/xen-bus.h"
+#include "sysemu/iothread.h"
+
+typedef struct XenBlockDataPlane XenBlockDataPlane;
+
+XenBlockDataPlane *xen_block_dataplane_create(XenDevice *xendev,
+ BlockBackend *blk,
+ unsigned int sector_size,
+ IOThread *iothread);
+void xen_block_dataplane_destroy(XenBlockDataPlane *dataplane);
+void xen_block_dataplane_start(XenBlockDataPlane *dataplane,
+ const unsigned int ring_ref[],
+ unsigned int nr_ring_ref,
+ unsigned int event_channel,
+ unsigned int protocol,
+ Error **errp);
+void xen_block_dataplane_stop(XenBlockDataPlane *dataplane);
+
+#endif /* HW_BLOCK_DATAPLANE_XEN_BLOCK_H */
diff --git a/hw/block/ecc.c b/hw/block/ecc.c
new file mode 100644
index 00000000..6e0d6384
--- /dev/null
+++ b/hw/block/ecc.c
@@ -0,0 +1,91 @@
+/*
+ * Calculate Error-correcting Codes. Used by NAND Flash controllers
+ * (not by NAND chips).
+ *
+ * Copyright (c) 2006 Openedhand Ltd.
+ * Written by Andrzej Zaborowski <balrog@zabor.org>
+ *
+ * This code is licensed under the GNU GPL v2.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu/osdep.h"
+#include "migration/vmstate.h"
+#include "hw/block/flash.h"
+
+/*
+ * Pre-calculated 256-way 1 byte column parity. Table borrowed from Linux.
+ */
+static const uint8_t nand_ecc_precalc_table[] = {
+ 0x00, 0x55, 0x56, 0x03, 0x59, 0x0c, 0x0f, 0x5a,
+ 0x5a, 0x0f, 0x0c, 0x59, 0x03, 0x56, 0x55, 0x00,
+ 0x65, 0x30, 0x33, 0x66, 0x3c, 0x69, 0x6a, 0x3f,
+ 0x3f, 0x6a, 0x69, 0x3c, 0x66, 0x33, 0x30, 0x65,
+ 0x66, 0x33, 0x30, 0x65, 0x3f, 0x6a, 0x69, 0x3c,
+ 0x3c, 0x69, 0x6a, 0x3f, 0x65, 0x30, 0x33, 0x66,
+ 0x03, 0x56, 0x55, 0x00, 0x5a, 0x0f, 0x0c, 0x59,
+ 0x59, 0x0c, 0x0f, 0x5a, 0x00, 0x55, 0x56, 0x03,
+ 0x69, 0x3c, 0x3f, 0x6a, 0x30, 0x65, 0x66, 0x33,
+ 0x33, 0x66, 0x65, 0x30, 0x6a, 0x3f, 0x3c, 0x69,
+ 0x0c, 0x59, 0x5a, 0x0f, 0x55, 0x00, 0x03, 0x56,
+ 0x56, 0x03, 0x00, 0x55, 0x0f, 0x5a, 0x59, 0x0c,
+ 0x0f, 0x5a, 0x59, 0x0c, 0x56, 0x03, 0x00, 0x55,
+ 0x55, 0x00, 0x03, 0x56, 0x0c, 0x59, 0x5a, 0x0f,
+ 0x6a, 0x3f, 0x3c, 0x69, 0x33, 0x66, 0x65, 0x30,
+ 0x30, 0x65, 0x66, 0x33, 0x69, 0x3c, 0x3f, 0x6a,
+ 0x6a, 0x3f, 0x3c, 0x69, 0x33, 0x66, 0x65, 0x30,
+ 0x30, 0x65, 0x66, 0x33, 0x69, 0x3c, 0x3f, 0x6a,
+ 0x0f, 0x5a, 0x59, 0x0c, 0x56, 0x03, 0x00, 0x55,
+ 0x55, 0x00, 0x03, 0x56, 0x0c, 0x59, 0x5a, 0x0f,
+ 0x0c, 0x59, 0x5a, 0x0f, 0x55, 0x00, 0x03, 0x56,
+ 0x56, 0x03, 0x00, 0x55, 0x0f, 0x5a, 0x59, 0x0c,
+ 0x69, 0x3c, 0x3f, 0x6a, 0x30, 0x65, 0x66, 0x33,
+ 0x33, 0x66, 0x65, 0x30, 0x6a, 0x3f, 0x3c, 0x69,
+ 0x03, 0x56, 0x55, 0x00, 0x5a, 0x0f, 0x0c, 0x59,
+ 0x59, 0x0c, 0x0f, 0x5a, 0x00, 0x55, 0x56, 0x03,
+ 0x66, 0x33, 0x30, 0x65, 0x3f, 0x6a, 0x69, 0x3c,
+ 0x3c, 0x69, 0x6a, 0x3f, 0x65, 0x30, 0x33, 0x66,
+ 0x65, 0x30, 0x33, 0x66, 0x3c, 0x69, 0x6a, 0x3f,
+ 0x3f, 0x6a, 0x69, 0x3c, 0x66, 0x33, 0x30, 0x65,
+ 0x00, 0x55, 0x56, 0x03, 0x59, 0x0c, 0x0f, 0x5a,
+ 0x5a, 0x0f, 0x0c, 0x59, 0x03, 0x56, 0x55, 0x00,
+};
+
+/* Update ECC parity count. */
+uint8_t ecc_digest(ECCState *s, uint8_t sample)
+{
+ uint8_t idx = nand_ecc_precalc_table[sample];
+
+ s->cp ^= idx & 0x3f;
+ if (idx & 0x40) {
+ s->lp[0] ^= ~s->count;
+ s->lp[1] ^= s->count;
+ }
+ s->count ++;
+
+ return sample;
+}
+
+/* Reinitialise the counters. */
+void ecc_reset(ECCState *s)
+{
+ s->lp[0] = 0x0000;
+ s->lp[1] = 0x0000;
+ s->cp = 0x00;
+ s->count = 0;
+}
+
+/* Save/restore */
+const VMStateDescription vmstate_ecc_state = {
+ .name = "ecc-state",
+ .version_id = 0,
+ .minimum_version_id = 0,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(cp, ECCState),
+ VMSTATE_UINT16_ARRAY(lp, ECCState, 2),
+ VMSTATE_UINT16(count, ECCState),
+ VMSTATE_END_OF_LIST(),
+ },
+};
diff --git a/hw/block/fdc-internal.h b/hw/block/fdc-internal.h
new file mode 100644
index 00000000..036392e9
--- /dev/null
+++ b/hw/block/fdc-internal.h
@@ -0,0 +1,158 @@
+/*
+ * QEMU Floppy disk emulator (Intel 82078)
+ *
+ * Copyright (c) 2003, 2007 Jocelyn Mayer
+ * Copyright (c) 2008 Hervé Poussineau
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef HW_BLOCK_FDC_INTERNAL_H
+#define HW_BLOCK_FDC_INTERNAL_H
+
+#include "exec/memory.h"
+#include "exec/ioport.h"
+#include "hw/block/block.h"
+#include "hw/block/fdc.h"
+#include "qapi/qapi-types-block.h"
+
+typedef struct FDCtrl FDCtrl;
+
+/* Floppy bus emulation */
+
+typedef struct FloppyBus {
+ BusState bus;
+ FDCtrl *fdc;
+} FloppyBus;
+
+/* Floppy disk drive emulation */
+
+typedef enum FDriveRate {
+ FDRIVE_RATE_500K = 0x00, /* 500 Kbps */
+ FDRIVE_RATE_300K = 0x01, /* 300 Kbps */
+ FDRIVE_RATE_250K = 0x02, /* 250 Kbps */
+ FDRIVE_RATE_1M = 0x03, /* 1 Mbps */
+} FDriveRate;
+
+typedef enum FDriveSize {
+ FDRIVE_SIZE_UNKNOWN,
+ FDRIVE_SIZE_350,
+ FDRIVE_SIZE_525,
+} FDriveSize;
+
+typedef struct FDFormat {
+ FloppyDriveType drive;
+ uint8_t last_sect;
+ uint8_t max_track;
+ uint8_t max_head;
+ FDriveRate rate;
+} FDFormat;
+
+typedef enum FDiskFlags {
+ FDISK_DBL_SIDES = 0x01,
+} FDiskFlags;
+
+typedef struct FDrive {
+ FDCtrl *fdctrl;
+ BlockBackend *blk;
+ BlockConf *conf;
+ /* Drive status */
+ FloppyDriveType drive; /* CMOS drive type */
+ uint8_t perpendicular; /* 2.88 MB access mode */
+ /* Position */
+ uint8_t head;
+ uint8_t track;
+ uint8_t sect;
+ /* Media */
+ FloppyDriveType disk; /* Current disk type */
+ FDiskFlags flags;
+ uint8_t last_sect; /* Nb sector per track */
+ uint8_t max_track; /* Nb of tracks */
+ uint16_t bps; /* Bytes per sector */
+ uint8_t ro; /* Is read-only */
+ uint8_t media_changed; /* Is media changed */
+ uint8_t media_rate; /* Data rate of medium */
+
+ bool media_validated; /* Have we validated the media? */
+} FDrive;
+
+struct FDCtrl {
+ MemoryRegion iomem;
+ qemu_irq irq;
+ /* Controller state */
+ QEMUTimer *result_timer;
+ int dma_chann;
+ uint8_t phase;
+ IsaDma *dma;
+ /* Controller's identification */
+ uint8_t version;
+ /* HW */
+ uint8_t sra;
+ uint8_t srb;
+ uint8_t dor;
+ uint8_t dor_vmstate; /* only used as temp during vmstate */
+ uint8_t tdr;
+ uint8_t dsr;
+ uint8_t msr;
+ uint8_t cur_drv;
+ uint8_t status0;
+ uint8_t status1;
+ uint8_t status2;
+ /* Command FIFO */
+ uint8_t *fifo;
+ int32_t fifo_size;
+ uint32_t data_pos;
+ uint32_t data_len;
+ uint8_t data_state;
+ uint8_t data_dir;
+ uint8_t eot; /* last wanted sector */
+ /* States kept only to be returned back */
+ /* precompensation */
+ uint8_t precomp_trk;
+ uint8_t config;
+ uint8_t lock;
+ /* Power down config (also with status regB access mode */
+ uint8_t pwrd;
+ /* Floppy drives */
+ FloppyBus bus;
+ uint8_t num_floppies;
+ FDrive drives[MAX_FD];
+ struct {
+ FloppyDriveType type;
+ } qdev_for_drives[MAX_FD];
+ int reset_sensei;
+ FloppyDriveType fallback; /* type=auto failure fallback */
+ /* Timers state */
+ uint8_t timer0;
+ uint8_t timer1;
+ PortioList portio_list;
+};
+
+extern const FDFormat fd_formats[];
+extern const VMStateDescription vmstate_fdc;
+
+uint32_t fdctrl_read(void *opaque, uint32_t reg);
+void fdctrl_write(void *opaque, uint32_t reg, uint32_t value);
+void fdctrl_reset(FDCtrl *fdctrl, int do_irq);
+void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp);
+
+int fdctrl_transfer_handler(void *opaque, int nchan, int dma_pos, int dma_len);
+
+void fdctrl_init_drives(FloppyBus *bus, DriveInfo **fds);
+
+#endif
diff --git a/hw/block/fdc-isa.c b/hw/block/fdc-isa.c
new file mode 100644
index 00000000..fee1ca68
--- /dev/null
+++ b/hw/block/fdc-isa.c
@@ -0,0 +1,327 @@
+/*
+ * QEMU Floppy disk emulator (Intel 82078)
+ *
+ * Copyright (c) 2003, 2007 Jocelyn Mayer
+ * Copyright (c) 2008 Hervé Poussineau
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+/*
+ * The controller is used in Sun4m systems in a slightly different
+ * way. There are changes in DOR register and DMA is not available.
+ */
+
+#include "qemu/osdep.h"
+#include "hw/block/fdc.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/timer.h"
+#include "hw/acpi/acpi_aml_interface.h"
+#include "hw/irq.h"
+#include "hw/isa/isa.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "migration/vmstate.h"
+#include "hw/block/block.h"
+#include "sysemu/block-backend.h"
+#include "sysemu/blockdev.h"
+#include "sysemu/sysemu.h"
+#include "qemu/log.h"
+#include "qemu/main-loop.h"
+#include "qemu/module.h"
+#include "trace.h"
+#include "qom/object.h"
+#include "fdc-internal.h"
+
+OBJECT_DECLARE_SIMPLE_TYPE(FDCtrlISABus, ISA_FDC)
+
+struct FDCtrlISABus {
+ /*< private >*/
+ ISADevice parent_obj;
+ /*< public >*/
+
+ uint32_t iobase;
+ uint32_t irq;
+ uint32_t dma;
+ struct FDCtrl state;
+ int32_t bootindexA;
+ int32_t bootindexB;
+};
+
+static void fdctrl_external_reset_isa(DeviceState *d)
+{
+ FDCtrlISABus *isa = ISA_FDC(d);
+ FDCtrl *s = &isa->state;
+
+ fdctrl_reset(s, 0);
+}
+
+void isa_fdc_init_drives(ISADevice *fdc, DriveInfo **fds)
+{
+ fdctrl_init_drives(&ISA_FDC(fdc)->state.bus, fds);
+}
+
+static const MemoryRegionPortio fdc_portio_list[] = {
+ { 1, 5, 1, .read = fdctrl_read, .write = fdctrl_write },
+ { 7, 1, 1, .read = fdctrl_read, .write = fdctrl_write },
+ PORTIO_END_OF_LIST(),
+};
+
+static void isabus_fdc_realize(DeviceState *dev, Error **errp)
+{
+ ISADevice *isadev = ISA_DEVICE(dev);
+ FDCtrlISABus *isa = ISA_FDC(dev);
+ FDCtrl *fdctrl = &isa->state;
+ Error *err = NULL;
+
+ isa_register_portio_list(isadev, &fdctrl->portio_list,
+ isa->iobase, fdc_portio_list, fdctrl,
+ "fdc");
+
+ fdctrl->irq = isa_get_irq(isadev, isa->irq);
+ fdctrl->dma_chann = isa->dma;
+ if (fdctrl->dma_chann != -1) {
+ IsaDmaClass *k;
+ fdctrl->dma = isa_get_dma(isa_bus_from_device(isadev), isa->dma);
+ if (!fdctrl->dma) {
+ error_setg(errp, "ISA controller does not support DMA");
+ return;
+ }
+ k = ISADMA_GET_CLASS(fdctrl->dma);
+ k->register_channel(fdctrl->dma, fdctrl->dma_chann,
+ &fdctrl_transfer_handler, fdctrl);
+ }
+
+ qdev_set_legacy_instance_id(dev, isa->iobase, 2);
+
+ fdctrl_realize_common(dev, fdctrl, &err);
+ if (err != NULL) {
+ error_propagate(errp, err);
+ return;
+ }
+}
+
+FloppyDriveType isa_fdc_get_drive_type(ISADevice *fdc, int i)
+{
+ FDCtrlISABus *isa = ISA_FDC(fdc);
+
+ return isa->state.drives[i].drive;
+}
+
+static void isa_fdc_get_drive_max_chs(FloppyDriveType type, uint8_t *maxc,
+ uint8_t *maxh, uint8_t *maxs)
+{
+ const FDFormat *fdf;
+
+ *maxc = *maxh = *maxs = 0;
+ for (fdf = fd_formats; fdf->drive != FLOPPY_DRIVE_TYPE_NONE; fdf++) {
+ if (fdf->drive != type) {
+ continue;
+ }
+ if (*maxc < fdf->max_track) {
+ *maxc = fdf->max_track;
+ }
+ if (*maxh < fdf->max_head) {
+ *maxh = fdf->max_head;
+ }
+ if (*maxs < fdf->last_sect) {
+ *maxs = fdf->last_sect;
+ }
+ }
+ (*maxc)--;
+}
+
+static Aml *build_fdinfo_aml(int idx, FloppyDriveType type)
+{
+ Aml *dev, *fdi;
+ uint8_t maxc, maxh, maxs;
+
+ isa_fdc_get_drive_max_chs(type, &maxc, &maxh, &maxs);
+
+ dev = aml_device("FLP%c", 'A' + idx);
+
+ aml_append(dev, aml_name_decl("_ADR", aml_int(idx)));
+
+ fdi = aml_package(16);
+ aml_append(fdi, aml_int(idx)); /* Drive Number */
+ aml_append(fdi,
+ aml_int(cmos_get_fd_drive_type(type))); /* Device Type */
+ /*
+ * the values below are the limits of the drive, and are thus independent
+ * of the inserted media
+ */
+ aml_append(fdi, aml_int(maxc)); /* Maximum Cylinder Number */
+ aml_append(fdi, aml_int(maxs)); /* Maximum Sector Number */
+ aml_append(fdi, aml_int(maxh)); /* Maximum Head Number */
+ /*
+ * SeaBIOS returns the below values for int 0x13 func 0x08 regardless of
+ * the drive type, so shall we
+ */
+ aml_append(fdi, aml_int(0xAF)); /* disk_specify_1 */
+ aml_append(fdi, aml_int(0x02)); /* disk_specify_2 */
+ aml_append(fdi, aml_int(0x25)); /* disk_motor_wait */
+ aml_append(fdi, aml_int(0x02)); /* disk_sector_siz */
+ aml_append(fdi, aml_int(0x12)); /* disk_eot */
+ aml_append(fdi, aml_int(0x1B)); /* disk_rw_gap */
+ aml_append(fdi, aml_int(0xFF)); /* disk_dtl */
+ aml_append(fdi, aml_int(0x6C)); /* disk_formt_gap */
+ aml_append(fdi, aml_int(0xF6)); /* disk_fill */
+ aml_append(fdi, aml_int(0x0F)); /* disk_head_sttl */
+ aml_append(fdi, aml_int(0x08)); /* disk_motor_strt */
+
+ aml_append(dev, aml_name_decl("_FDI", fdi));
+ return dev;
+}
+
+int cmos_get_fd_drive_type(FloppyDriveType fd0)
+{
+ int val;
+
+ switch (fd0) {
+ case FLOPPY_DRIVE_TYPE_144:
+ /* 1.44 Mb 3"5 drive */
+ val = 4;
+ break;
+ case FLOPPY_DRIVE_TYPE_288:
+ /* 2.88 Mb 3"5 drive */
+ val = 5;
+ break;
+ case FLOPPY_DRIVE_TYPE_120:
+ /* 1.2 Mb 5"5 drive */
+ val = 2;
+ break;
+ case FLOPPY_DRIVE_TYPE_NONE:
+ default:
+ val = 0;
+ break;
+ }
+ return val;
+}
+
+static void build_fdc_aml(AcpiDevAmlIf *adev, Aml *scope)
+{
+ FDCtrlISABus *isa = ISA_FDC(adev);
+ Aml *dev;
+ Aml *crs;
+ int i;
+
+#define ACPI_FDE_MAX_FD 4
+ uint32_t fde_buf[5] = {
+ 0, 0, 0, 0, /* presence of floppy drives #0 - #3 */
+ cpu_to_le32(2) /* tape presence (2 == never present) */
+ };
+
+ crs = aml_resource_template();
+ aml_append(crs,
+ aml_io(AML_DECODE16, isa->iobase + 2, isa->iobase + 2, 0x00, 0x04));
+ aml_append(crs,
+ aml_io(AML_DECODE16, isa->iobase + 7, isa->iobase + 7, 0x00, 0x01));
+ aml_append(crs, aml_irq_no_flags(isa->irq));
+ aml_append(crs,
+ aml_dma(AML_COMPATIBILITY, AML_NOTBUSMASTER, AML_TRANSFER8, isa->dma));
+
+ dev = aml_device("FDC0");
+ aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0700")));
+ aml_append(dev, aml_name_decl("_CRS", crs));
+
+ for (i = 0; i < MIN(MAX_FD, ACPI_FDE_MAX_FD); i++) {
+ FloppyDriveType type = isa_fdc_get_drive_type(ISA_DEVICE(adev), i);
+
+ if (type < FLOPPY_DRIVE_TYPE_NONE) {
+ fde_buf[i] = cpu_to_le32(1); /* drive present */
+ aml_append(dev, build_fdinfo_aml(i, type));
+ }
+ }
+ aml_append(dev, aml_name_decl("_FDE",
+ aml_buffer(sizeof(fde_buf), (uint8_t *)fde_buf)));
+
+ aml_append(scope, dev);
+}
+
+static const VMStateDescription vmstate_isa_fdc = {
+ .name = "fdc",
+ .version_id = 2,
+ .minimum_version_id = 2,
+ .fields = (VMStateField[]) {
+ VMSTATE_STRUCT(state, FDCtrlISABus, 0, vmstate_fdc, FDCtrl),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static Property isa_fdc_properties[] = {
+ DEFINE_PROP_UINT32("iobase", FDCtrlISABus, iobase, 0x3f0),
+ DEFINE_PROP_UINT32("irq", FDCtrlISABus, irq, 6),
+ DEFINE_PROP_UINT32("dma", FDCtrlISABus, dma, 2),
+ DEFINE_PROP_SIGNED("fdtypeA", FDCtrlISABus, state.qdev_for_drives[0].type,
+ FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type,
+ FloppyDriveType),
+ DEFINE_PROP_SIGNED("fdtypeB", FDCtrlISABus, state.qdev_for_drives[1].type,
+ FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type,
+ FloppyDriveType),
+ DEFINE_PROP_SIGNED("fallback", FDCtrlISABus, state.fallback,
+ FLOPPY_DRIVE_TYPE_288, qdev_prop_fdc_drive_type,
+ FloppyDriveType),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void isabus_fdc_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+ AcpiDevAmlIfClass *adevc = ACPI_DEV_AML_IF_CLASS(klass);
+
+ dc->desc = "virtual floppy controller";
+ dc->realize = isabus_fdc_realize;
+ dc->fw_name = "fdc";
+ dc->reset = fdctrl_external_reset_isa;
+ dc->vmsd = &vmstate_isa_fdc;
+ adevc->build_dev_aml = build_fdc_aml;
+ device_class_set_props(dc, isa_fdc_properties);
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+}
+
+static void isabus_fdc_instance_init(Object *obj)
+{
+ FDCtrlISABus *isa = ISA_FDC(obj);
+
+ device_add_bootindex_property(obj, &isa->bootindexA,
+ "bootindexA", "/floppy@0",
+ DEVICE(obj));
+ device_add_bootindex_property(obj, &isa->bootindexB,
+ "bootindexB", "/floppy@1",
+ DEVICE(obj));
+}
+
+static const TypeInfo isa_fdc_info = {
+ .name = TYPE_ISA_FDC,
+ .parent = TYPE_ISA_DEVICE,
+ .instance_size = sizeof(FDCtrlISABus),
+ .class_init = isabus_fdc_class_init,
+ .instance_init = isabus_fdc_instance_init,
+ .interfaces = (InterfaceInfo[]) {
+ { TYPE_ACPI_DEV_AML_IF },
+ { },
+ },
+};
+
+static void isa_fdc_register_types(void)
+{
+ type_register_static(&isa_fdc_info);
+}
+
+type_init(isa_fdc_register_types)
diff --git a/hw/block/fdc-sysbus.c b/hw/block/fdc-sysbus.c
new file mode 100644
index 00000000..86ea51d0
--- /dev/null
+++ b/hw/block/fdc-sysbus.c
@@ -0,0 +1,257 @@
+/*
+ * QEMU Floppy disk emulator (Intel 82078)
+ *
+ * Copyright (c) 2003, 2007 Jocelyn Mayer
+ * Copyright (c) 2008 Hervé Poussineau
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qom/object.h"
+#include "hw/sysbus.h"
+#include "hw/block/fdc.h"
+#include "migration/vmstate.h"
+#include "fdc-internal.h"
+#include "trace.h"
+
+#define TYPE_SYSBUS_FDC "base-sysbus-fdc"
+typedef struct FDCtrlSysBusClass FDCtrlSysBusClass;
+typedef struct FDCtrlSysBus FDCtrlSysBus;
+DECLARE_OBJ_CHECKERS(FDCtrlSysBus, FDCtrlSysBusClass,
+ SYSBUS_FDC, TYPE_SYSBUS_FDC)
+
+struct FDCtrlSysBusClass {
+ /*< private >*/
+ SysBusDeviceClass parent_class;
+ /*< public >*/
+
+ bool use_strict_io;
+};
+
+struct FDCtrlSysBus {
+ /*< private >*/
+ SysBusDevice parent_obj;
+ /*< public >*/
+
+ struct FDCtrl state;
+};
+
+static uint64_t fdctrl_read_mem(void *opaque, hwaddr reg, unsigned ize)
+{
+ return fdctrl_read(opaque, (uint32_t)reg);
+}
+
+static void fdctrl_write_mem(void *opaque, hwaddr reg,
+ uint64_t value, unsigned size)
+{
+ fdctrl_write(opaque, (uint32_t)reg, value);
+}
+
+static const MemoryRegionOps fdctrl_mem_ops = {
+ .read = fdctrl_read_mem,
+ .write = fdctrl_write_mem,
+ .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static const MemoryRegionOps fdctrl_mem_strict_ops = {
+ .read = fdctrl_read_mem,
+ .write = fdctrl_write_mem,
+ .endianness = DEVICE_NATIVE_ENDIAN,
+ .valid = {
+ .min_access_size = 1,
+ .max_access_size = 1,
+ },
+};
+
+static void fdctrl_external_reset_sysbus(DeviceState *d)
+{
+ FDCtrlSysBus *sys = SYSBUS_FDC(d);
+ FDCtrl *s = &sys->state;
+
+ fdctrl_reset(s, 0);
+}
+
+static void fdctrl_handle_tc(void *opaque, int irq, int level)
+{
+ trace_fdctrl_tc_pulse(level);
+}
+
+void fdctrl_init_sysbus(qemu_irq irq, hwaddr mmio_base, DriveInfo **fds)
+{
+ DeviceState *dev;
+ SysBusDevice *sbd;
+ FDCtrlSysBus *sys;
+
+ dev = qdev_new("sysbus-fdc");
+ sys = SYSBUS_FDC(dev);
+ sbd = SYS_BUS_DEVICE(dev);
+ sysbus_realize_and_unref(sbd, &error_fatal);
+ sysbus_connect_irq(sbd, 0, irq);
+ sysbus_mmio_map(sbd, 0, mmio_base);
+
+ fdctrl_init_drives(&sys->state.bus, fds);
+}
+
+void sun4m_fdctrl_init(qemu_irq irq, hwaddr io_base,
+ DriveInfo **fds, qemu_irq *fdc_tc)
+{
+ DeviceState *dev;
+ FDCtrlSysBus *sys;
+
+ dev = qdev_new("sun-fdtwo");
+ sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);
+ sys = SYSBUS_FDC(dev);
+ sysbus_connect_irq(SYS_BUS_DEVICE(sys), 0, irq);
+ sysbus_mmio_map(SYS_BUS_DEVICE(sys), 0, io_base);
+ *fdc_tc = qdev_get_gpio_in(dev, 0);
+
+ fdctrl_init_drives(&sys->state.bus, fds);
+}
+
+static void sysbus_fdc_common_instance_init(Object *obj)
+{
+ DeviceState *dev = DEVICE(obj);
+ FDCtrlSysBusClass *sbdc = SYSBUS_FDC_GET_CLASS(obj);
+ SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
+ FDCtrlSysBus *sys = SYSBUS_FDC(obj);
+ FDCtrl *fdctrl = &sys->state;
+
+ /*
+ * DMA is not currently supported for sysbus floppy controllers.
+ * If we wanted to add support then probably the best approach is
+ * to have a QOM link property 'dma-controller' which the board
+ * code can set to an instance of IsaDmaClass, and an integer
+ * property 'dma-channel', so that we can set fdctrl->dma and
+ * fdctrl->dma_chann accordingly.
+ */
+ fdctrl->dma_chann = -1;
+
+ qdev_set_legacy_instance_id(dev, 0 /* io */, 2); /* FIXME */
+
+ memory_region_init_io(&fdctrl->iomem, obj,
+ sbdc->use_strict_io ? &fdctrl_mem_strict_ops
+ : &fdctrl_mem_ops,
+ fdctrl, "fdc", 0x08);
+ sysbus_init_mmio(sbd, &fdctrl->iomem);
+
+ sysbus_init_irq(sbd, &fdctrl->irq);
+ qdev_init_gpio_in(dev, fdctrl_handle_tc, 1);
+}
+
+static void sysbus_fdc_realize(DeviceState *dev, Error **errp)
+{
+ FDCtrlSysBus *sys = SYSBUS_FDC(dev);
+ FDCtrl *fdctrl = &sys->state;
+
+ fdctrl_realize_common(dev, fdctrl, errp);
+}
+
+static const VMStateDescription vmstate_sysbus_fdc = {
+ .name = "fdc",
+ .version_id = 2,
+ .minimum_version_id = 2,
+ .fields = (VMStateField[]) {
+ VMSTATE_STRUCT(state, FDCtrlSysBus, 0, vmstate_fdc, FDCtrl),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static void sysbus_fdc_common_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ dc->realize = sysbus_fdc_realize;
+ dc->reset = fdctrl_external_reset_sysbus;
+ dc->vmsd = &vmstate_sysbus_fdc;
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+}
+
+static const TypeInfo sysbus_fdc_common_typeinfo = {
+ .name = TYPE_SYSBUS_FDC,
+ .parent = TYPE_SYS_BUS_DEVICE,
+ .instance_size = sizeof(FDCtrlSysBus),
+ .instance_init = sysbus_fdc_common_instance_init,
+ .abstract = true,
+ .class_init = sysbus_fdc_common_class_init,
+ .class_size = sizeof(FDCtrlSysBusClass),
+};
+
+static Property sysbus_fdc_properties[] = {
+ DEFINE_PROP_SIGNED("fdtypeA", FDCtrlSysBus, state.qdev_for_drives[0].type,
+ FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type,
+ FloppyDriveType),
+ DEFINE_PROP_SIGNED("fdtypeB", FDCtrlSysBus, state.qdev_for_drives[1].type,
+ FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type,
+ FloppyDriveType),
+ DEFINE_PROP_SIGNED("fallback", FDCtrlSysBus, state.fallback,
+ FLOPPY_DRIVE_TYPE_144, qdev_prop_fdc_drive_type,
+ FloppyDriveType),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void sysbus_fdc_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ dc->desc = "virtual floppy controller";
+ device_class_set_props(dc, sysbus_fdc_properties);
+}
+
+static const TypeInfo sysbus_fdc_typeinfo = {
+ .name = "sysbus-fdc",
+ .parent = TYPE_SYSBUS_FDC,
+ .class_init = sysbus_fdc_class_init,
+};
+
+static Property sun4m_fdc_properties[] = {
+ DEFINE_PROP_SIGNED("fdtype", FDCtrlSysBus, state.qdev_for_drives[0].type,
+ FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type,
+ FloppyDriveType),
+ DEFINE_PROP_SIGNED("fallback", FDCtrlSysBus, state.fallback,
+ FLOPPY_DRIVE_TYPE_144, qdev_prop_fdc_drive_type,
+ FloppyDriveType),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void sun4m_fdc_class_init(ObjectClass *klass, void *data)
+{
+ FDCtrlSysBusClass *sbdc = SYSBUS_FDC_CLASS(klass);
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ sbdc->use_strict_io = true;
+ dc->desc = "virtual floppy controller";
+ device_class_set_props(dc, sun4m_fdc_properties);
+}
+
+static const TypeInfo sun4m_fdc_typeinfo = {
+ .name = "sun-fdtwo",
+ .parent = TYPE_SYSBUS_FDC,
+ .class_init = sun4m_fdc_class_init,
+};
+
+static void sysbus_fdc_register_types(void)
+{
+ type_register_static(&sysbus_fdc_common_typeinfo);
+ type_register_static(&sysbus_fdc_typeinfo);
+ type_register_static(&sun4m_fdc_typeinfo);
+}
+
+type_init(sysbus_fdc_register_types)
diff --git a/hw/block/fdc.c b/hw/block/fdc.c
new file mode 100644
index 00000000..64ae4a68
--- /dev/null
+++ b/hw/block/fdc.c
@@ -0,0 +1,2393 @@
+/*
+ * QEMU Floppy disk emulator (Intel 82078)
+ *
+ * Copyright (c) 2003, 2007 Jocelyn Mayer
+ * Copyright (c) 2008 Hervé Poussineau
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+/*
+ * The controller is used in Sun4m systems in a slightly different
+ * way. There are changes in DOR register and DMA is not available.
+ */
+
+#include "qemu/osdep.h"
+#include "hw/block/fdc.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/timer.h"
+#include "qemu/memalign.h"
+#include "hw/irq.h"
+#include "hw/isa/isa.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "migration/vmstate.h"
+#include "hw/block/block.h"
+#include "sysemu/block-backend.h"
+#include "sysemu/blockdev.h"
+#include "sysemu/sysemu.h"
+#include "qemu/log.h"
+#include "qemu/main-loop.h"
+#include "qemu/module.h"
+#include "trace.h"
+#include "qom/object.h"
+#include "fdc-internal.h"
+
+/********************************************************/
+/* debug Floppy devices */
+
+#define DEBUG_FLOPPY 0
+
+#define FLOPPY_DPRINTF(fmt, ...) \
+ do { \
+ if (DEBUG_FLOPPY) { \
+ fprintf(stderr, "FLOPPY: " fmt , ## __VA_ARGS__); \
+ } \
+ } while (0)
+
+
+/* Anonymous BlockBackend for empty drive */
+static BlockBackend *blk_create_empty_drive(void)
+{
+ return blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL);
+}
+
+/********************************************************/
+/* qdev floppy bus */
+
+#define TYPE_FLOPPY_BUS "floppy-bus"
+OBJECT_DECLARE_SIMPLE_TYPE(FloppyBus, FLOPPY_BUS)
+
+static FDrive *get_drv(FDCtrl *fdctrl, int unit);
+
+static const TypeInfo floppy_bus_info = {
+ .name = TYPE_FLOPPY_BUS,
+ .parent = TYPE_BUS,
+ .instance_size = sizeof(FloppyBus),
+};
+
+static void floppy_bus_create(FDCtrl *fdc, FloppyBus *bus, DeviceState *dev)
+{
+ qbus_init(bus, sizeof(FloppyBus), TYPE_FLOPPY_BUS, dev, NULL);
+ bus->fdc = fdc;
+}
+
+
+/********************************************************/
+/* Floppy drive emulation */
+
+/* In many cases, the total sector size of a format is enough to uniquely
+ * identify it. However, there are some total sector collisions between
+ * formats of different physical size, and these are noted below by
+ * highlighting the total sector size for entries with collisions. */
+const FDFormat fd_formats[] = {
+ /* First entry is default format */
+ /* 1.44 MB 3"1/2 floppy disks */
+ { FLOPPY_DRIVE_TYPE_144, 18, 80, 1, FDRIVE_RATE_500K, }, /* 3.5" 2880 */
+ { FLOPPY_DRIVE_TYPE_144, 20, 80, 1, FDRIVE_RATE_500K, }, /* 3.5" 3200 */
+ { FLOPPY_DRIVE_TYPE_144, 21, 80, 1, FDRIVE_RATE_500K, },
+ { FLOPPY_DRIVE_TYPE_144, 21, 82, 1, FDRIVE_RATE_500K, },
+ { FLOPPY_DRIVE_TYPE_144, 21, 83, 1, FDRIVE_RATE_500K, },
+ { FLOPPY_DRIVE_TYPE_144, 22, 80, 1, FDRIVE_RATE_500K, },
+ { FLOPPY_DRIVE_TYPE_144, 23, 80, 1, FDRIVE_RATE_500K, },
+ { FLOPPY_DRIVE_TYPE_144, 24, 80, 1, FDRIVE_RATE_500K, },
+ /* 2.88 MB 3"1/2 floppy disks */
+ { FLOPPY_DRIVE_TYPE_288, 36, 80, 1, FDRIVE_RATE_1M, },
+ { FLOPPY_DRIVE_TYPE_288, 39, 80, 1, FDRIVE_RATE_1M, },
+ { FLOPPY_DRIVE_TYPE_288, 40, 80, 1, FDRIVE_RATE_1M, },
+ { FLOPPY_DRIVE_TYPE_288, 44, 80, 1, FDRIVE_RATE_1M, },
+ { FLOPPY_DRIVE_TYPE_288, 48, 80, 1, FDRIVE_RATE_1M, },
+ /* 720 kB 3"1/2 floppy disks */
+ { FLOPPY_DRIVE_TYPE_144, 9, 80, 1, FDRIVE_RATE_250K, }, /* 3.5" 1440 */
+ { FLOPPY_DRIVE_TYPE_144, 10, 80, 1, FDRIVE_RATE_250K, },
+ { FLOPPY_DRIVE_TYPE_144, 10, 82, 1, FDRIVE_RATE_250K, },
+ { FLOPPY_DRIVE_TYPE_144, 10, 83, 1, FDRIVE_RATE_250K, },
+ { FLOPPY_DRIVE_TYPE_144, 13, 80, 1, FDRIVE_RATE_250K, },
+ { FLOPPY_DRIVE_TYPE_144, 14, 80, 1, FDRIVE_RATE_250K, },
+ /* 1.2 MB 5"1/4 floppy disks */
+ { FLOPPY_DRIVE_TYPE_120, 15, 80, 1, FDRIVE_RATE_500K, },
+ { FLOPPY_DRIVE_TYPE_120, 18, 80, 1, FDRIVE_RATE_500K, }, /* 5.25" 2880 */
+ { FLOPPY_DRIVE_TYPE_120, 18, 82, 1, FDRIVE_RATE_500K, },
+ { FLOPPY_DRIVE_TYPE_120, 18, 83, 1, FDRIVE_RATE_500K, },
+ { FLOPPY_DRIVE_TYPE_120, 20, 80, 1, FDRIVE_RATE_500K, }, /* 5.25" 3200 */
+ /* 720 kB 5"1/4 floppy disks */
+ { FLOPPY_DRIVE_TYPE_120, 9, 80, 1, FDRIVE_RATE_250K, }, /* 5.25" 1440 */
+ { FLOPPY_DRIVE_TYPE_120, 11, 80, 1, FDRIVE_RATE_250K, },
+ /* 360 kB 5"1/4 floppy disks */
+ { FLOPPY_DRIVE_TYPE_120, 9, 40, 1, FDRIVE_RATE_300K, }, /* 5.25" 720 */
+ { FLOPPY_DRIVE_TYPE_120, 9, 40, 0, FDRIVE_RATE_300K, },
+ { FLOPPY_DRIVE_TYPE_120, 10, 41, 1, FDRIVE_RATE_300K, },
+ { FLOPPY_DRIVE_TYPE_120, 10, 42, 1, FDRIVE_RATE_300K, },
+ /* 320 kB 5"1/4 floppy disks */
+ { FLOPPY_DRIVE_TYPE_120, 8, 40, 1, FDRIVE_RATE_250K, },
+ { FLOPPY_DRIVE_TYPE_120, 8, 40, 0, FDRIVE_RATE_250K, },
+ /* 360 kB must match 5"1/4 better than 3"1/2... */
+ { FLOPPY_DRIVE_TYPE_144, 9, 80, 0, FDRIVE_RATE_250K, }, /* 3.5" 720 */
+ /* end */
+ { FLOPPY_DRIVE_TYPE_NONE, -1, -1, 0, 0, },
+};
+
+static FDriveSize drive_size(FloppyDriveType drive)
+{
+ switch (drive) {
+ case FLOPPY_DRIVE_TYPE_120:
+ return FDRIVE_SIZE_525;
+ case FLOPPY_DRIVE_TYPE_144:
+ case FLOPPY_DRIVE_TYPE_288:
+ return FDRIVE_SIZE_350;
+ default:
+ return FDRIVE_SIZE_UNKNOWN;
+ }
+}
+
+#define GET_CUR_DRV(fdctrl) ((fdctrl)->cur_drv)
+#define SET_CUR_DRV(fdctrl, drive) ((fdctrl)->cur_drv = (drive))
+
+/* Will always be a fixed parameter for us */
+#define FD_SECTOR_LEN 512
+#define FD_SECTOR_SC 2 /* Sector size code */
+#define FD_RESET_SENSEI_COUNT 4 /* Number of sense interrupts on RESET */
+
+
+static FloppyDriveType get_fallback_drive_type(FDrive *drv);
+
+/* Hack: FD_SEEK is expected to work on empty drives. However, QEMU
+ * currently goes through some pains to keep seeks within the bounds
+ * established by last_sect and max_track. Correcting this is difficult,
+ * as refactoring FDC code tends to expose nasty bugs in the Linux kernel.
+ *
+ * For now: allow empty drives to have large bounds so we can seek around,
+ * with the understanding that when a diskette is inserted, the bounds will
+ * properly tighten to match the geometry of that inserted medium.
+ */
+static void fd_empty_seek_hack(FDrive *drv)
+{
+ drv->last_sect = 0xFF;
+ drv->max_track = 0xFF;
+}
+
+static void fd_init(FDrive *drv)
+{
+ /* Drive */
+ drv->perpendicular = 0;
+ /* Disk */
+ drv->disk = FLOPPY_DRIVE_TYPE_NONE;
+ drv->last_sect = 0;
+ drv->max_track = 0;
+ drv->ro = true;
+ drv->media_changed = 1;
+}
+
+#define NUM_SIDES(drv) ((drv)->flags & FDISK_DBL_SIDES ? 2 : 1)
+
+static int fd_sector_calc(uint8_t head, uint8_t track, uint8_t sect,
+ uint8_t last_sect, uint8_t num_sides)
+{
+ return (((track * num_sides) + head) * last_sect) + sect - 1;
+}
+
+/* Returns current position, in sectors, for given drive */
+static int fd_sector(FDrive *drv)
+{
+ return fd_sector_calc(drv->head, drv->track, drv->sect, drv->last_sect,
+ NUM_SIDES(drv));
+}
+
+/* Returns current position, in bytes, for given drive */
+static int fd_offset(FDrive *drv)
+{
+ g_assert(fd_sector(drv) < INT_MAX >> BDRV_SECTOR_BITS);
+ return fd_sector(drv) << BDRV_SECTOR_BITS;
+}
+
+/* Seek to a new position:
+ * returns 0 if already on right track
+ * returns 1 if track changed
+ * returns 2 if track is invalid
+ * returns 3 if sector is invalid
+ * returns 4 if seek is disabled
+ */
+static int fd_seek(FDrive *drv, uint8_t head, uint8_t track, uint8_t sect,
+ int enable_seek)
+{
+ uint32_t sector;
+ int ret;
+
+ if (track > drv->max_track ||
+ (head != 0 && (drv->flags & FDISK_DBL_SIDES) == 0)) {
+ FLOPPY_DPRINTF("try to read %d %02x %02x (max=%d %d %02x %02x)\n",
+ head, track, sect, 1,
+ (drv->flags & FDISK_DBL_SIDES) == 0 ? 0 : 1,
+ drv->max_track, drv->last_sect);
+ return 2;
+ }
+ if (sect > drv->last_sect) {
+ FLOPPY_DPRINTF("try to read %d %02x %02x (max=%d %d %02x %02x)\n",
+ head, track, sect, 1,
+ (drv->flags & FDISK_DBL_SIDES) == 0 ? 0 : 1,
+ drv->max_track, drv->last_sect);
+ return 3;
+ }
+ sector = fd_sector_calc(head, track, sect, drv->last_sect, NUM_SIDES(drv));
+ ret = 0;
+ if (sector != fd_sector(drv)) {
+#if 0
+ if (!enable_seek) {
+ FLOPPY_DPRINTF("error: no implicit seek %d %02x %02x"
+ " (max=%d %02x %02x)\n",
+ head, track, sect, 1, drv->max_track,
+ drv->last_sect);
+ return 4;
+ }
+#endif
+ drv->head = head;
+ if (drv->track != track) {
+ if (drv->blk != NULL && blk_is_inserted(drv->blk)) {
+ drv->media_changed = 0;
+ }
+ ret = 1;
+ }
+ drv->track = track;
+ drv->sect = sect;
+ }
+
+ if (drv->blk == NULL || !blk_is_inserted(drv->blk)) {
+ ret = 2;
+ }
+
+ return ret;
+}
+
+/* Set drive back to track 0 */
+static void fd_recalibrate(FDrive *drv)
+{
+ FLOPPY_DPRINTF("recalibrate\n");
+ fd_seek(drv, 0, 0, 1, 1);
+}
+
+/**
+ * Determine geometry based on inserted diskette.
+ * Will not operate on an empty drive.
+ *
+ * @return: 0 on success, -1 if the drive is empty.
+ */
+static int pick_geometry(FDrive *drv)
+{
+ BlockBackend *blk = drv->blk;
+ const FDFormat *parse;
+ uint64_t nb_sectors, size;
+ int i;
+ int match, size_match, type_match;
+ bool magic = drv->drive == FLOPPY_DRIVE_TYPE_AUTO;
+
+ /* We can only pick a geometry if we have a diskette. */
+ if (!drv->blk || !blk_is_inserted(drv->blk) ||
+ drv->drive == FLOPPY_DRIVE_TYPE_NONE)
+ {
+ return -1;
+ }
+
+ /* We need to determine the likely geometry of the inserted medium.
+ * In order of preference, we look for:
+ * (1) The same drive type and number of sectors,
+ * (2) The same diskette size and number of sectors,
+ * (3) The same drive type.
+ *
+ * In all cases, matches that occur higher in the drive table will take
+ * precedence over matches that occur later in the table.
+ */
+ blk_get_geometry(blk, &nb_sectors);
+ match = size_match = type_match = -1;
+ for (i = 0; ; i++) {
+ parse = &fd_formats[i];
+ if (parse->drive == FLOPPY_DRIVE_TYPE_NONE) {
+ break;
+ }
+ size = (parse->max_head + 1) * parse->max_track * parse->last_sect;
+ if (nb_sectors == size) {
+ if (magic || parse->drive == drv->drive) {
+ /* (1) perfect match -- nb_sectors and drive type */
+ goto out;
+ } else if (drive_size(parse->drive) == drive_size(drv->drive)) {
+ /* (2) size match -- nb_sectors and physical medium size */
+ match = (match == -1) ? i : match;
+ } else {
+ /* This is suspicious -- Did the user misconfigure? */
+ size_match = (size_match == -1) ? i : size_match;
+ }
+ } else if (type_match == -1) {
+ if ((parse->drive == drv->drive) ||
+ (magic && (parse->drive == get_fallback_drive_type(drv)))) {
+ /* (3) type match -- nb_sectors mismatch, but matches the type
+ * specified explicitly by the user, or matches the fallback
+ * default type when using the drive autodetect mechanism */
+ type_match = i;
+ }
+ }
+ }
+
+ /* No exact match found */
+ if (match == -1) {
+ if (size_match != -1) {
+ parse = &fd_formats[size_match];
+ FLOPPY_DPRINTF("User requested floppy drive type '%s', "
+ "but inserted medium appears to be a "
+ "%"PRId64" sector '%s' type\n",
+ FloppyDriveType_str(drv->drive),
+ nb_sectors,
+ FloppyDriveType_str(parse->drive));
+ }
+ assert(type_match != -1 && "misconfigured fd_format");
+ match = type_match;
+ }
+ parse = &(fd_formats[match]);
+
+ out:
+ if (parse->max_head == 0) {
+ drv->flags &= ~FDISK_DBL_SIDES;
+ } else {
+ drv->flags |= FDISK_DBL_SIDES;
+ }
+ drv->max_track = parse->max_track;
+ drv->last_sect = parse->last_sect;
+ drv->disk = parse->drive;
+ drv->media_rate = parse->rate;
+ return 0;
+}
+
+static void pick_drive_type(FDrive *drv)
+{
+ if (drv->drive != FLOPPY_DRIVE_TYPE_AUTO) {
+ return;
+ }
+
+ if (pick_geometry(drv) == 0) {
+ drv->drive = drv->disk;
+ } else {
+ drv->drive = get_fallback_drive_type(drv);
+ }
+
+ g_assert(drv->drive != FLOPPY_DRIVE_TYPE_AUTO);
+}
+
+/* Revalidate a disk drive after a disk change */
+static void fd_revalidate(FDrive *drv)
+{
+ int rc;
+
+ FLOPPY_DPRINTF("revalidate\n");
+ if (drv->blk != NULL) {
+ drv->ro = !blk_is_writable(drv->blk);
+ if (!blk_is_inserted(drv->blk)) {
+ FLOPPY_DPRINTF("No disk in drive\n");
+ drv->disk = FLOPPY_DRIVE_TYPE_NONE;
+ fd_empty_seek_hack(drv);
+ } else if (!drv->media_validated) {
+ rc = pick_geometry(drv);
+ if (rc) {
+ FLOPPY_DPRINTF("Could not validate floppy drive media");
+ } else {
+ drv->media_validated = true;
+ FLOPPY_DPRINTF("Floppy disk (%d h %d t %d s) %s\n",
+ (drv->flags & FDISK_DBL_SIDES) ? 2 : 1,
+ drv->max_track, drv->last_sect,
+ drv->ro ? "ro" : "rw");
+ }
+ }
+ } else {
+ FLOPPY_DPRINTF("No drive connected\n");
+ drv->last_sect = 0;
+ drv->max_track = 0;
+ drv->flags &= ~FDISK_DBL_SIDES;
+ drv->drive = FLOPPY_DRIVE_TYPE_NONE;
+ drv->disk = FLOPPY_DRIVE_TYPE_NONE;
+ }
+}
+
+static void fd_change_cb(void *opaque, bool load, Error **errp)
+{
+ FDrive *drive = opaque;
+
+ if (!load) {
+ blk_set_perm(drive->blk, 0, BLK_PERM_ALL, &error_abort);
+ } else {
+ if (!blkconf_apply_backend_options(drive->conf,
+ !blk_supports_write_perm(drive->blk),
+ false, errp)) {
+ return;
+ }
+ }
+
+ drive->media_changed = 1;
+ drive->media_validated = false;
+ fd_revalidate(drive);
+}
+
+static const BlockDevOps fd_block_ops = {
+ .change_media_cb = fd_change_cb,
+};
+
+
+#define TYPE_FLOPPY_DRIVE "floppy"
+OBJECT_DECLARE_SIMPLE_TYPE(FloppyDrive, FLOPPY_DRIVE)
+
+struct FloppyDrive {
+ DeviceState qdev;
+ uint32_t unit;
+ BlockConf conf;
+ FloppyDriveType type;
+};
+
+static Property floppy_drive_properties[] = {
+ DEFINE_PROP_UINT32("unit", FloppyDrive, unit, -1),
+ DEFINE_BLOCK_PROPERTIES(FloppyDrive, conf),
+ DEFINE_PROP_SIGNED("drive-type", FloppyDrive, type,
+ FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type,
+ FloppyDriveType),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void floppy_drive_realize(DeviceState *qdev, Error **errp)
+{
+ FloppyDrive *dev = FLOPPY_DRIVE(qdev);
+ FloppyBus *bus = FLOPPY_BUS(qdev->parent_bus);
+ FDrive *drive;
+ bool read_only;
+ int ret;
+
+ if (dev->unit == -1) {
+ for (dev->unit = 0; dev->unit < MAX_FD; dev->unit++) {
+ drive = get_drv(bus->fdc, dev->unit);
+ if (!drive->blk) {
+ break;
+ }
+ }
+ }
+
+ if (dev->unit >= MAX_FD) {
+ error_setg(errp, "Can't create floppy unit %d, bus supports "
+ "only %d units", dev->unit, MAX_FD);
+ return;
+ }
+
+ drive = get_drv(bus->fdc, dev->unit);
+ if (drive->blk) {
+ error_setg(errp, "Floppy unit %d is in use", dev->unit);
+ return;
+ }
+
+ if (!dev->conf.blk) {
+ dev->conf.blk = blk_create_empty_drive();
+ ret = blk_attach_dev(dev->conf.blk, qdev);
+ assert(ret == 0);
+
+ /* Don't take write permissions on an empty drive to allow attaching a
+ * read-only node later */
+ read_only = true;
+ } else {
+ read_only = !blk_bs(dev->conf.blk) ||
+ !blk_supports_write_perm(dev->conf.blk);
+ }
+
+ if (!blkconf_blocksizes(&dev->conf, errp)) {
+ return;
+ }
+
+ if (dev->conf.logical_block_size != 512 ||
+ dev->conf.physical_block_size != 512)
+ {
+ error_setg(errp, "Physical and logical block size must "
+ "be 512 for floppy");
+ return;
+ }
+
+ /* rerror/werror aren't supported by fdc and therefore not even registered
+ * with qdev. So set the defaults manually before they are used in
+ * blkconf_apply_backend_options(). */
+ dev->conf.rerror = BLOCKDEV_ON_ERROR_AUTO;
+ dev->conf.werror = BLOCKDEV_ON_ERROR_AUTO;
+
+ if (!blkconf_apply_backend_options(&dev->conf, read_only, false, errp)) {
+ return;
+ }
+
+ /* 'enospc' is the default for -drive, 'report' is what blk_new() gives us
+ * for empty drives. */
+ if (blk_get_on_error(dev->conf.blk, 0) != BLOCKDEV_ON_ERROR_ENOSPC &&
+ blk_get_on_error(dev->conf.blk, 0) != BLOCKDEV_ON_ERROR_REPORT) {
+ error_setg(errp, "fdc doesn't support drive option werror");
+ return;
+ }
+ if (blk_get_on_error(dev->conf.blk, 1) != BLOCKDEV_ON_ERROR_REPORT) {
+ error_setg(errp, "fdc doesn't support drive option rerror");
+ return;
+ }
+
+ drive->conf = &dev->conf;
+ drive->blk = dev->conf.blk;
+ drive->fdctrl = bus->fdc;
+
+ fd_init(drive);
+ blk_set_dev_ops(drive->blk, &fd_block_ops, drive);
+
+ /* Keep 'type' qdev property and FDrive->drive in sync */
+ drive->drive = dev->type;
+ pick_drive_type(drive);
+ dev->type = drive->drive;
+
+ fd_revalidate(drive);
+}
+
+static void floppy_drive_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *k = DEVICE_CLASS(klass);
+ k->realize = floppy_drive_realize;
+ set_bit(DEVICE_CATEGORY_STORAGE, k->categories);
+ k->bus_type = TYPE_FLOPPY_BUS;
+ device_class_set_props(k, floppy_drive_properties);
+ k->desc = "virtual floppy drive";
+}
+
+static const TypeInfo floppy_drive_info = {
+ .name = TYPE_FLOPPY_DRIVE,
+ .parent = TYPE_DEVICE,
+ .instance_size = sizeof(FloppyDrive),
+ .class_init = floppy_drive_class_init,
+};
+
+/********************************************************/
+/* Intel 82078 floppy disk controller emulation */
+
+static void fdctrl_to_command_phase(FDCtrl *fdctrl);
+static void fdctrl_raise_irq(FDCtrl *fdctrl);
+static FDrive *get_cur_drv(FDCtrl *fdctrl);
+
+static uint32_t fdctrl_read_statusA(FDCtrl *fdctrl);
+static uint32_t fdctrl_read_statusB(FDCtrl *fdctrl);
+static uint32_t fdctrl_read_dor(FDCtrl *fdctrl);
+static void fdctrl_write_dor(FDCtrl *fdctrl, uint32_t value);
+static uint32_t fdctrl_read_tape(FDCtrl *fdctrl);
+static void fdctrl_write_tape(FDCtrl *fdctrl, uint32_t value);
+static uint32_t fdctrl_read_main_status(FDCtrl *fdctrl);
+static void fdctrl_write_rate(FDCtrl *fdctrl, uint32_t value);
+static uint32_t fdctrl_read_data(FDCtrl *fdctrl);
+static void fdctrl_write_data(FDCtrl *fdctrl, uint32_t value);
+static uint32_t fdctrl_read_dir(FDCtrl *fdctrl);
+static void fdctrl_write_ccr(FDCtrl *fdctrl, uint32_t value);
+
+enum {
+ FD_DIR_WRITE = 0,
+ FD_DIR_READ = 1,
+ FD_DIR_SCANE = 2,
+ FD_DIR_SCANL = 3,
+ FD_DIR_SCANH = 4,
+ FD_DIR_VERIFY = 5,
+};
+
+enum {
+ FD_STATE_MULTI = 0x01, /* multi track flag */
+ FD_STATE_FORMAT = 0x02, /* format flag */
+};
+
+enum {
+ FD_REG_SRA = 0x00,
+ FD_REG_SRB = 0x01,
+ FD_REG_DOR = 0x02,
+ FD_REG_TDR = 0x03,
+ FD_REG_MSR = 0x04,
+ FD_REG_DSR = 0x04,
+ FD_REG_FIFO = 0x05,
+ FD_REG_DIR = 0x07,
+ FD_REG_CCR = 0x07,
+};
+
+enum {
+ FD_CMD_READ_TRACK = 0x02,
+ FD_CMD_SPECIFY = 0x03,
+ FD_CMD_SENSE_DRIVE_STATUS = 0x04,
+ FD_CMD_WRITE = 0x05,
+ FD_CMD_READ = 0x06,
+ FD_CMD_RECALIBRATE = 0x07,
+ FD_CMD_SENSE_INTERRUPT_STATUS = 0x08,
+ FD_CMD_WRITE_DELETED = 0x09,
+ FD_CMD_READ_ID = 0x0a,
+ FD_CMD_READ_DELETED = 0x0c,
+ FD_CMD_FORMAT_TRACK = 0x0d,
+ FD_CMD_DUMPREG = 0x0e,
+ FD_CMD_SEEK = 0x0f,
+ FD_CMD_VERSION = 0x10,
+ FD_CMD_SCAN_EQUAL = 0x11,
+ FD_CMD_PERPENDICULAR_MODE = 0x12,
+ FD_CMD_CONFIGURE = 0x13,
+ FD_CMD_LOCK = 0x14,
+ FD_CMD_VERIFY = 0x16,
+ FD_CMD_POWERDOWN_MODE = 0x17,
+ FD_CMD_PART_ID = 0x18,
+ FD_CMD_SCAN_LOW_OR_EQUAL = 0x19,
+ FD_CMD_SCAN_HIGH_OR_EQUAL = 0x1d,
+ FD_CMD_SAVE = 0x2e,
+ FD_CMD_OPTION = 0x33,
+ FD_CMD_RESTORE = 0x4e,
+ FD_CMD_DRIVE_SPECIFICATION_COMMAND = 0x8e,
+ FD_CMD_RELATIVE_SEEK_OUT = 0x8f,
+ FD_CMD_FORMAT_AND_WRITE = 0xcd,
+ FD_CMD_RELATIVE_SEEK_IN = 0xcf,
+};
+
+enum {
+ FD_CONFIG_PRETRK = 0xff, /* Pre-compensation set to track 0 */
+ FD_CONFIG_FIFOTHR = 0x0f, /* FIFO threshold set to 1 byte */
+ FD_CONFIG_POLL = 0x10, /* Poll enabled */
+ FD_CONFIG_EFIFO = 0x20, /* FIFO disabled */
+ FD_CONFIG_EIS = 0x40, /* No implied seeks */
+};
+
+enum {
+ FD_SR0_DS0 = 0x01,
+ FD_SR0_DS1 = 0x02,
+ FD_SR0_HEAD = 0x04,
+ FD_SR0_EQPMT = 0x10,
+ FD_SR0_SEEK = 0x20,
+ FD_SR0_ABNTERM = 0x40,
+ FD_SR0_INVCMD = 0x80,
+ FD_SR0_RDYCHG = 0xc0,
+};
+
+enum {
+ FD_SR1_MA = 0x01, /* Missing address mark */
+ FD_SR1_NW = 0x02, /* Not writable */
+ FD_SR1_EC = 0x80, /* End of cylinder */
+};
+
+enum {
+ FD_SR2_SNS = 0x04, /* Scan not satisfied */
+ FD_SR2_SEH = 0x08, /* Scan equal hit */
+};
+
+enum {
+ FD_SRA_DIR = 0x01,
+ FD_SRA_nWP = 0x02,
+ FD_SRA_nINDX = 0x04,
+ FD_SRA_HDSEL = 0x08,
+ FD_SRA_nTRK0 = 0x10,
+ FD_SRA_STEP = 0x20,
+ FD_SRA_nDRV2 = 0x40,
+ FD_SRA_INTPEND = 0x80,
+};
+
+enum {
+ FD_SRB_MTR0 = 0x01,
+ FD_SRB_MTR1 = 0x02,
+ FD_SRB_WGATE = 0x04,
+ FD_SRB_RDATA = 0x08,
+ FD_SRB_WDATA = 0x10,
+ FD_SRB_DR0 = 0x20,
+};
+
+enum {
+#if MAX_FD == 4
+ FD_DOR_SELMASK = 0x03,
+#else
+ FD_DOR_SELMASK = 0x01,
+#endif
+ FD_DOR_nRESET = 0x04,
+ FD_DOR_DMAEN = 0x08,
+ FD_DOR_MOTEN0 = 0x10,
+ FD_DOR_MOTEN1 = 0x20,
+ FD_DOR_MOTEN2 = 0x40,
+ FD_DOR_MOTEN3 = 0x80,
+};
+
+enum {
+#if MAX_FD == 4
+ FD_TDR_BOOTSEL = 0x0c,
+#else
+ FD_TDR_BOOTSEL = 0x04,
+#endif
+};
+
+enum {
+ FD_DSR_DRATEMASK= 0x03,
+ FD_DSR_PWRDOWN = 0x40,
+ FD_DSR_SWRESET = 0x80,
+};
+
+enum {
+ FD_MSR_DRV0BUSY = 0x01,
+ FD_MSR_DRV1BUSY = 0x02,
+ FD_MSR_DRV2BUSY = 0x04,
+ FD_MSR_DRV3BUSY = 0x08,
+ FD_MSR_CMDBUSY = 0x10,
+ FD_MSR_NONDMA = 0x20,
+ FD_MSR_DIO = 0x40,
+ FD_MSR_RQM = 0x80,
+};
+
+enum {
+ FD_DIR_DSKCHG = 0x80,
+};
+
+/*
+ * See chapter 5.0 "Controller phases" of the spec:
+ *
+ * Command phase:
+ * The host writes a command and its parameters into the FIFO. The command
+ * phase is completed when all parameters for the command have been supplied,
+ * and execution phase is entered.
+ *
+ * Execution phase:
+ * Data transfers, either DMA or non-DMA. For non-DMA transfers, the FIFO
+ * contains the payload now, otherwise it's unused. When all bytes of the
+ * required data have been transferred, the state is switched to either result
+ * phase (if the command produces status bytes) or directly back into the
+ * command phase for the next command.
+ *
+ * Result phase:
+ * The host reads out the FIFO, which contains one or more result bytes now.
+ */
+enum {
+ /* Only for migration: reconstruct phase from registers like qemu 2.3 */
+ FD_PHASE_RECONSTRUCT = 0,
+
+ FD_PHASE_COMMAND = 1,
+ FD_PHASE_EXECUTION = 2,
+ FD_PHASE_RESULT = 3,
+};
+
+#define FD_MULTI_TRACK(state) ((state) & FD_STATE_MULTI)
+#define FD_FORMAT_CMD(state) ((state) & FD_STATE_FORMAT)
+
+static FloppyDriveType get_fallback_drive_type(FDrive *drv)
+{
+ return drv->fdctrl->fallback;
+}
+
+uint32_t fdctrl_read(void *opaque, uint32_t reg)
+{
+ FDCtrl *fdctrl = opaque;
+ uint32_t retval;
+
+ reg &= 7;
+ switch (reg) {
+ case FD_REG_SRA:
+ retval = fdctrl_read_statusA(fdctrl);
+ break;
+ case FD_REG_SRB:
+ retval = fdctrl_read_statusB(fdctrl);
+ break;
+ case FD_REG_DOR:
+ retval = fdctrl_read_dor(fdctrl);
+ break;
+ case FD_REG_TDR:
+ retval = fdctrl_read_tape(fdctrl);
+ break;
+ case FD_REG_MSR:
+ retval = fdctrl_read_main_status(fdctrl);
+ break;
+ case FD_REG_FIFO:
+ retval = fdctrl_read_data(fdctrl);
+ break;
+ case FD_REG_DIR:
+ retval = fdctrl_read_dir(fdctrl);
+ break;
+ default:
+ retval = (uint32_t)(-1);
+ break;
+ }
+ trace_fdc_ioport_read(reg, retval);
+
+ return retval;
+}
+
+void fdctrl_write(void *opaque, uint32_t reg, uint32_t value)
+{
+ FDCtrl *fdctrl = opaque;
+
+ reg &= 7;
+ trace_fdc_ioport_write(reg, value);
+ switch (reg) {
+ case FD_REG_DOR:
+ fdctrl_write_dor(fdctrl, value);
+ break;
+ case FD_REG_TDR:
+ fdctrl_write_tape(fdctrl, value);
+ break;
+ case FD_REG_DSR:
+ fdctrl_write_rate(fdctrl, value);
+ break;
+ case FD_REG_FIFO:
+ fdctrl_write_data(fdctrl, value);
+ break;
+ case FD_REG_CCR:
+ fdctrl_write_ccr(fdctrl, value);
+ break;
+ default:
+ break;
+ }
+}
+
+static bool fdrive_media_changed_needed(void *opaque)
+{
+ FDrive *drive = opaque;
+
+ return (drive->blk != NULL && drive->media_changed != 1);
+}
+
+static const VMStateDescription vmstate_fdrive_media_changed = {
+ .name = "fdrive/media_changed",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = fdrive_media_changed_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(media_changed, FDrive),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static const VMStateDescription vmstate_fdrive_media_rate = {
+ .name = "fdrive/media_rate",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(media_rate, FDrive),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static bool fdrive_perpendicular_needed(void *opaque)
+{
+ FDrive *drive = opaque;
+
+ return drive->perpendicular != 0;
+}
+
+static const VMStateDescription vmstate_fdrive_perpendicular = {
+ .name = "fdrive/perpendicular",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = fdrive_perpendicular_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(perpendicular, FDrive),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static int fdrive_post_load(void *opaque, int version_id)
+{
+ fd_revalidate(opaque);
+ return 0;
+}
+
+static const VMStateDescription vmstate_fdrive = {
+ .name = "fdrive",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .post_load = fdrive_post_load,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(head, FDrive),
+ VMSTATE_UINT8(track, FDrive),
+ VMSTATE_UINT8(sect, FDrive),
+ VMSTATE_END_OF_LIST()
+ },
+ .subsections = (const VMStateDescription*[]) {
+ &vmstate_fdrive_media_changed,
+ &vmstate_fdrive_media_rate,
+ &vmstate_fdrive_perpendicular,
+ NULL
+ }
+};
+
+/*
+ * Reconstructs the phase from register values according to the logic that was
+ * implemented in qemu 2.3. This is the default value that is used if the phase
+ * subsection is not present on migration.
+ *
+ * Don't change this function to reflect newer qemu versions, it is part of
+ * the migration ABI.
+ */
+static int reconstruct_phase(FDCtrl *fdctrl)
+{
+ if (fdctrl->msr & FD_MSR_NONDMA) {
+ return FD_PHASE_EXECUTION;
+ } else if ((fdctrl->msr & FD_MSR_RQM) == 0) {
+ /* qemu 2.3 disabled RQM only during DMA transfers */
+ return FD_PHASE_EXECUTION;
+ } else if (fdctrl->msr & FD_MSR_DIO) {
+ return FD_PHASE_RESULT;
+ } else {
+ return FD_PHASE_COMMAND;
+ }
+}
+
+static int fdc_pre_save(void *opaque)
+{
+ FDCtrl *s = opaque;
+
+ s->dor_vmstate = s->dor | GET_CUR_DRV(s);
+
+ return 0;
+}
+
+static int fdc_pre_load(void *opaque)
+{
+ FDCtrl *s = opaque;
+ s->phase = FD_PHASE_RECONSTRUCT;
+ return 0;
+}
+
+static int fdc_post_load(void *opaque, int version_id)
+{
+ FDCtrl *s = opaque;
+
+ SET_CUR_DRV(s, s->dor_vmstate & FD_DOR_SELMASK);
+ s->dor = s->dor_vmstate & ~FD_DOR_SELMASK;
+
+ if (s->phase == FD_PHASE_RECONSTRUCT) {
+ s->phase = reconstruct_phase(s);
+ }
+
+ return 0;
+}
+
+static bool fdc_reset_sensei_needed(void *opaque)
+{
+ FDCtrl *s = opaque;
+
+ return s->reset_sensei != 0;
+}
+
+static const VMStateDescription vmstate_fdc_reset_sensei = {
+ .name = "fdc/reset_sensei",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = fdc_reset_sensei_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_INT32(reset_sensei, FDCtrl),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static bool fdc_result_timer_needed(void *opaque)
+{
+ FDCtrl *s = opaque;
+
+ return timer_pending(s->result_timer);
+}
+
+static const VMStateDescription vmstate_fdc_result_timer = {
+ .name = "fdc/result_timer",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = fdc_result_timer_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_TIMER_PTR(result_timer, FDCtrl),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static bool fdc_phase_needed(void *opaque)
+{
+ FDCtrl *fdctrl = opaque;
+
+ return reconstruct_phase(fdctrl) != fdctrl->phase;
+}
+
+static const VMStateDescription vmstate_fdc_phase = {
+ .name = "fdc/phase",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = fdc_phase_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(phase, FDCtrl),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+const VMStateDescription vmstate_fdc = {
+ .name = "fdc",
+ .version_id = 2,
+ .minimum_version_id = 2,
+ .pre_save = fdc_pre_save,
+ .pre_load = fdc_pre_load,
+ .post_load = fdc_post_load,
+ .fields = (VMStateField[]) {
+ /* Controller State */
+ VMSTATE_UINT8(sra, FDCtrl),
+ VMSTATE_UINT8(srb, FDCtrl),
+ VMSTATE_UINT8(dor_vmstate, FDCtrl),
+ VMSTATE_UINT8(tdr, FDCtrl),
+ VMSTATE_UINT8(dsr, FDCtrl),
+ VMSTATE_UINT8(msr, FDCtrl),
+ VMSTATE_UINT8(status0, FDCtrl),
+ VMSTATE_UINT8(status1, FDCtrl),
+ VMSTATE_UINT8(status2, FDCtrl),
+ /* Command FIFO */
+ VMSTATE_VARRAY_INT32(fifo, FDCtrl, fifo_size, 0, vmstate_info_uint8,
+ uint8_t),
+ VMSTATE_UINT32(data_pos, FDCtrl),
+ VMSTATE_UINT32(data_len, FDCtrl),
+ VMSTATE_UINT8(data_state, FDCtrl),
+ VMSTATE_UINT8(data_dir, FDCtrl),
+ VMSTATE_UINT8(eot, FDCtrl),
+ /* States kept only to be returned back */
+ VMSTATE_UINT8(timer0, FDCtrl),
+ VMSTATE_UINT8(timer1, FDCtrl),
+ VMSTATE_UINT8(precomp_trk, FDCtrl),
+ VMSTATE_UINT8(config, FDCtrl),
+ VMSTATE_UINT8(lock, FDCtrl),
+ VMSTATE_UINT8(pwrd, FDCtrl),
+ VMSTATE_UINT8_EQUAL(num_floppies, FDCtrl, NULL),
+ VMSTATE_STRUCT_ARRAY(drives, FDCtrl, MAX_FD, 1,
+ vmstate_fdrive, FDrive),
+ VMSTATE_END_OF_LIST()
+ },
+ .subsections = (const VMStateDescription*[]) {
+ &vmstate_fdc_reset_sensei,
+ &vmstate_fdc_result_timer,
+ &vmstate_fdc_phase,
+ NULL
+ }
+};
+
+/* Change IRQ state */
+static void fdctrl_reset_irq(FDCtrl *fdctrl)
+{
+ fdctrl->status0 = 0;
+ if (!(fdctrl->sra & FD_SRA_INTPEND))
+ return;
+ FLOPPY_DPRINTF("Reset interrupt\n");
+ qemu_set_irq(fdctrl->irq, 0);
+ fdctrl->sra &= ~FD_SRA_INTPEND;
+}
+
+static void fdctrl_raise_irq(FDCtrl *fdctrl)
+{
+ if (!(fdctrl->sra & FD_SRA_INTPEND)) {
+ qemu_set_irq(fdctrl->irq, 1);
+ fdctrl->sra |= FD_SRA_INTPEND;
+ }
+
+ fdctrl->reset_sensei = 0;
+ FLOPPY_DPRINTF("Set interrupt status to 0x%02x\n", fdctrl->status0);
+}
+
+/* Reset controller */
+void fdctrl_reset(FDCtrl *fdctrl, int do_irq)
+{
+ int i;
+
+ FLOPPY_DPRINTF("reset controller\n");
+ fdctrl_reset_irq(fdctrl);
+ /* Initialise controller */
+ fdctrl->sra = 0;
+ fdctrl->srb = 0xc0;
+ if (!fdctrl->drives[1].blk) {
+ fdctrl->sra |= FD_SRA_nDRV2;
+ }
+ fdctrl->cur_drv = 0;
+ fdctrl->dor = FD_DOR_nRESET;
+ fdctrl->dor |= (fdctrl->dma_chann != -1) ? FD_DOR_DMAEN : 0;
+ fdctrl->msr = FD_MSR_RQM;
+ fdctrl->reset_sensei = 0;
+ timer_del(fdctrl->result_timer);
+ /* FIFO state */
+ fdctrl->data_pos = 0;
+ fdctrl->data_len = 0;
+ fdctrl->data_state = 0;
+ fdctrl->data_dir = FD_DIR_WRITE;
+ for (i = 0; i < MAX_FD; i++)
+ fd_recalibrate(&fdctrl->drives[i]);
+ fdctrl_to_command_phase(fdctrl);
+ if (do_irq) {
+ fdctrl->status0 |= FD_SR0_RDYCHG;
+ fdctrl_raise_irq(fdctrl);
+ fdctrl->reset_sensei = FD_RESET_SENSEI_COUNT;
+ }
+}
+
+static inline FDrive *drv0(FDCtrl *fdctrl)
+{
+ return &fdctrl->drives[(fdctrl->tdr & FD_TDR_BOOTSEL) >> 2];
+}
+
+static inline FDrive *drv1(FDCtrl *fdctrl)
+{
+ if ((fdctrl->tdr & FD_TDR_BOOTSEL) < (1 << 2))
+ return &fdctrl->drives[1];
+ else
+ return &fdctrl->drives[0];
+}
+
+#if MAX_FD == 4
+static inline FDrive *drv2(FDCtrl *fdctrl)
+{
+ if ((fdctrl->tdr & FD_TDR_BOOTSEL) < (2 << 2))
+ return &fdctrl->drives[2];
+ else
+ return &fdctrl->drives[1];
+}
+
+static inline FDrive *drv3(FDCtrl *fdctrl)
+{
+ if ((fdctrl->tdr & FD_TDR_BOOTSEL) < (3 << 2))
+ return &fdctrl->drives[3];
+ else
+ return &fdctrl->drives[2];
+}
+#endif
+
+static FDrive *get_drv(FDCtrl *fdctrl, int unit)
+{
+ switch (unit) {
+ case 0: return drv0(fdctrl);
+ case 1: return drv1(fdctrl);
+#if MAX_FD == 4
+ case 2: return drv2(fdctrl);
+ case 3: return drv3(fdctrl);
+#endif
+ default: return NULL;
+ }
+}
+
+static FDrive *get_cur_drv(FDCtrl *fdctrl)
+{
+ FDrive *cur_drv = get_drv(fdctrl, fdctrl->cur_drv);
+
+ if (!cur_drv->blk) {
+ /*
+ * Kludge: empty drive line selected. Create an anonymous
+ * BlockBackend to avoid NULL deref with various BlockBackend
+ * API calls within this model (CVE-2021-20196).
+ * Due to the controller QOM model limitations, we don't
+ * attach the created to the controller device.
+ */
+ cur_drv->blk = blk_create_empty_drive();
+ }
+ return cur_drv;
+}
+
+/* Status A register : 0x00 (read-only) */
+static uint32_t fdctrl_read_statusA(FDCtrl *fdctrl)
+{
+ uint32_t retval = fdctrl->sra;
+
+ FLOPPY_DPRINTF("status register A: 0x%02x\n", retval);
+
+ return retval;
+}
+
+/* Status B register : 0x01 (read-only) */
+static uint32_t fdctrl_read_statusB(FDCtrl *fdctrl)
+{
+ uint32_t retval = fdctrl->srb;
+
+ FLOPPY_DPRINTF("status register B: 0x%02x\n", retval);
+
+ return retval;
+}
+
+/* Digital output register : 0x02 */
+static uint32_t fdctrl_read_dor(FDCtrl *fdctrl)
+{
+ uint32_t retval = fdctrl->dor;
+
+ /* Selected drive */
+ retval |= fdctrl->cur_drv;
+ FLOPPY_DPRINTF("digital output register: 0x%02x\n", retval);
+
+ return retval;
+}
+
+static void fdctrl_write_dor(FDCtrl *fdctrl, uint32_t value)
+{
+ FLOPPY_DPRINTF("digital output register set to 0x%02x\n", value);
+
+ /* Motors */
+ if (value & FD_DOR_MOTEN0)
+ fdctrl->srb |= FD_SRB_MTR0;
+ else
+ fdctrl->srb &= ~FD_SRB_MTR0;
+ if (value & FD_DOR_MOTEN1)
+ fdctrl->srb |= FD_SRB_MTR1;
+ else
+ fdctrl->srb &= ~FD_SRB_MTR1;
+
+ /* Drive */
+ if (value & 1)
+ fdctrl->srb |= FD_SRB_DR0;
+ else
+ fdctrl->srb &= ~FD_SRB_DR0;
+
+ /* Reset */
+ if (!(value & FD_DOR_nRESET)) {
+ if (fdctrl->dor & FD_DOR_nRESET) {
+ FLOPPY_DPRINTF("controller enter RESET state\n");
+ }
+ } else {
+ if (!(fdctrl->dor & FD_DOR_nRESET)) {
+ FLOPPY_DPRINTF("controller out of RESET state\n");
+ fdctrl_reset(fdctrl, 1);
+ fdctrl->dsr &= ~FD_DSR_PWRDOWN;
+ }
+ }
+ /* Selected drive */
+ fdctrl->cur_drv = value & FD_DOR_SELMASK;
+
+ fdctrl->dor = value;
+}
+
+/* Tape drive register : 0x03 */
+static uint32_t fdctrl_read_tape(FDCtrl *fdctrl)
+{
+ uint32_t retval = fdctrl->tdr;
+
+ FLOPPY_DPRINTF("tape drive register: 0x%02x\n", retval);
+
+ return retval;
+}
+
+static void fdctrl_write_tape(FDCtrl *fdctrl, uint32_t value)
+{
+ /* Reset mode */
+ if (!(fdctrl->dor & FD_DOR_nRESET)) {
+ FLOPPY_DPRINTF("Floppy controller in RESET state !\n");
+ return;
+ }
+ FLOPPY_DPRINTF("tape drive register set to 0x%02x\n", value);
+ /* Disk boot selection indicator */
+ fdctrl->tdr = value & FD_TDR_BOOTSEL;
+ /* Tape indicators: never allow */
+}
+
+/* Main status register : 0x04 (read) */
+static uint32_t fdctrl_read_main_status(FDCtrl *fdctrl)
+{
+ uint32_t retval = fdctrl->msr;
+
+ fdctrl->dsr &= ~FD_DSR_PWRDOWN;
+ fdctrl->dor |= FD_DOR_nRESET;
+
+ FLOPPY_DPRINTF("main status register: 0x%02x\n", retval);
+
+ return retval;
+}
+
+/* Data select rate register : 0x04 (write) */
+static void fdctrl_write_rate(FDCtrl *fdctrl, uint32_t value)
+{
+ /* Reset mode */
+ if (!(fdctrl->dor & FD_DOR_nRESET)) {
+ FLOPPY_DPRINTF("Floppy controller in RESET state !\n");
+ return;
+ }
+ FLOPPY_DPRINTF("select rate register set to 0x%02x\n", value);
+ /* Reset: autoclear */
+ if (value & FD_DSR_SWRESET) {
+ fdctrl->dor &= ~FD_DOR_nRESET;
+ fdctrl_reset(fdctrl, 1);
+ fdctrl->dor |= FD_DOR_nRESET;
+ }
+ if (value & FD_DSR_PWRDOWN) {
+ fdctrl_reset(fdctrl, 1);
+ }
+ fdctrl->dsr = value;
+}
+
+/* Configuration control register: 0x07 (write) */
+static void fdctrl_write_ccr(FDCtrl *fdctrl, uint32_t value)
+{
+ /* Reset mode */
+ if (!(fdctrl->dor & FD_DOR_nRESET)) {
+ FLOPPY_DPRINTF("Floppy controller in RESET state !\n");
+ return;
+ }
+ FLOPPY_DPRINTF("configuration control register set to 0x%02x\n", value);
+
+ /* Only the rate selection bits used in AT mode, and we
+ * store those in the DSR.
+ */
+ fdctrl->dsr = (fdctrl->dsr & ~FD_DSR_DRATEMASK) |
+ (value & FD_DSR_DRATEMASK);
+}
+
+static int fdctrl_media_changed(FDrive *drv)
+{
+ return drv->media_changed;
+}
+
+/* Digital input register : 0x07 (read-only) */
+static uint32_t fdctrl_read_dir(FDCtrl *fdctrl)
+{
+ uint32_t retval = 0;
+
+ if (fdctrl_media_changed(get_cur_drv(fdctrl))) {
+ retval |= FD_DIR_DSKCHG;
+ }
+ if (retval != 0) {
+ FLOPPY_DPRINTF("Floppy digital input register: 0x%02x\n", retval);
+ }
+
+ return retval;
+}
+
+/* Clear the FIFO and update the state for receiving the next command */
+static void fdctrl_to_command_phase(FDCtrl *fdctrl)
+{
+ fdctrl->phase = FD_PHASE_COMMAND;
+ fdctrl->data_dir = FD_DIR_WRITE;
+ fdctrl->data_pos = 0;
+ fdctrl->data_len = 1; /* Accept command byte, adjust for params later */
+ fdctrl->msr &= ~(FD_MSR_CMDBUSY | FD_MSR_DIO);
+ fdctrl->msr |= FD_MSR_RQM;
+}
+
+/* Update the state to allow the guest to read out the command status.
+ * @fifo_len is the number of result bytes to be read out. */
+static void fdctrl_to_result_phase(FDCtrl *fdctrl, int fifo_len)
+{
+ fdctrl->phase = FD_PHASE_RESULT;
+ fdctrl->data_dir = FD_DIR_READ;
+ fdctrl->data_len = fifo_len;
+ fdctrl->data_pos = 0;
+ fdctrl->msr |= FD_MSR_CMDBUSY | FD_MSR_RQM | FD_MSR_DIO;
+}
+
+/* Set an error: unimplemented/unknown command */
+static void fdctrl_unimplemented(FDCtrl *fdctrl, int direction)
+{
+ qemu_log_mask(LOG_UNIMP, "fdc: unimplemented command 0x%02x\n",
+ fdctrl->fifo[0]);
+ fdctrl->fifo[0] = FD_SR0_INVCMD;
+ fdctrl_to_result_phase(fdctrl, 1);
+}
+
+/* Seek to next sector
+ * returns 0 when end of track reached (for DBL_SIDES on head 1)
+ * otherwise returns 1
+ */
+static int fdctrl_seek_to_next_sect(FDCtrl *fdctrl, FDrive *cur_drv)
+{
+ FLOPPY_DPRINTF("seek to next sector (%d %02x %02x => %d)\n",
+ cur_drv->head, cur_drv->track, cur_drv->sect,
+ fd_sector(cur_drv));
+ /* XXX: cur_drv->sect >= cur_drv->last_sect should be an
+ error in fact */
+ uint8_t new_head = cur_drv->head;
+ uint8_t new_track = cur_drv->track;
+ uint8_t new_sect = cur_drv->sect;
+
+ int ret = 1;
+
+ if (new_sect >= cur_drv->last_sect ||
+ new_sect == fdctrl->eot) {
+ new_sect = 1;
+ if (FD_MULTI_TRACK(fdctrl->data_state)) {
+ if (new_head == 0 &&
+ (cur_drv->flags & FDISK_DBL_SIDES) != 0) {
+ new_head = 1;
+ } else {
+ new_head = 0;
+ new_track++;
+ fdctrl->status0 |= FD_SR0_SEEK;
+ if ((cur_drv->flags & FDISK_DBL_SIDES) == 0) {
+ ret = 0;
+ }
+ }
+ } else {
+ fdctrl->status0 |= FD_SR0_SEEK;
+ new_track++;
+ ret = 0;
+ }
+ if (ret == 1) {
+ FLOPPY_DPRINTF("seek to next track (%d %02x %02x => %d)\n",
+ new_head, new_track, new_sect, fd_sector(cur_drv));
+ }
+ } else {
+ new_sect++;
+ }
+ fd_seek(cur_drv, new_head, new_track, new_sect, 1);
+ return ret;
+}
+
+/* Callback for transfer end (stop or abort) */
+static void fdctrl_stop_transfer(FDCtrl *fdctrl, uint8_t status0,
+ uint8_t status1, uint8_t status2)
+{
+ FDrive *cur_drv;
+ cur_drv = get_cur_drv(fdctrl);
+
+ fdctrl->status0 &= ~(FD_SR0_DS0 | FD_SR0_DS1 | FD_SR0_HEAD);
+ fdctrl->status0 |= GET_CUR_DRV(fdctrl);
+ if (cur_drv->head) {
+ fdctrl->status0 |= FD_SR0_HEAD;
+ }
+ fdctrl->status0 |= status0;
+
+ FLOPPY_DPRINTF("transfer status: %02x %02x %02x (%02x)\n",
+ status0, status1, status2, fdctrl->status0);
+ fdctrl->fifo[0] = fdctrl->status0;
+ fdctrl->fifo[1] = status1;
+ fdctrl->fifo[2] = status2;
+ fdctrl->fifo[3] = cur_drv->track;
+ fdctrl->fifo[4] = cur_drv->head;
+ fdctrl->fifo[5] = cur_drv->sect;
+ fdctrl->fifo[6] = FD_SECTOR_SC;
+ fdctrl->data_dir = FD_DIR_READ;
+ if (fdctrl->dma_chann != -1 && !(fdctrl->msr & FD_MSR_NONDMA)) {
+ IsaDmaClass *k = ISADMA_GET_CLASS(fdctrl->dma);
+ k->release_DREQ(fdctrl->dma, fdctrl->dma_chann);
+ }
+ fdctrl->msr |= FD_MSR_RQM | FD_MSR_DIO;
+ fdctrl->msr &= ~FD_MSR_NONDMA;
+
+ fdctrl_to_result_phase(fdctrl, 7);
+ fdctrl_raise_irq(fdctrl);
+}
+
+/* Prepare a data transfer (either DMA or FIFO) */
+static void fdctrl_start_transfer(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv;
+ uint8_t kh, kt, ks;
+
+ SET_CUR_DRV(fdctrl, fdctrl->fifo[1] & FD_DOR_SELMASK);
+ cur_drv = get_cur_drv(fdctrl);
+ kt = fdctrl->fifo[2];
+ kh = fdctrl->fifo[3];
+ ks = fdctrl->fifo[4];
+ FLOPPY_DPRINTF("Start transfer at %d %d %02x %02x (%d)\n",
+ GET_CUR_DRV(fdctrl), kh, kt, ks,
+ fd_sector_calc(kh, kt, ks, cur_drv->last_sect,
+ NUM_SIDES(cur_drv)));
+ switch (fd_seek(cur_drv, kh, kt, ks, fdctrl->config & FD_CONFIG_EIS)) {
+ case 2:
+ /* sect too big */
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, 0x00, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ case 3:
+ /* track too big */
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, FD_SR1_EC, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ case 4:
+ /* No seek enabled */
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, 0x00, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ case 1:
+ fdctrl->status0 |= FD_SR0_SEEK;
+ break;
+ default:
+ break;
+ }
+
+ /* Check the data rate. If the programmed data rate does not match
+ * the currently inserted medium, the operation has to fail. */
+ if ((fdctrl->dsr & FD_DSR_DRATEMASK) != cur_drv->media_rate) {
+ FLOPPY_DPRINTF("data rate mismatch (fdc=%d, media=%d)\n",
+ fdctrl->dsr & FD_DSR_DRATEMASK, cur_drv->media_rate);
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, FD_SR1_MA, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ }
+
+ /* Set the FIFO state */
+ fdctrl->data_dir = direction;
+ fdctrl->data_pos = 0;
+ assert(fdctrl->msr & FD_MSR_CMDBUSY);
+ if (fdctrl->fifo[0] & 0x80)
+ fdctrl->data_state |= FD_STATE_MULTI;
+ else
+ fdctrl->data_state &= ~FD_STATE_MULTI;
+ if (fdctrl->fifo[5] == 0) {
+ fdctrl->data_len = fdctrl->fifo[8];
+ } else {
+ int tmp;
+ fdctrl->data_len = 128 << (fdctrl->fifo[5] > 7 ? 7 : fdctrl->fifo[5]);
+ tmp = (fdctrl->fifo[6] - ks + 1);
+ if (tmp < 0) {
+ FLOPPY_DPRINTF("invalid EOT: %d\n", tmp);
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, FD_SR1_MA, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ }
+ if (fdctrl->fifo[0] & 0x80)
+ tmp += fdctrl->fifo[6];
+ fdctrl->data_len *= tmp;
+ }
+ fdctrl->eot = fdctrl->fifo[6];
+ if (fdctrl->dor & FD_DOR_DMAEN) {
+ /* DMA transfer is enabled. */
+ IsaDmaClass *k = ISADMA_GET_CLASS(fdctrl->dma);
+
+ FLOPPY_DPRINTF("direction=%d (%d - %d)\n",
+ direction, (128 << fdctrl->fifo[5]) *
+ (cur_drv->last_sect - ks + 1), fdctrl->data_len);
+
+ /* No access is allowed until DMA transfer has completed */
+ fdctrl->msr &= ~FD_MSR_RQM;
+ if (direction != FD_DIR_VERIFY) {
+ /*
+ * Now, we just have to wait for the DMA controller to
+ * recall us...
+ */
+ k->hold_DREQ(fdctrl->dma, fdctrl->dma_chann);
+ k->schedule(fdctrl->dma);
+ } else {
+ /* Start transfer */
+ fdctrl_transfer_handler(fdctrl, fdctrl->dma_chann, 0,
+ fdctrl->data_len);
+ }
+ return;
+ }
+ FLOPPY_DPRINTF("start non-DMA transfer\n");
+ fdctrl->msr |= FD_MSR_NONDMA | FD_MSR_RQM;
+ if (direction != FD_DIR_WRITE)
+ fdctrl->msr |= FD_MSR_DIO;
+ /* IO based transfer: calculate len */
+ fdctrl_raise_irq(fdctrl);
+}
+
+/* Prepare a transfer of deleted data */
+static void fdctrl_start_transfer_del(FDCtrl *fdctrl, int direction)
+{
+ qemu_log_mask(LOG_UNIMP, "fdctrl_start_transfer_del() unimplemented\n");
+
+ /* We don't handle deleted data,
+ * so we don't return *ANYTHING*
+ */
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM | FD_SR0_SEEK, 0x00, 0x00);
+}
+
+/* handlers for DMA transfers */
+int fdctrl_transfer_handler(void *opaque, int nchan, int dma_pos, int dma_len)
+{
+ FDCtrl *fdctrl;
+ FDrive *cur_drv;
+ int len, start_pos, rel_pos;
+ uint8_t status0 = 0x00, status1 = 0x00, status2 = 0x00;
+ IsaDmaClass *k;
+
+ fdctrl = opaque;
+ if (fdctrl->msr & FD_MSR_RQM) {
+ FLOPPY_DPRINTF("Not in DMA transfer mode !\n");
+ return 0;
+ }
+ k = ISADMA_GET_CLASS(fdctrl->dma);
+ cur_drv = get_cur_drv(fdctrl);
+ if (fdctrl->data_dir == FD_DIR_SCANE || fdctrl->data_dir == FD_DIR_SCANL ||
+ fdctrl->data_dir == FD_DIR_SCANH)
+ status2 = FD_SR2_SNS;
+ if (dma_len > fdctrl->data_len)
+ dma_len = fdctrl->data_len;
+ if (cur_drv->blk == NULL) {
+ if (fdctrl->data_dir == FD_DIR_WRITE)
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM | FD_SR0_SEEK, 0x00, 0x00);
+ else
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, 0x00, 0x00);
+ len = 0;
+ goto transfer_error;
+ }
+ rel_pos = fdctrl->data_pos % FD_SECTOR_LEN;
+ for (start_pos = fdctrl->data_pos; fdctrl->data_pos < dma_len;) {
+ len = dma_len - fdctrl->data_pos;
+ if (len + rel_pos > FD_SECTOR_LEN)
+ len = FD_SECTOR_LEN - rel_pos;
+ FLOPPY_DPRINTF("copy %d bytes (%d %d %d) %d pos %d %02x "
+ "(%d-0x%08x 0x%08x)\n", len, dma_len, fdctrl->data_pos,
+ fdctrl->data_len, GET_CUR_DRV(fdctrl), cur_drv->head,
+ cur_drv->track, cur_drv->sect, fd_sector(cur_drv),
+ fd_sector(cur_drv) * FD_SECTOR_LEN);
+ if (fdctrl->data_dir != FD_DIR_WRITE ||
+ len < FD_SECTOR_LEN || rel_pos != 0) {
+ /* READ & SCAN commands and realign to a sector for WRITE */
+ if (blk_pread(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE,
+ fdctrl->fifo, 0) < 0) {
+ FLOPPY_DPRINTF("Floppy: error getting sector %d\n",
+ fd_sector(cur_drv));
+ /* Sure, image size is too small... */
+ memset(fdctrl->fifo, 0, FD_SECTOR_LEN);
+ }
+ }
+ switch (fdctrl->data_dir) {
+ case FD_DIR_READ:
+ /* READ commands */
+ k->write_memory(fdctrl->dma, nchan, fdctrl->fifo + rel_pos,
+ fdctrl->data_pos, len);
+ break;
+ case FD_DIR_WRITE:
+ /* WRITE commands */
+ if (cur_drv->ro) {
+ /* Handle readonly medium early, no need to do DMA, touch the
+ * LED or attempt any writes. A real floppy doesn't attempt
+ * to write to readonly media either. */
+ fdctrl_stop_transfer(fdctrl,
+ FD_SR0_ABNTERM | FD_SR0_SEEK, FD_SR1_NW,
+ 0x00);
+ goto transfer_error;
+ }
+
+ k->read_memory(fdctrl->dma, nchan, fdctrl->fifo + rel_pos,
+ fdctrl->data_pos, len);
+ if (blk_pwrite(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE,
+ fdctrl->fifo, 0) < 0) {
+ FLOPPY_DPRINTF("error writing sector %d\n",
+ fd_sector(cur_drv));
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM | FD_SR0_SEEK, 0x00, 0x00);
+ goto transfer_error;
+ }
+ break;
+ case FD_DIR_VERIFY:
+ /* VERIFY commands */
+ break;
+ default:
+ /* SCAN commands */
+ {
+ uint8_t tmpbuf[FD_SECTOR_LEN];
+ int ret;
+ k->read_memory(fdctrl->dma, nchan, tmpbuf, fdctrl->data_pos,
+ len);
+ ret = memcmp(tmpbuf, fdctrl->fifo + rel_pos, len);
+ if (ret == 0) {
+ status2 = FD_SR2_SEH;
+ goto end_transfer;
+ }
+ if ((ret < 0 && fdctrl->data_dir == FD_DIR_SCANL) ||
+ (ret > 0 && fdctrl->data_dir == FD_DIR_SCANH)) {
+ status2 = 0x00;
+ goto end_transfer;
+ }
+ }
+ break;
+ }
+ fdctrl->data_pos += len;
+ rel_pos = fdctrl->data_pos % FD_SECTOR_LEN;
+ if (rel_pos == 0) {
+ /* Seek to next sector */
+ if (!fdctrl_seek_to_next_sect(fdctrl, cur_drv))
+ break;
+ }
+ }
+ end_transfer:
+ len = fdctrl->data_pos - start_pos;
+ FLOPPY_DPRINTF("end transfer %d %d %d\n",
+ fdctrl->data_pos, len, fdctrl->data_len);
+ if (fdctrl->data_dir == FD_DIR_SCANE ||
+ fdctrl->data_dir == FD_DIR_SCANL ||
+ fdctrl->data_dir == FD_DIR_SCANH)
+ status2 = FD_SR2_SEH;
+ fdctrl->data_len -= len;
+ fdctrl_stop_transfer(fdctrl, status0, status1, status2);
+ transfer_error:
+
+ return len;
+}
+
+/* Data register : 0x05 */
+static uint32_t fdctrl_read_data(FDCtrl *fdctrl)
+{
+ FDrive *cur_drv;
+ uint32_t retval = 0;
+ uint32_t pos;
+
+ cur_drv = get_cur_drv(fdctrl);
+ fdctrl->dsr &= ~FD_DSR_PWRDOWN;
+ if (!(fdctrl->msr & FD_MSR_RQM) || !(fdctrl->msr & FD_MSR_DIO)) {
+ FLOPPY_DPRINTF("error: controller not ready for reading\n");
+ return 0;
+ }
+
+ /* If data_len spans multiple sectors, the current position in the FIFO
+ * wraps around while fdctrl->data_pos is the real position in the whole
+ * request. */
+ pos = fdctrl->data_pos;
+ pos %= FD_SECTOR_LEN;
+
+ switch (fdctrl->phase) {
+ case FD_PHASE_EXECUTION:
+ assert(fdctrl->msr & FD_MSR_NONDMA);
+ if (pos == 0) {
+ if (fdctrl->data_pos != 0)
+ if (!fdctrl_seek_to_next_sect(fdctrl, cur_drv)) {
+ FLOPPY_DPRINTF("error seeking to next sector %d\n",
+ fd_sector(cur_drv));
+ return 0;
+ }
+ if (blk_pread(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE,
+ fdctrl->fifo, 0)
+ < 0) {
+ FLOPPY_DPRINTF("error getting sector %d\n",
+ fd_sector(cur_drv));
+ /* Sure, image size is too small... */
+ memset(fdctrl->fifo, 0, FD_SECTOR_LEN);
+ }
+ }
+
+ if (++fdctrl->data_pos == fdctrl->data_len) {
+ fdctrl->msr &= ~FD_MSR_RQM;
+ fdctrl_stop_transfer(fdctrl, 0x00, 0x00, 0x00);
+ }
+ break;
+
+ case FD_PHASE_RESULT:
+ assert(!(fdctrl->msr & FD_MSR_NONDMA));
+ if (++fdctrl->data_pos == fdctrl->data_len) {
+ fdctrl->msr &= ~FD_MSR_RQM;
+ fdctrl_to_command_phase(fdctrl);
+ fdctrl_reset_irq(fdctrl);
+ }
+ break;
+
+ case FD_PHASE_COMMAND:
+ default:
+ abort();
+ }
+
+ retval = fdctrl->fifo[pos];
+ FLOPPY_DPRINTF("data register: 0x%02x\n", retval);
+
+ return retval;
+}
+
+static void fdctrl_format_sector(FDCtrl *fdctrl)
+{
+ FDrive *cur_drv;
+ uint8_t kh, kt, ks;
+
+ SET_CUR_DRV(fdctrl, fdctrl->fifo[1] & FD_DOR_SELMASK);
+ cur_drv = get_cur_drv(fdctrl);
+ kt = fdctrl->fifo[6];
+ kh = fdctrl->fifo[7];
+ ks = fdctrl->fifo[8];
+ FLOPPY_DPRINTF("format sector at %d %d %02x %02x (%d)\n",
+ GET_CUR_DRV(fdctrl), kh, kt, ks,
+ fd_sector_calc(kh, kt, ks, cur_drv->last_sect,
+ NUM_SIDES(cur_drv)));
+ switch (fd_seek(cur_drv, kh, kt, ks, fdctrl->config & FD_CONFIG_EIS)) {
+ case 2:
+ /* sect too big */
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, 0x00, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ case 3:
+ /* track too big */
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, FD_SR1_EC, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ case 4:
+ /* No seek enabled */
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, 0x00, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ case 1:
+ fdctrl->status0 |= FD_SR0_SEEK;
+ break;
+ default:
+ break;
+ }
+ memset(fdctrl->fifo, 0, FD_SECTOR_LEN);
+ if (cur_drv->blk == NULL ||
+ blk_pwrite(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE,
+ fdctrl->fifo, 0) < 0) {
+ FLOPPY_DPRINTF("error formatting sector %d\n", fd_sector(cur_drv));
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM | FD_SR0_SEEK, 0x00, 0x00);
+ } else {
+ if (cur_drv->sect == cur_drv->last_sect) {
+ fdctrl->data_state &= ~FD_STATE_FORMAT;
+ /* Last sector done */
+ fdctrl_stop_transfer(fdctrl, 0x00, 0x00, 0x00);
+ } else {
+ /* More to do */
+ fdctrl->data_pos = 0;
+ fdctrl->data_len = 4;
+ }
+ }
+}
+
+static void fdctrl_handle_lock(FDCtrl *fdctrl, int direction)
+{
+ fdctrl->lock = (fdctrl->fifo[0] & 0x80) ? 1 : 0;
+ fdctrl->fifo[0] = fdctrl->lock << 4;
+ fdctrl_to_result_phase(fdctrl, 1);
+}
+
+static void fdctrl_handle_dumpreg(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv = get_cur_drv(fdctrl);
+
+ /* Drives position */
+ fdctrl->fifo[0] = drv0(fdctrl)->track;
+ fdctrl->fifo[1] = drv1(fdctrl)->track;
+#if MAX_FD == 4
+ fdctrl->fifo[2] = drv2(fdctrl)->track;
+ fdctrl->fifo[3] = drv3(fdctrl)->track;
+#else
+ fdctrl->fifo[2] = 0;
+ fdctrl->fifo[3] = 0;
+#endif
+ /* timers */
+ fdctrl->fifo[4] = fdctrl->timer0;
+ fdctrl->fifo[5] = (fdctrl->timer1 << 1) | (fdctrl->dor & FD_DOR_DMAEN ? 1 : 0);
+ fdctrl->fifo[6] = cur_drv->last_sect;
+ fdctrl->fifo[7] = (fdctrl->lock << 7) |
+ (cur_drv->perpendicular << 2);
+ fdctrl->fifo[8] = fdctrl->config;
+ fdctrl->fifo[9] = fdctrl->precomp_trk;
+ fdctrl_to_result_phase(fdctrl, 10);
+}
+
+static void fdctrl_handle_version(FDCtrl *fdctrl, int direction)
+{
+ /* Controller's version */
+ fdctrl->fifo[0] = fdctrl->version;
+ fdctrl_to_result_phase(fdctrl, 1);
+}
+
+static void fdctrl_handle_partid(FDCtrl *fdctrl, int direction)
+{
+ fdctrl->fifo[0] = 0x41; /* Stepping 1 */
+ fdctrl_to_result_phase(fdctrl, 1);
+}
+
+static void fdctrl_handle_restore(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv = get_cur_drv(fdctrl);
+
+ /* Drives position */
+ drv0(fdctrl)->track = fdctrl->fifo[3];
+ drv1(fdctrl)->track = fdctrl->fifo[4];
+#if MAX_FD == 4
+ drv2(fdctrl)->track = fdctrl->fifo[5];
+ drv3(fdctrl)->track = fdctrl->fifo[6];
+#endif
+ /* timers */
+ fdctrl->timer0 = fdctrl->fifo[7];
+ fdctrl->timer1 = fdctrl->fifo[8];
+ cur_drv->last_sect = fdctrl->fifo[9];
+ fdctrl->lock = fdctrl->fifo[10] >> 7;
+ cur_drv->perpendicular = (fdctrl->fifo[10] >> 2) & 0xF;
+ fdctrl->config = fdctrl->fifo[11];
+ fdctrl->precomp_trk = fdctrl->fifo[12];
+ fdctrl->pwrd = fdctrl->fifo[13];
+ fdctrl_to_command_phase(fdctrl);
+}
+
+static void fdctrl_handle_save(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv = get_cur_drv(fdctrl);
+
+ fdctrl->fifo[0] = 0;
+ fdctrl->fifo[1] = 0;
+ /* Drives position */
+ fdctrl->fifo[2] = drv0(fdctrl)->track;
+ fdctrl->fifo[3] = drv1(fdctrl)->track;
+#if MAX_FD == 4
+ fdctrl->fifo[4] = drv2(fdctrl)->track;
+ fdctrl->fifo[5] = drv3(fdctrl)->track;
+#else
+ fdctrl->fifo[4] = 0;
+ fdctrl->fifo[5] = 0;
+#endif
+ /* timers */
+ fdctrl->fifo[6] = fdctrl->timer0;
+ fdctrl->fifo[7] = fdctrl->timer1;
+ fdctrl->fifo[8] = cur_drv->last_sect;
+ fdctrl->fifo[9] = (fdctrl->lock << 7) |
+ (cur_drv->perpendicular << 2);
+ fdctrl->fifo[10] = fdctrl->config;
+ fdctrl->fifo[11] = fdctrl->precomp_trk;
+ fdctrl->fifo[12] = fdctrl->pwrd;
+ fdctrl->fifo[13] = 0;
+ fdctrl->fifo[14] = 0;
+ fdctrl_to_result_phase(fdctrl, 15);
+}
+
+static void fdctrl_handle_readid(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv = get_cur_drv(fdctrl);
+
+ cur_drv->head = (fdctrl->fifo[1] >> 2) & 1;
+ timer_mod(fdctrl->result_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+ (NANOSECONDS_PER_SECOND / 50));
+}
+
+static void fdctrl_handle_format_track(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv;
+
+ SET_CUR_DRV(fdctrl, fdctrl->fifo[1] & FD_DOR_SELMASK);
+ cur_drv = get_cur_drv(fdctrl);
+ fdctrl->data_state |= FD_STATE_FORMAT;
+ if (fdctrl->fifo[0] & 0x80)
+ fdctrl->data_state |= FD_STATE_MULTI;
+ else
+ fdctrl->data_state &= ~FD_STATE_MULTI;
+ cur_drv->bps =
+ fdctrl->fifo[2] > 7 ? 16384 : 128 << fdctrl->fifo[2];
+#if 0
+ cur_drv->last_sect =
+ cur_drv->flags & FDISK_DBL_SIDES ? fdctrl->fifo[3] :
+ fdctrl->fifo[3] / 2;
+#else
+ cur_drv->last_sect = fdctrl->fifo[3];
+#endif
+ /* TODO: implement format using DMA expected by the Bochs BIOS
+ * and Linux fdformat (read 3 bytes per sector via DMA and fill
+ * the sector with the specified fill byte
+ */
+ fdctrl->data_state &= ~FD_STATE_FORMAT;
+ fdctrl_stop_transfer(fdctrl, 0x00, 0x00, 0x00);
+}
+
+static void fdctrl_handle_specify(FDCtrl *fdctrl, int direction)
+{
+ fdctrl->timer0 = (fdctrl->fifo[1] >> 4) & 0xF;
+ fdctrl->timer1 = fdctrl->fifo[2] >> 1;
+ if (fdctrl->fifo[2] & 1)
+ fdctrl->dor &= ~FD_DOR_DMAEN;
+ else
+ fdctrl->dor |= FD_DOR_DMAEN;
+ /* No result back */
+ fdctrl_to_command_phase(fdctrl);
+}
+
+static void fdctrl_handle_sense_drive_status(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv;
+
+ SET_CUR_DRV(fdctrl, fdctrl->fifo[1] & FD_DOR_SELMASK);
+ cur_drv = get_cur_drv(fdctrl);
+ cur_drv->head = (fdctrl->fifo[1] >> 2) & 1;
+ /* 1 Byte status back */
+ fdctrl->fifo[0] = (cur_drv->ro << 6) |
+ (cur_drv->track == 0 ? 0x10 : 0x00) |
+ (cur_drv->head << 2) |
+ GET_CUR_DRV(fdctrl) |
+ 0x28;
+ fdctrl_to_result_phase(fdctrl, 1);
+}
+
+static void fdctrl_handle_recalibrate(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv;
+
+ SET_CUR_DRV(fdctrl, fdctrl->fifo[1] & FD_DOR_SELMASK);
+ cur_drv = get_cur_drv(fdctrl);
+ fd_recalibrate(cur_drv);
+ fdctrl_to_command_phase(fdctrl);
+ /* Raise Interrupt */
+ fdctrl->status0 |= FD_SR0_SEEK;
+ fdctrl_raise_irq(fdctrl);
+}
+
+static void fdctrl_handle_sense_interrupt_status(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv = get_cur_drv(fdctrl);
+
+ if (fdctrl->reset_sensei > 0) {
+ fdctrl->fifo[0] =
+ FD_SR0_RDYCHG + FD_RESET_SENSEI_COUNT - fdctrl->reset_sensei;
+ fdctrl->reset_sensei--;
+ } else if (!(fdctrl->sra & FD_SRA_INTPEND)) {
+ fdctrl->fifo[0] = FD_SR0_INVCMD;
+ fdctrl_to_result_phase(fdctrl, 1);
+ return;
+ } else {
+ fdctrl->fifo[0] =
+ (fdctrl->status0 & ~(FD_SR0_HEAD | FD_SR0_DS1 | FD_SR0_DS0))
+ | GET_CUR_DRV(fdctrl);
+ }
+
+ fdctrl->fifo[1] = cur_drv->track;
+ fdctrl_to_result_phase(fdctrl, 2);
+ fdctrl_reset_irq(fdctrl);
+ fdctrl->status0 = FD_SR0_RDYCHG;
+}
+
+static void fdctrl_handle_seek(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv;
+
+ SET_CUR_DRV(fdctrl, fdctrl->fifo[1] & FD_DOR_SELMASK);
+ cur_drv = get_cur_drv(fdctrl);
+ fdctrl_to_command_phase(fdctrl);
+ /* The seek command just sends step pulses to the drive and doesn't care if
+ * there is a medium inserted of if it's banging the head against the drive.
+ */
+ fd_seek(cur_drv, cur_drv->head, fdctrl->fifo[2], cur_drv->sect, 1);
+ /* Raise Interrupt */
+ fdctrl->status0 |= FD_SR0_SEEK;
+ fdctrl_raise_irq(fdctrl);
+}
+
+static void fdctrl_handle_perpendicular_mode(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv = get_cur_drv(fdctrl);
+
+ if (fdctrl->fifo[1] & 0x80)
+ cur_drv->perpendicular = fdctrl->fifo[1] & 0x7;
+ /* No result back */
+ fdctrl_to_command_phase(fdctrl);
+}
+
+static void fdctrl_handle_configure(FDCtrl *fdctrl, int direction)
+{
+ fdctrl->config = fdctrl->fifo[2];
+ fdctrl->precomp_trk = fdctrl->fifo[3];
+ /* No result back */
+ fdctrl_to_command_phase(fdctrl);
+}
+
+static void fdctrl_handle_powerdown_mode(FDCtrl *fdctrl, int direction)
+{
+ fdctrl->pwrd = fdctrl->fifo[1];
+ fdctrl->fifo[0] = fdctrl->fifo[1];
+ fdctrl_to_result_phase(fdctrl, 1);
+}
+
+static void fdctrl_handle_option(FDCtrl *fdctrl, int direction)
+{
+ /* No result back */
+ fdctrl_to_command_phase(fdctrl);
+}
+
+static void fdctrl_handle_drive_specification_command(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv = get_cur_drv(fdctrl);
+ uint32_t pos;
+
+ pos = fdctrl->data_pos - 1;
+ pos %= FD_SECTOR_LEN;
+ if (fdctrl->fifo[pos] & 0x80) {
+ /* Command parameters done */
+ if (fdctrl->fifo[pos] & 0x40) {
+ fdctrl->fifo[0] = fdctrl->fifo[1];
+ fdctrl->fifo[2] = 0;
+ fdctrl->fifo[3] = 0;
+ fdctrl_to_result_phase(fdctrl, 4);
+ } else {
+ fdctrl_to_command_phase(fdctrl);
+ }
+ } else if (fdctrl->data_len > 7) {
+ /* ERROR */
+ fdctrl->fifo[0] = 0x80 |
+ (cur_drv->head << 2) | GET_CUR_DRV(fdctrl);
+ fdctrl_to_result_phase(fdctrl, 1);
+ }
+}
+
+static void fdctrl_handle_relative_seek_in(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv;
+
+ SET_CUR_DRV(fdctrl, fdctrl->fifo[1] & FD_DOR_SELMASK);
+ cur_drv = get_cur_drv(fdctrl);
+ if (fdctrl->fifo[2] + cur_drv->track >= cur_drv->max_track) {
+ fd_seek(cur_drv, cur_drv->head, cur_drv->max_track - 1,
+ cur_drv->sect, 1);
+ } else {
+ fd_seek(cur_drv, cur_drv->head,
+ cur_drv->track + fdctrl->fifo[2], cur_drv->sect, 1);
+ }
+ fdctrl_to_command_phase(fdctrl);
+ /* Raise Interrupt */
+ fdctrl->status0 |= FD_SR0_SEEK;
+ fdctrl_raise_irq(fdctrl);
+}
+
+static void fdctrl_handle_relative_seek_out(FDCtrl *fdctrl, int direction)
+{
+ FDrive *cur_drv;
+
+ SET_CUR_DRV(fdctrl, fdctrl->fifo[1] & FD_DOR_SELMASK);
+ cur_drv = get_cur_drv(fdctrl);
+ if (fdctrl->fifo[2] > cur_drv->track) {
+ fd_seek(cur_drv, cur_drv->head, 0, cur_drv->sect, 1);
+ } else {
+ fd_seek(cur_drv, cur_drv->head,
+ cur_drv->track - fdctrl->fifo[2], cur_drv->sect, 1);
+ }
+ fdctrl_to_command_phase(fdctrl);
+ /* Raise Interrupt */
+ fdctrl->status0 |= FD_SR0_SEEK;
+ fdctrl_raise_irq(fdctrl);
+}
+
+/*
+ * Handlers for the execution phase of each command
+ */
+typedef struct FDCtrlCommand {
+ uint8_t value;
+ uint8_t mask;
+ const char* name;
+ int parameters;
+ void (*handler)(FDCtrl *fdctrl, int direction);
+ int direction;
+} FDCtrlCommand;
+
+static const FDCtrlCommand handlers[] = {
+ { FD_CMD_READ, 0x1f, "READ", 8, fdctrl_start_transfer, FD_DIR_READ },
+ { FD_CMD_WRITE, 0x3f, "WRITE", 8, fdctrl_start_transfer, FD_DIR_WRITE },
+ { FD_CMD_SEEK, 0xff, "SEEK", 2, fdctrl_handle_seek },
+ { FD_CMD_SENSE_INTERRUPT_STATUS, 0xff, "SENSE INTERRUPT STATUS", 0, fdctrl_handle_sense_interrupt_status },
+ { FD_CMD_RECALIBRATE, 0xff, "RECALIBRATE", 1, fdctrl_handle_recalibrate },
+ { FD_CMD_FORMAT_TRACK, 0xbf, "FORMAT TRACK", 5, fdctrl_handle_format_track },
+ { FD_CMD_READ_TRACK, 0xbf, "READ TRACK", 8, fdctrl_start_transfer, FD_DIR_READ },
+ { FD_CMD_RESTORE, 0xff, "RESTORE", 17, fdctrl_handle_restore }, /* part of READ DELETED DATA */
+ { FD_CMD_SAVE, 0xff, "SAVE", 0, fdctrl_handle_save }, /* part of READ DELETED DATA */
+ { FD_CMD_READ_DELETED, 0x1f, "READ DELETED DATA", 8, fdctrl_start_transfer_del, FD_DIR_READ },
+ { FD_CMD_SCAN_EQUAL, 0x1f, "SCAN EQUAL", 8, fdctrl_start_transfer, FD_DIR_SCANE },
+ { FD_CMD_VERIFY, 0x1f, "VERIFY", 8, fdctrl_start_transfer, FD_DIR_VERIFY },
+ { FD_CMD_SCAN_LOW_OR_EQUAL, 0x1f, "SCAN LOW OR EQUAL", 8, fdctrl_start_transfer, FD_DIR_SCANL },
+ { FD_CMD_SCAN_HIGH_OR_EQUAL, 0x1f, "SCAN HIGH OR EQUAL", 8, fdctrl_start_transfer, FD_DIR_SCANH },
+ { FD_CMD_WRITE_DELETED, 0x3f, "WRITE DELETED DATA", 8, fdctrl_start_transfer_del, FD_DIR_WRITE },
+ { FD_CMD_READ_ID, 0xbf, "READ ID", 1, fdctrl_handle_readid },
+ { FD_CMD_SPECIFY, 0xff, "SPECIFY", 2, fdctrl_handle_specify },
+ { FD_CMD_SENSE_DRIVE_STATUS, 0xff, "SENSE DRIVE STATUS", 1, fdctrl_handle_sense_drive_status },
+ { FD_CMD_PERPENDICULAR_MODE, 0xff, "PERPENDICULAR MODE", 1, fdctrl_handle_perpendicular_mode },
+ { FD_CMD_CONFIGURE, 0xff, "CONFIGURE", 3, fdctrl_handle_configure },
+ { FD_CMD_POWERDOWN_MODE, 0xff, "POWERDOWN MODE", 2, fdctrl_handle_powerdown_mode },
+ { FD_CMD_OPTION, 0xff, "OPTION", 1, fdctrl_handle_option },
+ { FD_CMD_DRIVE_SPECIFICATION_COMMAND, 0xff, "DRIVE SPECIFICATION COMMAND", 5, fdctrl_handle_drive_specification_command },
+ { FD_CMD_RELATIVE_SEEK_OUT, 0xff, "RELATIVE SEEK OUT", 2, fdctrl_handle_relative_seek_out },
+ { FD_CMD_FORMAT_AND_WRITE, 0xff, "FORMAT AND WRITE", 10, fdctrl_unimplemented },
+ { FD_CMD_RELATIVE_SEEK_IN, 0xff, "RELATIVE SEEK IN", 2, fdctrl_handle_relative_seek_in },
+ { FD_CMD_LOCK, 0x7f, "LOCK", 0, fdctrl_handle_lock },
+ { FD_CMD_DUMPREG, 0xff, "DUMPREG", 0, fdctrl_handle_dumpreg },
+ { FD_CMD_VERSION, 0xff, "VERSION", 0, fdctrl_handle_version },
+ { FD_CMD_PART_ID, 0xff, "PART ID", 0, fdctrl_handle_partid },
+ { FD_CMD_WRITE, 0x1f, "WRITE (BeOS)", 8, fdctrl_start_transfer, FD_DIR_WRITE }, /* not in specification ; BeOS 4.5 bug */
+ { 0, 0, "unknown", 0, fdctrl_unimplemented }, /* default handler */
+};
+/* Associate command to an index in the 'handlers' array */
+static uint8_t command_to_handler[256];
+
+static const FDCtrlCommand *get_command(uint8_t cmd)
+{
+ int idx;
+
+ idx = command_to_handler[cmd];
+ FLOPPY_DPRINTF("%s command\n", handlers[idx].name);
+ return &handlers[idx];
+}
+
+static void fdctrl_write_data(FDCtrl *fdctrl, uint32_t value)
+{
+ FDrive *cur_drv;
+ const FDCtrlCommand *cmd;
+ uint32_t pos;
+
+ /* Reset mode */
+ if (!(fdctrl->dor & FD_DOR_nRESET)) {
+ FLOPPY_DPRINTF("Floppy controller in RESET state !\n");
+ return;
+ }
+ if (!(fdctrl->msr & FD_MSR_RQM) || (fdctrl->msr & FD_MSR_DIO)) {
+ FLOPPY_DPRINTF("error: controller not ready for writing\n");
+ return;
+ }
+ fdctrl->dsr &= ~FD_DSR_PWRDOWN;
+
+ FLOPPY_DPRINTF("%s: %02x\n", __func__, value);
+
+ /* If data_len spans multiple sectors, the current position in the FIFO
+ * wraps around while fdctrl->data_pos is the real position in the whole
+ * request. */
+ pos = fdctrl->data_pos++;
+ pos %= FD_SECTOR_LEN;
+ fdctrl->fifo[pos] = value;
+
+ if (fdctrl->data_pos == fdctrl->data_len) {
+ fdctrl->msr &= ~FD_MSR_RQM;
+ }
+
+ switch (fdctrl->phase) {
+ case FD_PHASE_EXECUTION:
+ /* For DMA requests, RQM should be cleared during execution phase, so
+ * we would have errored out above. */
+ assert(fdctrl->msr & FD_MSR_NONDMA);
+
+ /* FIFO data write */
+ if (pos == FD_SECTOR_LEN - 1 ||
+ fdctrl->data_pos == fdctrl->data_len) {
+ cur_drv = get_cur_drv(fdctrl);
+ if (blk_pwrite(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE,
+ fdctrl->fifo, 0) < 0) {
+ FLOPPY_DPRINTF("error writing sector %d\n",
+ fd_sector(cur_drv));
+ break;
+ }
+ if (!fdctrl_seek_to_next_sect(fdctrl, cur_drv)) {
+ FLOPPY_DPRINTF("error seeking to next sector %d\n",
+ fd_sector(cur_drv));
+ break;
+ }
+ }
+
+ /* Switch to result phase when done with the transfer */
+ if (fdctrl->data_pos == fdctrl->data_len) {
+ fdctrl_stop_transfer(fdctrl, 0x00, 0x00, 0x00);
+ }
+ break;
+
+ case FD_PHASE_COMMAND:
+ assert(!(fdctrl->msr & FD_MSR_NONDMA));
+ assert(fdctrl->data_pos < FD_SECTOR_LEN);
+
+ if (pos == 0) {
+ /* The first byte specifies the command. Now we start reading
+ * as many parameters as this command requires. */
+ cmd = get_command(value);
+ fdctrl->data_len = cmd->parameters + 1;
+ if (cmd->parameters) {
+ fdctrl->msr |= FD_MSR_RQM;
+ }
+ fdctrl->msr |= FD_MSR_CMDBUSY;
+ }
+
+ if (fdctrl->data_pos == fdctrl->data_len) {
+ /* We have all parameters now, execute the command */
+ fdctrl->phase = FD_PHASE_EXECUTION;
+
+ if (fdctrl->data_state & FD_STATE_FORMAT) {
+ fdctrl_format_sector(fdctrl);
+ break;
+ }
+
+ cmd = get_command(fdctrl->fifo[0]);
+ FLOPPY_DPRINTF("Calling handler for '%s'\n", cmd->name);
+ cmd->handler(fdctrl, cmd->direction);
+ }
+ break;
+
+ case FD_PHASE_RESULT:
+ default:
+ abort();
+ }
+}
+
+static void fdctrl_result_timer(void *opaque)
+{
+ FDCtrl *fdctrl = opaque;
+ FDrive *cur_drv = get_cur_drv(fdctrl);
+
+ /* Pretend we are spinning.
+ * This is needed for Coherent, which uses READ ID to check for
+ * sector interleaving.
+ */
+ if (cur_drv->last_sect != 0) {
+ cur_drv->sect = (cur_drv->sect % cur_drv->last_sect) + 1;
+ }
+ /* READ_ID can't automatically succeed! */
+ if ((fdctrl->dsr & FD_DSR_DRATEMASK) != cur_drv->media_rate) {
+ FLOPPY_DPRINTF("read id rate mismatch (fdc=%d, media=%d)\n",
+ fdctrl->dsr & FD_DSR_DRATEMASK, cur_drv->media_rate);
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, FD_SR1_MA, 0x00);
+ } else {
+ fdctrl_stop_transfer(fdctrl, 0x00, 0x00, 0x00);
+ }
+}
+
+/* Init functions */
+
+void fdctrl_init_drives(FloppyBus *bus, DriveInfo **fds)
+{
+ DeviceState *dev;
+ int i;
+
+ for (i = 0; i < MAX_FD; i++) {
+ if (fds[i]) {
+ dev = qdev_new("floppy");
+ qdev_prop_set_uint32(dev, "unit", i);
+ qdev_prop_set_enum(dev, "drive-type", FLOPPY_DRIVE_TYPE_AUTO);
+ qdev_prop_set_drive_err(dev, "drive", blk_by_legacy_dinfo(fds[i]),
+ &error_fatal);
+ qdev_realize_and_unref(dev, &bus->bus, &error_fatal);
+ }
+ }
+}
+
+void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp)
+{
+ int i, j;
+ FDrive *drive;
+ static int command_tables_inited = 0;
+
+ if (fdctrl->fallback == FLOPPY_DRIVE_TYPE_AUTO) {
+ error_setg(errp, "Cannot choose a fallback FDrive type of 'auto'");
+ return;
+ }
+
+ /* Fill 'command_to_handler' lookup table */
+ if (!command_tables_inited) {
+ command_tables_inited = 1;
+ for (i = ARRAY_SIZE(handlers) - 1; i >= 0; i--) {
+ for (j = 0; j < sizeof(command_to_handler); j++) {
+ if ((j & handlers[i].mask) == handlers[i].value) {
+ command_to_handler[j] = i;
+ }
+ }
+ }
+ }
+
+ FLOPPY_DPRINTF("init controller\n");
+ fdctrl->fifo = qemu_memalign(512, FD_SECTOR_LEN);
+ memset(fdctrl->fifo, 0, FD_SECTOR_LEN);
+ fdctrl->fifo_size = 512;
+ fdctrl->result_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+ fdctrl_result_timer, fdctrl);
+
+ fdctrl->version = 0x90; /* Intel 82078 controller */
+ fdctrl->config = FD_CONFIG_EIS | FD_CONFIG_EFIFO; /* Implicit seek, polling & FIFO enabled */
+ fdctrl->num_floppies = MAX_FD;
+
+ floppy_bus_create(fdctrl, &fdctrl->bus, dev);
+
+ for (i = 0; i < MAX_FD; i++) {
+ drive = &fdctrl->drives[i];
+ drive->fdctrl = fdctrl;
+ fd_init(drive);
+ fd_revalidate(drive);
+ }
+}
+
+static void fdc_register_types(void)
+{
+ type_register_static(&floppy_bus_info);
+ type_register_static(&floppy_drive_info);
+}
+
+type_init(fdc_register_types)
diff --git a/hw/block/hd-geometry.c b/hw/block/hd-geometry.c
new file mode 100644
index 00000000..dae13ab1
--- /dev/null
+++ b/hw/block/hd-geometry.c
@@ -0,0 +1,168 @@
+/*
+ * Hard disk geometry utilities
+ *
+ * Copyright (C) 2012 Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *
+ * Copyright (c) 2003 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+#include "sysemu/block-backend.h"
+#include "qapi/qapi-types-block.h"
+#include "qemu/bswap.h"
+#include "hw/block/block.h"
+#include "trace.h"
+
+struct partition {
+ uint8_t boot_ind; /* 0x80 - active */
+ uint8_t head; /* starting head */
+ uint8_t sector; /* starting sector */
+ uint8_t cyl; /* starting cylinder */
+ uint8_t sys_ind; /* What partition type */
+ uint8_t end_head; /* end head */
+ uint8_t end_sector; /* end sector */
+ uint8_t end_cyl; /* end cylinder */
+ uint32_t start_sect; /* starting sector counting from 0 */
+ uint32_t nr_sects; /* nr of sectors in partition */
+} QEMU_PACKED;
+
+/* try to guess the disk logical geometry from the MSDOS partition table.
+ Return 0 if OK, -1 if could not guess */
+static int guess_disk_lchs(BlockBackend *blk,
+ int *pcylinders, int *pheads, int *psectors)
+{
+ uint8_t buf[BDRV_SECTOR_SIZE];
+ int i, heads, sectors, cylinders;
+ struct partition *p;
+ uint32_t nr_sects;
+ uint64_t nb_sectors;
+
+ blk_get_geometry(blk, &nb_sectors);
+
+ if (blk_pread(blk, 0, BDRV_SECTOR_SIZE, buf, 0) < 0) {
+ return -1;
+ }
+ /* test msdos magic */
+ if (buf[510] != 0x55 || buf[511] != 0xaa) {
+ return -1;
+ }
+ for (i = 0; i < 4; i++) {
+ p = ((struct partition *)(buf + 0x1be)) + i;
+ nr_sects = le32_to_cpu(p->nr_sects);
+ if (nr_sects && p->end_head) {
+ /* We make the assumption that the partition terminates on
+ a cylinder boundary */
+ heads = p->end_head + 1;
+ sectors = p->end_sector & 63;
+ if (sectors == 0) {
+ continue;
+ }
+ cylinders = nb_sectors / (heads * sectors);
+ if (cylinders < 1 || cylinders > 16383) {
+ continue;
+ }
+ *pheads = heads;
+ *psectors = sectors;
+ *pcylinders = cylinders;
+ trace_hd_geometry_lchs_guess(blk, cylinders, heads, sectors);
+ return 0;
+ }
+ }
+ return -1;
+}
+
+static void guess_chs_for_size(BlockBackend *blk,
+ uint32_t *pcyls, uint32_t *pheads, uint32_t *psecs)
+{
+ uint64_t nb_sectors;
+ int cylinders;
+
+ blk_get_geometry(blk, &nb_sectors);
+
+ cylinders = nb_sectors / (16 * 63);
+ if (cylinders > 16383) {
+ cylinders = 16383;
+ } else if (cylinders < 2) {
+ cylinders = 2;
+ }
+ *pcyls = cylinders;
+ *pheads = 16;
+ *psecs = 63;
+}
+
+void hd_geometry_guess(BlockBackend *blk,
+ uint32_t *pcyls, uint32_t *pheads, uint32_t *psecs,
+ int *ptrans)
+{
+ int cylinders, heads, secs, translation;
+ HDGeometry geo;
+
+ /* Try to probe the backing device geometry, otherwise fallback
+ to the old logic. (as of 12/2014 probing only succeeds on DASDs) */
+ if (blk_probe_geometry(blk, &geo) == 0) {
+ *pcyls = geo.cylinders;
+ *psecs = geo.sectors;
+ *pheads = geo.heads;
+ translation = BIOS_ATA_TRANSLATION_NONE;
+ } else if (guess_disk_lchs(blk, &cylinders, &heads, &secs) < 0) {
+ /* no LCHS guess: use a standard physical disk geometry */
+ guess_chs_for_size(blk, pcyls, pheads, psecs);
+ translation = hd_bios_chs_auto_trans(*pcyls, *pheads, *psecs);
+ } else if (heads > 16) {
+ /* LCHS guess with heads > 16 means that a BIOS LBA
+ translation was active, so a standard physical disk
+ geometry is OK */
+ guess_chs_for_size(blk, pcyls, pheads, psecs);
+ translation = *pcyls * *pheads <= 131072
+ ? BIOS_ATA_TRANSLATION_LARGE
+ : BIOS_ATA_TRANSLATION_LBA;
+ } else {
+ /* LCHS guess with heads <= 16: use as physical geometry */
+ *pcyls = cylinders;
+ *pheads = heads;
+ *psecs = secs;
+ /* disable any translation to be in sync with
+ the logical geometry */
+ translation = BIOS_ATA_TRANSLATION_NONE;
+ }
+ if (ptrans) {
+ if (*ptrans == BIOS_ATA_TRANSLATION_AUTO) {
+ *ptrans = translation;
+ } else {
+ /* Defer to the translation specified by the user. */
+ translation = *ptrans;
+ }
+ }
+ trace_hd_geometry_guess(blk, *pcyls, *pheads, *psecs, translation);
+}
+
+int hd_bios_chs_auto_trans(uint32_t cyls, uint32_t heads, uint32_t secs)
+{
+ return cyls <= 1024 && heads <= 16 && secs <= 63
+ ? BIOS_ATA_TRANSLATION_NONE
+ : BIOS_ATA_TRANSLATION_LBA;
+}
diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c
new file mode 100644
index 00000000..02adc875
--- /dev/null
+++ b/hw/block/m25p80.c
@@ -0,0 +1,1831 @@
+/*
+ * ST M25P80 emulator. Emulate all SPI flash devices based on the m25p80 command
+ * set. Known devices table current as of Jun/2012 and taken from linux.
+ * See drivers/mtd/devices/m25p80.c.
+ *
+ * Copyright (C) 2011 Edgar E. Iglesias <edgar.iglesias@gmail.com>
+ * Copyright (C) 2012 Peter A. G. Crosthwaite <peter.crosthwaite@petalogix.com>
+ * Copyright (C) 2012 PetaLogix
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 or
+ * (at your option) a later version of the License.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/units.h"
+#include "sysemu/block-backend.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "hw/ssi/ssi.h"
+#include "migration/vmstate.h"
+#include "qemu/bitops.h"
+#include "qemu/log.h"
+#include "qemu/module.h"
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+#include "trace.h"
+#include "qom/object.h"
+#include "m25p80_sfdp.h"
+
+/* 16 MiB max in 3 byte address mode */
+#define MAX_3BYTES_SIZE 0x1000000
+#define SPI_NOR_MAX_ID_LEN 6
+
+/* Fields for FlashPartInfo->flags */
+enum spi_flash_option_flags {
+ ER_4K = BIT(0),
+ ER_32K = BIT(1),
+ EEPROM = BIT(2),
+ HAS_SR_TB = BIT(3),
+ HAS_SR_BP3_BIT6 = BIT(4),
+};
+
+typedef struct FlashPartInfo {
+ const char *part_name;
+ /*
+ * This array stores the ID bytes.
+ * The first three bytes are the JEDIC ID.
+ * JEDEC ID zero means "no ID" (mostly older chips).
+ */
+ uint8_t id[SPI_NOR_MAX_ID_LEN];
+ uint8_t id_len;
+ /* there is confusion between manufacturers as to what a sector is. In this
+ * device model, a "sector" is the size that is erased by the ERASE_SECTOR
+ * command (opcode 0xd8).
+ */
+ uint32_t sector_size;
+ uint32_t n_sectors;
+ uint32_t page_size;
+ uint16_t flags;
+ /*
+ * Big sized spi nor are often stacked devices, thus sometime
+ * replace chip erase with die erase.
+ * This field inform how many die is in the chip.
+ */
+ uint8_t die_cnt;
+ uint8_t (*sfdp_read)(uint32_t sfdp_addr);
+} FlashPartInfo;
+
+/* adapted from linux */
+/* Used when the "_ext_id" is two bytes at most */
+#define INFO(_part_name, _jedec_id, _ext_id, _sector_size, _n_sectors, _flags)\
+ .part_name = _part_name,\
+ .id = {\
+ ((_jedec_id) >> 16) & 0xff,\
+ ((_jedec_id) >> 8) & 0xff,\
+ (_jedec_id) & 0xff,\
+ ((_ext_id) >> 8) & 0xff,\
+ (_ext_id) & 0xff,\
+ },\
+ .id_len = (!(_jedec_id) ? 0 : (3 + ((_ext_id) ? 2 : 0))),\
+ .sector_size = (_sector_size),\
+ .n_sectors = (_n_sectors),\
+ .page_size = 256,\
+ .flags = (_flags),\
+ .die_cnt = 0
+
+#define INFO6(_part_name, _jedec_id, _ext_id, _sector_size, _n_sectors, _flags)\
+ .part_name = _part_name,\
+ .id = {\
+ ((_jedec_id) >> 16) & 0xff,\
+ ((_jedec_id) >> 8) & 0xff,\
+ (_jedec_id) & 0xff,\
+ ((_ext_id) >> 16) & 0xff,\
+ ((_ext_id) >> 8) & 0xff,\
+ (_ext_id) & 0xff,\
+ },\
+ .id_len = 6,\
+ .sector_size = (_sector_size),\
+ .n_sectors = (_n_sectors),\
+ .page_size = 256,\
+ .flags = (_flags),\
+ .die_cnt = 0
+
+#define INFO_STACKED(_part_name, _jedec_id, _ext_id, _sector_size, _n_sectors,\
+ _flags, _die_cnt)\
+ .part_name = _part_name,\
+ .id = {\
+ ((_jedec_id) >> 16) & 0xff,\
+ ((_jedec_id) >> 8) & 0xff,\
+ (_jedec_id) & 0xff,\
+ ((_ext_id) >> 8) & 0xff,\
+ (_ext_id) & 0xff,\
+ },\
+ .id_len = (!(_jedec_id) ? 0 : (3 + ((_ext_id) ? 2 : 0))),\
+ .sector_size = (_sector_size),\
+ .n_sectors = (_n_sectors),\
+ .page_size = 256,\
+ .flags = (_flags),\
+ .die_cnt = _die_cnt
+
+#define JEDEC_NUMONYX 0x20
+#define JEDEC_WINBOND 0xEF
+#define JEDEC_SPANSION 0x01
+
+/* Numonyx (Micron) Configuration register macros */
+#define VCFG_DUMMY 0x1
+#define VCFG_WRAP_SEQUENTIAL 0x2
+#define NVCFG_XIP_MODE_DISABLED (7 << 9)
+#define NVCFG_XIP_MODE_MASK (7 << 9)
+#define VCFG_XIP_MODE_DISABLED (1 << 3)
+#define CFG_DUMMY_CLK_LEN 4
+#define NVCFG_DUMMY_CLK_POS 12
+#define VCFG_DUMMY_CLK_POS 4
+#define EVCFG_OUT_DRIVER_STRENGTH_DEF 7
+#define EVCFG_VPP_ACCELERATOR (1 << 3)
+#define EVCFG_RESET_HOLD_ENABLED (1 << 4)
+#define NVCFG_DUAL_IO_MASK (1 << 2)
+#define EVCFG_DUAL_IO_DISABLED (1 << 6)
+#define NVCFG_QUAD_IO_MASK (1 << 3)
+#define EVCFG_QUAD_IO_DISABLED (1 << 7)
+#define NVCFG_4BYTE_ADDR_MASK (1 << 0)
+#define NVCFG_LOWER_SEGMENT_MASK (1 << 1)
+
+/* Numonyx (Micron) Flag Status Register macros */
+#define FSR_4BYTE_ADDR_MODE_ENABLED 0x1
+#define FSR_FLASH_READY (1 << 7)
+
+/* Spansion configuration registers macros. */
+#define SPANSION_QUAD_CFG_POS 0
+#define SPANSION_QUAD_CFG_LEN 1
+#define SPANSION_DUMMY_CLK_POS 0
+#define SPANSION_DUMMY_CLK_LEN 4
+#define SPANSION_ADDR_LEN_POS 7
+#define SPANSION_ADDR_LEN_LEN 1
+
+/*
+ * Spansion read mode command length in bytes,
+ * the mode is currently not supported.
+*/
+
+#define SPANSION_CONTINUOUS_READ_MODE_CMD_LEN 1
+#define WINBOND_CONTINUOUS_READ_MODE_CMD_LEN 1
+
+static const FlashPartInfo known_devices[] = {
+ /* Atmel -- some are (confusingly) marketed as "DataFlash" */
+ { INFO("at25fs010", 0x1f6601, 0, 32 << 10, 4, ER_4K) },
+ { INFO("at25fs040", 0x1f6604, 0, 64 << 10, 8, ER_4K) },
+
+ { INFO("at25df041a", 0x1f4401, 0, 64 << 10, 8, ER_4K) },
+ { INFO("at25df321a", 0x1f4701, 0, 64 << 10, 64, ER_4K) },
+ { INFO("at25df641", 0x1f4800, 0, 64 << 10, 128, ER_4K) },
+
+ { INFO("at26f004", 0x1f0400, 0, 64 << 10, 8, ER_4K) },
+ { INFO("at26df081a", 0x1f4501, 0, 64 << 10, 16, ER_4K) },
+ { INFO("at26df161a", 0x1f4601, 0, 64 << 10, 32, ER_4K) },
+ { INFO("at26df321", 0x1f4700, 0, 64 << 10, 64, ER_4K) },
+
+ { INFO("at45db081d", 0x1f2500, 0, 64 << 10, 16, ER_4K) },
+
+ /* Atmel EEPROMS - it is assumed, that don't care bit in command
+ * is set to 0. Block protection is not supported.
+ */
+ { INFO("at25128a-nonjedec", 0x0, 0, 1, 131072, EEPROM) },
+ { INFO("at25256a-nonjedec", 0x0, 0, 1, 262144, EEPROM) },
+
+ /* EON -- en25xxx */
+ { INFO("en25f32", 0x1c3116, 0, 64 << 10, 64, ER_4K) },
+ { INFO("en25p32", 0x1c2016, 0, 64 << 10, 64, 0) },
+ { INFO("en25q32b", 0x1c3016, 0, 64 << 10, 64, 0) },
+ { INFO("en25p64", 0x1c2017, 0, 64 << 10, 128, 0) },
+ { INFO("en25q64", 0x1c3017, 0, 64 << 10, 128, ER_4K) },
+
+ /* GigaDevice */
+ { INFO("gd25q32", 0xc84016, 0, 64 << 10, 64, ER_4K) },
+ { INFO("gd25q64", 0xc84017, 0, 64 << 10, 128, ER_4K) },
+
+ /* Intel/Numonyx -- xxxs33b */
+ { INFO("160s33b", 0x898911, 0, 64 << 10, 32, 0) },
+ { INFO("320s33b", 0x898912, 0, 64 << 10, 64, 0) },
+ { INFO("640s33b", 0x898913, 0, 64 << 10, 128, 0) },
+ { INFO("n25q064", 0x20ba17, 0, 64 << 10, 128, 0) },
+
+ /* ISSI */
+ { INFO("is25lq040b", 0x9d4013, 0, 64 << 10, 8, ER_4K) },
+ { INFO("is25lp080d", 0x9d6014, 0, 64 << 10, 16, ER_4K) },
+ { INFO("is25lp016d", 0x9d6015, 0, 64 << 10, 32, ER_4K) },
+ { INFO("is25lp032", 0x9d6016, 0, 64 << 10, 64, ER_4K) },
+ { INFO("is25lp064", 0x9d6017, 0, 64 << 10, 128, ER_4K) },
+ { INFO("is25lp128", 0x9d6018, 0, 64 << 10, 256, ER_4K) },
+ { INFO("is25lp256", 0x9d6019, 0, 64 << 10, 512, ER_4K) },
+ { INFO("is25wp032", 0x9d7016, 0, 64 << 10, 64, ER_4K) },
+ { INFO("is25wp064", 0x9d7017, 0, 64 << 10, 128, ER_4K) },
+ { INFO("is25wp128", 0x9d7018, 0, 64 << 10, 256, ER_4K) },
+ { INFO("is25wp256", 0x9d7019, 0, 64 << 10, 512, ER_4K) },
+
+ /* Macronix */
+ { INFO("mx25l2005a", 0xc22012, 0, 64 << 10, 4, ER_4K) },
+ { INFO("mx25l4005a", 0xc22013, 0, 64 << 10, 8, ER_4K) },
+ { INFO("mx25l8005", 0xc22014, 0, 64 << 10, 16, 0) },
+ { INFO("mx25l1606e", 0xc22015, 0, 64 << 10, 32, ER_4K) },
+ { INFO("mx25l3205d", 0xc22016, 0, 64 << 10, 64, 0) },
+ { INFO("mx25l6405d", 0xc22017, 0, 64 << 10, 128, 0) },
+ { INFO("mx25l12805d", 0xc22018, 0, 64 << 10, 256, 0) },
+ { INFO("mx25l12855e", 0xc22618, 0, 64 << 10, 256, 0) },
+ { INFO6("mx25l25635e", 0xc22019, 0xc22019, 64 << 10, 512,
+ ER_4K | ER_32K), .sfdp_read = m25p80_sfdp_mx25l25635e },
+ { INFO6("mx25l25635f", 0xc22019, 0xc22019, 64 << 10, 512,
+ ER_4K | ER_32K), .sfdp_read = m25p80_sfdp_mx25l25635f },
+ { INFO("mx25l25655e", 0xc22619, 0, 64 << 10, 512, 0) },
+ { INFO("mx66l51235f", 0xc2201a, 0, 64 << 10, 1024, ER_4K | ER_32K) },
+ { INFO("mx66u51235f", 0xc2253a, 0, 64 << 10, 1024, ER_4K | ER_32K) },
+ { INFO("mx66u1g45g", 0xc2253b, 0, 64 << 10, 2048, ER_4K | ER_32K) },
+ { INFO("mx66l1g45g", 0xc2201b, 0, 64 << 10, 2048, ER_4K | ER_32K),
+ .sfdp_read = m25p80_sfdp_mx66l1g45g },
+
+ /* Micron */
+ { INFO("n25q032a11", 0x20bb16, 0, 64 << 10, 64, ER_4K) },
+ { INFO("n25q032a13", 0x20ba16, 0, 64 << 10, 64, ER_4K) },
+ { INFO("n25q064a11", 0x20bb17, 0, 64 << 10, 128, ER_4K) },
+ { INFO("n25q064a13", 0x20ba17, 0, 64 << 10, 128, ER_4K) },
+ { INFO("n25q128a11", 0x20bb18, 0, 64 << 10, 256, ER_4K) },
+ { INFO("n25q128a13", 0x20ba18, 0, 64 << 10, 256, ER_4K) },
+ { INFO("n25q256a11", 0x20bb19, 0, 64 << 10, 512, ER_4K) },
+ { INFO("n25q256a13", 0x20ba19, 0, 64 << 10, 512, ER_4K),
+ .sfdp_read = m25p80_sfdp_n25q256a },
+ { INFO("n25q512a11", 0x20bb20, 0, 64 << 10, 1024, ER_4K) },
+ { INFO("n25q512a13", 0x20ba20, 0, 64 << 10, 1024, ER_4K) },
+ { INFO("n25q128", 0x20ba18, 0, 64 << 10, 256, 0) },
+ { INFO("n25q256a", 0x20ba19, 0, 64 << 10, 512,
+ ER_4K | HAS_SR_BP3_BIT6 | HAS_SR_TB),
+ .sfdp_read = m25p80_sfdp_n25q256a },
+ { INFO("n25q512a", 0x20ba20, 0, 64 << 10, 1024, ER_4K) },
+ { INFO("n25q512ax3", 0x20ba20, 0x1000, 64 << 10, 1024, ER_4K) },
+ { INFO("mt25ql512ab", 0x20ba20, 0x1044, 64 << 10, 1024, ER_4K | ER_32K) },
+ { INFO_STACKED("mt35xu01g", 0x2c5b1b, 0x104100, 128 << 10, 1024,
+ ER_4K | ER_32K, 2) },
+ { INFO_STACKED("n25q00", 0x20ba21, 0x1000, 64 << 10, 2048, ER_4K, 4) },
+ { INFO_STACKED("n25q00a", 0x20bb21, 0x1000, 64 << 10, 2048, ER_4K, 4) },
+ { INFO_STACKED("mt25ql01g", 0x20ba21, 0x1040, 64 << 10, 2048, ER_4K, 2) },
+ { INFO_STACKED("mt25qu01g", 0x20bb21, 0x1040, 64 << 10, 2048, ER_4K, 2) },
+ { INFO_STACKED("mt25ql02g", 0x20ba22, 0x1040, 64 << 10, 4096, ER_4K | ER_32K, 2) },
+ { INFO_STACKED("mt25qu02g", 0x20bb22, 0x1040, 64 << 10, 4096, ER_4K | ER_32K, 2) },
+
+ /* Spansion -- single (large) sector size only, at least
+ * for the chips listed here (without boot sectors).
+ */
+ { INFO("s25sl032p", 0x010215, 0x4d00, 64 << 10, 64, ER_4K) },
+ { INFO("s25sl064p", 0x010216, 0x4d00, 64 << 10, 128, ER_4K) },
+ { INFO("s25fl256s0", 0x010219, 0x4d00, 256 << 10, 128, 0) },
+ { INFO("s25fl256s1", 0x010219, 0x4d01, 64 << 10, 512, 0) },
+ { INFO6("s25fl512s", 0x010220, 0x4d0080, 256 << 10, 256, 0) },
+ { INFO6("s70fl01gs", 0x010221, 0x4d0080, 256 << 10, 512, 0) },
+ { INFO("s25sl12800", 0x012018, 0x0300, 256 << 10, 64, 0) },
+ { INFO("s25sl12801", 0x012018, 0x0301, 64 << 10, 256, 0) },
+ { INFO("s25fl129p0", 0x012018, 0x4d00, 256 << 10, 64, 0) },
+ { INFO("s25fl129p1", 0x012018, 0x4d01, 64 << 10, 256, 0) },
+ { INFO("s25sl004a", 0x010212, 0, 64 << 10, 8, 0) },
+ { INFO("s25sl008a", 0x010213, 0, 64 << 10, 16, 0) },
+ { INFO("s25sl016a", 0x010214, 0, 64 << 10, 32, 0) },
+ { INFO("s25sl032a", 0x010215, 0, 64 << 10, 64, 0) },
+ { INFO("s25sl064a", 0x010216, 0, 64 << 10, 128, 0) },
+ { INFO("s25fl016k", 0xef4015, 0, 64 << 10, 32, ER_4K | ER_32K) },
+ { INFO("s25fl064k", 0xef4017, 0, 64 << 10, 128, ER_4K | ER_32K) },
+
+ /* Spansion -- boot sectors support */
+ { INFO6("s25fs512s", 0x010220, 0x4d0081, 256 << 10, 256, 0) },
+ { INFO6("s70fs01gs", 0x010221, 0x4d0081, 256 << 10, 512, 0) },
+
+ /* SST -- large erase sizes are "overlays", "sectors" are 4<< 10 */
+ { INFO("sst25vf040b", 0xbf258d, 0, 64 << 10, 8, ER_4K) },
+ { INFO("sst25vf080b", 0xbf258e, 0, 64 << 10, 16, ER_4K) },
+ { INFO("sst25vf016b", 0xbf2541, 0, 64 << 10, 32, ER_4K) },
+ { INFO("sst25vf032b", 0xbf254a, 0, 64 << 10, 64, ER_4K) },
+ { INFO("sst25wf512", 0xbf2501, 0, 64 << 10, 1, ER_4K) },
+ { INFO("sst25wf010", 0xbf2502, 0, 64 << 10, 2, ER_4K) },
+ { INFO("sst25wf020", 0xbf2503, 0, 64 << 10, 4, ER_4K) },
+ { INFO("sst25wf040", 0xbf2504, 0, 64 << 10, 8, ER_4K) },
+ { INFO("sst25wf080", 0xbf2505, 0, 64 << 10, 16, ER_4K) },
+
+ /* ST Microelectronics -- newer production may have feature updates */
+ { INFO("m25p05", 0x202010, 0, 32 << 10, 2, 0) },
+ { INFO("m25p10", 0x202011, 0, 32 << 10, 4, 0) },
+ { INFO("m25p20", 0x202012, 0, 64 << 10, 4, 0) },
+ { INFO("m25p40", 0x202013, 0, 64 << 10, 8, 0) },
+ { INFO("m25p80", 0x202014, 0, 64 << 10, 16, 0) },
+ { INFO("m25p16", 0x202015, 0, 64 << 10, 32, 0) },
+ { INFO("m25p32", 0x202016, 0, 64 << 10, 64, 0) },
+ { INFO("m25p64", 0x202017, 0, 64 << 10, 128, 0) },
+ { INFO("m25p128", 0x202018, 0, 256 << 10, 64, 0) },
+ { INFO("n25q032", 0x20ba16, 0, 64 << 10, 64, 0) },
+
+ { INFO("m45pe10", 0x204011, 0, 64 << 10, 2, 0) },
+ { INFO("m45pe80", 0x204014, 0, 64 << 10, 16, 0) },
+ { INFO("m45pe16", 0x204015, 0, 64 << 10, 32, 0) },
+
+ { INFO("m25pe20", 0x208012, 0, 64 << 10, 4, 0) },
+ { INFO("m25pe80", 0x208014, 0, 64 << 10, 16, 0) },
+ { INFO("m25pe16", 0x208015, 0, 64 << 10, 32, ER_4K) },
+
+ { INFO("m25px32", 0x207116, 0, 64 << 10, 64, ER_4K) },
+ { INFO("m25px32-s0", 0x207316, 0, 64 << 10, 64, ER_4K) },
+ { INFO("m25px32-s1", 0x206316, 0, 64 << 10, 64, ER_4K) },
+ { INFO("m25px64", 0x207117, 0, 64 << 10, 128, 0) },
+
+ /* Winbond -- w25x "blocks" are 64k, "sectors" are 4KiB */
+ { INFO("w25x10", 0xef3011, 0, 64 << 10, 2, ER_4K) },
+ { INFO("w25x20", 0xef3012, 0, 64 << 10, 4, ER_4K) },
+ { INFO("w25x40", 0xef3013, 0, 64 << 10, 8, ER_4K) },
+ { INFO("w25x80", 0xef3014, 0, 64 << 10, 16, ER_4K) },
+ { INFO("w25x16", 0xef3015, 0, 64 << 10, 32, ER_4K) },
+ { INFO("w25x32", 0xef3016, 0, 64 << 10, 64, ER_4K) },
+ { INFO("w25q32", 0xef4016, 0, 64 << 10, 64, ER_4K) },
+ { INFO("w25q32dw", 0xef6016, 0, 64 << 10, 64, ER_4K) },
+ { INFO("w25x64", 0xef3017, 0, 64 << 10, 128, ER_4K) },
+ { INFO("w25q64", 0xef4017, 0, 64 << 10, 128, ER_4K) },
+ { INFO("w25q80", 0xef5014, 0, 64 << 10, 16, ER_4K) },
+ { INFO("w25q80bl", 0xef4014, 0, 64 << 10, 16, ER_4K) },
+ { INFO("w25q256", 0xef4019, 0, 64 << 10, 512, ER_4K),
+ .sfdp_read = m25p80_sfdp_w25q256 },
+ { INFO("w25q512jv", 0xef4020, 0, 64 << 10, 1024, ER_4K),
+ .sfdp_read = m25p80_sfdp_w25q512jv },
+ { INFO("w25q01jvq", 0xef4021, 0, 64 << 10, 2048, ER_4K),
+ .sfdp_read = m25p80_sfdp_w25q01jvq },
+};
+
+typedef enum {
+ NOP = 0,
+ WRSR = 0x1,
+ WRDI = 0x4,
+ RDSR = 0x5,
+ WREN = 0x6,
+ BRRD = 0x16,
+ BRWR = 0x17,
+ JEDEC_READ = 0x9f,
+ BULK_ERASE_60 = 0x60,
+ BULK_ERASE = 0xc7,
+ READ_FSR = 0x70,
+ RDCR = 0x15,
+ RDSFDP = 0x5a,
+
+ READ = 0x03,
+ READ4 = 0x13,
+ FAST_READ = 0x0b,
+ FAST_READ4 = 0x0c,
+ DOR = 0x3b,
+ DOR4 = 0x3c,
+ QOR = 0x6b,
+ QOR4 = 0x6c,
+ DIOR = 0xbb,
+ DIOR4 = 0xbc,
+ QIOR = 0xeb,
+ QIOR4 = 0xec,
+
+ PP = 0x02,
+ PP4 = 0x12,
+ PP4_4 = 0x3e,
+ DPP = 0xa2,
+ QPP = 0x32,
+ QPP_4 = 0x34,
+ RDID_90 = 0x90,
+ RDID_AB = 0xab,
+ AAI_WP = 0xad,
+
+ ERASE_4K = 0x20,
+ ERASE4_4K = 0x21,
+ ERASE_32K = 0x52,
+ ERASE4_32K = 0x5c,
+ ERASE_SECTOR = 0xd8,
+ ERASE4_SECTOR = 0xdc,
+
+ EN_4BYTE_ADDR = 0xB7,
+ EX_4BYTE_ADDR = 0xE9,
+
+ EXTEND_ADDR_READ = 0xC8,
+ EXTEND_ADDR_WRITE = 0xC5,
+
+ RESET_ENABLE = 0x66,
+ RESET_MEMORY = 0x99,
+
+ /*
+ * Micron: 0x35 - enable QPI
+ * Spansion: 0x35 - read control register
+ */
+ RDCR_EQIO = 0x35,
+ RSTQIO = 0xf5,
+
+ RNVCR = 0xB5,
+ WNVCR = 0xB1,
+
+ RVCR = 0x85,
+ WVCR = 0x81,
+
+ REVCR = 0x65,
+ WEVCR = 0x61,
+
+ DIE_ERASE = 0xC4,
+} FlashCMD;
+
+typedef enum {
+ STATE_IDLE,
+ STATE_PAGE_PROGRAM,
+ STATE_READ,
+ STATE_COLLECTING_DATA,
+ STATE_COLLECTING_VAR_LEN_DATA,
+ STATE_READING_DATA,
+ STATE_READING_SFDP,
+} CMDState;
+
+typedef enum {
+ MAN_SPANSION,
+ MAN_MACRONIX,
+ MAN_NUMONYX,
+ MAN_WINBOND,
+ MAN_SST,
+ MAN_ISSI,
+ MAN_GENERIC,
+} Manufacturer;
+
+typedef enum {
+ MODE_STD = 0,
+ MODE_DIO = 1,
+ MODE_QIO = 2
+} SPIMode;
+
+#define M25P80_INTERNAL_DATA_BUFFER_SZ 16
+
+struct Flash {
+ SSIPeripheral parent_obj;
+
+ BlockBackend *blk;
+
+ uint8_t *storage;
+ uint32_t size;
+ int page_size;
+
+ uint8_t state;
+ uint8_t data[M25P80_INTERNAL_DATA_BUFFER_SZ];
+ uint32_t len;
+ uint32_t pos;
+ bool data_read_loop;
+ uint8_t needed_bytes;
+ uint8_t cmd_in_progress;
+ uint32_t cur_addr;
+ uint32_t nonvolatile_cfg;
+ /* Configuration register for Macronix */
+ uint32_t volatile_cfg;
+ uint32_t enh_volatile_cfg;
+ /* Spansion cfg registers. */
+ uint8_t spansion_cr1nv;
+ uint8_t spansion_cr2nv;
+ uint8_t spansion_cr3nv;
+ uint8_t spansion_cr4nv;
+ uint8_t spansion_cr1v;
+ uint8_t spansion_cr2v;
+ uint8_t spansion_cr3v;
+ uint8_t spansion_cr4v;
+ bool wp_level;
+ bool write_enable;
+ bool four_bytes_address_mode;
+ bool reset_enable;
+ bool quad_enable;
+ bool aai_enable;
+ bool block_protect0;
+ bool block_protect1;
+ bool block_protect2;
+ bool block_protect3;
+ bool top_bottom_bit;
+ bool status_register_write_disabled;
+ uint8_t ear;
+
+ int64_t dirty_page;
+
+ const FlashPartInfo *pi;
+
+};
+
+struct M25P80Class {
+ SSIPeripheralClass parent_class;
+ FlashPartInfo *pi;
+};
+
+#define TYPE_M25P80 "m25p80-generic"
+OBJECT_DECLARE_TYPE(Flash, M25P80Class, M25P80)
+
+static inline Manufacturer get_man(Flash *s)
+{
+ switch (s->pi->id[0]) {
+ case 0x20:
+ return MAN_NUMONYX;
+ case 0xEF:
+ return MAN_WINBOND;
+ case 0x01:
+ return MAN_SPANSION;
+ case 0xC2:
+ return MAN_MACRONIX;
+ case 0xBF:
+ return MAN_SST;
+ case 0x9D:
+ return MAN_ISSI;
+ default:
+ return MAN_GENERIC;
+ }
+}
+
+static void blk_sync_complete(void *opaque, int ret)
+{
+ QEMUIOVector *iov = opaque;
+
+ qemu_iovec_destroy(iov);
+ g_free(iov);
+
+ /* do nothing. Masters do not directly interact with the backing store,
+ * only the working copy so no mutexing required.
+ */
+}
+
+static void flash_sync_page(Flash *s, int page)
+{
+ QEMUIOVector *iov;
+
+ if (!s->blk || !blk_is_writable(s->blk)) {
+ return;
+ }
+
+ iov = g_new(QEMUIOVector, 1);
+ qemu_iovec_init(iov, 1);
+ qemu_iovec_add(iov, s->storage + page * s->pi->page_size,
+ s->pi->page_size);
+ blk_aio_pwritev(s->blk, page * s->pi->page_size, iov, 0,
+ blk_sync_complete, iov);
+}
+
+static inline void flash_sync_area(Flash *s, int64_t off, int64_t len)
+{
+ QEMUIOVector *iov;
+
+ if (!s->blk || !blk_is_writable(s->blk)) {
+ return;
+ }
+
+ assert(!(len % BDRV_SECTOR_SIZE));
+ iov = g_new(QEMUIOVector, 1);
+ qemu_iovec_init(iov, 1);
+ qemu_iovec_add(iov, s->storage + off, len);
+ blk_aio_pwritev(s->blk, off, iov, 0, blk_sync_complete, iov);
+}
+
+static void flash_erase(Flash *s, int offset, FlashCMD cmd)
+{
+ uint32_t len;
+ uint8_t capa_to_assert = 0;
+
+ switch (cmd) {
+ case ERASE_4K:
+ case ERASE4_4K:
+ len = 4 * KiB;
+ capa_to_assert = ER_4K;
+ break;
+ case ERASE_32K:
+ case ERASE4_32K:
+ len = 32 * KiB;
+ capa_to_assert = ER_32K;
+ break;
+ case ERASE_SECTOR:
+ case ERASE4_SECTOR:
+ len = s->pi->sector_size;
+ break;
+ case BULK_ERASE:
+ len = s->size;
+ break;
+ case DIE_ERASE:
+ if (s->pi->die_cnt) {
+ len = s->size / s->pi->die_cnt;
+ offset = offset & (~(len - 1));
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: die erase is not supported"
+ " by device\n");
+ return;
+ }
+ break;
+ default:
+ abort();
+ }
+
+ trace_m25p80_flash_erase(s, offset, len);
+
+ if ((s->pi->flags & capa_to_assert) != capa_to_assert) {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: %d erase size not supported by"
+ " device\n", len);
+ }
+
+ if (!s->write_enable) {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: erase with write protect!\n");
+ return;
+ }
+ memset(s->storage + offset, 0xff, len);
+ flash_sync_area(s, offset, len);
+}
+
+static inline void flash_sync_dirty(Flash *s, int64_t newpage)
+{
+ if (s->dirty_page >= 0 && s->dirty_page != newpage) {
+ flash_sync_page(s, s->dirty_page);
+ s->dirty_page = newpage;
+ }
+}
+
+static inline
+void flash_write8(Flash *s, uint32_t addr, uint8_t data)
+{
+ uint32_t page = addr / s->pi->page_size;
+ uint8_t prev = s->storage[s->cur_addr];
+ uint32_t block_protect_value = (s->block_protect3 << 3) |
+ (s->block_protect2 << 2) |
+ (s->block_protect1 << 1) |
+ (s->block_protect0 << 0);
+
+ if (!s->write_enable) {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: write with write protect!\n");
+ return;
+ }
+
+ if (block_protect_value > 0) {
+ uint32_t num_protected_sectors = 1 << (block_protect_value - 1);
+ uint32_t sector = addr / s->pi->sector_size;
+
+ /* top_bottom_bit == 0 means TOP */
+ if (!s->top_bottom_bit) {
+ if (s->pi->n_sectors <= sector + num_protected_sectors) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "M25P80: write with write protect!\n");
+ return;
+ }
+ } else {
+ if (sector < num_protected_sectors) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "M25P80: write with write protect!\n");
+ return;
+ }
+ }
+ }
+
+ if ((prev ^ data) & data) {
+ trace_m25p80_programming_zero_to_one(s, addr, prev, data);
+ }
+
+ if (s->pi->flags & EEPROM) {
+ s->storage[s->cur_addr] = data;
+ } else {
+ s->storage[s->cur_addr] &= data;
+ }
+
+ flash_sync_dirty(s, page);
+ s->dirty_page = page;
+}
+
+static inline int get_addr_length(Flash *s)
+{
+ /* check if eeprom is in use */
+ if (s->pi->flags == EEPROM) {
+ return 2;
+ }
+
+ switch (s->cmd_in_progress) {
+ case RDSFDP:
+ return 3;
+ case PP4:
+ case PP4_4:
+ case QPP_4:
+ case READ4:
+ case QIOR4:
+ case ERASE4_4K:
+ case ERASE4_32K:
+ case ERASE4_SECTOR:
+ case FAST_READ4:
+ case DOR4:
+ case QOR4:
+ case DIOR4:
+ return 4;
+ default:
+ return s->four_bytes_address_mode ? 4 : 3;
+ }
+}
+
+static void complete_collecting_data(Flash *s)
+{
+ int i, n;
+
+ n = get_addr_length(s);
+ s->cur_addr = (n == 3 ? s->ear : 0);
+ for (i = 0; i < n; ++i) {
+ s->cur_addr <<= 8;
+ s->cur_addr |= s->data[i];
+ }
+
+ s->cur_addr &= s->size - 1;
+
+ s->state = STATE_IDLE;
+
+ trace_m25p80_complete_collecting(s, s->cmd_in_progress, n, s->ear,
+ s->cur_addr);
+
+ switch (s->cmd_in_progress) {
+ case DPP:
+ case QPP:
+ case QPP_4:
+ case PP:
+ case PP4:
+ case PP4_4:
+ s->state = STATE_PAGE_PROGRAM;
+ break;
+ case AAI_WP:
+ /* AAI programming starts from the even address */
+ s->cur_addr &= ~BIT(0);
+ s->state = STATE_PAGE_PROGRAM;
+ break;
+ case READ:
+ case READ4:
+ case FAST_READ:
+ case FAST_READ4:
+ case DOR:
+ case DOR4:
+ case QOR:
+ case QOR4:
+ case DIOR:
+ case DIOR4:
+ case QIOR:
+ case QIOR4:
+ s->state = STATE_READ;
+ break;
+ case ERASE_4K:
+ case ERASE4_4K:
+ case ERASE_32K:
+ case ERASE4_32K:
+ case ERASE_SECTOR:
+ case ERASE4_SECTOR:
+ case DIE_ERASE:
+ flash_erase(s, s->cur_addr, s->cmd_in_progress);
+ break;
+ case WRSR:
+ s->status_register_write_disabled = extract32(s->data[0], 7, 1);
+ s->block_protect0 = extract32(s->data[0], 2, 1);
+ s->block_protect1 = extract32(s->data[0], 3, 1);
+ s->block_protect2 = extract32(s->data[0], 4, 1);
+ if (s->pi->flags & HAS_SR_TB) {
+ s->top_bottom_bit = extract32(s->data[0], 5, 1);
+ }
+ if (s->pi->flags & HAS_SR_BP3_BIT6) {
+ s->block_protect3 = extract32(s->data[0], 6, 1);
+ }
+
+ switch (get_man(s)) {
+ case MAN_SPANSION:
+ s->quad_enable = !!(s->data[1] & 0x02);
+ break;
+ case MAN_ISSI:
+ s->quad_enable = extract32(s->data[0], 6, 1);
+ break;
+ case MAN_MACRONIX:
+ s->quad_enable = extract32(s->data[0], 6, 1);
+ if (s->len > 1) {
+ s->volatile_cfg = s->data[1];
+ s->four_bytes_address_mode = extract32(s->data[1], 5, 1);
+ }
+ break;
+ default:
+ break;
+ }
+ if (s->write_enable) {
+ s->write_enable = false;
+ }
+ break;
+ case BRWR:
+ case EXTEND_ADDR_WRITE:
+ s->ear = s->data[0];
+ break;
+ case WNVCR:
+ s->nonvolatile_cfg = s->data[0] | (s->data[1] << 8);
+ break;
+ case WVCR:
+ s->volatile_cfg = s->data[0];
+ break;
+ case WEVCR:
+ s->enh_volatile_cfg = s->data[0];
+ break;
+ case RDID_90:
+ case RDID_AB:
+ if (get_man(s) == MAN_SST) {
+ if (s->cur_addr <= 1) {
+ if (s->cur_addr) {
+ s->data[0] = s->pi->id[2];
+ s->data[1] = s->pi->id[0];
+ } else {
+ s->data[0] = s->pi->id[0];
+ s->data[1] = s->pi->id[2];
+ }
+ s->pos = 0;
+ s->len = 2;
+ s->data_read_loop = true;
+ s->state = STATE_READING_DATA;
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "M25P80: Invalid read id address\n");
+ }
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "M25P80: Read id (command 0x90/0xAB) is not supported"
+ " by device\n");
+ }
+ break;
+
+ case RDSFDP:
+ s->state = STATE_READING_SFDP;
+ break;
+
+ default:
+ break;
+ }
+}
+
+static void reset_memory(Flash *s)
+{
+ s->cmd_in_progress = NOP;
+ s->cur_addr = 0;
+ s->ear = 0;
+ s->four_bytes_address_mode = false;
+ s->len = 0;
+ s->needed_bytes = 0;
+ s->pos = 0;
+ s->state = STATE_IDLE;
+ s->write_enable = false;
+ s->reset_enable = false;
+ s->quad_enable = false;
+ s->aai_enable = false;
+
+ switch (get_man(s)) {
+ case MAN_NUMONYX:
+ s->volatile_cfg = 0;
+ s->volatile_cfg |= VCFG_DUMMY;
+ s->volatile_cfg |= VCFG_WRAP_SEQUENTIAL;
+ if ((s->nonvolatile_cfg & NVCFG_XIP_MODE_MASK)
+ == NVCFG_XIP_MODE_DISABLED) {
+ s->volatile_cfg |= VCFG_XIP_MODE_DISABLED;
+ }
+ s->volatile_cfg |= deposit32(s->volatile_cfg,
+ VCFG_DUMMY_CLK_POS,
+ CFG_DUMMY_CLK_LEN,
+ extract32(s->nonvolatile_cfg,
+ NVCFG_DUMMY_CLK_POS,
+ CFG_DUMMY_CLK_LEN)
+ );
+
+ s->enh_volatile_cfg = 0;
+ s->enh_volatile_cfg |= EVCFG_OUT_DRIVER_STRENGTH_DEF;
+ s->enh_volatile_cfg |= EVCFG_VPP_ACCELERATOR;
+ s->enh_volatile_cfg |= EVCFG_RESET_HOLD_ENABLED;
+ if (s->nonvolatile_cfg & NVCFG_DUAL_IO_MASK) {
+ s->enh_volatile_cfg |= EVCFG_DUAL_IO_DISABLED;
+ }
+ if (s->nonvolatile_cfg & NVCFG_QUAD_IO_MASK) {
+ s->enh_volatile_cfg |= EVCFG_QUAD_IO_DISABLED;
+ }
+ if (!(s->nonvolatile_cfg & NVCFG_4BYTE_ADDR_MASK)) {
+ s->four_bytes_address_mode = true;
+ }
+ if (!(s->nonvolatile_cfg & NVCFG_LOWER_SEGMENT_MASK)) {
+ s->ear = s->size / MAX_3BYTES_SIZE - 1;
+ }
+ break;
+ case MAN_MACRONIX:
+ s->volatile_cfg = 0x7;
+ break;
+ case MAN_SPANSION:
+ s->spansion_cr1v = s->spansion_cr1nv;
+ s->spansion_cr2v = s->spansion_cr2nv;
+ s->spansion_cr3v = s->spansion_cr3nv;
+ s->spansion_cr4v = s->spansion_cr4nv;
+ s->quad_enable = extract32(s->spansion_cr1v,
+ SPANSION_QUAD_CFG_POS,
+ SPANSION_QUAD_CFG_LEN
+ );
+ s->four_bytes_address_mode = extract32(s->spansion_cr2v,
+ SPANSION_ADDR_LEN_POS,
+ SPANSION_ADDR_LEN_LEN
+ );
+ break;
+ default:
+ break;
+ }
+
+ trace_m25p80_reset_done(s);
+}
+
+static uint8_t numonyx_mode(Flash *s)
+{
+ if (!(s->enh_volatile_cfg & EVCFG_QUAD_IO_DISABLED)) {
+ return MODE_QIO;
+ } else if (!(s->enh_volatile_cfg & EVCFG_DUAL_IO_DISABLED)) {
+ return MODE_DIO;
+ } else {
+ return MODE_STD;
+ }
+}
+
+static uint8_t numonyx_extract_cfg_num_dummies(Flash *s)
+{
+ uint8_t num_dummies;
+ uint8_t mode;
+ assert(get_man(s) == MAN_NUMONYX);
+
+ mode = numonyx_mode(s);
+ num_dummies = extract32(s->volatile_cfg, 4, 4);
+
+ if (num_dummies == 0x0 || num_dummies == 0xf) {
+ switch (s->cmd_in_progress) {
+ case QIOR:
+ case QIOR4:
+ num_dummies = 10;
+ break;
+ default:
+ num_dummies = (mode == MODE_QIO) ? 10 : 8;
+ break;
+ }
+ }
+
+ return num_dummies;
+}
+
+static void decode_fast_read_cmd(Flash *s)
+{
+ s->needed_bytes = get_addr_length(s);
+ switch (get_man(s)) {
+ /* Dummy cycles - modeled with bytes writes instead of bits */
+ case MAN_SST:
+ s->needed_bytes += 1;
+ break;
+ case MAN_WINBOND:
+ s->needed_bytes += 8;
+ break;
+ case MAN_NUMONYX:
+ s->needed_bytes += numonyx_extract_cfg_num_dummies(s);
+ break;
+ case MAN_MACRONIX:
+ if (extract32(s->volatile_cfg, 6, 2) == 1) {
+ s->needed_bytes += 6;
+ } else {
+ s->needed_bytes += 8;
+ }
+ break;
+ case MAN_SPANSION:
+ s->needed_bytes += extract32(s->spansion_cr2v,
+ SPANSION_DUMMY_CLK_POS,
+ SPANSION_DUMMY_CLK_LEN
+ );
+ break;
+ case MAN_ISSI:
+ /*
+ * The Fast Read instruction code is followed by address bytes and
+ * dummy cycles, transmitted via the SI line.
+ *
+ * The number of dummy cycles is configurable but this is currently
+ * unmodeled, hence the default value 8 is used.
+ *
+ * QPI (Quad Peripheral Interface) mode has different default value
+ * of dummy cycles, but this is unsupported at the time being.
+ */
+ s->needed_bytes += 1;
+ break;
+ default:
+ break;
+ }
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+}
+
+static void decode_dio_read_cmd(Flash *s)
+{
+ s->needed_bytes = get_addr_length(s);
+ /* Dummy cycles modeled with bytes writes instead of bits */
+ switch (get_man(s)) {
+ case MAN_WINBOND:
+ s->needed_bytes += WINBOND_CONTINUOUS_READ_MODE_CMD_LEN;
+ break;
+ case MAN_SPANSION:
+ s->needed_bytes += SPANSION_CONTINUOUS_READ_MODE_CMD_LEN;
+ s->needed_bytes += extract32(s->spansion_cr2v,
+ SPANSION_DUMMY_CLK_POS,
+ SPANSION_DUMMY_CLK_LEN
+ );
+ break;
+ case MAN_NUMONYX:
+ s->needed_bytes += numonyx_extract_cfg_num_dummies(s);
+ break;
+ case MAN_MACRONIX:
+ switch (extract32(s->volatile_cfg, 6, 2)) {
+ case 1:
+ s->needed_bytes += 6;
+ break;
+ case 2:
+ s->needed_bytes += 8;
+ break;
+ default:
+ s->needed_bytes += 4;
+ break;
+ }
+ break;
+ case MAN_ISSI:
+ /*
+ * The Fast Read Dual I/O instruction code is followed by address bytes
+ * and dummy cycles, transmitted via the IO1 and IO0 line.
+ *
+ * The number of dummy cycles is configurable but this is currently
+ * unmodeled, hence the default value 4 is used.
+ */
+ s->needed_bytes += 1;
+ break;
+ default:
+ break;
+ }
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+}
+
+static void decode_qio_read_cmd(Flash *s)
+{
+ s->needed_bytes = get_addr_length(s);
+ /* Dummy cycles modeled with bytes writes instead of bits */
+ switch (get_man(s)) {
+ case MAN_WINBOND:
+ s->needed_bytes += WINBOND_CONTINUOUS_READ_MODE_CMD_LEN;
+ s->needed_bytes += 4;
+ break;
+ case MAN_SPANSION:
+ s->needed_bytes += SPANSION_CONTINUOUS_READ_MODE_CMD_LEN;
+ s->needed_bytes += extract32(s->spansion_cr2v,
+ SPANSION_DUMMY_CLK_POS,
+ SPANSION_DUMMY_CLK_LEN
+ );
+ break;
+ case MAN_NUMONYX:
+ s->needed_bytes += numonyx_extract_cfg_num_dummies(s);
+ break;
+ case MAN_MACRONIX:
+ switch (extract32(s->volatile_cfg, 6, 2)) {
+ case 1:
+ s->needed_bytes += 4;
+ break;
+ case 2:
+ s->needed_bytes += 8;
+ break;
+ default:
+ s->needed_bytes += 6;
+ break;
+ }
+ break;
+ case MAN_ISSI:
+ /*
+ * The Fast Read Quad I/O instruction code is followed by address bytes
+ * and dummy cycles, transmitted via the IO3, IO2, IO1 and IO0 line.
+ *
+ * The number of dummy cycles is configurable but this is currently
+ * unmodeled, hence the default value 6 is used.
+ *
+ * QPI (Quad Peripheral Interface) mode has different default value
+ * of dummy cycles, but this is unsupported at the time being.
+ */
+ s->needed_bytes += 3;
+ break;
+ default:
+ break;
+ }
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+}
+
+static bool is_valid_aai_cmd(uint32_t cmd)
+{
+ return cmd == AAI_WP || cmd == WRDI || cmd == RDSR;
+}
+
+static void decode_new_cmd(Flash *s, uint32_t value)
+{
+ int i;
+
+ s->cmd_in_progress = value;
+ trace_m25p80_command_decoded(s, value);
+
+ if (value != RESET_MEMORY) {
+ s->reset_enable = false;
+ }
+
+ if (get_man(s) == MAN_SST && s->aai_enable && !is_valid_aai_cmd(value)) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "M25P80: Invalid cmd within AAI programming sequence");
+ }
+
+ switch (value) {
+
+ case ERASE_4K:
+ case ERASE4_4K:
+ case ERASE_32K:
+ case ERASE4_32K:
+ case ERASE_SECTOR:
+ case ERASE4_SECTOR:
+ case PP:
+ case PP4:
+ case DIE_ERASE:
+ case RDID_90:
+ case RDID_AB:
+ s->needed_bytes = get_addr_length(s);
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+ break;
+ case READ:
+ case READ4:
+ if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) == MODE_STD) {
+ s->needed_bytes = get_addr_length(s);
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in "
+ "DIO or QIO mode\n", s->cmd_in_progress);
+ }
+ break;
+ case DPP:
+ if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_QIO) {
+ s->needed_bytes = get_addr_length(s);
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in "
+ "QIO mode\n", s->cmd_in_progress);
+ }
+ break;
+ case QPP:
+ case QPP_4:
+ case PP4_4:
+ if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_DIO) {
+ s->needed_bytes = get_addr_length(s);
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in "
+ "DIO mode\n", s->cmd_in_progress);
+ }
+ break;
+
+ case FAST_READ:
+ case FAST_READ4:
+ decode_fast_read_cmd(s);
+ break;
+ case DOR:
+ case DOR4:
+ if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_QIO) {
+ decode_fast_read_cmd(s);
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in "
+ "QIO mode\n", s->cmd_in_progress);
+ }
+ break;
+ case QOR:
+ case QOR4:
+ if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_DIO) {
+ decode_fast_read_cmd(s);
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in "
+ "DIO mode\n", s->cmd_in_progress);
+ }
+ break;
+
+ case DIOR:
+ case DIOR4:
+ if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_QIO) {
+ decode_dio_read_cmd(s);
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in "
+ "QIO mode\n", s->cmd_in_progress);
+ }
+ break;
+
+ case QIOR:
+ case QIOR4:
+ if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_DIO) {
+ decode_qio_read_cmd(s);
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in "
+ "DIO mode\n", s->cmd_in_progress);
+ }
+ break;
+
+ case WRSR:
+ /*
+ * If WP# is low and status_register_write_disabled is high,
+ * status register writes are disabled.
+ * This is also called "hardware protected mode" (HPM). All other
+ * combinations of the two states are called "software protected mode"
+ * (SPM), and status register writes are permitted.
+ */
+ if ((s->wp_level == 0 && s->status_register_write_disabled)
+ || !s->write_enable) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "M25P80: Status register write is disabled!\n");
+ break;
+ }
+
+ switch (get_man(s)) {
+ case MAN_SPANSION:
+ s->needed_bytes = 2;
+ s->state = STATE_COLLECTING_DATA;
+ break;
+ case MAN_MACRONIX:
+ s->needed_bytes = 2;
+ s->state = STATE_COLLECTING_VAR_LEN_DATA;
+ break;
+ default:
+ s->needed_bytes = 1;
+ s->state = STATE_COLLECTING_DATA;
+ }
+ s->pos = 0;
+ break;
+
+ case WRDI:
+ s->write_enable = false;
+ if (get_man(s) == MAN_SST) {
+ s->aai_enable = false;
+ }
+ break;
+ case WREN:
+ s->write_enable = true;
+ break;
+
+ case RDSR:
+ s->data[0] = (!!s->write_enable) << 1;
+ s->data[0] |= (!!s->status_register_write_disabled) << 7;
+ s->data[0] |= (!!s->block_protect0) << 2;
+ s->data[0] |= (!!s->block_protect1) << 3;
+ s->data[0] |= (!!s->block_protect2) << 4;
+ if (s->pi->flags & HAS_SR_TB) {
+ s->data[0] |= (!!s->top_bottom_bit) << 5;
+ }
+ if (s->pi->flags & HAS_SR_BP3_BIT6) {
+ s->data[0] |= (!!s->block_protect3) << 6;
+ }
+
+ if (get_man(s) == MAN_MACRONIX || get_man(s) == MAN_ISSI) {
+ s->data[0] |= (!!s->quad_enable) << 6;
+ }
+ if (get_man(s) == MAN_SST) {
+ s->data[0] |= (!!s->aai_enable) << 6;
+ }
+
+ s->pos = 0;
+ s->len = 1;
+ s->data_read_loop = true;
+ s->state = STATE_READING_DATA;
+ break;
+
+ case READ_FSR:
+ s->data[0] = FSR_FLASH_READY;
+ if (s->four_bytes_address_mode) {
+ s->data[0] |= FSR_4BYTE_ADDR_MODE_ENABLED;
+ }
+ s->pos = 0;
+ s->len = 1;
+ s->data_read_loop = true;
+ s->state = STATE_READING_DATA;
+ break;
+
+ case JEDEC_READ:
+ if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) == MODE_STD) {
+ trace_m25p80_populated_jedec(s);
+ for (i = 0; i < s->pi->id_len; i++) {
+ s->data[i] = s->pi->id[i];
+ }
+ for (; i < SPI_NOR_MAX_ID_LEN; i++) {
+ s->data[i] = 0;
+ }
+
+ s->len = SPI_NOR_MAX_ID_LEN;
+ s->pos = 0;
+ s->state = STATE_READING_DATA;
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute JEDEC read "
+ "in DIO or QIO mode\n");
+ }
+ break;
+
+ case RDCR:
+ s->data[0] = s->volatile_cfg & 0xFF;
+ s->data[0] |= (!!s->four_bytes_address_mode) << 5;
+ s->pos = 0;
+ s->len = 1;
+ s->state = STATE_READING_DATA;
+ break;
+
+ case BULK_ERASE_60:
+ case BULK_ERASE:
+ if (s->write_enable) {
+ trace_m25p80_chip_erase(s);
+ flash_erase(s, 0, BULK_ERASE);
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: chip erase with write "
+ "protect!\n");
+ }
+ break;
+ case NOP:
+ break;
+ case EN_4BYTE_ADDR:
+ s->four_bytes_address_mode = true;
+ break;
+ case EX_4BYTE_ADDR:
+ s->four_bytes_address_mode = false;
+ break;
+ case BRRD:
+ case EXTEND_ADDR_READ:
+ s->data[0] = s->ear;
+ s->pos = 0;
+ s->len = 1;
+ s->state = STATE_READING_DATA;
+ break;
+ case BRWR:
+ case EXTEND_ADDR_WRITE:
+ if (s->write_enable) {
+ s->needed_bytes = 1;
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+ }
+ break;
+ case RNVCR:
+ s->data[0] = s->nonvolatile_cfg & 0xFF;
+ s->data[1] = (s->nonvolatile_cfg >> 8) & 0xFF;
+ s->pos = 0;
+ s->len = 2;
+ s->state = STATE_READING_DATA;
+ break;
+ case WNVCR:
+ if (s->write_enable && get_man(s) == MAN_NUMONYX) {
+ s->needed_bytes = 2;
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+ }
+ break;
+ case RVCR:
+ s->data[0] = s->volatile_cfg & 0xFF;
+ s->pos = 0;
+ s->len = 1;
+ s->state = STATE_READING_DATA;
+ break;
+ case WVCR:
+ if (s->write_enable) {
+ s->needed_bytes = 1;
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+ }
+ break;
+ case REVCR:
+ s->data[0] = s->enh_volatile_cfg & 0xFF;
+ s->pos = 0;
+ s->len = 1;
+ s->state = STATE_READING_DATA;
+ break;
+ case WEVCR:
+ if (s->write_enable) {
+ s->needed_bytes = 1;
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+ }
+ break;
+ case RESET_ENABLE:
+ s->reset_enable = true;
+ break;
+ case RESET_MEMORY:
+ if (s->reset_enable) {
+ reset_memory(s);
+ }
+ break;
+ case RDCR_EQIO:
+ switch (get_man(s)) {
+ case MAN_SPANSION:
+ s->data[0] = (!!s->quad_enable) << 1;
+ s->pos = 0;
+ s->len = 1;
+ s->state = STATE_READING_DATA;
+ break;
+ case MAN_MACRONIX:
+ s->quad_enable = true;
+ break;
+ default:
+ break;
+ }
+ break;
+ case RSTQIO:
+ s->quad_enable = false;
+ break;
+ case AAI_WP:
+ if (get_man(s) == MAN_SST) {
+ if (s->write_enable) {
+ if (s->aai_enable) {
+ s->state = STATE_PAGE_PROGRAM;
+ } else {
+ s->aai_enable = true;
+ s->needed_bytes = get_addr_length(s);
+ s->state = STATE_COLLECTING_DATA;
+ }
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "M25P80: AAI_WP with write protect\n");
+ }
+ } else {
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Unknown cmd %x\n", value);
+ }
+ break;
+ case RDSFDP:
+ if (s->pi->sfdp_read) {
+ s->needed_bytes = get_addr_length(s) + 1; /* SFDP addr + dummy */
+ s->pos = 0;
+ s->len = 0;
+ s->state = STATE_COLLECTING_DATA;
+ break;
+ }
+ /* Fallthrough */
+
+ default:
+ s->pos = 0;
+ s->len = 1;
+ s->state = STATE_READING_DATA;
+ s->data_read_loop = true;
+ s->data[0] = 0;
+ qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Unknown cmd %x\n", value);
+ break;
+ }
+}
+
+static int m25p80_cs(SSIPeripheral *ss, bool select)
+{
+ Flash *s = M25P80(ss);
+
+ if (select) {
+ if (s->state == STATE_COLLECTING_VAR_LEN_DATA) {
+ complete_collecting_data(s);
+ }
+ s->len = 0;
+ s->pos = 0;
+ s->state = STATE_IDLE;
+ flash_sync_dirty(s, -1);
+ s->data_read_loop = false;
+ }
+
+ trace_m25p80_select(s, select ? "de" : "");
+
+ return 0;
+}
+
+static uint32_t m25p80_transfer8(SSIPeripheral *ss, uint32_t tx)
+{
+ Flash *s = M25P80(ss);
+ uint32_t r = 0;
+
+ trace_m25p80_transfer(s, s->state, s->len, s->needed_bytes, s->pos,
+ s->cur_addr, (uint8_t)tx);
+
+ switch (s->state) {
+
+ case STATE_PAGE_PROGRAM:
+ trace_m25p80_page_program(s, s->cur_addr, (uint8_t)tx);
+ flash_write8(s, s->cur_addr, (uint8_t)tx);
+ s->cur_addr = (s->cur_addr + 1) & (s->size - 1);
+
+ if (get_man(s) == MAN_SST && s->aai_enable && s->cur_addr == 0) {
+ /*
+ * There is no wrap mode during AAI programming once the highest
+ * unprotected memory address is reached. The Write-Enable-Latch
+ * bit is automatically reset, and AAI programming mode aborts.
+ */
+ s->write_enable = false;
+ s->aai_enable = false;
+ }
+
+ break;
+
+ case STATE_READ:
+ r = s->storage[s->cur_addr];
+ trace_m25p80_read_byte(s, s->cur_addr, (uint8_t)r);
+ s->cur_addr = (s->cur_addr + 1) & (s->size - 1);
+ break;
+
+ case STATE_COLLECTING_DATA:
+ case STATE_COLLECTING_VAR_LEN_DATA:
+
+ if (s->len >= M25P80_INTERNAL_DATA_BUFFER_SZ) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "M25P80: Write overrun internal data buffer. "
+ "SPI controller (QEMU emulator or guest driver) "
+ "is misbehaving\n");
+ s->len = s->pos = 0;
+ s->state = STATE_IDLE;
+ break;
+ }
+
+ s->data[s->len] = (uint8_t)tx;
+ s->len++;
+
+ if (s->len == s->needed_bytes) {
+ complete_collecting_data(s);
+ }
+ break;
+
+ case STATE_READING_DATA:
+
+ if (s->pos >= M25P80_INTERNAL_DATA_BUFFER_SZ) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "M25P80: Read overrun internal data buffer. "
+ "SPI controller (QEMU emulator or guest driver) "
+ "is misbehaving\n");
+ s->len = s->pos = 0;
+ s->state = STATE_IDLE;
+ break;
+ }
+
+ r = s->data[s->pos];
+ trace_m25p80_read_data(s, s->pos, (uint8_t)r);
+ s->pos++;
+ if (s->pos == s->len) {
+ s->pos = 0;
+ if (!s->data_read_loop) {
+ s->state = STATE_IDLE;
+ }
+ }
+ break;
+ case STATE_READING_SFDP:
+ assert(s->pi->sfdp_read);
+ r = s->pi->sfdp_read(s->cur_addr);
+ trace_m25p80_read_sfdp(s, s->cur_addr, (uint8_t)r);
+ s->cur_addr = (s->cur_addr + 1) & (M25P80_SFDP_MAX_SIZE - 1);
+ break;
+
+ default:
+ case STATE_IDLE:
+ decode_new_cmd(s, (uint8_t)tx);
+ break;
+ }
+
+ return r;
+}
+
+static void m25p80_write_protect_pin_irq_handler(void *opaque, int n, int level)
+{
+ Flash *s = M25P80(opaque);
+ /* WP# is just a single pin. */
+ assert(n == 0);
+ s->wp_level = !!level;
+}
+
+static void m25p80_realize(SSIPeripheral *ss, Error **errp)
+{
+ Flash *s = M25P80(ss);
+ M25P80Class *mc = M25P80_GET_CLASS(s);
+ int ret;
+
+ s->pi = mc->pi;
+
+ s->size = s->pi->sector_size * s->pi->n_sectors;
+ s->dirty_page = -1;
+
+ if (s->blk) {
+ uint64_t perm = BLK_PERM_CONSISTENT_READ |
+ (blk_supports_write_perm(s->blk) ? BLK_PERM_WRITE : 0);
+ ret = blk_set_perm(s->blk, perm, BLK_PERM_ALL, errp);
+ if (ret < 0) {
+ return;
+ }
+
+ trace_m25p80_binding(s);
+ s->storage = blk_blockalign(s->blk, s->size);
+
+ if (blk_pread(s->blk, 0, s->size, s->storage, 0) < 0) {
+ error_setg(errp, "failed to read the initial flash content");
+ return;
+ }
+ } else {
+ trace_m25p80_binding_no_bdrv(s);
+ s->storage = blk_blockalign(NULL, s->size);
+ memset(s->storage, 0xFF, s->size);
+ }
+
+ qdev_init_gpio_in_named(DEVICE(s),
+ m25p80_write_protect_pin_irq_handler, "WP#", 1);
+}
+
+static void m25p80_reset(DeviceState *d)
+{
+ Flash *s = M25P80(d);
+
+ s->wp_level = true;
+ s->status_register_write_disabled = false;
+ s->block_protect0 = false;
+ s->block_protect1 = false;
+ s->block_protect2 = false;
+ s->block_protect3 = false;
+ s->top_bottom_bit = false;
+
+ reset_memory(s);
+}
+
+static int m25p80_pre_save(void *opaque)
+{
+ flash_sync_dirty((Flash *)opaque, -1);
+
+ return 0;
+}
+
+static Property m25p80_properties[] = {
+ /* This is default value for Micron flash */
+ DEFINE_PROP_BOOL("write-enable", Flash, write_enable, false),
+ DEFINE_PROP_UINT32("nonvolatile-cfg", Flash, nonvolatile_cfg, 0x8FFF),
+ DEFINE_PROP_UINT8("spansion-cr1nv", Flash, spansion_cr1nv, 0x0),
+ DEFINE_PROP_UINT8("spansion-cr2nv", Flash, spansion_cr2nv, 0x8),
+ DEFINE_PROP_UINT8("spansion-cr3nv", Flash, spansion_cr3nv, 0x2),
+ DEFINE_PROP_UINT8("spansion-cr4nv", Flash, spansion_cr4nv, 0x10),
+ DEFINE_PROP_DRIVE("drive", Flash, blk),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static int m25p80_pre_load(void *opaque)
+{
+ Flash *s = (Flash *)opaque;
+
+ s->data_read_loop = false;
+ return 0;
+}
+
+static bool m25p80_data_read_loop_needed(void *opaque)
+{
+ Flash *s = (Flash *)opaque;
+
+ return s->data_read_loop;
+}
+
+static const VMStateDescription vmstate_m25p80_data_read_loop = {
+ .name = "m25p80/data_read_loop",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = m25p80_data_read_loop_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_BOOL(data_read_loop, Flash),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static bool m25p80_aai_enable_needed(void *opaque)
+{
+ Flash *s = (Flash *)opaque;
+
+ return s->aai_enable;
+}
+
+static const VMStateDescription vmstate_m25p80_aai_enable = {
+ .name = "m25p80/aai_enable",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = m25p80_aai_enable_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_BOOL(aai_enable, Flash),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static bool m25p80_wp_level_srwd_needed(void *opaque)
+{
+ Flash *s = (Flash *)opaque;
+
+ return !s->wp_level || s->status_register_write_disabled;
+}
+
+static const VMStateDescription vmstate_m25p80_write_protect = {
+ .name = "m25p80/write_protect",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = m25p80_wp_level_srwd_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_BOOL(wp_level, Flash),
+ VMSTATE_BOOL(status_register_write_disabled, Flash),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static bool m25p80_block_protect_needed(void *opaque)
+{
+ Flash *s = (Flash *)opaque;
+
+ return s->block_protect0 ||
+ s->block_protect1 ||
+ s->block_protect2 ||
+ s->block_protect3 ||
+ s->top_bottom_bit;
+}
+
+static const VMStateDescription vmstate_m25p80_block_protect = {
+ .name = "m25p80/block_protect",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = m25p80_block_protect_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_BOOL(block_protect0, Flash),
+ VMSTATE_BOOL(block_protect1, Flash),
+ VMSTATE_BOOL(block_protect2, Flash),
+ VMSTATE_BOOL(block_protect3, Flash),
+ VMSTATE_BOOL(top_bottom_bit, Flash),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static const VMStateDescription vmstate_m25p80 = {
+ .name = "m25p80",
+ .version_id = 0,
+ .minimum_version_id = 0,
+ .pre_save = m25p80_pre_save,
+ .pre_load = m25p80_pre_load,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(state, Flash),
+ VMSTATE_UINT8_ARRAY(data, Flash, M25P80_INTERNAL_DATA_BUFFER_SZ),
+ VMSTATE_UINT32(len, Flash),
+ VMSTATE_UINT32(pos, Flash),
+ VMSTATE_UINT8(needed_bytes, Flash),
+ VMSTATE_UINT8(cmd_in_progress, Flash),
+ VMSTATE_UINT32(cur_addr, Flash),
+ VMSTATE_BOOL(write_enable, Flash),
+ VMSTATE_BOOL(reset_enable, Flash),
+ VMSTATE_UINT8(ear, Flash),
+ VMSTATE_BOOL(four_bytes_address_mode, Flash),
+ VMSTATE_UINT32(nonvolatile_cfg, Flash),
+ VMSTATE_UINT32(volatile_cfg, Flash),
+ VMSTATE_UINT32(enh_volatile_cfg, Flash),
+ VMSTATE_BOOL(quad_enable, Flash),
+ VMSTATE_UINT8(spansion_cr1nv, Flash),
+ VMSTATE_UINT8(spansion_cr2nv, Flash),
+ VMSTATE_UINT8(spansion_cr3nv, Flash),
+ VMSTATE_UINT8(spansion_cr4nv, Flash),
+ VMSTATE_END_OF_LIST()
+ },
+ .subsections = (const VMStateDescription * []) {
+ &vmstate_m25p80_data_read_loop,
+ &vmstate_m25p80_aai_enable,
+ &vmstate_m25p80_write_protect,
+ &vmstate_m25p80_block_protect,
+ NULL
+ }
+};
+
+static void m25p80_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+ SSIPeripheralClass *k = SSI_PERIPHERAL_CLASS(klass);
+ M25P80Class *mc = M25P80_CLASS(klass);
+
+ k->realize = m25p80_realize;
+ k->transfer = m25p80_transfer8;
+ k->set_cs = m25p80_cs;
+ k->cs_polarity = SSI_CS_LOW;
+ dc->vmsd = &vmstate_m25p80;
+ device_class_set_props(dc, m25p80_properties);
+ dc->reset = m25p80_reset;
+ mc->pi = data;
+}
+
+static const TypeInfo m25p80_info = {
+ .name = TYPE_M25P80,
+ .parent = TYPE_SSI_PERIPHERAL,
+ .instance_size = sizeof(Flash),
+ .class_size = sizeof(M25P80Class),
+ .abstract = true,
+};
+
+static void m25p80_register_types(void)
+{
+ int i;
+
+ type_register_static(&m25p80_info);
+ for (i = 0; i < ARRAY_SIZE(known_devices); ++i) {
+ TypeInfo ti = {
+ .name = known_devices[i].part_name,
+ .parent = TYPE_M25P80,
+ .class_init = m25p80_class_init,
+ .class_data = (void *)&known_devices[i],
+ };
+ type_register(&ti);
+ }
+}
+
+type_init(m25p80_register_types)
diff --git a/hw/block/m25p80_sfdp.c b/hw/block/m25p80_sfdp.c
new file mode 100644
index 00000000..77615fa2
--- /dev/null
+++ b/hw/block/m25p80_sfdp.c
@@ -0,0 +1,332 @@
+/*
+ * M25P80 Serial Flash Discoverable Parameter (SFDP)
+ *
+ * Copyright (c) 2020, IBM Corporation.
+ *
+ * This code is licensed under the GPL version 2 or later. See the
+ * COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/host-utils.h"
+#include "m25p80_sfdp.h"
+
+#define define_sfdp_read(model) \
+ uint8_t m25p80_sfdp_##model(uint32_t addr) \
+ { \
+ assert(is_power_of_2(sizeof(sfdp_##model))); \
+ return sfdp_##model[addr & (sizeof(sfdp_##model) - 1)]; \
+ }
+
+/*
+ * Micron
+ */
+static const uint8_t sfdp_n25q256a[] = {
+ 0x53, 0x46, 0x44, 0x50, 0x00, 0x01, 0x00, 0xff,
+ 0x00, 0x00, 0x01, 0x09, 0x30, 0x00, 0x00, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xe5, 0x20, 0xfb, 0xff, 0xff, 0xff, 0xff, 0x0f,
+ 0x29, 0xeb, 0x27, 0x6b, 0x08, 0x3b, 0x27, 0xbb,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x27, 0xbb,
+ 0xff, 0xff, 0x29, 0xeb, 0x0c, 0x20, 0x10, 0xd8,
+ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+};
+define_sfdp_read(n25q256a);
+
+
+/*
+ * Matronix
+ */
+
+/* mx25l25635e. No 4B opcodes */
+static const uint8_t sfdp_mx25l25635e[] = {
+ 0x53, 0x46, 0x44, 0x50, 0x00, 0x01, 0x01, 0xff,
+ 0x00, 0x00, 0x01, 0x09, 0x30, 0x00, 0x00, 0xff,
+ 0xc2, 0x00, 0x01, 0x04, 0x60, 0x00, 0x00, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xe5, 0x20, 0xf3, 0xff, 0xff, 0xff, 0xff, 0x0f,
+ 0x44, 0xeb, 0x08, 0x6b, 0x08, 0x3b, 0x04, 0xbb,
+ 0xee, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0xff,
+ 0xff, 0xff, 0x00, 0xff, 0x0c, 0x20, 0x0f, 0x52,
+ 0x10, 0xd8, 0x00, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0x00, 0x36, 0x00, 0x27, 0xf7, 0x4f, 0xff, 0xff,
+ 0xd9, 0xc8, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+};
+define_sfdp_read(mx25l25635e)
+
+static const uint8_t sfdp_mx25l25635f[] = {
+ 0x53, 0x46, 0x44, 0x50, 0x00, 0x01, 0x01, 0xff,
+ 0x00, 0x00, 0x01, 0x09, 0x30, 0x00, 0x00, 0xff,
+ 0xc2, 0x00, 0x01, 0x04, 0x60, 0x00, 0x00, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xe5, 0x20, 0xf3, 0xff, 0xff, 0xff, 0xff, 0x0f,
+ 0x44, 0xeb, 0x08, 0x6b, 0x08, 0x3b, 0x04, 0xbb,
+ 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0xff,
+ 0xff, 0xff, 0x44, 0xeb, 0x0c, 0x20, 0x0f, 0x52,
+ 0x10, 0xd8, 0x00, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0x00, 0x36, 0x00, 0x27, 0x9d, 0xf9, 0xc0, 0x64,
+ 0x85, 0xcb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xc2, 0xf5, 0x08, 0x0a,
+ 0x08, 0x04, 0x03, 0x06, 0x00, 0x00, 0x07, 0x29,
+ 0x17, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+};
+define_sfdp_read(mx25l25635f);
+
+static const uint8_t sfdp_mx66l1g45g[] = {
+ 0x53, 0x46, 0x44, 0x50, 0x06, 0x01, 0x02, 0xff,
+ 0x00, 0x06, 0x01, 0x10, 0x30, 0x00, 0x00, 0xff,
+ 0xc2, 0x00, 0x01, 0x04, 0x10, 0x01, 0x00, 0xff,
+ 0x84, 0x00, 0x01, 0x02, 0xc0, 0x00, 0x00, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xe5, 0x20, 0xfb, 0xff, 0xff, 0xff, 0xff, 0x3f,
+ 0x44, 0xeb, 0x08, 0x6b, 0x08, 0x3b, 0x04, 0xbb,
+ 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0xff,
+ 0xff, 0xff, 0x44, 0xeb, 0x0c, 0x20, 0x0f, 0x52,
+ 0x10, 0xd8, 0x00, 0xff, 0xd6, 0x49, 0xc5, 0x00,
+ 0x85, 0xdf, 0x04, 0xe3, 0x44, 0x03, 0x67, 0x38,
+ 0x30, 0xb0, 0x30, 0xb0, 0xf7, 0xbd, 0xd5, 0x5c,
+ 0x4a, 0x9e, 0x29, 0xff, 0xf0, 0x50, 0xf9, 0x85,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0x7f, 0xef, 0xff, 0xff, 0x21, 0x5c, 0xdc, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0x00, 0x36, 0x00, 0x27, 0x9d, 0xf9, 0xc0, 0x64,
+ 0x85, 0xcb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xc2, 0xf5, 0x08, 0x00, 0x0c, 0x04, 0x08, 0x08,
+ 0x01, 0x00, 0x19, 0x0f, 0x01, 0x01, 0x06, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+};
+define_sfdp_read(mx66l1g45g);
+
+/*
+ * Windbond
+ */
+
+static const uint8_t sfdp_w25q256[] = {
+ 0x53, 0x46, 0x44, 0x50, 0x00, 0x01, 0x00, 0xff,
+ 0x00, 0x00, 0x01, 0x09, 0x80, 0x00, 0x00, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xe5, 0x20, 0xf3, 0xff, 0xff, 0xff, 0xff, 0x0f,
+ 0x44, 0xeb, 0x08, 0x6b, 0x08, 0x3b, 0x42, 0xbb,
+ 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00,
+ 0xff, 0xff, 0x21, 0xeb, 0x0c, 0x20, 0x0f, 0x52,
+ 0x10, 0xd8, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+};
+define_sfdp_read(w25q256);
+
+static const uint8_t sfdp_w25q512jv[] = {
+ 0x53, 0x46, 0x44, 0x50, 0x06, 0x01, 0x01, 0xff,
+ 0x00, 0x06, 0x01, 0x10, 0x80, 0x00, 0x00, 0xff,
+ 0x84, 0x00, 0x01, 0x02, 0xd0, 0x00, 0x00, 0xff,
+ 0x03, 0x00, 0x01, 0x02, 0xf0, 0x00, 0x00, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xe5, 0x20, 0xfb, 0xff, 0xff, 0xff, 0xff, 0x1f,
+ 0x44, 0xeb, 0x08, 0x6b, 0x08, 0x3b, 0x42, 0xbb,
+ 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00,
+ 0xff, 0xff, 0x40, 0xeb, 0x0c, 0x20, 0x0f, 0x52,
+ 0x10, 0xd8, 0x00, 0x00, 0x36, 0x02, 0xa6, 0x00,
+ 0x82, 0xea, 0x14, 0xe2, 0xe9, 0x63, 0x76, 0x33,
+ 0x7a, 0x75, 0x7a, 0x75, 0xf7, 0xa2, 0xd5, 0x5c,
+ 0x19, 0xf7, 0x4d, 0xff, 0xe9, 0x70, 0xf9, 0xa5,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0x0a, 0xf0, 0xff, 0x21, 0xff, 0xdc, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+};
+define_sfdp_read(w25q512jv);
+
+static const uint8_t sfdp_w25q01jvq[] = {
+ 0x53, 0x46, 0x44, 0x50, 0x06, 0x01, 0x01, 0xff,
+ 0x00, 0x06, 0x01, 0x10, 0x80, 0x00, 0x00, 0xff,
+ 0x84, 0x00, 0x01, 0x02, 0xd0, 0x00, 0x00, 0xff,
+ 0x03, 0x00, 0x01, 0x02, 0xf0, 0x00, 0x00, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xe5, 0x20, 0xfb, 0xff, 0xff, 0xff, 0xff, 0x3f,
+ 0x44, 0xeb, 0x08, 0x6b, 0x08, 0x3b, 0x42, 0xbb,
+ 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00,
+ 0xff, 0xff, 0x40, 0xeb, 0x0c, 0x20, 0x0f, 0x52,
+ 0x10, 0xd8, 0x00, 0x00, 0x36, 0x02, 0xa6, 0x00,
+ 0x82, 0xea, 0x14, 0xe2, 0xe9, 0x63, 0x76, 0x33,
+ 0x7a, 0x75, 0x7a, 0x75, 0xf7, 0xa2, 0xd5, 0x5c,
+ 0x19, 0xf7, 0x4d, 0xff, 0xe9, 0x70, 0xf9, 0xa5,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0x0a, 0xf0, 0xff, 0x21, 0xff, 0xdc, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+};
+define_sfdp_read(w25q01jvq);
diff --git a/hw/block/m25p80_sfdp.h b/hw/block/m25p80_sfdp.h
new file mode 100644
index 00000000..df7adfb5
--- /dev/null
+++ b/hw/block/m25p80_sfdp.h
@@ -0,0 +1,29 @@
+/*
+ * M25P80 SFDP
+ *
+ * Copyright (c) 2020, IBM Corporation.
+ *
+ * This code is licensed under the GPL version 2 or later. See the
+ * COPYING file in the top-level directory.
+ */
+
+#ifndef HW_M25P80_SFDP_H
+#define HW_M25P80_SFDP_H
+
+/*
+ * SFDP area has a 3 bytes address space.
+ */
+#define M25P80_SFDP_MAX_SIZE (1 << 24)
+
+uint8_t m25p80_sfdp_n25q256a(uint32_t addr);
+
+uint8_t m25p80_sfdp_mx25l25635e(uint32_t addr);
+uint8_t m25p80_sfdp_mx25l25635f(uint32_t addr);
+uint8_t m25p80_sfdp_mx66l1g45g(uint32_t addr);
+
+uint8_t m25p80_sfdp_w25q256(uint32_t addr);
+uint8_t m25p80_sfdp_w25q512jv(uint32_t addr);
+
+uint8_t m25p80_sfdp_w25q01jvq(uint32_t addr);
+
+#endif
diff --git a/hw/block/meson.build b/hw/block/meson.build
new file mode 100644
index 00000000..b434d565
--- /dev/null
+++ b/hw/block/meson.build
@@ -0,0 +1,23 @@
+softmmu_ss.add(files(
+ 'block.c',
+ 'cdrom.c',
+ 'hd-geometry.c'
+))
+softmmu_ss.add(when: 'CONFIG_ECC', if_true: files('ecc.c'))
+softmmu_ss.add(when: 'CONFIG_FDC', if_true: files('fdc.c'))
+softmmu_ss.add(when: 'CONFIG_FDC_ISA', if_true: files('fdc-isa.c'))
+softmmu_ss.add(when: 'CONFIG_FDC_SYSBUS', if_true: files('fdc-sysbus.c'))
+softmmu_ss.add(when: 'CONFIG_NAND', if_true: files('nand.c'))
+softmmu_ss.add(when: 'CONFIG_ONENAND', if_true: files('onenand.c'))
+softmmu_ss.add(when: 'CONFIG_PFLASH_CFI01', if_true: files('pflash_cfi01.c'))
+softmmu_ss.add(when: 'CONFIG_PFLASH_CFI02', if_true: files('pflash_cfi02.c'))
+softmmu_ss.add(when: 'CONFIG_SSI_M25P80', if_true: files('m25p80.c'))
+softmmu_ss.add(when: 'CONFIG_SSI_M25P80', if_true: files('m25p80_sfdp.c'))
+softmmu_ss.add(when: 'CONFIG_SWIM', if_true: files('swim.c'))
+softmmu_ss.add(when: 'CONFIG_XEN', if_true: files('xen-block.c'))
+softmmu_ss.add(when: 'CONFIG_TC58128', if_true: files('tc58128.c'))
+
+specific_ss.add(when: 'CONFIG_VIRTIO_BLK', if_true: files('virtio-blk.c', 'virtio-blk-common.c'))
+specific_ss.add(when: 'CONFIG_VHOST_USER_BLK', if_true: files('vhost-user-blk.c', 'virtio-blk-common.c'))
+
+subdir('dataplane')
diff --git a/hw/block/nand.c b/hw/block/nand.c
new file mode 100644
index 00000000..1aee1cb2
--- /dev/null
+++ b/hw/block/nand.c
@@ -0,0 +1,815 @@
+/*
+ * Flash NAND memory emulation. Based on "16M x 8 Bit NAND Flash
+ * Memory" datasheet for the KM29U128AT / K9F2808U0A chips from
+ * Samsung Electronic.
+ *
+ * Copyright (c) 2006 Openedhand Ltd.
+ * Written by Andrzej Zaborowski <balrog@zabor.org>
+ *
+ * Support for additional features based on "MT29F2G16ABCWP 2Gx16"
+ * datasheet from Micron Technology and "NAND02G-B2C" datasheet
+ * from ST Microelectronics.
+ *
+ * This code is licensed under the GNU GPL v2.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#ifndef NAND_IO
+
+#include "qemu/osdep.h"
+#include "hw/hw.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "hw/block/flash.h"
+#include "sysemu/block-backend.h"
+#include "migration/vmstate.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/module.h"
+#include "qom/object.h"
+
+# define NAND_CMD_READ0 0x00
+# define NAND_CMD_READ1 0x01
+# define NAND_CMD_READ2 0x50
+# define NAND_CMD_LPREAD2 0x30
+# define NAND_CMD_NOSERIALREAD2 0x35
+# define NAND_CMD_RANDOMREAD1 0x05
+# define NAND_CMD_RANDOMREAD2 0xe0
+# define NAND_CMD_READID 0x90
+# define NAND_CMD_RESET 0xff
+# define NAND_CMD_PAGEPROGRAM1 0x80
+# define NAND_CMD_PAGEPROGRAM2 0x10
+# define NAND_CMD_CACHEPROGRAM2 0x15
+# define NAND_CMD_BLOCKERASE1 0x60
+# define NAND_CMD_BLOCKERASE2 0xd0
+# define NAND_CMD_READSTATUS 0x70
+# define NAND_CMD_COPYBACKPRG1 0x85
+
+# define NAND_IOSTATUS_ERROR (1 << 0)
+# define NAND_IOSTATUS_PLANE0 (1 << 1)
+# define NAND_IOSTATUS_PLANE1 (1 << 2)
+# define NAND_IOSTATUS_PLANE2 (1 << 3)
+# define NAND_IOSTATUS_PLANE3 (1 << 4)
+# define NAND_IOSTATUS_READY (1 << 6)
+# define NAND_IOSTATUS_UNPROTCT (1 << 7)
+
+# define MAX_PAGE 0x800
+# define MAX_OOB 0x40
+
+typedef struct NANDFlashState NANDFlashState;
+struct NANDFlashState {
+ DeviceState parent_obj;
+
+ uint8_t manf_id, chip_id;
+ uint8_t buswidth; /* in BYTES */
+ int size, pages;
+ int page_shift, oob_shift, erase_shift, addr_shift;
+ uint8_t *storage;
+ BlockBackend *blk;
+ int mem_oob;
+
+ uint8_t cle, ale, ce, wp, gnd;
+
+ uint8_t io[MAX_PAGE + MAX_OOB + 0x400];
+ uint8_t *ioaddr;
+ int iolen;
+
+ uint32_t cmd;
+ uint64_t addr;
+ int addrlen;
+ int status;
+ int offset;
+
+ void (*blk_write)(NANDFlashState *s);
+ void (*blk_erase)(NANDFlashState *s);
+ void (*blk_load)(NANDFlashState *s, uint64_t addr, int offset);
+
+ uint32_t ioaddr_vmstate;
+};
+
+#define TYPE_NAND "nand"
+
+OBJECT_DECLARE_SIMPLE_TYPE(NANDFlashState, NAND)
+
+static void mem_and(uint8_t *dest, const uint8_t *src, size_t n)
+{
+ /* Like memcpy() but we logical-AND the data into the destination */
+ int i;
+ for (i = 0; i < n; i++) {
+ dest[i] &= src[i];
+ }
+}
+
+# define NAND_NO_AUTOINCR 0x00000001
+# define NAND_BUSWIDTH_16 0x00000002
+# define NAND_NO_PADDING 0x00000004
+# define NAND_CACHEPRG 0x00000008
+# define NAND_COPYBACK 0x00000010
+# define NAND_IS_AND 0x00000020
+# define NAND_4PAGE_ARRAY 0x00000040
+# define NAND_NO_READRDY 0x00000100
+# define NAND_SAMSUNG_LP (NAND_NO_PADDING | NAND_COPYBACK)
+
+# define NAND_IO
+
+# define PAGE(addr) ((addr) >> ADDR_SHIFT)
+# define PAGE_START(page) (PAGE(page) * (NAND_PAGE_SIZE + OOB_SIZE))
+# define PAGE_MASK ((1 << ADDR_SHIFT) - 1)
+# define OOB_SHIFT (PAGE_SHIFT - 5)
+# define OOB_SIZE (1 << OOB_SHIFT)
+# define SECTOR(addr) ((addr) >> (9 + ADDR_SHIFT - PAGE_SHIFT))
+# define SECTOR_OFFSET(addr) ((addr) & ((511 >> PAGE_SHIFT) << 8))
+
+# define NAND_PAGE_SIZE 256
+# define PAGE_SHIFT 8
+# define PAGE_SECTORS 1
+# define ADDR_SHIFT 8
+# include "nand.c"
+# define NAND_PAGE_SIZE 512
+# define PAGE_SHIFT 9
+# define PAGE_SECTORS 1
+# define ADDR_SHIFT 8
+# include "nand.c"
+# define NAND_PAGE_SIZE 2048
+# define PAGE_SHIFT 11
+# define PAGE_SECTORS 4
+# define ADDR_SHIFT 16
+# include "nand.c"
+
+/* Information based on Linux drivers/mtd/nand/raw/nand_ids.c */
+static const struct {
+ int size;
+ int width;
+ int page_shift;
+ int erase_shift;
+ uint32_t options;
+} nand_flash_ids[0x100] = {
+ [0 ... 0xff] = { 0 },
+
+ [0x6b] = { 4, 8, 9, 4, 0 },
+ [0xe3] = { 4, 8, 9, 4, 0 },
+ [0xe5] = { 4, 8, 9, 4, 0 },
+ [0xd6] = { 8, 8, 9, 4, 0 },
+ [0xe6] = { 8, 8, 9, 4, 0 },
+
+ [0x33] = { 16, 8, 9, 5, 0 },
+ [0x73] = { 16, 8, 9, 5, 0 },
+ [0x43] = { 16, 16, 9, 5, NAND_BUSWIDTH_16 },
+ [0x53] = { 16, 16, 9, 5, NAND_BUSWIDTH_16 },
+
+ [0x35] = { 32, 8, 9, 5, 0 },
+ [0x75] = { 32, 8, 9, 5, 0 },
+ [0x45] = { 32, 16, 9, 5, NAND_BUSWIDTH_16 },
+ [0x55] = { 32, 16, 9, 5, NAND_BUSWIDTH_16 },
+
+ [0x36] = { 64, 8, 9, 5, 0 },
+ [0x76] = { 64, 8, 9, 5, 0 },
+ [0x46] = { 64, 16, 9, 5, NAND_BUSWIDTH_16 },
+ [0x56] = { 64, 16, 9, 5, NAND_BUSWIDTH_16 },
+
+ [0x78] = { 128, 8, 9, 5, 0 },
+ [0x39] = { 128, 8, 9, 5, 0 },
+ [0x79] = { 128, 8, 9, 5, 0 },
+ [0x72] = { 128, 16, 9, 5, NAND_BUSWIDTH_16 },
+ [0x49] = { 128, 16, 9, 5, NAND_BUSWIDTH_16 },
+ [0x74] = { 128, 16, 9, 5, NAND_BUSWIDTH_16 },
+ [0x59] = { 128, 16, 9, 5, NAND_BUSWIDTH_16 },
+
+ [0x71] = { 256, 8, 9, 5, 0 },
+
+ /*
+ * These are the new chips with large page size. The pagesize and the
+ * erasesize is determined from the extended id bytes
+ */
+# define LP_OPTIONS (NAND_SAMSUNG_LP | NAND_NO_READRDY | NAND_NO_AUTOINCR)
+# define LP_OPTIONS16 (LP_OPTIONS | NAND_BUSWIDTH_16)
+
+ /* 512 Megabit */
+ [0xa2] = { 64, 8, 0, 0, LP_OPTIONS },
+ [0xf2] = { 64, 8, 0, 0, LP_OPTIONS },
+ [0xb2] = { 64, 16, 0, 0, LP_OPTIONS16 },
+ [0xc2] = { 64, 16, 0, 0, LP_OPTIONS16 },
+
+ /* 1 Gigabit */
+ [0xa1] = { 128, 8, 0, 0, LP_OPTIONS },
+ [0xf1] = { 128, 8, 0, 0, LP_OPTIONS },
+ [0xb1] = { 128, 16, 0, 0, LP_OPTIONS16 },
+ [0xc1] = { 128, 16, 0, 0, LP_OPTIONS16 },
+
+ /* 2 Gigabit */
+ [0xaa] = { 256, 8, 0, 0, LP_OPTIONS },
+ [0xda] = { 256, 8, 0, 0, LP_OPTIONS },
+ [0xba] = { 256, 16, 0, 0, LP_OPTIONS16 },
+ [0xca] = { 256, 16, 0, 0, LP_OPTIONS16 },
+
+ /* 4 Gigabit */
+ [0xac] = { 512, 8, 0, 0, LP_OPTIONS },
+ [0xdc] = { 512, 8, 0, 0, LP_OPTIONS },
+ [0xbc] = { 512, 16, 0, 0, LP_OPTIONS16 },
+ [0xcc] = { 512, 16, 0, 0, LP_OPTIONS16 },
+
+ /* 8 Gigabit */
+ [0xa3] = { 1024, 8, 0, 0, LP_OPTIONS },
+ [0xd3] = { 1024, 8, 0, 0, LP_OPTIONS },
+ [0xb3] = { 1024, 16, 0, 0, LP_OPTIONS16 },
+ [0xc3] = { 1024, 16, 0, 0, LP_OPTIONS16 },
+
+ /* 16 Gigabit */
+ [0xa5] = { 2048, 8, 0, 0, LP_OPTIONS },
+ [0xd5] = { 2048, 8, 0, 0, LP_OPTIONS },
+ [0xb5] = { 2048, 16, 0, 0, LP_OPTIONS16 },
+ [0xc5] = { 2048, 16, 0, 0, LP_OPTIONS16 },
+};
+
+static void nand_reset(DeviceState *dev)
+{
+ NANDFlashState *s = NAND(dev);
+ s->cmd = NAND_CMD_READ0;
+ s->addr = 0;
+ s->addrlen = 0;
+ s->iolen = 0;
+ s->offset = 0;
+ s->status &= NAND_IOSTATUS_UNPROTCT;
+ s->status |= NAND_IOSTATUS_READY;
+}
+
+static inline void nand_pushio_byte(NANDFlashState *s, uint8_t value)
+{
+ s->ioaddr[s->iolen++] = value;
+ for (value = s->buswidth; --value;) {
+ s->ioaddr[s->iolen++] = 0;
+ }
+}
+
+static void nand_command(NANDFlashState *s)
+{
+ unsigned int offset;
+ switch (s->cmd) {
+ case NAND_CMD_READ0:
+ s->iolen = 0;
+ break;
+
+ case NAND_CMD_READID:
+ s->ioaddr = s->io;
+ s->iolen = 0;
+ nand_pushio_byte(s, s->manf_id);
+ nand_pushio_byte(s, s->chip_id);
+ nand_pushio_byte(s, 'Q'); /* Don't-care byte (often 0xa5) */
+ if (nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP) {
+ /* Page Size, Block Size, Spare Size; bit 6 indicates
+ * 8 vs 16 bit width NAND.
+ */
+ nand_pushio_byte(s, (s->buswidth == 2) ? 0x55 : 0x15);
+ } else {
+ nand_pushio_byte(s, 0xc0); /* Multi-plane */
+ }
+ break;
+
+ case NAND_CMD_RANDOMREAD2:
+ case NAND_CMD_NOSERIALREAD2:
+ if (!(nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP))
+ break;
+ offset = s->addr & ((1 << s->addr_shift) - 1);
+ s->blk_load(s, s->addr, offset);
+ if (s->gnd)
+ s->iolen = (1 << s->page_shift) - offset;
+ else
+ s->iolen = (1 << s->page_shift) + (1 << s->oob_shift) - offset;
+ break;
+
+ case NAND_CMD_RESET:
+ nand_reset(DEVICE(s));
+ break;
+
+ case NAND_CMD_PAGEPROGRAM1:
+ s->ioaddr = s->io;
+ s->iolen = 0;
+ break;
+
+ case NAND_CMD_PAGEPROGRAM2:
+ if (s->wp) {
+ s->blk_write(s);
+ }
+ break;
+
+ case NAND_CMD_BLOCKERASE1:
+ break;
+
+ case NAND_CMD_BLOCKERASE2:
+ s->addr &= (1ull << s->addrlen * 8) - 1;
+ s->addr <<= nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP ?
+ 16 : 8;
+
+ if (s->wp) {
+ s->blk_erase(s);
+ }
+ break;
+
+ case NAND_CMD_READSTATUS:
+ s->ioaddr = s->io;
+ s->iolen = 0;
+ nand_pushio_byte(s, s->status);
+ break;
+
+ default:
+ printf("%s: Unknown NAND command 0x%02x\n", __func__, s->cmd);
+ }
+}
+
+static int nand_pre_save(void *opaque)
+{
+ NANDFlashState *s = NAND(opaque);
+
+ s->ioaddr_vmstate = s->ioaddr - s->io;
+
+ return 0;
+}
+
+static int nand_post_load(void *opaque, int version_id)
+{
+ NANDFlashState *s = NAND(opaque);
+
+ if (s->ioaddr_vmstate > sizeof(s->io)) {
+ return -EINVAL;
+ }
+ s->ioaddr = s->io + s->ioaddr_vmstate;
+
+ return 0;
+}
+
+static const VMStateDescription vmstate_nand = {
+ .name = "nand",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .pre_save = nand_pre_save,
+ .post_load = nand_post_load,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(cle, NANDFlashState),
+ VMSTATE_UINT8(ale, NANDFlashState),
+ VMSTATE_UINT8(ce, NANDFlashState),
+ VMSTATE_UINT8(wp, NANDFlashState),
+ VMSTATE_UINT8(gnd, NANDFlashState),
+ VMSTATE_BUFFER(io, NANDFlashState),
+ VMSTATE_UINT32(ioaddr_vmstate, NANDFlashState),
+ VMSTATE_INT32(iolen, NANDFlashState),
+ VMSTATE_UINT32(cmd, NANDFlashState),
+ VMSTATE_UINT64(addr, NANDFlashState),
+ VMSTATE_INT32(addrlen, NANDFlashState),
+ VMSTATE_INT32(status, NANDFlashState),
+ VMSTATE_INT32(offset, NANDFlashState),
+ /* XXX: do we want to save s->storage too? */
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static void nand_realize(DeviceState *dev, Error **errp)
+{
+ int pagesize;
+ NANDFlashState *s = NAND(dev);
+ int ret;
+
+
+ s->buswidth = nand_flash_ids[s->chip_id].width >> 3;
+ s->size = nand_flash_ids[s->chip_id].size << 20;
+ if (nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP) {
+ s->page_shift = 11;
+ s->erase_shift = 6;
+ } else {
+ s->page_shift = nand_flash_ids[s->chip_id].page_shift;
+ s->erase_shift = nand_flash_ids[s->chip_id].erase_shift;
+ }
+
+ switch (1 << s->page_shift) {
+ case 256:
+ nand_init_256(s);
+ break;
+ case 512:
+ nand_init_512(s);
+ break;
+ case 2048:
+ nand_init_2048(s);
+ break;
+ default:
+ error_setg(errp, "Unsupported NAND block size %#x",
+ 1 << s->page_shift);
+ return;
+ }
+
+ pagesize = 1 << s->oob_shift;
+ s->mem_oob = 1;
+ if (s->blk) {
+ if (!blk_supports_write_perm(s->blk)) {
+ error_setg(errp, "Can't use a read-only drive");
+ return;
+ }
+ ret = blk_set_perm(s->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+ BLK_PERM_ALL, errp);
+ if (ret < 0) {
+ return;
+ }
+ if (blk_getlength(s->blk) >=
+ (s->pages << s->page_shift) + (s->pages << s->oob_shift)) {
+ pagesize = 0;
+ s->mem_oob = 0;
+ }
+ } else {
+ pagesize += 1 << s->page_shift;
+ }
+ if (pagesize) {
+ s->storage = (uint8_t *) memset(g_malloc(s->pages * pagesize),
+ 0xff, s->pages * pagesize);
+ }
+ /* Give s->ioaddr a sane value in case we save state before it is used. */
+ s->ioaddr = s->io;
+}
+
+static Property nand_properties[] = {
+ DEFINE_PROP_UINT8("manufacturer_id", NANDFlashState, manf_id, 0),
+ DEFINE_PROP_UINT8("chip_id", NANDFlashState, chip_id, 0),
+ DEFINE_PROP_DRIVE("drive", NANDFlashState, blk),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void nand_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ dc->realize = nand_realize;
+ dc->reset = nand_reset;
+ dc->vmsd = &vmstate_nand;
+ device_class_set_props(dc, nand_properties);
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+}
+
+static const TypeInfo nand_info = {
+ .name = TYPE_NAND,
+ .parent = TYPE_DEVICE,
+ .instance_size = sizeof(NANDFlashState),
+ .class_init = nand_class_init,
+};
+
+static void nand_register_types(void)
+{
+ type_register_static(&nand_info);
+}
+
+/*
+ * Chip inputs are CLE, ALE, CE, WP, GND and eight I/O pins. Chip
+ * outputs are R/B and eight I/O pins.
+ *
+ * CE, WP and R/B are active low.
+ */
+void nand_setpins(DeviceState *dev, uint8_t cle, uint8_t ale,
+ uint8_t ce, uint8_t wp, uint8_t gnd)
+{
+ NANDFlashState *s = NAND(dev);
+
+ s->cle = cle;
+ s->ale = ale;
+ s->ce = ce;
+ s->wp = wp;
+ s->gnd = gnd;
+ if (wp) {
+ s->status |= NAND_IOSTATUS_UNPROTCT;
+ } else {
+ s->status &= ~NAND_IOSTATUS_UNPROTCT;
+ }
+}
+
+void nand_getpins(DeviceState *dev, int *rb)
+{
+ *rb = 1;
+}
+
+void nand_setio(DeviceState *dev, uint32_t value)
+{
+ int i;
+ NANDFlashState *s = NAND(dev);
+
+ if (!s->ce && s->cle) {
+ if (nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP) {
+ if (s->cmd == NAND_CMD_READ0 && value == NAND_CMD_LPREAD2)
+ return;
+ if (value == NAND_CMD_RANDOMREAD1) {
+ s->addr &= ~((1 << s->addr_shift) - 1);
+ s->addrlen = 0;
+ return;
+ }
+ }
+ if (value == NAND_CMD_READ0) {
+ s->offset = 0;
+ } else if (value == NAND_CMD_READ1) {
+ s->offset = 0x100;
+ value = NAND_CMD_READ0;
+ } else if (value == NAND_CMD_READ2) {
+ s->offset = 1 << s->page_shift;
+ value = NAND_CMD_READ0;
+ }
+
+ s->cmd = value;
+
+ if (s->cmd == NAND_CMD_READSTATUS ||
+ s->cmd == NAND_CMD_PAGEPROGRAM2 ||
+ s->cmd == NAND_CMD_BLOCKERASE1 ||
+ s->cmd == NAND_CMD_BLOCKERASE2 ||
+ s->cmd == NAND_CMD_NOSERIALREAD2 ||
+ s->cmd == NAND_CMD_RANDOMREAD2 ||
+ s->cmd == NAND_CMD_RESET) {
+ nand_command(s);
+ }
+
+ if (s->cmd != NAND_CMD_RANDOMREAD2) {
+ s->addrlen = 0;
+ }
+ }
+
+ if (s->ale) {
+ unsigned int shift = s->addrlen * 8;
+ uint64_t mask = ~(0xffull << shift);
+ uint64_t v = (uint64_t)value << shift;
+
+ s->addr = (s->addr & mask) | v;
+ s->addrlen ++;
+
+ switch (s->addrlen) {
+ case 1:
+ if (s->cmd == NAND_CMD_READID) {
+ nand_command(s);
+ }
+ break;
+ case 2: /* fix cache address as a byte address */
+ s->addr <<= (s->buswidth - 1);
+ break;
+ case 3:
+ if (!(nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP) &&
+ (s->cmd == NAND_CMD_READ0 ||
+ s->cmd == NAND_CMD_PAGEPROGRAM1)) {
+ nand_command(s);
+ }
+ break;
+ case 4:
+ if ((nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP) &&
+ nand_flash_ids[s->chip_id].size < 256 && /* 1Gb or less */
+ (s->cmd == NAND_CMD_READ0 ||
+ s->cmd == NAND_CMD_PAGEPROGRAM1)) {
+ nand_command(s);
+ }
+ break;
+ case 5:
+ if ((nand_flash_ids[s->chip_id].options & NAND_SAMSUNG_LP) &&
+ nand_flash_ids[s->chip_id].size >= 256 && /* 2Gb or more */
+ (s->cmd == NAND_CMD_READ0 ||
+ s->cmd == NAND_CMD_PAGEPROGRAM1)) {
+ nand_command(s);
+ }
+ break;
+ default:
+ break;
+ }
+ }
+
+ if (!s->cle && !s->ale && s->cmd == NAND_CMD_PAGEPROGRAM1) {
+ if (s->iolen < (1 << s->page_shift) + (1 << s->oob_shift)) {
+ for (i = s->buswidth; i--; value >>= 8) {
+ s->io[s->iolen ++] = (uint8_t) (value & 0xff);
+ }
+ }
+ } else if (!s->cle && !s->ale && s->cmd == NAND_CMD_COPYBACKPRG1) {
+ if ((s->addr & ((1 << s->addr_shift) - 1)) <
+ (1 << s->page_shift) + (1 << s->oob_shift)) {
+ for (i = s->buswidth; i--; s->addr++, value >>= 8) {
+ s->io[s->iolen + (s->addr & ((1 << s->addr_shift) - 1))] =
+ (uint8_t) (value & 0xff);
+ }
+ }
+ }
+}
+
+uint32_t nand_getio(DeviceState *dev)
+{
+ int offset;
+ uint32_t x = 0;
+ NANDFlashState *s = NAND(dev);
+
+ /* Allow sequential reading */
+ if (!s->iolen && s->cmd == NAND_CMD_READ0) {
+ offset = (int) (s->addr & ((1 << s->addr_shift) - 1)) + s->offset;
+ s->offset = 0;
+
+ s->blk_load(s, s->addr, offset);
+ if (s->gnd)
+ s->iolen = (1 << s->page_shift) - offset;
+ else
+ s->iolen = (1 << s->page_shift) + (1 << s->oob_shift) - offset;
+ }
+
+ if (s->ce || s->iolen <= 0) {
+ return 0;
+ }
+
+ for (offset = s->buswidth; offset--;) {
+ x |= s->ioaddr[offset] << (offset << 3);
+ }
+ /* after receiving READ STATUS command all subsequent reads will
+ * return the status register value until another command is issued
+ */
+ if (s->cmd != NAND_CMD_READSTATUS) {
+ s->addr += s->buswidth;
+ s->ioaddr += s->buswidth;
+ s->iolen -= s->buswidth;
+ }
+ return x;
+}
+
+uint32_t nand_getbuswidth(DeviceState *dev)
+{
+ NANDFlashState *s = (NANDFlashState *) dev;
+ return s->buswidth << 3;
+}
+
+DeviceState *nand_init(BlockBackend *blk, int manf_id, int chip_id)
+{
+ DeviceState *dev;
+
+ if (nand_flash_ids[chip_id].size == 0) {
+ hw_error("%s: Unsupported NAND chip ID.\n", __func__);
+ }
+ dev = qdev_new(TYPE_NAND);
+ qdev_prop_set_uint8(dev, "manufacturer_id", manf_id);
+ qdev_prop_set_uint8(dev, "chip_id", chip_id);
+ if (blk) {
+ qdev_prop_set_drive_err(dev, "drive", blk, &error_fatal);
+ }
+
+ qdev_realize(dev, NULL, &error_fatal);
+ return dev;
+}
+
+type_init(nand_register_types)
+
+#else
+
+/* Program a single page */
+static void glue(nand_blk_write_, NAND_PAGE_SIZE)(NANDFlashState *s)
+{
+ uint64_t off, page, sector, soff;
+ uint8_t iobuf[(PAGE_SECTORS + 2) * 0x200];
+ if (PAGE(s->addr) >= s->pages)
+ return;
+
+ if (!s->blk) {
+ mem_and(s->storage + PAGE_START(s->addr) + (s->addr & PAGE_MASK) +
+ s->offset, s->io, s->iolen);
+ } else if (s->mem_oob) {
+ sector = SECTOR(s->addr);
+ off = (s->addr & PAGE_MASK) + s->offset;
+ soff = SECTOR_OFFSET(s->addr);
+ if (blk_pread(s->blk, sector << BDRV_SECTOR_BITS,
+ PAGE_SECTORS << BDRV_SECTOR_BITS, iobuf, 0) < 0) {
+ printf("%s: read error in sector %" PRIu64 "\n", __func__, sector);
+ return;
+ }
+
+ mem_and(iobuf + (soff | off), s->io, MIN(s->iolen, NAND_PAGE_SIZE - off));
+ if (off + s->iolen > NAND_PAGE_SIZE) {
+ page = PAGE(s->addr);
+ mem_and(s->storage + (page << OOB_SHIFT), s->io + NAND_PAGE_SIZE - off,
+ MIN(OOB_SIZE, off + s->iolen - NAND_PAGE_SIZE));
+ }
+
+ if (blk_pwrite(s->blk, sector << BDRV_SECTOR_BITS,
+ PAGE_SECTORS << BDRV_SECTOR_BITS, iobuf, 0) < 0) {
+ printf("%s: write error in sector %" PRIu64 "\n", __func__, sector);
+ }
+ } else {
+ off = PAGE_START(s->addr) + (s->addr & PAGE_MASK) + s->offset;
+ sector = off >> 9;
+ soff = off & 0x1ff;
+ if (blk_pread(s->blk, sector << BDRV_SECTOR_BITS,
+ (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, iobuf, 0) < 0) {
+ printf("%s: read error in sector %" PRIu64 "\n", __func__, sector);
+ return;
+ }
+
+ mem_and(iobuf + soff, s->io, s->iolen);
+
+ if (blk_pwrite(s->blk, sector << BDRV_SECTOR_BITS,
+ (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, iobuf, 0) < 0) {
+ printf("%s: write error in sector %" PRIu64 "\n", __func__, sector);
+ }
+ }
+ s->offset = 0;
+}
+
+/* Erase a single block */
+static void glue(nand_blk_erase_, NAND_PAGE_SIZE)(NANDFlashState *s)
+{
+ uint64_t i, page, addr;
+ uint8_t iobuf[0x200] = { [0 ... 0x1ff] = 0xff, };
+ addr = s->addr & ~((1 << (ADDR_SHIFT + s->erase_shift)) - 1);
+
+ if (PAGE(addr) >= s->pages) {
+ return;
+ }
+
+ if (!s->blk) {
+ memset(s->storage + PAGE_START(addr),
+ 0xff, (NAND_PAGE_SIZE + OOB_SIZE) << s->erase_shift);
+ } else if (s->mem_oob) {
+ memset(s->storage + (PAGE(addr) << OOB_SHIFT),
+ 0xff, OOB_SIZE << s->erase_shift);
+ i = SECTOR(addr);
+ page = SECTOR(addr + (1 << (ADDR_SHIFT + s->erase_shift)));
+ for (; i < page; i ++)
+ if (blk_pwrite(s->blk, i << BDRV_SECTOR_BITS,
+ BDRV_SECTOR_SIZE, iobuf, 0) < 0) {
+ printf("%s: write error in sector %" PRIu64 "\n", __func__, i);
+ }
+ } else {
+ addr = PAGE_START(addr);
+ page = addr >> 9;
+ if (blk_pread(s->blk, page << BDRV_SECTOR_BITS,
+ BDRV_SECTOR_SIZE, iobuf, 0) < 0) {
+ printf("%s: read error in sector %" PRIu64 "\n", __func__, page);
+ }
+ memset(iobuf + (addr & 0x1ff), 0xff, (~addr & 0x1ff) + 1);
+ if (blk_pwrite(s->blk, page << BDRV_SECTOR_BITS,
+ BDRV_SECTOR_SIZE, iobuf, 0) < 0) {
+ printf("%s: write error in sector %" PRIu64 "\n", __func__, page);
+ }
+
+ memset(iobuf, 0xff, 0x200);
+ i = (addr & ~0x1ff) + 0x200;
+ for (addr += ((NAND_PAGE_SIZE + OOB_SIZE) << s->erase_shift) - 0x200;
+ i < addr; i += 0x200) {
+ if (blk_pwrite(s->blk, i, BDRV_SECTOR_SIZE, iobuf, 0) < 0) {
+ printf("%s: write error in sector %" PRIu64 "\n",
+ __func__, i >> 9);
+ }
+ }
+
+ page = i >> 9;
+ if (blk_pread(s->blk, page << BDRV_SECTOR_BITS,
+ BDRV_SECTOR_SIZE, iobuf, 0) < 0) {
+ printf("%s: read error in sector %" PRIu64 "\n", __func__, page);
+ }
+ memset(iobuf, 0xff, ((addr - 1) & 0x1ff) + 1);
+ if (blk_pwrite(s->blk, page << BDRV_SECTOR_BITS,
+ BDRV_SECTOR_SIZE, iobuf, 0) < 0) {
+ printf("%s: write error in sector %" PRIu64 "\n", __func__, page);
+ }
+ }
+}
+
+static void glue(nand_blk_load_, NAND_PAGE_SIZE)(NANDFlashState *s,
+ uint64_t addr, int offset)
+{
+ if (PAGE(addr) >= s->pages) {
+ return;
+ }
+
+ if (s->blk) {
+ if (s->mem_oob) {
+ if (blk_pread(s->blk, SECTOR(addr) << BDRV_SECTOR_BITS,
+ PAGE_SECTORS << BDRV_SECTOR_BITS, s->io, 0) < 0) {
+ printf("%s: read error in sector %" PRIu64 "\n",
+ __func__, SECTOR(addr));
+ }
+ memcpy(s->io + SECTOR_OFFSET(s->addr) + NAND_PAGE_SIZE,
+ s->storage + (PAGE(s->addr) << OOB_SHIFT),
+ OOB_SIZE);
+ s->ioaddr = s->io + SECTOR_OFFSET(s->addr) + offset;
+ } else {
+ if (blk_pread(s->blk, PAGE_START(addr),
+ (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, s->io, 0)
+ < 0) {
+ printf("%s: read error in sector %" PRIu64 "\n",
+ __func__, PAGE_START(addr) >> 9);
+ }
+ s->ioaddr = s->io + (PAGE_START(addr) & 0x1ff) + offset;
+ }
+ } else {
+ memcpy(s->io, s->storage + PAGE_START(s->addr) +
+ offset, NAND_PAGE_SIZE + OOB_SIZE - offset);
+ s->ioaddr = s->io;
+ }
+}
+
+static void glue(nand_init_, NAND_PAGE_SIZE)(NANDFlashState *s)
+{
+ s->oob_shift = PAGE_SHIFT - 5;
+ s->pages = s->size >> PAGE_SHIFT;
+ s->addr_shift = ADDR_SHIFT;
+
+ s->blk_erase = glue(nand_blk_erase_, NAND_PAGE_SIZE);
+ s->blk_write = glue(nand_blk_write_, NAND_PAGE_SIZE);
+ s->blk_load = glue(nand_blk_load_, NAND_PAGE_SIZE);
+}
+
+# undef NAND_PAGE_SIZE
+# undef PAGE_SHIFT
+# undef PAGE_SECTORS
+# undef ADDR_SHIFT
+#endif /* NAND_IO */
diff --git a/hw/block/onenand.c b/hw/block/onenand.c
new file mode 100644
index 00000000..1fde9750
--- /dev/null
+++ b/hw/block/onenand.c
@@ -0,0 +1,872 @@
+/*
+ * OneNAND flash memories emulation.
+ *
+ * Copyright (C) 2008 Nokia Corporation
+ * Written by Andrzej Zaborowski <andrew@openedhand.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 or
+ * (at your option) version 3 of the License.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "hw/hw.h"
+#include "hw/block/flash.h"
+#include "hw/irq.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "sysemu/block-backend.h"
+#include "exec/memory.h"
+#include "hw/sysbus.h"
+#include "migration/vmstate.h"
+#include "qemu/error-report.h"
+#include "qemu/log.h"
+#include "qemu/module.h"
+#include "qom/object.h"
+
+/* 11 for 2kB-page OneNAND ("2nd generation") and 10 for 1kB-page chips */
+#define PAGE_SHIFT 11
+
+/* Fixed */
+#define BLOCK_SHIFT (PAGE_SHIFT + 6)
+
+#define TYPE_ONE_NAND "onenand"
+OBJECT_DECLARE_SIMPLE_TYPE(OneNANDState, ONE_NAND)
+
+struct OneNANDState {
+ SysBusDevice parent_obj;
+
+ struct {
+ uint16_t man;
+ uint16_t dev;
+ uint16_t ver;
+ } id;
+ int shift;
+ hwaddr base;
+ qemu_irq intr;
+ qemu_irq rdy;
+ BlockBackend *blk;
+ BlockBackend *blk_cur;
+ uint8_t *image;
+ uint8_t *otp;
+ uint8_t *current;
+ MemoryRegion ram;
+ MemoryRegion mapped_ram;
+ uint8_t current_direction;
+ uint8_t *boot[2];
+ uint8_t *data[2][2];
+ MemoryRegion iomem;
+ MemoryRegion container;
+ int cycle;
+ int otpmode;
+
+ uint16_t addr[8];
+ uint16_t unladdr[8];
+ int bufaddr;
+ int count;
+ uint16_t command;
+ uint16_t config[2];
+ uint16_t status;
+ uint16_t intstatus;
+ uint16_t wpstatus;
+
+ ECCState ecc;
+
+ int density_mask;
+ int secs;
+ int secs_cur;
+ int blocks;
+ uint8_t *blockwp;
+};
+
+enum {
+ ONEN_BUF_BLOCK = 0,
+ ONEN_BUF_BLOCK2 = 1,
+ ONEN_BUF_DEST_BLOCK = 2,
+ ONEN_BUF_DEST_PAGE = 3,
+ ONEN_BUF_PAGE = 7,
+};
+
+enum {
+ ONEN_ERR_CMD = 1 << 10,
+ ONEN_ERR_ERASE = 1 << 11,
+ ONEN_ERR_PROG = 1 << 12,
+ ONEN_ERR_LOAD = 1 << 13,
+};
+
+enum {
+ ONEN_INT_RESET = 1 << 4,
+ ONEN_INT_ERASE = 1 << 5,
+ ONEN_INT_PROG = 1 << 6,
+ ONEN_INT_LOAD = 1 << 7,
+ ONEN_INT = 1 << 15,
+};
+
+enum {
+ ONEN_LOCK_LOCKTIGHTEN = 1 << 0,
+ ONEN_LOCK_LOCKED = 1 << 1,
+ ONEN_LOCK_UNLOCKED = 1 << 2,
+};
+
+static void onenand_mem_setup(OneNANDState *s)
+{
+ /* XXX: We should use IO_MEM_ROMD but we broke it earlier...
+ * Both 0x0000 ... 0x01ff and 0x8000 ... 0x800f can be used to
+ * write boot commands. Also take note of the BWPS bit. */
+ memory_region_init(&s->container, OBJECT(s), "onenand",
+ 0x10000 << s->shift);
+ memory_region_add_subregion(&s->container, 0, &s->iomem);
+ memory_region_init_alias(&s->mapped_ram, OBJECT(s), "onenand-mapped-ram",
+ &s->ram, 0x0200 << s->shift,
+ 0xbe00 << s->shift);
+ memory_region_add_subregion_overlap(&s->container,
+ 0x0200 << s->shift,
+ &s->mapped_ram,
+ 1);
+}
+
+static void onenand_intr_update(OneNANDState *s)
+{
+ qemu_set_irq(s->intr, ((s->intstatus >> 15) ^ (~s->config[0] >> 6)) & 1);
+}
+
+static int onenand_pre_save(void *opaque)
+{
+ OneNANDState *s = opaque;
+ if (s->current == s->otp) {
+ s->current_direction = 1;
+ } else if (s->current == s->image) {
+ s->current_direction = 2;
+ } else {
+ s->current_direction = 0;
+ }
+
+ return 0;
+}
+
+static int onenand_post_load(void *opaque, int version_id)
+{
+ OneNANDState *s = opaque;
+ switch (s->current_direction) {
+ case 0:
+ break;
+ case 1:
+ s->current = s->otp;
+ break;
+ case 2:
+ s->current = s->image;
+ break;
+ default:
+ return -1;
+ }
+ onenand_intr_update(s);
+ return 0;
+}
+
+static const VMStateDescription vmstate_onenand = {
+ .name = "onenand",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .pre_save = onenand_pre_save,
+ .post_load = onenand_post_load,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(current_direction, OneNANDState),
+ VMSTATE_INT32(cycle, OneNANDState),
+ VMSTATE_INT32(otpmode, OneNANDState),
+ VMSTATE_UINT16_ARRAY(addr, OneNANDState, 8),
+ VMSTATE_UINT16_ARRAY(unladdr, OneNANDState, 8),
+ VMSTATE_INT32(bufaddr, OneNANDState),
+ VMSTATE_INT32(count, OneNANDState),
+ VMSTATE_UINT16(command, OneNANDState),
+ VMSTATE_UINT16_ARRAY(config, OneNANDState, 2),
+ VMSTATE_UINT16(status, OneNANDState),
+ VMSTATE_UINT16(intstatus, OneNANDState),
+ VMSTATE_UINT16(wpstatus, OneNANDState),
+ VMSTATE_INT32(secs_cur, OneNANDState),
+ VMSTATE_PARTIAL_VBUFFER(blockwp, OneNANDState, blocks),
+ VMSTATE_UINT8(ecc.cp, OneNANDState),
+ VMSTATE_UINT16_ARRAY(ecc.lp, OneNANDState, 2),
+ VMSTATE_UINT16(ecc.count, OneNANDState),
+ VMSTATE_BUFFER_POINTER_UNSAFE(otp, OneNANDState, 0,
+ ((64 + 2) << PAGE_SHIFT)),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+/* Hot reset (Reset OneNAND command) or warm reset (RP pin low) */
+static void onenand_reset(OneNANDState *s, int cold)
+{
+ memset(&s->addr, 0, sizeof(s->addr));
+ s->command = 0;
+ s->count = 1;
+ s->bufaddr = 0;
+ s->config[0] = 0x40c0;
+ s->config[1] = 0x0000;
+ onenand_intr_update(s);
+ qemu_irq_raise(s->rdy);
+ s->status = 0x0000;
+ s->intstatus = cold ? 0x8080 : 0x8010;
+ s->unladdr[0] = 0;
+ s->unladdr[1] = 0;
+ s->wpstatus = 0x0002;
+ s->cycle = 0;
+ s->otpmode = 0;
+ s->blk_cur = s->blk;
+ s->current = s->image;
+ s->secs_cur = s->secs;
+
+ if (cold) {
+ /* Lock the whole flash */
+ memset(s->blockwp, ONEN_LOCK_LOCKED, s->blocks);
+
+ if (s->blk_cur && blk_pread(s->blk_cur, 0, 8 << BDRV_SECTOR_BITS,
+ s->boot[0], 0) < 0) {
+ hw_error("%s: Loading the BootRAM failed.\n", __func__);
+ }
+ }
+}
+
+static void onenand_system_reset(DeviceState *dev)
+{
+ OneNANDState *s = ONE_NAND(dev);
+
+ onenand_reset(s, 1);
+}
+
+static inline int onenand_load_main(OneNANDState *s, int sec, int secn,
+ void *dest)
+{
+ assert(UINT32_MAX >> BDRV_SECTOR_BITS > sec);
+ assert(UINT32_MAX >> BDRV_SECTOR_BITS > secn);
+ if (s->blk_cur) {
+ return blk_pread(s->blk_cur, sec << BDRV_SECTOR_BITS,
+ secn << BDRV_SECTOR_BITS, dest, 0) < 0;
+ } else if (sec + secn > s->secs_cur) {
+ return 1;
+ }
+
+ memcpy(dest, s->current + (sec << 9), secn << 9);
+
+ return 0;
+}
+
+static inline int onenand_prog_main(OneNANDState *s, int sec, int secn,
+ void *src)
+{
+ int result = 0;
+
+ if (secn > 0) {
+ uint32_t size = secn << BDRV_SECTOR_BITS;
+ uint32_t offset = sec << BDRV_SECTOR_BITS;
+ assert(UINT32_MAX >> BDRV_SECTOR_BITS > sec);
+ assert(UINT32_MAX >> BDRV_SECTOR_BITS > secn);
+ const uint8_t *sp = (const uint8_t *)src;
+ uint8_t *dp = 0;
+ if (s->blk_cur) {
+ dp = g_malloc(size);
+ if (!dp || blk_pread(s->blk_cur, offset, size, dp, 0) < 0) {
+ result = 1;
+ }
+ } else {
+ if (sec + secn > s->secs_cur) {
+ result = 1;
+ } else {
+ dp = (uint8_t *)s->current + offset;
+ }
+ }
+ if (!result) {
+ uint32_t i;
+ for (i = 0; i < size; i++) {
+ dp[i] &= sp[i];
+ }
+ if (s->blk_cur) {
+ result = blk_pwrite(s->blk_cur, offset, size, dp, 0) < 0;
+ }
+ }
+ if (dp && s->blk_cur) {
+ g_free(dp);
+ }
+ }
+
+ return result;
+}
+
+static inline int onenand_load_spare(OneNANDState *s, int sec, int secn,
+ void *dest)
+{
+ uint8_t buf[512];
+
+ if (s->blk_cur) {
+ uint32_t offset = (s->secs_cur + (sec >> 5)) << BDRV_SECTOR_BITS;
+ if (blk_pread(s->blk_cur, offset, BDRV_SECTOR_SIZE, buf, 0) < 0) {
+ return 1;
+ }
+ memcpy(dest, buf + ((sec & 31) << 4), secn << 4);
+ } else if (sec + secn > s->secs_cur) {
+ return 1;
+ } else {
+ memcpy(dest, s->current + (s->secs_cur << 9) + (sec << 4), secn << 4);
+ }
+
+ return 0;
+}
+
+static inline int onenand_prog_spare(OneNANDState *s, int sec, int secn,
+ void *src)
+{
+ int result = 0;
+ if (secn > 0) {
+ const uint8_t *sp = (const uint8_t *)src;
+ uint8_t *dp = 0, *dpp = 0;
+ uint32_t offset = (s->secs_cur + (sec >> 5)) << BDRV_SECTOR_BITS;
+ assert(UINT32_MAX >> BDRV_SECTOR_BITS > s->secs_cur + (sec >> 5));
+ if (s->blk_cur) {
+ dp = g_malloc(512);
+ if (!dp
+ || blk_pread(s->blk_cur, offset, BDRV_SECTOR_SIZE, dp, 0) < 0) {
+ result = 1;
+ } else {
+ dpp = dp + ((sec & 31) << 4);
+ }
+ } else {
+ if (sec + secn > s->secs_cur) {
+ result = 1;
+ } else {
+ dpp = s->current + (s->secs_cur << 9) + (sec << 4);
+ }
+ }
+ if (!result) {
+ uint32_t i;
+ for (i = 0; i < (secn << 4); i++) {
+ dpp[i] &= sp[i];
+ }
+ if (s->blk_cur) {
+ result = blk_pwrite(s->blk_cur, offset, BDRV_SECTOR_SIZE, dp,
+ 0) < 0;
+ }
+ }
+ g_free(dp);
+ }
+ return result;
+}
+
+static inline int onenand_erase(OneNANDState *s, int sec, int num)
+{
+ uint8_t *blankbuf, *tmpbuf;
+
+ blankbuf = g_malloc(512);
+ tmpbuf = g_malloc(512);
+ memset(blankbuf, 0xff, 512);
+ for (; num > 0; num--, sec++) {
+ if (s->blk_cur) {
+ int erasesec = s->secs_cur + (sec >> 5);
+ if (blk_pwrite(s->blk_cur, sec << BDRV_SECTOR_BITS,
+ BDRV_SECTOR_SIZE, blankbuf, 0) < 0) {
+ goto fail;
+ }
+ if (blk_pread(s->blk_cur, erasesec << BDRV_SECTOR_BITS,
+ BDRV_SECTOR_SIZE, tmpbuf, 0) < 0) {
+ goto fail;
+ }
+ memcpy(tmpbuf + ((sec & 31) << 4), blankbuf, 1 << 4);
+ if (blk_pwrite(s->blk_cur, erasesec << BDRV_SECTOR_BITS,
+ BDRV_SECTOR_SIZE, tmpbuf, 0) < 0) {
+ goto fail;
+ }
+ } else {
+ if (sec + 1 > s->secs_cur) {
+ goto fail;
+ }
+ memcpy(s->current + (sec << 9), blankbuf, 512);
+ memcpy(s->current + (s->secs_cur << 9) + (sec << 4),
+ blankbuf, 1 << 4);
+ }
+ }
+
+ g_free(tmpbuf);
+ g_free(blankbuf);
+ return 0;
+
+fail:
+ g_free(tmpbuf);
+ g_free(blankbuf);
+ return 1;
+}
+
+static void onenand_command(OneNANDState *s)
+{
+ int b;
+ int sec;
+ void *buf;
+#define SETADDR(block, page) \
+ sec = (s->addr[page] & 3) + \
+ ((((s->addr[page] >> 2) & 0x3f) + \
+ (((s->addr[block] & 0xfff) | \
+ (s->addr[block] >> 15 ? \
+ s->density_mask : 0)) << 6)) << (PAGE_SHIFT - 9));
+#define SETBUF_M() \
+ buf = (s->bufaddr & 8) ? \
+ s->data[(s->bufaddr >> 2) & 1][0] : s->boot[0]; \
+ buf += (s->bufaddr & 3) << 9;
+#define SETBUF_S() \
+ buf = (s->bufaddr & 8) ? \
+ s->data[(s->bufaddr >> 2) & 1][1] : s->boot[1]; \
+ buf += (s->bufaddr & 3) << 4;
+
+ switch (s->command) {
+ case 0x00: /* Load single/multiple sector data unit into buffer */
+ SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE)
+
+ SETBUF_M()
+ if (onenand_load_main(s, sec, s->count, buf))
+ s->status |= ONEN_ERR_CMD | ONEN_ERR_LOAD;
+
+#if 0
+ SETBUF_S()
+ if (onenand_load_spare(s, sec, s->count, buf))
+ s->status |= ONEN_ERR_CMD | ONEN_ERR_LOAD;
+#endif
+
+ /* TODO: if (s->bufaddr & 3) + s->count was > 4 (2k-pages)
+ * or if (s->bufaddr & 1) + s->count was > 2 (1k-pages)
+ * then we need two split the read/write into two chunks.
+ */
+ s->intstatus |= ONEN_INT | ONEN_INT_LOAD;
+ break;
+ case 0x13: /* Load single/multiple spare sector into buffer */
+ SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE)
+
+ SETBUF_S()
+ if (onenand_load_spare(s, sec, s->count, buf))
+ s->status |= ONEN_ERR_CMD | ONEN_ERR_LOAD;
+
+ /* TODO: if (s->bufaddr & 3) + s->count was > 4 (2k-pages)
+ * or if (s->bufaddr & 1) + s->count was > 2 (1k-pages)
+ * then we need two split the read/write into two chunks.
+ */
+ s->intstatus |= ONEN_INT | ONEN_INT_LOAD;
+ break;
+ case 0x80: /* Program single/multiple sector data unit from buffer */
+ SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE)
+
+ SETBUF_M()
+ if (onenand_prog_main(s, sec, s->count, buf))
+ s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG;
+
+#if 0
+ SETBUF_S()
+ if (onenand_prog_spare(s, sec, s->count, buf))
+ s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG;
+#endif
+
+ /* TODO: if (s->bufaddr & 3) + s->count was > 4 (2k-pages)
+ * or if (s->bufaddr & 1) + s->count was > 2 (1k-pages)
+ * then we need two split the read/write into two chunks.
+ */
+ s->intstatus |= ONEN_INT | ONEN_INT_PROG;
+ break;
+ case 0x1a: /* Program single/multiple spare area sector from buffer */
+ SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE)
+
+ SETBUF_S()
+ if (onenand_prog_spare(s, sec, s->count, buf))
+ s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG;
+
+ /* TODO: if (s->bufaddr & 3) + s->count was > 4 (2k-pages)
+ * or if (s->bufaddr & 1) + s->count was > 2 (1k-pages)
+ * then we need two split the read/write into two chunks.
+ */
+ s->intstatus |= ONEN_INT | ONEN_INT_PROG;
+ break;
+ case 0x1b: /* Copy-back program */
+ SETBUF_S()
+
+ SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE)
+ if (onenand_load_main(s, sec, s->count, buf))
+ s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG;
+
+ SETADDR(ONEN_BUF_DEST_BLOCK, ONEN_BUF_DEST_PAGE)
+ if (onenand_prog_main(s, sec, s->count, buf))
+ s->status |= ONEN_ERR_CMD | ONEN_ERR_PROG;
+
+ /* TODO: spare areas */
+
+ s->intstatus |= ONEN_INT | ONEN_INT_PROG;
+ break;
+
+ case 0x23: /* Unlock NAND array block(s) */
+ s->intstatus |= ONEN_INT;
+
+ /* XXX the previous (?) area should be locked automatically */
+ for (b = s->unladdr[0]; b <= s->unladdr[1]; b ++) {
+ if (b >= s->blocks) {
+ s->status |= ONEN_ERR_CMD;
+ break;
+ }
+ if (s->blockwp[b] == ONEN_LOCK_LOCKTIGHTEN)
+ break;
+
+ s->wpstatus = s->blockwp[b] = ONEN_LOCK_UNLOCKED;
+ }
+ break;
+ case 0x27: /* Unlock All NAND array blocks */
+ s->intstatus |= ONEN_INT;
+
+ for (b = 0; b < s->blocks; b ++) {
+ if (s->blockwp[b] == ONEN_LOCK_LOCKTIGHTEN)
+ break;
+
+ s->wpstatus = s->blockwp[b] = ONEN_LOCK_UNLOCKED;
+ }
+ break;
+
+ case 0x2a: /* Lock NAND array block(s) */
+ s->intstatus |= ONEN_INT;
+
+ for (b = s->unladdr[0]; b <= s->unladdr[1]; b ++) {
+ if (b >= s->blocks) {
+ s->status |= ONEN_ERR_CMD;
+ break;
+ }
+ if (s->blockwp[b] == ONEN_LOCK_LOCKTIGHTEN)
+ break;
+
+ s->wpstatus = s->blockwp[b] = ONEN_LOCK_LOCKED;
+ }
+ break;
+ case 0x2c: /* Lock-tight NAND array block(s) */
+ s->intstatus |= ONEN_INT;
+
+ for (b = s->unladdr[0]; b <= s->unladdr[1]; b ++) {
+ if (b >= s->blocks) {
+ s->status |= ONEN_ERR_CMD;
+ break;
+ }
+ if (s->blockwp[b] == ONEN_LOCK_UNLOCKED)
+ continue;
+
+ s->wpstatus = s->blockwp[b] = ONEN_LOCK_LOCKTIGHTEN;
+ }
+ break;
+
+ case 0x71: /* Erase-Verify-Read */
+ s->intstatus |= ONEN_INT;
+ break;
+ case 0x95: /* Multi-block erase */
+ qemu_irq_pulse(s->intr);
+ /* Fall through. */
+ case 0x94: /* Block erase */
+ sec = ((s->addr[ONEN_BUF_BLOCK] & 0xfff) |
+ (s->addr[ONEN_BUF_BLOCK] >> 15 ? s->density_mask : 0))
+ << (BLOCK_SHIFT - 9);
+ if (onenand_erase(s, sec, 1 << (BLOCK_SHIFT - 9)))
+ s->status |= ONEN_ERR_CMD | ONEN_ERR_ERASE;
+
+ s->intstatus |= ONEN_INT | ONEN_INT_ERASE;
+ break;
+ case 0xb0: /* Erase suspend */
+ break;
+ case 0x30: /* Erase resume */
+ s->intstatus |= ONEN_INT | ONEN_INT_ERASE;
+ break;
+
+ case 0xf0: /* Reset NAND Flash core */
+ onenand_reset(s, 0);
+ break;
+ case 0xf3: /* Reset OneNAND */
+ onenand_reset(s, 0);
+ break;
+
+ case 0x65: /* OTP Access */
+ s->intstatus |= ONEN_INT;
+ s->blk_cur = NULL;
+ s->current = s->otp;
+ s->secs_cur = 1 << (BLOCK_SHIFT - 9);
+ s->addr[ONEN_BUF_BLOCK] = 0;
+ s->otpmode = 1;
+ break;
+
+ default:
+ s->status |= ONEN_ERR_CMD;
+ s->intstatus |= ONEN_INT;
+ qemu_log_mask(LOG_GUEST_ERROR, "unknown OneNAND command %x\n",
+ s->command);
+ }
+
+ onenand_intr_update(s);
+}
+
+static uint64_t onenand_read(void *opaque, hwaddr addr,
+ unsigned size)
+{
+ OneNANDState *s = (OneNANDState *) opaque;
+ int offset = addr >> s->shift;
+
+ switch (offset) {
+ case 0x0000 ... 0xbffe:
+ return lduw_le_p(s->boot[0] + addr);
+
+ case 0xf000: /* Manufacturer ID */
+ return s->id.man;
+ case 0xf001: /* Device ID */
+ return s->id.dev;
+ case 0xf002: /* Version ID */
+ return s->id.ver;
+ /* TODO: get the following values from a real chip! */
+ case 0xf003: /* Data Buffer size */
+ return 1 << PAGE_SHIFT;
+ case 0xf004: /* Boot Buffer size */
+ return 0x200;
+ case 0xf005: /* Amount of buffers */
+ return 1 | (2 << 8);
+ case 0xf006: /* Technology */
+ return 0;
+
+ case 0xf100 ... 0xf107: /* Start addresses */
+ return s->addr[offset - 0xf100];
+
+ case 0xf200: /* Start buffer */
+ return (s->bufaddr << 8) | ((s->count - 1) & (1 << (PAGE_SHIFT - 10)));
+
+ case 0xf220: /* Command */
+ return s->command;
+ case 0xf221: /* System Configuration 1 */
+ return s->config[0] & 0xffe0;
+ case 0xf222: /* System Configuration 2 */
+ return s->config[1];
+
+ case 0xf240: /* Controller Status */
+ return s->status;
+ case 0xf241: /* Interrupt */
+ return s->intstatus;
+ case 0xf24c: /* Unlock Start Block Address */
+ return s->unladdr[0];
+ case 0xf24d: /* Unlock End Block Address */
+ return s->unladdr[1];
+ case 0xf24e: /* Write Protection Status */
+ return s->wpstatus;
+
+ case 0xff00: /* ECC Status */
+ return 0x00;
+ case 0xff01: /* ECC Result of main area data */
+ case 0xff02: /* ECC Result of spare area data */
+ case 0xff03: /* ECC Result of main area data */
+ case 0xff04: /* ECC Result of spare area data */
+ qemu_log_mask(LOG_UNIMP,
+ "onenand: ECC result registers unimplemented\n");
+ return 0x0000;
+ }
+
+ qemu_log_mask(LOG_GUEST_ERROR, "read of unknown OneNAND register 0x%x\n",
+ offset);
+ return 0;
+}
+
+static void onenand_write(void *opaque, hwaddr addr,
+ uint64_t value, unsigned size)
+{
+ OneNANDState *s = (OneNANDState *) opaque;
+ int offset = addr >> s->shift;
+ int sec;
+
+ switch (offset) {
+ case 0x0000 ... 0x01ff:
+ case 0x8000 ... 0x800f:
+ if (s->cycle) {
+ s->cycle = 0;
+
+ if (value == 0x0000) {
+ SETADDR(ONEN_BUF_BLOCK, ONEN_BUF_PAGE)
+ onenand_load_main(s, sec,
+ 1 << (PAGE_SHIFT - 9), s->data[0][0]);
+ s->addr[ONEN_BUF_PAGE] += 4;
+ s->addr[ONEN_BUF_PAGE] &= 0xff;
+ }
+ break;
+ }
+
+ switch (value) {
+ case 0x00f0: /* Reset OneNAND */
+ onenand_reset(s, 0);
+ break;
+
+ case 0x00e0: /* Load Data into Buffer */
+ s->cycle = 1;
+ break;
+
+ case 0x0090: /* Read Identification Data */
+ memset(s->boot[0], 0, 3 << s->shift);
+ s->boot[0][0 << s->shift] = s->id.man & 0xff;
+ s->boot[0][1 << s->shift] = s->id.dev & 0xff;
+ s->boot[0][2 << s->shift] = s->wpstatus & 0xff;
+ break;
+
+ default:
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "unknown OneNAND boot command %" PRIx64 "\n",
+ value);
+ }
+ break;
+
+ case 0xf100 ... 0xf107: /* Start addresses */
+ s->addr[offset - 0xf100] = value;
+ break;
+
+ case 0xf200: /* Start buffer */
+ s->bufaddr = (value >> 8) & 0xf;
+ if (PAGE_SHIFT == 11)
+ s->count = (value & 3) ?: 4;
+ else if (PAGE_SHIFT == 10)
+ s->count = (value & 1) ?: 2;
+ break;
+
+ case 0xf220: /* Command */
+ if (s->intstatus & (1 << 15))
+ break;
+ s->command = value;
+ onenand_command(s);
+ break;
+ case 0xf221: /* System Configuration 1 */
+ s->config[0] = value;
+ onenand_intr_update(s);
+ qemu_set_irq(s->rdy, (s->config[0] >> 7) & 1);
+ break;
+ case 0xf222: /* System Configuration 2 */
+ s->config[1] = value;
+ break;
+
+ case 0xf241: /* Interrupt */
+ s->intstatus &= value;
+ if ((1 << 15) & ~s->intstatus)
+ s->status &= ~(ONEN_ERR_CMD | ONEN_ERR_ERASE |
+ ONEN_ERR_PROG | ONEN_ERR_LOAD);
+ onenand_intr_update(s);
+ break;
+ case 0xf24c: /* Unlock Start Block Address */
+ s->unladdr[0] = value & (s->blocks - 1);
+ /* For some reason we have to set the end address to by default
+ * be same as start because the software forgets to write anything
+ * in there. */
+ s->unladdr[1] = value & (s->blocks - 1);
+ break;
+ case 0xf24d: /* Unlock End Block Address */
+ s->unladdr[1] = value & (s->blocks - 1);
+ break;
+
+ default:
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "write to unknown OneNAND register 0x%x\n",
+ offset);
+ }
+}
+
+static const MemoryRegionOps onenand_ops = {
+ .read = onenand_read,
+ .write = onenand_write,
+ .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static void onenand_realize(DeviceState *dev, Error **errp)
+{
+ SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
+ OneNANDState *s = ONE_NAND(dev);
+ uint32_t size = 1 << (24 + ((s->id.dev >> 4) & 7));
+ void *ram;
+ Error *local_err = NULL;
+
+ s->base = (hwaddr)-1;
+ s->rdy = NULL;
+ s->blocks = size >> BLOCK_SHIFT;
+ s->secs = size >> 9;
+ s->blockwp = g_malloc(s->blocks);
+ s->density_mask = (s->id.dev & 0x08)
+ ? (1 << (6 + ((s->id.dev >> 4) & 7))) : 0;
+ memory_region_init_io(&s->iomem, OBJECT(s), &onenand_ops, s, "onenand",
+ 0x10000 << s->shift);
+ if (!s->blk) {
+ s->image = memset(g_malloc(size + (size >> 5)),
+ 0xff, size + (size >> 5));
+ } else {
+ if (!blk_supports_write_perm(s->blk)) {
+ error_setg(errp, "Can't use a read-only drive");
+ return;
+ }
+ blk_set_perm(s->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+ BLK_PERM_ALL, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return;
+ }
+ s->blk_cur = s->blk;
+ }
+ s->otp = memset(g_malloc((64 + 2) << PAGE_SHIFT),
+ 0xff, (64 + 2) << PAGE_SHIFT);
+ memory_region_init_ram_nomigrate(&s->ram, OBJECT(s), "onenand.ram",
+ 0xc000 << s->shift, &error_fatal);
+ vmstate_register_ram_global(&s->ram);
+ ram = memory_region_get_ram_ptr(&s->ram);
+ s->boot[0] = ram + (0x0000 << s->shift);
+ s->boot[1] = ram + (0x8000 << s->shift);
+ s->data[0][0] = ram + ((0x0200 + (0 << (PAGE_SHIFT - 1))) << s->shift);
+ s->data[0][1] = ram + ((0x8010 + (0 << (PAGE_SHIFT - 6))) << s->shift);
+ s->data[1][0] = ram + ((0x0200 + (1 << (PAGE_SHIFT - 1))) << s->shift);
+ s->data[1][1] = ram + ((0x8010 + (1 << (PAGE_SHIFT - 6))) << s->shift);
+ onenand_mem_setup(s);
+ sysbus_init_irq(sbd, &s->intr);
+ sysbus_init_mmio(sbd, &s->container);
+ vmstate_register(VMSTATE_IF(dev),
+ ((s->shift & 0x7f) << 24)
+ | ((s->id.man & 0xff) << 16)
+ | ((s->id.dev & 0xff) << 8)
+ | (s->id.ver & 0xff),
+ &vmstate_onenand, s);
+}
+
+static Property onenand_properties[] = {
+ DEFINE_PROP_UINT16("manufacturer_id", OneNANDState, id.man, 0),
+ DEFINE_PROP_UINT16("device_id", OneNANDState, id.dev, 0),
+ DEFINE_PROP_UINT16("version_id", OneNANDState, id.ver, 0),
+ DEFINE_PROP_INT32("shift", OneNANDState, shift, 0),
+ DEFINE_PROP_DRIVE("drive", OneNANDState, blk),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void onenand_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ dc->realize = onenand_realize;
+ dc->reset = onenand_system_reset;
+ device_class_set_props(dc, onenand_properties);
+}
+
+static const TypeInfo onenand_info = {
+ .name = TYPE_ONE_NAND,
+ .parent = TYPE_SYS_BUS_DEVICE,
+ .instance_size = sizeof(OneNANDState),
+ .class_init = onenand_class_init,
+};
+
+static void onenand_register_types(void)
+{
+ type_register_static(&onenand_info);
+}
+
+void *onenand_raw_otp(DeviceState *onenand_device)
+{
+ OneNANDState *s = ONE_NAND(onenand_device);
+
+ return s->otp;
+}
+
+type_init(onenand_register_types)
diff --git a/hw/block/pflash_cfi01.c b/hw/block/pflash_cfi01.c
new file mode 100644
index 00000000..0cbc2fb4
--- /dev/null
+++ b/hw/block/pflash_cfi01.c
@@ -0,0 +1,1043 @@
+/*
+ * CFI parallel flash with Intel command set emulation
+ *
+ * Copyright (c) 2006 Thorsten Zitterell
+ * Copyright (c) 2005 Jocelyn Mayer
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * For now, this code can emulate flashes of 1, 2 or 4 bytes width.
+ * Supported commands/modes are:
+ * - flash read
+ * - flash write
+ * - flash ID read
+ * - sector erase
+ * - CFI queries
+ *
+ * It does not support timings
+ * It does not support flash interleaving
+ * It does not implement software data protection as found in many real chips
+ * It does not implement erase suspend/resume commands
+ * It does not implement multiple sectors erase
+ *
+ * It does not implement much more ...
+ */
+
+#include "qemu/osdep.h"
+#include "hw/block/block.h"
+#include "hw/block/flash.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "sysemu/block-backend.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/bitops.h"
+#include "qemu/error-report.h"
+#include "qemu/host-utils.h"
+#include "qemu/log.h"
+#include "qemu/module.h"
+#include "qemu/option.h"
+#include "hw/sysbus.h"
+#include "migration/vmstate.h"
+#include "sysemu/blockdev.h"
+#include "sysemu/runstate.h"
+#include "trace.h"
+
+#define PFLASH_BE 0
+#define PFLASH_SECURE 1
+
+struct PFlashCFI01 {
+ /*< private >*/
+ SysBusDevice parent_obj;
+ /*< public >*/
+
+ BlockBackend *blk;
+ uint32_t nb_blocs;
+ uint64_t sector_len;
+ uint8_t bank_width;
+ uint8_t device_width; /* If 0, device width not specified. */
+ uint8_t max_device_width; /* max device width in bytes */
+ uint32_t features;
+ uint8_t wcycle; /* if 0, the flash is read normally */
+ bool ro;
+ uint8_t cmd;
+ uint8_t status;
+ uint16_t ident0;
+ uint16_t ident1;
+ uint16_t ident2;
+ uint16_t ident3;
+ uint8_t cfi_table[0x52];
+ uint64_t counter;
+ unsigned int writeblock_size;
+ MemoryRegion mem;
+ char *name;
+ void *storage;
+ VMChangeStateEntry *vmstate;
+ bool old_multiple_chip_handling;
+};
+
+static int pflash_post_load(void *opaque, int version_id);
+
+static const VMStateDescription vmstate_pflash = {
+ .name = "pflash_cfi01",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .post_load = pflash_post_load,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT8(wcycle, PFlashCFI01),
+ VMSTATE_UINT8(cmd, PFlashCFI01),
+ VMSTATE_UINT8(status, PFlashCFI01),
+ VMSTATE_UINT64(counter, PFlashCFI01),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+/*
+ * Perform a CFI query based on the bank width of the flash.
+ * If this code is called we know we have a device_width set for
+ * this flash.
+ */
+static uint32_t pflash_cfi_query(PFlashCFI01 *pfl, hwaddr offset)
+{
+ int i;
+ uint32_t resp = 0;
+ hwaddr boff;
+
+ /*
+ * Adjust incoming offset to match expected device-width
+ * addressing. CFI query addresses are always specified in terms of
+ * the maximum supported width of the device. This means that x8
+ * devices and x8/x16 devices in x8 mode behave differently. For
+ * devices that are not used at their max width, we will be
+ * provided with addresses that use higher address bits than
+ * expected (based on the max width), so we will shift them lower
+ * so that they will match the addresses used when
+ * device_width==max_device_width.
+ */
+ boff = offset >> (ctz32(pfl->bank_width) +
+ ctz32(pfl->max_device_width) - ctz32(pfl->device_width));
+
+ if (boff >= sizeof(pfl->cfi_table)) {
+ return 0;
+ }
+ /*
+ * Now we will construct the CFI response generated by a single
+ * device, then replicate that for all devices that make up the
+ * bus. For wide parts used in x8 mode, CFI query responses
+ * are different than native byte-wide parts.
+ */
+ resp = pfl->cfi_table[boff];
+ if (pfl->device_width != pfl->max_device_width) {
+ /* The only case currently supported is x8 mode for a
+ * wider part.
+ */
+ if (pfl->device_width != 1 || pfl->bank_width > 4) {
+ trace_pflash_unsupported_device_configuration(pfl->name,
+ pfl->device_width, pfl->max_device_width);
+ return 0;
+ }
+ /* CFI query data is repeated, rather than zero padded for
+ * wide devices used in x8 mode.
+ */
+ for (i = 1; i < pfl->max_device_width; i++) {
+ resp = deposit32(resp, 8 * i, 8, pfl->cfi_table[boff]);
+ }
+ }
+ /* Replicate responses for each device in bank. */
+ if (pfl->device_width < pfl->bank_width) {
+ for (i = pfl->device_width;
+ i < pfl->bank_width; i += pfl->device_width) {
+ resp = deposit32(resp, 8 * i, 8 * pfl->device_width, resp);
+ }
+ }
+
+ return resp;
+}
+
+
+
+/* Perform a device id query based on the bank width of the flash. */
+static uint32_t pflash_devid_query(PFlashCFI01 *pfl, hwaddr offset)
+{
+ int i;
+ uint32_t resp;
+ hwaddr boff;
+
+ /*
+ * Adjust incoming offset to match expected device-width
+ * addressing. Device ID read addresses are always specified in
+ * terms of the maximum supported width of the device. This means
+ * that x8 devices and x8/x16 devices in x8 mode behave
+ * differently. For devices that are not used at their max width,
+ * we will be provided with addresses that use higher address bits
+ * than expected (based on the max width), so we will shift them
+ * lower so that they will match the addresses used when
+ * device_width==max_device_width.
+ */
+ boff = offset >> (ctz32(pfl->bank_width) +
+ ctz32(pfl->max_device_width) - ctz32(pfl->device_width));
+
+ /*
+ * Mask off upper bits which may be used in to query block
+ * or sector lock status at other addresses.
+ * Offsets 2/3 are block lock status, is not emulated.
+ */
+ switch (boff & 0xFF) {
+ case 0:
+ resp = pfl->ident0;
+ trace_pflash_manufacturer_id(pfl->name, resp);
+ break;
+ case 1:
+ resp = pfl->ident1;
+ trace_pflash_device_id(pfl->name, resp);
+ break;
+ default:
+ trace_pflash_device_info(pfl->name, offset);
+ return 0;
+ }
+ /* Replicate responses for each device in bank. */
+ if (pfl->device_width < pfl->bank_width) {
+ for (i = pfl->device_width;
+ i < pfl->bank_width; i += pfl->device_width) {
+ resp = deposit32(resp, 8 * i, 8 * pfl->device_width, resp);
+ }
+ }
+
+ return resp;
+}
+
+static uint32_t pflash_data_read(PFlashCFI01 *pfl, hwaddr offset,
+ int width, int be)
+{
+ uint8_t *p;
+ uint32_t ret;
+
+ p = pfl->storage;
+ switch (width) {
+ case 1:
+ ret = p[offset];
+ break;
+ case 2:
+ if (be) {
+ ret = p[offset] << 8;
+ ret |= p[offset + 1];
+ } else {
+ ret = p[offset];
+ ret |= p[offset + 1] << 8;
+ }
+ break;
+ case 4:
+ if (be) {
+ ret = p[offset] << 24;
+ ret |= p[offset + 1] << 16;
+ ret |= p[offset + 2] << 8;
+ ret |= p[offset + 3];
+ } else {
+ ret = p[offset];
+ ret |= p[offset + 1] << 8;
+ ret |= p[offset + 2] << 16;
+ ret |= p[offset + 3] << 24;
+ }
+ break;
+ default:
+ abort();
+ }
+ trace_pflash_data_read(pfl->name, offset, width, ret);
+ return ret;
+}
+
+static uint32_t pflash_read(PFlashCFI01 *pfl, hwaddr offset,
+ int width, int be)
+{
+ hwaddr boff;
+ uint32_t ret;
+
+ ret = -1;
+ switch (pfl->cmd) {
+ default:
+ /* This should never happen : reset state & treat it as a read */
+ trace_pflash_read_unknown_state(pfl->name, pfl->cmd);
+ pfl->wcycle = 0;
+ /*
+ * The command 0x00 is not assigned by the CFI open standard,
+ * but QEMU historically uses it for the READ_ARRAY command (0xff).
+ */
+ pfl->cmd = 0x00;
+ /* fall through to read code */
+ case 0x00: /* This model reset value for READ_ARRAY (not CFI compliant) */
+ /* Flash area read */
+ ret = pflash_data_read(pfl, offset, width, be);
+ break;
+ case 0x10: /* Single byte program */
+ case 0x20: /* Block erase */
+ case 0x28: /* Block erase */
+ case 0x40: /* single byte program */
+ case 0x50: /* Clear status register */
+ case 0x60: /* Block /un)lock */
+ case 0x70: /* Status Register */
+ case 0xe8: /* Write block */
+ /*
+ * Status register read. Return status from each device in
+ * bank.
+ */
+ ret = pfl->status;
+ if (pfl->device_width && width > pfl->device_width) {
+ int shift = pfl->device_width * 8;
+ while (shift + pfl->device_width * 8 <= width * 8) {
+ ret |= pfl->status << shift;
+ shift += pfl->device_width * 8;
+ }
+ } else if (!pfl->device_width && width > 2) {
+ /*
+ * Handle 32 bit flash cases where device width is not
+ * set. (Existing behavior before device width added.)
+ */
+ ret |= pfl->status << 16;
+ }
+ trace_pflash_read_status(pfl->name, ret);
+ break;
+ case 0x90:
+ if (!pfl->device_width) {
+ /* Preserve old behavior if device width not specified */
+ boff = offset & 0xFF;
+ if (pfl->bank_width == 2) {
+ boff = boff >> 1;
+ } else if (pfl->bank_width == 4) {
+ boff = boff >> 2;
+ }
+
+ switch (boff) {
+ case 0:
+ ret = pfl->ident0 << 8 | pfl->ident1;
+ trace_pflash_manufacturer_id(pfl->name, ret);
+ break;
+ case 1:
+ ret = pfl->ident2 << 8 | pfl->ident3;
+ trace_pflash_device_id(pfl->name, ret);
+ break;
+ default:
+ trace_pflash_device_info(pfl->name, boff);
+ ret = 0;
+ break;
+ }
+ } else {
+ /*
+ * If we have a read larger than the bank_width, combine multiple
+ * manufacturer/device ID queries into a single response.
+ */
+ int i;
+ for (i = 0; i < width; i += pfl->bank_width) {
+ ret = deposit32(ret, i * 8, pfl->bank_width * 8,
+ pflash_devid_query(pfl,
+ offset + i * pfl->bank_width));
+ }
+ }
+ break;
+ case 0x98: /* Query mode */
+ if (!pfl->device_width) {
+ /* Preserve old behavior if device width not specified */
+ boff = offset & 0xFF;
+ if (pfl->bank_width == 2) {
+ boff = boff >> 1;
+ } else if (pfl->bank_width == 4) {
+ boff = boff >> 2;
+ }
+
+ if (boff < sizeof(pfl->cfi_table)) {
+ ret = pfl->cfi_table[boff];
+ } else {
+ ret = 0;
+ }
+ } else {
+ /*
+ * If we have a read larger than the bank_width, combine multiple
+ * CFI queries into a single response.
+ */
+ int i;
+ for (i = 0; i < width; i += pfl->bank_width) {
+ ret = deposit32(ret, i * 8, pfl->bank_width * 8,
+ pflash_cfi_query(pfl,
+ offset + i * pfl->bank_width));
+ }
+ }
+
+ break;
+ }
+ trace_pflash_io_read(pfl->name, offset, width, ret, pfl->cmd, pfl->wcycle);
+
+ return ret;
+}
+
+/* update flash content on disk */
+static void pflash_update(PFlashCFI01 *pfl, int offset,
+ int size)
+{
+ int offset_end;
+ int ret;
+ if (pfl->blk) {
+ offset_end = offset + size;
+ /* widen to sector boundaries */
+ offset = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE);
+ offset_end = QEMU_ALIGN_UP(offset_end, BDRV_SECTOR_SIZE);
+ ret = blk_pwrite(pfl->blk, offset, offset_end - offset,
+ pfl->storage + offset, 0);
+ if (ret < 0) {
+ /* TODO set error bit in status */
+ error_report("Could not update PFLASH: %s", strerror(-ret));
+ }
+ }
+}
+
+static inline void pflash_data_write(PFlashCFI01 *pfl, hwaddr offset,
+ uint32_t value, int width, int be)
+{
+ uint8_t *p = pfl->storage;
+
+ trace_pflash_data_write(pfl->name, offset, width, value, pfl->counter);
+ switch (width) {
+ case 1:
+ p[offset] = value;
+ break;
+ case 2:
+ if (be) {
+ p[offset] = value >> 8;
+ p[offset + 1] = value;
+ } else {
+ p[offset] = value;
+ p[offset + 1] = value >> 8;
+ }
+ break;
+ case 4:
+ if (be) {
+ p[offset] = value >> 24;
+ p[offset + 1] = value >> 16;
+ p[offset + 2] = value >> 8;
+ p[offset + 3] = value;
+ } else {
+ p[offset] = value;
+ p[offset + 1] = value >> 8;
+ p[offset + 2] = value >> 16;
+ p[offset + 3] = value >> 24;
+ }
+ break;
+ }
+
+}
+
+static void pflash_write(PFlashCFI01 *pfl, hwaddr offset,
+ uint32_t value, int width, int be)
+{
+ uint8_t *p;
+ uint8_t cmd;
+
+ cmd = value;
+
+ trace_pflash_io_write(pfl->name, offset, width, value, pfl->wcycle);
+ if (!pfl->wcycle) {
+ /* Set the device in I/O access mode */
+ memory_region_rom_device_set_romd(&pfl->mem, false);
+ }
+
+ switch (pfl->wcycle) {
+ case 0:
+ /* read mode */
+ switch (cmd) {
+ case 0x00: /* This model reset value for READ_ARRAY (not CFI) */
+ goto mode_read_array;
+ case 0x10: /* Single Byte Program */
+ case 0x40: /* Single Byte Program */
+ trace_pflash_write(pfl->name, "single byte program (0)");
+ break;
+ case 0x20: /* Block erase */
+ p = pfl->storage;
+ offset &= ~(pfl->sector_len - 1);
+
+ trace_pflash_write_block_erase(pfl->name, offset, pfl->sector_len);
+
+ if (!pfl->ro) {
+ memset(p + offset, 0xff, pfl->sector_len);
+ pflash_update(pfl, offset, pfl->sector_len);
+ } else {
+ pfl->status |= 0x20; /* Block erase error */
+ }
+ pfl->status |= 0x80; /* Ready! */
+ break;
+ case 0x50: /* Clear status bits */
+ trace_pflash_write(pfl->name, "clear status bits");
+ pfl->status = 0x0;
+ goto mode_read_array;
+ case 0x60: /* Block (un)lock */
+ trace_pflash_write(pfl->name, "block unlock");
+ break;
+ case 0x70: /* Status Register */
+ trace_pflash_write(pfl->name, "read status register");
+ pfl->cmd = cmd;
+ return;
+ case 0x90: /* Read Device ID */
+ trace_pflash_write(pfl->name, "read device information");
+ pfl->cmd = cmd;
+ return;
+ case 0x98: /* CFI query */
+ trace_pflash_write(pfl->name, "CFI query");
+ break;
+ case 0xe8: /* Write to buffer */
+ trace_pflash_write(pfl->name, "write to buffer");
+ /* FIXME should save @offset, @width for case 1+ */
+ qemu_log_mask(LOG_UNIMP,
+ "%s: Write to buffer emulation is flawed\n",
+ __func__);
+ pfl->status |= 0x80; /* Ready! */
+ break;
+ case 0xf0: /* Probe for AMD flash */
+ trace_pflash_write(pfl->name, "probe for AMD flash");
+ goto mode_read_array;
+ case 0xff: /* Read Array */
+ trace_pflash_write(pfl->name, "read array mode");
+ goto mode_read_array;
+ default:
+ goto error_flash;
+ }
+ pfl->wcycle++;
+ pfl->cmd = cmd;
+ break;
+ case 1:
+ switch (pfl->cmd) {
+ case 0x10: /* Single Byte Program */
+ case 0x40: /* Single Byte Program */
+ trace_pflash_write(pfl->name, "single byte program (1)");
+ if (!pfl->ro) {
+ pflash_data_write(pfl, offset, value, width, be);
+ pflash_update(pfl, offset, width);
+ } else {
+ pfl->status |= 0x10; /* Programming error */
+ }
+ pfl->status |= 0x80; /* Ready! */
+ pfl->wcycle = 0;
+ break;
+ case 0x20: /* Block erase */
+ case 0x28:
+ if (cmd == 0xd0) { /* confirm */
+ pfl->wcycle = 0;
+ pfl->status |= 0x80;
+ } else if (cmd == 0xff) { /* Read Array */
+ goto mode_read_array;
+ } else
+ goto error_flash;
+
+ break;
+ case 0xe8:
+ /*
+ * Mask writeblock size based on device width, or bank width if
+ * device width not specified.
+ */
+ /* FIXME check @offset, @width */
+ if (pfl->device_width) {
+ value = extract32(value, 0, pfl->device_width * 8);
+ } else {
+ value = extract32(value, 0, pfl->bank_width * 8);
+ }
+ trace_pflash_write_block(pfl->name, value);
+ pfl->counter = value;
+ pfl->wcycle++;
+ break;
+ case 0x60:
+ if (cmd == 0xd0) {
+ pfl->wcycle = 0;
+ pfl->status |= 0x80;
+ } else if (cmd == 0x01) {
+ pfl->wcycle = 0;
+ pfl->status |= 0x80;
+ } else if (cmd == 0xff) { /* Read Array */
+ goto mode_read_array;
+ } else {
+ trace_pflash_write(pfl->name, "unknown (un)locking command");
+ goto mode_read_array;
+ }
+ break;
+ case 0x98:
+ if (cmd == 0xff) { /* Read Array */
+ goto mode_read_array;
+ } else {
+ trace_pflash_write(pfl->name, "leaving query mode");
+ }
+ break;
+ default:
+ goto error_flash;
+ }
+ break;
+ case 2:
+ switch (pfl->cmd) {
+ case 0xe8: /* Block write */
+ /* FIXME check @offset, @width */
+ if (!pfl->ro) {
+ /*
+ * FIXME writing straight to memory is *wrong*. We
+ * should write to a buffer, and flush it to memory
+ * only on confirm command (see below).
+ */
+ pflash_data_write(pfl, offset, value, width, be);
+ } else {
+ pfl->status |= 0x10; /* Programming error */
+ }
+
+ pfl->status |= 0x80;
+
+ if (!pfl->counter) {
+ hwaddr mask = pfl->writeblock_size - 1;
+ mask = ~mask;
+
+ trace_pflash_write(pfl->name, "block write finished");
+ pfl->wcycle++;
+ if (!pfl->ro) {
+ /* Flush the entire write buffer onto backing storage. */
+ /* FIXME premature! */
+ pflash_update(pfl, offset & mask, pfl->writeblock_size);
+ } else {
+ pfl->status |= 0x10; /* Programming error */
+ }
+ }
+
+ pfl->counter--;
+ break;
+ default:
+ goto error_flash;
+ }
+ break;
+ case 3: /* Confirm mode */
+ switch (pfl->cmd) {
+ case 0xe8: /* Block write */
+ if (cmd == 0xd0) {
+ /* FIXME this is where we should write out the buffer */
+ pfl->wcycle = 0;
+ pfl->status |= 0x80;
+ } else {
+ qemu_log_mask(LOG_UNIMP,
+ "%s: Aborting write to buffer not implemented,"
+ " the data is already written to storage!\n"
+ "Flash device reset into READ mode.\n",
+ __func__);
+ goto mode_read_array;
+ }
+ break;
+ default:
+ goto error_flash;
+ }
+ break;
+ default:
+ /* Should never happen */
+ trace_pflash_write(pfl->name, "invalid write state");
+ goto mode_read_array;
+ }
+ return;
+
+ error_flash:
+ qemu_log_mask(LOG_UNIMP, "%s: Unimplemented flash cmd sequence "
+ "(offset " TARGET_FMT_plx ", wcycle 0x%x cmd 0x%x value 0x%x)"
+ "\n", __func__, offset, pfl->wcycle, pfl->cmd, value);
+
+ mode_read_array:
+ trace_pflash_mode_read_array(pfl->name);
+ memory_region_rom_device_set_romd(&pfl->mem, true);
+ pfl->wcycle = 0;
+ pfl->cmd = 0x00; /* This model reset value for READ_ARRAY (not CFI) */
+}
+
+
+static MemTxResult pflash_mem_read_with_attrs(void *opaque, hwaddr addr, uint64_t *value,
+ unsigned len, MemTxAttrs attrs)
+{
+ PFlashCFI01 *pfl = opaque;
+ bool be = !!(pfl->features & (1 << PFLASH_BE));
+
+ if ((pfl->features & (1 << PFLASH_SECURE)) && !attrs.secure) {
+ *value = pflash_data_read(opaque, addr, len, be);
+ } else {
+ *value = pflash_read(opaque, addr, len, be);
+ }
+ return MEMTX_OK;
+}
+
+static MemTxResult pflash_mem_write_with_attrs(void *opaque, hwaddr addr, uint64_t value,
+ unsigned len, MemTxAttrs attrs)
+{
+ PFlashCFI01 *pfl = opaque;
+ bool be = !!(pfl->features & (1 << PFLASH_BE));
+
+ if ((pfl->features & (1 << PFLASH_SECURE)) && !attrs.secure) {
+ return MEMTX_ERROR;
+ } else {
+ pflash_write(opaque, addr, value, len, be);
+ return MEMTX_OK;
+ }
+}
+
+static const MemoryRegionOps pflash_cfi01_ops = {
+ .read_with_attrs = pflash_mem_read_with_attrs,
+ .write_with_attrs = pflash_mem_write_with_attrs,
+ .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static void pflash_cfi01_fill_cfi_table(PFlashCFI01 *pfl)
+{
+ uint64_t blocks_per_device, sector_len_per_device, device_len;
+ int num_devices;
+
+ /*
+ * These are only used to expose the parameters of each device
+ * in the cfi_table[].
+ */
+ num_devices = pfl->device_width ? (pfl->bank_width / pfl->device_width) : 1;
+ if (pfl->old_multiple_chip_handling) {
+ blocks_per_device = pfl->nb_blocs / num_devices;
+ sector_len_per_device = pfl->sector_len;
+ } else {
+ blocks_per_device = pfl->nb_blocs;
+ sector_len_per_device = pfl->sector_len / num_devices;
+ }
+ device_len = sector_len_per_device * blocks_per_device;
+
+ /* Hardcoded CFI table */
+ /* Standard "QRY" string */
+ pfl->cfi_table[0x10] = 'Q';
+ pfl->cfi_table[0x11] = 'R';
+ pfl->cfi_table[0x12] = 'Y';
+ /* Command set (Intel) */
+ pfl->cfi_table[0x13] = 0x01;
+ pfl->cfi_table[0x14] = 0x00;
+ /* Primary extended table address (none) */
+ pfl->cfi_table[0x15] = 0x31;
+ pfl->cfi_table[0x16] = 0x00;
+ /* Alternate command set (none) */
+ pfl->cfi_table[0x17] = 0x00;
+ pfl->cfi_table[0x18] = 0x00;
+ /* Alternate extended table (none) */
+ pfl->cfi_table[0x19] = 0x00;
+ pfl->cfi_table[0x1A] = 0x00;
+ /* Vcc min */
+ pfl->cfi_table[0x1B] = 0x45;
+ /* Vcc max */
+ pfl->cfi_table[0x1C] = 0x55;
+ /* Vpp min (no Vpp pin) */
+ pfl->cfi_table[0x1D] = 0x00;
+ /* Vpp max (no Vpp pin) */
+ pfl->cfi_table[0x1E] = 0x00;
+ /* Reserved */
+ pfl->cfi_table[0x1F] = 0x07;
+ /* Timeout for min size buffer write */
+ pfl->cfi_table[0x20] = 0x07;
+ /* Typical timeout for block erase */
+ pfl->cfi_table[0x21] = 0x0a;
+ /* Typical timeout for full chip erase (4096 ms) */
+ pfl->cfi_table[0x22] = 0x00;
+ /* Reserved */
+ pfl->cfi_table[0x23] = 0x04;
+ /* Max timeout for buffer write */
+ pfl->cfi_table[0x24] = 0x04;
+ /* Max timeout for block erase */
+ pfl->cfi_table[0x25] = 0x04;
+ /* Max timeout for chip erase */
+ pfl->cfi_table[0x26] = 0x00;
+ /* Device size */
+ pfl->cfi_table[0x27] = ctz32(device_len); /* + 1; */
+ /* Flash device interface (8 & 16 bits) */
+ pfl->cfi_table[0x28] = 0x02;
+ pfl->cfi_table[0x29] = 0x00;
+ /* Max number of bytes in multi-bytes write */
+ if (pfl->bank_width == 1) {
+ pfl->cfi_table[0x2A] = 0x08;
+ } else {
+ pfl->cfi_table[0x2A] = 0x0B;
+ }
+ pfl->writeblock_size = 1 << pfl->cfi_table[0x2A];
+ if (!pfl->old_multiple_chip_handling && num_devices > 1) {
+ pfl->writeblock_size *= num_devices;
+ }
+
+ pfl->cfi_table[0x2B] = 0x00;
+ /* Number of erase block regions (uniform) */
+ pfl->cfi_table[0x2C] = 0x01;
+ /* Erase block region 1 */
+ pfl->cfi_table[0x2D] = blocks_per_device - 1;
+ pfl->cfi_table[0x2E] = (blocks_per_device - 1) >> 8;
+ pfl->cfi_table[0x2F] = sector_len_per_device >> 8;
+ pfl->cfi_table[0x30] = sector_len_per_device >> 16;
+
+ /* Extended */
+ pfl->cfi_table[0x31] = 'P';
+ pfl->cfi_table[0x32] = 'R';
+ pfl->cfi_table[0x33] = 'I';
+
+ pfl->cfi_table[0x34] = '1';
+ pfl->cfi_table[0x35] = '0';
+
+ pfl->cfi_table[0x36] = 0x00;
+ pfl->cfi_table[0x37] = 0x00;
+ pfl->cfi_table[0x38] = 0x00;
+ pfl->cfi_table[0x39] = 0x00;
+
+ pfl->cfi_table[0x3a] = 0x00;
+
+ pfl->cfi_table[0x3b] = 0x00;
+ pfl->cfi_table[0x3c] = 0x00;
+
+ pfl->cfi_table[0x3f] = 0x01; /* Number of protection fields */
+}
+
+static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
+{
+ ERRP_GUARD();
+ PFlashCFI01 *pfl = PFLASH_CFI01(dev);
+ uint64_t total_len;
+ int ret;
+
+ if (pfl->sector_len == 0) {
+ error_setg(errp, "attribute \"sector-length\" not specified or zero.");
+ return;
+ }
+ if (pfl->nb_blocs == 0) {
+ error_setg(errp, "attribute \"num-blocks\" not specified or zero.");
+ return;
+ }
+ if (pfl->name == NULL) {
+ error_setg(errp, "attribute \"name\" not specified.");
+ return;
+ }
+
+ total_len = pfl->sector_len * pfl->nb_blocs;
+
+ memory_region_init_rom_device(
+ &pfl->mem, OBJECT(dev),
+ &pflash_cfi01_ops,
+ pfl,
+ pfl->name, total_len, errp);
+ if (*errp) {
+ return;
+ }
+
+ pfl->storage = memory_region_get_ram_ptr(&pfl->mem);
+ sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem);
+
+ if (pfl->blk) {
+ uint64_t perm;
+ pfl->ro = !blk_supports_write_perm(pfl->blk);
+ perm = BLK_PERM_CONSISTENT_READ | (pfl->ro ? 0 : BLK_PERM_WRITE);
+ ret = blk_set_perm(pfl->blk, perm, BLK_PERM_ALL, errp);
+ if (ret < 0) {
+ return;
+ }
+ } else {
+ pfl->ro = false;
+ }
+
+ if (pfl->blk) {
+ if (!blk_check_size_and_read_all(pfl->blk, pfl->storage, total_len,
+ errp)) {
+ vmstate_unregister_ram(&pfl->mem, DEVICE(pfl));
+ return;
+ }
+ }
+
+ /*
+ * Default to devices being used at their maximum device width. This was
+ * assumed before the device_width support was added.
+ */
+ if (!pfl->max_device_width) {
+ pfl->max_device_width = pfl->device_width;
+ }
+
+ pfl->wcycle = 0;
+ /*
+ * The command 0x00 is not assigned by the CFI open standard,
+ * but QEMU historically uses it for the READ_ARRAY command (0xff).
+ */
+ pfl->cmd = 0x00;
+ pfl->status = 0x80; /* WSM ready */
+ pflash_cfi01_fill_cfi_table(pfl);
+}
+
+static void pflash_cfi01_system_reset(DeviceState *dev)
+{
+ PFlashCFI01 *pfl = PFLASH_CFI01(dev);
+
+ trace_pflash_reset(pfl->name);
+ /*
+ * The command 0x00 is not assigned by the CFI open standard,
+ * but QEMU historically uses it for the READ_ARRAY command (0xff).
+ */
+ pfl->cmd = 0x00;
+ pfl->wcycle = 0;
+ memory_region_rom_device_set_romd(&pfl->mem, true);
+ /*
+ * The WSM ready timer occurs at most 150ns after system reset.
+ * This model deliberately ignores this delay.
+ */
+ pfl->status = 0x80;
+}
+
+static Property pflash_cfi01_properties[] = {
+ DEFINE_PROP_DRIVE("drive", PFlashCFI01, blk),
+ /* num-blocks is the number of blocks actually visible to the guest,
+ * ie the total size of the device divided by the sector length.
+ * If we're emulating flash devices wired in parallel the actual
+ * number of blocks per indvidual device will differ.
+ */
+ DEFINE_PROP_UINT32("num-blocks", PFlashCFI01, nb_blocs, 0),
+ DEFINE_PROP_UINT64("sector-length", PFlashCFI01, sector_len, 0),
+ /* width here is the overall width of this QEMU device in bytes.
+ * The QEMU device may be emulating a number of flash devices
+ * wired up in parallel; the width of each individual flash
+ * device should be specified via device-width. If the individual
+ * devices have a maximum width which is greater than the width
+ * they are being used for, this maximum width should be set via
+ * max-device-width (which otherwise defaults to device-width).
+ * So for instance a 32-bit wide QEMU flash device made from four
+ * 16-bit flash devices used in 8-bit wide mode would be configured
+ * with width = 4, device-width = 1, max-device-width = 2.
+ *
+ * If device-width is not specified we default to backwards
+ * compatible behaviour which is a bad emulation of two
+ * 16 bit devices making up a 32 bit wide QEMU device. This
+ * is deprecated for new uses of this device.
+ */
+ DEFINE_PROP_UINT8("width", PFlashCFI01, bank_width, 0),
+ DEFINE_PROP_UINT8("device-width", PFlashCFI01, device_width, 0),
+ DEFINE_PROP_UINT8("max-device-width", PFlashCFI01, max_device_width, 0),
+ DEFINE_PROP_BIT("big-endian", PFlashCFI01, features, PFLASH_BE, 0),
+ DEFINE_PROP_BIT("secure", PFlashCFI01, features, PFLASH_SECURE, 0),
+ DEFINE_PROP_UINT16("id0", PFlashCFI01, ident0, 0),
+ DEFINE_PROP_UINT16("id1", PFlashCFI01, ident1, 0),
+ DEFINE_PROP_UINT16("id2", PFlashCFI01, ident2, 0),
+ DEFINE_PROP_UINT16("id3", PFlashCFI01, ident3, 0),
+ DEFINE_PROP_STRING("name", PFlashCFI01, name),
+ DEFINE_PROP_BOOL("old-multiple-chip-handling", PFlashCFI01,
+ old_multiple_chip_handling, false),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void pflash_cfi01_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ dc->reset = pflash_cfi01_system_reset;
+ dc->realize = pflash_cfi01_realize;
+ device_class_set_props(dc, pflash_cfi01_properties);
+ dc->vmsd = &vmstate_pflash;
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+}
+
+
+static const TypeInfo pflash_cfi01_info = {
+ .name = TYPE_PFLASH_CFI01,
+ .parent = TYPE_SYS_BUS_DEVICE,
+ .instance_size = sizeof(PFlashCFI01),
+ .class_init = pflash_cfi01_class_init,
+};
+
+static void pflash_cfi01_register_types(void)
+{
+ type_register_static(&pflash_cfi01_info);
+}
+
+type_init(pflash_cfi01_register_types)
+
+PFlashCFI01 *pflash_cfi01_register(hwaddr base,
+ const char *name,
+ hwaddr size,
+ BlockBackend *blk,
+ uint32_t sector_len,
+ int bank_width,
+ uint16_t id0, uint16_t id1,
+ uint16_t id2, uint16_t id3,
+ int be)
+{
+ DeviceState *dev = qdev_new(TYPE_PFLASH_CFI01);
+
+ if (blk) {
+ qdev_prop_set_drive(dev, "drive", blk);
+ }
+ assert(QEMU_IS_ALIGNED(size, sector_len));
+ qdev_prop_set_uint32(dev, "num-blocks", size / sector_len);
+ qdev_prop_set_uint64(dev, "sector-length", sector_len);
+ qdev_prop_set_uint8(dev, "width", bank_width);
+ qdev_prop_set_bit(dev, "big-endian", !!be);
+ qdev_prop_set_uint16(dev, "id0", id0);
+ qdev_prop_set_uint16(dev, "id1", id1);
+ qdev_prop_set_uint16(dev, "id2", id2);
+ qdev_prop_set_uint16(dev, "id3", id3);
+ qdev_prop_set_string(dev, "name", name);
+ sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);
+
+ sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base);
+ return PFLASH_CFI01(dev);
+}
+
+BlockBackend *pflash_cfi01_get_blk(PFlashCFI01 *fl)
+{
+ return fl->blk;
+}
+
+MemoryRegion *pflash_cfi01_get_memory(PFlashCFI01 *fl)
+{
+ return &fl->mem;
+}
+
+/*
+ * Handle -drive if=pflash for machines that use properties.
+ * If @dinfo is null, do nothing.
+ * Else if @fl's property "drive" is already set, fatal error.
+ * Else set it to the BlockBackend with @dinfo.
+ */
+void pflash_cfi01_legacy_drive(PFlashCFI01 *fl, DriveInfo *dinfo)
+{
+ Location loc;
+
+ if (!dinfo) {
+ return;
+ }
+
+ loc_push_none(&loc);
+ qemu_opts_loc_restore(dinfo->opts);
+ if (fl->blk) {
+ error_report("clashes with -machine");
+ exit(1);
+ }
+ qdev_prop_set_drive_err(DEVICE(fl), "drive", blk_by_legacy_dinfo(dinfo),
+ &error_fatal);
+ loc_pop(&loc);
+}
+
+static void postload_update_cb(void *opaque, bool running, RunState state)
+{
+ PFlashCFI01 *pfl = opaque;
+
+ /* This is called after bdrv_activate_all. */
+ qemu_del_vm_change_state_handler(pfl->vmstate);
+ pfl->vmstate = NULL;
+
+ trace_pflash_postload_cb(pfl->name);
+ pflash_update(pfl, 0, pfl->sector_len * pfl->nb_blocs);
+}
+
+static int pflash_post_load(void *opaque, int version_id)
+{
+ PFlashCFI01 *pfl = opaque;
+
+ if (!pfl->ro) {
+ pfl->vmstate = qemu_add_vm_change_state_handler(postload_update_cb,
+ pfl);
+ }
+ return 0;
+}
diff --git a/hw/block/pflash_cfi02.c b/hw/block/pflash_cfi02.c
new file mode 100644
index 00000000..2a99b286
--- /dev/null
+++ b/hw/block/pflash_cfi02.c
@@ -0,0 +1,1031 @@
+/*
+ * CFI parallel flash with AMD command set emulation
+ *
+ * Copyright (c) 2005 Jocelyn Mayer
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * For now, this code can emulate flashes of 1, 2 or 4 bytes width.
+ * Supported commands/modes are:
+ * - flash read
+ * - flash write
+ * - flash ID read
+ * - sector erase
+ * - chip erase
+ * - unlock bypass command
+ * - CFI queries
+ *
+ * It does not support flash interleaving.
+ * It does not implement software data protection as found in many real chips
+ */
+
+#include "qemu/osdep.h"
+#include "hw/block/block.h"
+#include "hw/block/flash.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/bitmap.h"
+#include "qemu/timer.h"
+#include "sysemu/block-backend.h"
+#include "qemu/host-utils.h"
+#include "qemu/module.h"
+#include "hw/sysbus.h"
+#include "migration/vmstate.h"
+#include "trace.h"
+
+#define PFLASH_LAZY_ROMD_THRESHOLD 42
+
+/*
+ * The size of the cfi_table indirectly depends on this and the start of the
+ * PRI table directly depends on it. 4 is the maximum size (and also what
+ * seems common) without changing the PRT table address.
+ */
+#define PFLASH_MAX_ERASE_REGIONS 4
+
+/* Special write cycles for CFI queries. */
+enum {
+ WCYCLE_CFI = 7,
+ WCYCLE_AUTOSELECT_CFI = 8,
+};
+
+struct PFlashCFI02 {
+ /*< private >*/
+ SysBusDevice parent_obj;
+ /*< public >*/
+
+ BlockBackend *blk;
+ uint32_t uniform_nb_blocs;
+ uint32_t uniform_sector_len;
+ uint32_t total_sectors;
+ uint32_t nb_blocs[PFLASH_MAX_ERASE_REGIONS];
+ uint32_t sector_len[PFLASH_MAX_ERASE_REGIONS];
+ uint32_t chip_len;
+ uint8_t mappings;
+ uint8_t width;
+ uint8_t be;
+ int wcycle; /* if 0, the flash is read normally */
+ int bypass;
+ int ro;
+ uint8_t cmd;
+ uint8_t status;
+ /* FIXME: implement array device properties */
+ uint16_t ident0;
+ uint16_t ident1;
+ uint16_t ident2;
+ uint16_t ident3;
+ uint16_t unlock_addr0;
+ uint16_t unlock_addr1;
+ uint8_t cfi_table[0x4d];
+ QEMUTimer timer;
+ /*
+ * The device replicates the flash memory across its memory space. Emulate
+ * that by having a container (.mem) filled with an array of aliases
+ * (.mem_mappings) pointing to the flash memory (.orig_mem).
+ */
+ MemoryRegion mem;
+ MemoryRegion *mem_mappings; /* array; one per mapping */
+ MemoryRegion orig_mem;
+ bool rom_mode;
+ int read_counter; /* used for lazy switch-back to rom mode */
+ int sectors_to_erase;
+ uint64_t erase_time_remaining;
+ unsigned long *sector_erase_map;
+ char *name;
+ void *storage;
+};
+
+/*
+ * Toggle status bit DQ7.
+ */
+static inline void toggle_dq7(PFlashCFI02 *pfl)
+{
+ pfl->status ^= 0x80;
+}
+
+/*
+ * Set status bit DQ7 to bit 7 of value.
+ */
+static inline void set_dq7(PFlashCFI02 *pfl, uint8_t value)
+{
+ pfl->status &= 0x7F;
+ pfl->status |= value & 0x80;
+}
+
+/*
+ * Toggle status bit DQ6.
+ */
+static inline void toggle_dq6(PFlashCFI02 *pfl)
+{
+ pfl->status ^= 0x40;
+}
+
+/*
+ * Turn on DQ3.
+ */
+static inline void assert_dq3(PFlashCFI02 *pfl)
+{
+ pfl->status |= 0x08;
+}
+
+/*
+ * Turn off DQ3.
+ */
+static inline void reset_dq3(PFlashCFI02 *pfl)
+{
+ pfl->status &= ~0x08;
+}
+
+/*
+ * Toggle status bit DQ2.
+ */
+static inline void toggle_dq2(PFlashCFI02 *pfl)
+{
+ pfl->status ^= 0x04;
+}
+
+/*
+ * Set up replicated mappings of the same region.
+ */
+static void pflash_setup_mappings(PFlashCFI02 *pfl)
+{
+ unsigned i;
+ hwaddr size = memory_region_size(&pfl->orig_mem);
+
+ memory_region_init(&pfl->mem, OBJECT(pfl), "pflash", pfl->mappings * size);
+ pfl->mem_mappings = g_new(MemoryRegion, pfl->mappings);
+ for (i = 0; i < pfl->mappings; ++i) {
+ memory_region_init_alias(&pfl->mem_mappings[i], OBJECT(pfl),
+ "pflash-alias", &pfl->orig_mem, 0, size);
+ memory_region_add_subregion(&pfl->mem, i * size, &pfl->mem_mappings[i]);
+ }
+}
+
+static void pflash_reset_state_machine(PFlashCFI02 *pfl)
+{
+ trace_pflash_reset(pfl->name);
+ pfl->cmd = 0x00;
+ pfl->wcycle = 0;
+}
+
+static void pflash_mode_read_array(PFlashCFI02 *pfl)
+{
+ trace_pflash_mode_read_array(pfl->name);
+ pflash_reset_state_machine(pfl);
+ pfl->rom_mode = true;
+ memory_region_rom_device_set_romd(&pfl->orig_mem, true);
+}
+
+static size_t pflash_regions_count(PFlashCFI02 *pfl)
+{
+ return pfl->cfi_table[0x2c];
+}
+
+/*
+ * Returns the time it takes to erase the number of sectors scheduled for
+ * erasure based on CFI address 0x21 which is "Typical timeout per individual
+ * block erase 2^N ms."
+ */
+static uint64_t pflash_erase_time(PFlashCFI02 *pfl)
+{
+ /*
+ * If there are no sectors to erase (which can happen if all of the sectors
+ * to be erased are protected), then erase takes 100 us. Protected sectors
+ * aren't supported so this should never happen.
+ */
+ return ((1ULL << pfl->cfi_table[0x21]) * pfl->sectors_to_erase) * SCALE_US;
+}
+
+/*
+ * Returns true if the device is currently in erase suspend mode.
+ */
+static inline bool pflash_erase_suspend_mode(PFlashCFI02 *pfl)
+{
+ return pfl->erase_time_remaining > 0;
+}
+
+static void pflash_timer(void *opaque)
+{
+ PFlashCFI02 *pfl = opaque;
+
+ trace_pflash_timer_expired(pfl->name, pfl->cmd);
+ if (pfl->cmd == 0x30) {
+ /*
+ * Sector erase. If DQ3 is 0 when the timer expires, then the 50
+ * us erase timeout has expired so we need to start the timer for the
+ * sector erase algorithm. Otherwise, the erase completed and we should
+ * go back to read array mode.
+ */
+ if ((pfl->status & 0x08) == 0) {
+ assert_dq3(pfl);
+ uint64_t timeout = pflash_erase_time(pfl);
+ timer_mod(&pfl->timer,
+ qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + timeout);
+ trace_pflash_erase_timeout(pfl->name, pfl->sectors_to_erase);
+ return;
+ }
+ trace_pflash_erase_complete(pfl->name);
+ bitmap_zero(pfl->sector_erase_map, pfl->total_sectors);
+ pfl->sectors_to_erase = 0;
+ reset_dq3(pfl);
+ }
+
+ /* Reset flash */
+ toggle_dq7(pfl);
+ if (pfl->bypass) {
+ pfl->wcycle = 2;
+ pfl->cmd = 0;
+ } else {
+ pflash_mode_read_array(pfl);
+ }
+}
+
+/*
+ * Read data from flash.
+ */
+static uint64_t pflash_data_read(PFlashCFI02 *pfl, hwaddr offset,
+ unsigned int width)
+{
+ uint8_t *p = (uint8_t *)pfl->storage + offset;
+ uint64_t ret = pfl->be ? ldn_be_p(p, width) : ldn_le_p(p, width);
+ trace_pflash_data_read(pfl->name, offset, width, ret);
+ return ret;
+}
+
+typedef struct {
+ uint32_t len;
+ uint32_t num;
+} SectorInfo;
+
+/*
+ * offset should be a byte offset of the QEMU device and _not_ a device
+ * offset.
+ */
+static SectorInfo pflash_sector_info(PFlashCFI02 *pfl, hwaddr offset)
+{
+ assert(offset < pfl->chip_len);
+ hwaddr addr = 0;
+ uint32_t sector_num = 0;
+ for (int i = 0; i < pflash_regions_count(pfl); ++i) {
+ uint64_t region_size = (uint64_t)pfl->nb_blocs[i] * pfl->sector_len[i];
+ if (addr <= offset && offset < addr + region_size) {
+ return (SectorInfo) {
+ .len = pfl->sector_len[i],
+ .num = sector_num + (offset - addr) / pfl->sector_len[i],
+ };
+ }
+ sector_num += pfl->nb_blocs[i];
+ addr += region_size;
+ }
+ abort();
+}
+
+/*
+ * Returns true if the offset refers to a flash sector that is currently being
+ * erased.
+ */
+static bool pflash_sector_is_erasing(PFlashCFI02 *pfl, hwaddr offset)
+{
+ long sector_num = pflash_sector_info(pfl, offset).num;
+ return test_bit(sector_num, pfl->sector_erase_map);
+}
+
+static uint64_t pflash_read(void *opaque, hwaddr offset, unsigned int width)
+{
+ PFlashCFI02 *pfl = opaque;
+ hwaddr boff;
+ uint64_t ret;
+
+ /* Lazy reset to ROMD mode after a certain amount of read accesses */
+ if (!pfl->rom_mode && pfl->wcycle == 0 &&
+ ++pfl->read_counter > PFLASH_LAZY_ROMD_THRESHOLD) {
+ pflash_mode_read_array(pfl);
+ }
+ offset &= pfl->chip_len - 1;
+ boff = offset & 0xFF;
+ if (pfl->width == 2) {
+ boff = boff >> 1;
+ } else if (pfl->width == 4) {
+ boff = boff >> 2;
+ }
+ switch (pfl->cmd) {
+ default:
+ /* This should never happen : reset state & treat it as a read*/
+ trace_pflash_read_unknown_state(pfl->name, pfl->cmd);
+ pflash_reset_state_machine(pfl);
+ /* fall through to the read code */
+ case 0x80: /* Erase (unlock) */
+ /* We accept reads during second unlock sequence... */
+ case 0x00:
+ if (pflash_erase_suspend_mode(pfl) &&
+ pflash_sector_is_erasing(pfl, offset)) {
+ /* Toggle bit 2, but not 6. */
+ toggle_dq2(pfl);
+ /* Status register read */
+ ret = pfl->status;
+ trace_pflash_read_status(pfl->name, ret);
+ break;
+ }
+ /* Flash area read */
+ ret = pflash_data_read(pfl, offset, width);
+ break;
+ case 0x90: /* flash ID read */
+ switch (boff) {
+ case 0x00:
+ case 0x01:
+ ret = boff & 0x01 ? pfl->ident1 : pfl->ident0;
+ break;
+ case 0x02:
+ ret = 0x00; /* Pretend all sectors are unprotected */
+ break;
+ case 0x0E:
+ case 0x0F:
+ ret = boff & 0x01 ? pfl->ident3 : pfl->ident2;
+ if (ret != (uint8_t)-1) {
+ break;
+ }
+ /* Fall through to data read. */
+ default:
+ ret = pflash_data_read(pfl, offset, width);
+ }
+ trace_pflash_read_done(pfl->name, boff, ret);
+ break;
+ case 0x10: /* Chip Erase */
+ case 0x30: /* Sector Erase */
+ /* Toggle bit 2 during erase, but not program. */
+ toggle_dq2(pfl);
+ /* fall through */
+ case 0xA0: /* Program */
+ /* Toggle bit 6 */
+ toggle_dq6(pfl);
+ /* Status register read */
+ ret = pfl->status;
+ trace_pflash_read_status(pfl->name, ret);
+ break;
+ case 0x98:
+ /* CFI query mode */
+ if (boff < sizeof(pfl->cfi_table)) {
+ ret = pfl->cfi_table[boff];
+ } else {
+ ret = 0;
+ }
+ break;
+ }
+ trace_pflash_io_read(pfl->name, offset, width, ret, pfl->cmd, pfl->wcycle);
+
+ return ret;
+}
+
+/* update flash content on disk */
+static void pflash_update(PFlashCFI02 *pfl, int offset, int size)
+{
+ int offset_end;
+ int ret;
+ if (pfl->blk) {
+ offset_end = offset + size;
+ /* widen to sector boundaries */
+ offset = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE);
+ offset_end = QEMU_ALIGN_UP(offset_end, BDRV_SECTOR_SIZE);
+ ret = blk_pwrite(pfl->blk, offset, offset_end - offset,
+ pfl->storage + offset, 0);
+ if (ret < 0) {
+ /* TODO set error bit in status */
+ error_report("Could not update PFLASH: %s", strerror(-ret));
+ }
+ }
+}
+
+static void pflash_sector_erase(PFlashCFI02 *pfl, hwaddr offset)
+{
+ SectorInfo sector_info = pflash_sector_info(pfl, offset);
+ uint64_t sector_len = sector_info.len;
+ offset &= ~(sector_len - 1);
+ trace_pflash_sector_erase_start(pfl->name, pfl->width * 2, offset,
+ pfl->width * 2, offset + sector_len - 1);
+ if (!pfl->ro) {
+ uint8_t *p = pfl->storage;
+ memset(p + offset, 0xff, sector_len);
+ pflash_update(pfl, offset, sector_len);
+ }
+ set_dq7(pfl, 0x00);
+ ++pfl->sectors_to_erase;
+ set_bit(sector_info.num, pfl->sector_erase_map);
+ /* Set (or reset) the 50 us timer for additional erase commands. */
+ timer_mod(&pfl->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 50000);
+}
+
+static void pflash_write(void *opaque, hwaddr offset, uint64_t value,
+ unsigned int width)
+{
+ PFlashCFI02 *pfl = opaque;
+ hwaddr boff;
+ uint8_t *p;
+ uint8_t cmd;
+
+ trace_pflash_io_write(pfl->name, offset, width, value, pfl->wcycle);
+ cmd = value;
+ if (pfl->cmd != 0xA0) {
+ /* Reset does nothing during chip erase and sector erase. */
+ if (cmd == 0xF0 && pfl->cmd != 0x10 && pfl->cmd != 0x30) {
+ if (pfl->wcycle == WCYCLE_AUTOSELECT_CFI) {
+ /* Return to autoselect mode. */
+ pfl->wcycle = 3;
+ pfl->cmd = 0x90;
+ return;
+ }
+ goto reset_flash;
+ }
+ }
+ offset &= pfl->chip_len - 1;
+
+ boff = offset;
+ if (pfl->width == 2) {
+ boff = boff >> 1;
+ } else if (pfl->width == 4) {
+ boff = boff >> 2;
+ }
+ /* Only the least-significant 11 bits are used in most cases. */
+ boff &= 0x7FF;
+ switch (pfl->wcycle) {
+ case 0:
+ /* Set the device in I/O access mode if required */
+ if (pfl->rom_mode) {
+ pfl->rom_mode = false;
+ memory_region_rom_device_set_romd(&pfl->orig_mem, false);
+ }
+ pfl->read_counter = 0;
+ /* We're in read mode */
+ check_unlock0:
+ if (boff == 0x55 && cmd == 0x98) {
+ /* Enter CFI query mode */
+ pfl->wcycle = WCYCLE_CFI;
+ pfl->cmd = 0x98;
+ return;
+ }
+ /* Handle erase resume in erase suspend mode, otherwise reset. */
+ if (cmd == 0x30) { /* Erase Resume */
+ if (pflash_erase_suspend_mode(pfl)) {
+ /* Resume the erase. */
+ timer_mod(&pfl->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+ pfl->erase_time_remaining);
+ pfl->erase_time_remaining = 0;
+ pfl->wcycle = 6;
+ pfl->cmd = 0x30;
+ set_dq7(pfl, 0x00);
+ assert_dq3(pfl);
+ return;
+ }
+ goto reset_flash;
+ }
+ /* Ignore erase suspend. */
+ if (cmd == 0xB0) { /* Erase Suspend */
+ return;
+ }
+ if (boff != pfl->unlock_addr0 || cmd != 0xAA) {
+ trace_pflash_unlock0_failed(pfl->name, boff,
+ cmd, pfl->unlock_addr0);
+ goto reset_flash;
+ }
+ trace_pflash_write(pfl->name, "unlock sequence started");
+ break;
+ case 1:
+ /* We started an unlock sequence */
+ check_unlock1:
+ if (boff != pfl->unlock_addr1 || cmd != 0x55) {
+ trace_pflash_unlock1_failed(pfl->name, boff, cmd);
+ goto reset_flash;
+ }
+ trace_pflash_write(pfl->name, "unlock sequence done");
+ break;
+ case 2:
+ /* We finished an unlock sequence */
+ if (!pfl->bypass && boff != pfl->unlock_addr0) {
+ trace_pflash_write_failed(pfl->name, boff, cmd);
+ goto reset_flash;
+ }
+ switch (cmd) {
+ case 0x20:
+ pfl->bypass = 1;
+ goto do_bypass;
+ case 0x80: /* Erase */
+ case 0x90: /* Autoselect */
+ case 0xA0: /* Program */
+ pfl->cmd = cmd;
+ trace_pflash_write_start(pfl->name, cmd);
+ break;
+ default:
+ trace_pflash_write_unknown(pfl->name, cmd);
+ goto reset_flash;
+ }
+ break;
+ case 3:
+ switch (pfl->cmd) {
+ case 0x80: /* Erase */
+ /* We need another unlock sequence */
+ goto check_unlock0;
+ case 0xA0: /* Program */
+ if (pflash_erase_suspend_mode(pfl) &&
+ pflash_sector_is_erasing(pfl, offset)) {
+ /* Ignore writes to erasing sectors. */
+ if (pfl->bypass) {
+ goto do_bypass;
+ }
+ goto reset_flash;
+ }
+ trace_pflash_data_write(pfl->name, offset, width, value, 0);
+ if (!pfl->ro) {
+ p = (uint8_t *)pfl->storage + offset;
+ if (pfl->be) {
+ uint64_t current = ldn_be_p(p, width);
+ stn_be_p(p, width, current & value);
+ } else {
+ uint64_t current = ldn_le_p(p, width);
+ stn_le_p(p, width, current & value);
+ }
+ pflash_update(pfl, offset, width);
+ }
+ /*
+ * While programming, status bit DQ7 should hold the opposite
+ * value from how it was programmed.
+ */
+ set_dq7(pfl, ~value);
+ /* Let's pretend write is immediate */
+ if (pfl->bypass)
+ goto do_bypass;
+ goto reset_flash;
+ case 0x90: /* Autoselect */
+ if (pfl->bypass && cmd == 0x00) {
+ /* Unlock bypass reset */
+ goto reset_flash;
+ }
+ /*
+ * We can enter CFI query mode from autoselect mode, but we must
+ * return to autoselect mode after a reset.
+ */
+ if (boff == 0x55 && cmd == 0x98) {
+ /* Enter autoselect CFI query mode */
+ pfl->wcycle = WCYCLE_AUTOSELECT_CFI;
+ pfl->cmd = 0x98;
+ return;
+ }
+ /* fall through */
+ default:
+ trace_pflash_write_invalid(pfl->name, pfl->cmd);
+ goto reset_flash;
+ }
+ case 4:
+ switch (pfl->cmd) {
+ case 0xA0: /* Program */
+ /* Ignore writes while flash data write is occurring */
+ /* As we suppose write is immediate, this should never happen */
+ return;
+ case 0x80: /* Erase */
+ goto check_unlock1;
+ default:
+ /* Should never happen */
+ trace_pflash_write_invalid_state(pfl->name, pfl->cmd, 5);
+ goto reset_flash;
+ }
+ break;
+ case 5:
+ if (pflash_erase_suspend_mode(pfl)) {
+ /* Erasing is not supported in erase suspend mode. */
+ goto reset_flash;
+ }
+ switch (cmd) {
+ case 0x10: /* Chip Erase */
+ if (boff != pfl->unlock_addr0) {
+ trace_pflash_chip_erase_invalid(pfl->name, offset);
+ goto reset_flash;
+ }
+ /* Chip erase */
+ trace_pflash_chip_erase_start(pfl->name);
+ if (!pfl->ro) {
+ memset(pfl->storage, 0xff, pfl->chip_len);
+ pflash_update(pfl, 0, pfl->chip_len);
+ }
+ set_dq7(pfl, 0x00);
+ /* Wait the time specified at CFI address 0x22. */
+ timer_mod(&pfl->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+ (1ULL << pfl->cfi_table[0x22]) * SCALE_MS);
+ break;
+ case 0x30: /* Sector erase */
+ pflash_sector_erase(pfl, offset);
+ break;
+ default:
+ trace_pflash_write_invalid_command(pfl->name, cmd);
+ goto reset_flash;
+ }
+ pfl->cmd = cmd;
+ break;
+ case 6:
+ switch (pfl->cmd) {
+ case 0x10: /* Chip Erase */
+ /* Ignore writes during chip erase */
+ return;
+ case 0x30: /* Sector erase */
+ if (cmd == 0xB0) {
+ /*
+ * If erase suspend happens during the erase timeout (so DQ3 is
+ * 0), then the device suspends erasing immediately. Set the
+ * remaining time to be the total time to erase. Otherwise,
+ * there is a maximum amount of time it can take to enter
+ * suspend mode. Let's ignore that and suspend immediately and
+ * set the remaining time to the actual time remaining on the
+ * timer.
+ */
+ if ((pfl->status & 0x08) == 0) {
+ pfl->erase_time_remaining = pflash_erase_time(pfl);
+ } else {
+ int64_t delta = timer_expire_time_ns(&pfl->timer) -
+ qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+ /* Make sure we have a positive time remaining. */
+ pfl->erase_time_remaining = delta <= 0 ? 1 : delta;
+ }
+ reset_dq3(pfl);
+ timer_del(&pfl->timer);
+ pflash_reset_state_machine(pfl);
+ return;
+ }
+ /*
+ * If DQ3 is 0, additional sector erase commands can be
+ * written and anything else (other than an erase suspend) resets
+ * the device.
+ */
+ if ((pfl->status & 0x08) == 0) {
+ if (cmd == 0x30) {
+ pflash_sector_erase(pfl, offset);
+ } else {
+ goto reset_flash;
+ }
+ }
+ /* Ignore writes during the actual erase. */
+ return;
+ default:
+ /* Should never happen */
+ trace_pflash_write_invalid_state(pfl->name, pfl->cmd, 6);
+ goto reset_flash;
+ }
+ break;
+ /* Special values for CFI queries */
+ case WCYCLE_CFI:
+ case WCYCLE_AUTOSELECT_CFI:
+ trace_pflash_write(pfl->name, "invalid write in CFI query mode");
+ goto reset_flash;
+ default:
+ /* Should never happen */
+ trace_pflash_write(pfl->name, "invalid write state (wc 7)");
+ goto reset_flash;
+ }
+ pfl->wcycle++;
+
+ return;
+
+ /* Reset flash */
+ reset_flash:
+ pfl->bypass = 0;
+ pflash_reset_state_machine(pfl);
+ return;
+
+ do_bypass:
+ pfl->wcycle = 2;
+ pfl->cmd = 0;
+}
+
+static const MemoryRegionOps pflash_cfi02_ops = {
+ .read = pflash_read,
+ .write = pflash_write,
+ .valid.min_access_size = 1,
+ .valid.max_access_size = 4,
+ .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static void pflash_cfi02_fill_cfi_table(PFlashCFI02 *pfl, int nb_regions)
+{
+ /* Hardcoded CFI table (mostly from SG29 Spansion flash) */
+ const uint16_t pri_ofs = 0x40;
+ /* Standard "QRY" string */
+ pfl->cfi_table[0x10] = 'Q';
+ pfl->cfi_table[0x11] = 'R';
+ pfl->cfi_table[0x12] = 'Y';
+ /* Command set (AMD/Fujitsu) */
+ pfl->cfi_table[0x13] = 0x02;
+ pfl->cfi_table[0x14] = 0x00;
+ /* Primary extended table address */
+ pfl->cfi_table[0x15] = pri_ofs;
+ pfl->cfi_table[0x16] = pri_ofs >> 8;
+ /* Alternate command set (none) */
+ pfl->cfi_table[0x17] = 0x00;
+ pfl->cfi_table[0x18] = 0x00;
+ /* Alternate extended table (none) */
+ pfl->cfi_table[0x19] = 0x00;
+ pfl->cfi_table[0x1A] = 0x00;
+ /* Vcc min */
+ pfl->cfi_table[0x1B] = 0x27;
+ /* Vcc max */
+ pfl->cfi_table[0x1C] = 0x36;
+ /* Vpp min (no Vpp pin) */
+ pfl->cfi_table[0x1D] = 0x00;
+ /* Vpp max (no Vpp pin) */
+ pfl->cfi_table[0x1E] = 0x00;
+ /* Timeout per single byte/word write (128 ms) */
+ pfl->cfi_table[0x1F] = 0x07;
+ /* Timeout for min size buffer write (NA) */
+ pfl->cfi_table[0x20] = 0x00;
+ /* Typical timeout for block erase (512 ms) */
+ pfl->cfi_table[0x21] = 0x09;
+ /* Typical timeout for full chip erase (4096 ms) */
+ pfl->cfi_table[0x22] = 0x0C;
+ /* Reserved */
+ pfl->cfi_table[0x23] = 0x01;
+ /* Max timeout for buffer write (NA) */
+ pfl->cfi_table[0x24] = 0x00;
+ /* Max timeout for block erase */
+ pfl->cfi_table[0x25] = 0x0A;
+ /* Max timeout for chip erase */
+ pfl->cfi_table[0x26] = 0x0D;
+ /* Device size */
+ pfl->cfi_table[0x27] = ctz32(pfl->chip_len);
+ /* Flash device interface (8 & 16 bits) */
+ pfl->cfi_table[0x28] = 0x02;
+ pfl->cfi_table[0x29] = 0x00;
+ /* Max number of bytes in multi-bytes write */
+ /*
+ * XXX: disable buffered write as it's not supported
+ * pfl->cfi_table[0x2A] = 0x05;
+ */
+ pfl->cfi_table[0x2A] = 0x00;
+ pfl->cfi_table[0x2B] = 0x00;
+ /* Number of erase block regions */
+ pfl->cfi_table[0x2c] = nb_regions;
+ /* Erase block regions */
+ for (int i = 0; i < nb_regions; ++i) {
+ uint32_t sector_len_per_device = pfl->sector_len[i];
+ pfl->cfi_table[0x2d + 4 * i] = pfl->nb_blocs[i] - 1;
+ pfl->cfi_table[0x2e + 4 * i] = (pfl->nb_blocs[i] - 1) >> 8;
+ pfl->cfi_table[0x2f + 4 * i] = sector_len_per_device >> 8;
+ pfl->cfi_table[0x30 + 4 * i] = sector_len_per_device >> 16;
+ }
+ assert(0x2c + 4 * nb_regions < pri_ofs);
+
+ /* Extended */
+ pfl->cfi_table[0x00 + pri_ofs] = 'P';
+ pfl->cfi_table[0x01 + pri_ofs] = 'R';
+ pfl->cfi_table[0x02 + pri_ofs] = 'I';
+
+ /* Extended version 1.0 */
+ pfl->cfi_table[0x03 + pri_ofs] = '1';
+ pfl->cfi_table[0x04 + pri_ofs] = '0';
+
+ /* Address sensitive unlock required. */
+ pfl->cfi_table[0x05 + pri_ofs] = 0x00;
+ /* Erase suspend to read/write. */
+ pfl->cfi_table[0x06 + pri_ofs] = 0x02;
+ /* Sector protect not supported. */
+ pfl->cfi_table[0x07 + pri_ofs] = 0x00;
+ /* Temporary sector unprotect not supported. */
+ pfl->cfi_table[0x08 + pri_ofs] = 0x00;
+
+ /* Sector protect/unprotect scheme. */
+ pfl->cfi_table[0x09 + pri_ofs] = 0x00;
+
+ /* Simultaneous operation not supported. */
+ pfl->cfi_table[0x0a + pri_ofs] = 0x00;
+ /* Burst mode not supported. */
+ pfl->cfi_table[0x0b + pri_ofs] = 0x00;
+ /* Page mode not supported. */
+ pfl->cfi_table[0x0c + pri_ofs] = 0x00;
+ assert(0x0c + pri_ofs < ARRAY_SIZE(pfl->cfi_table));
+}
+
+static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
+{
+ ERRP_GUARD();
+ PFlashCFI02 *pfl = PFLASH_CFI02(dev);
+ int ret;
+
+ if (pfl->uniform_sector_len == 0 && pfl->sector_len[0] == 0) {
+ error_setg(errp, "attribute \"sector-length\" not specified or zero.");
+ return;
+ }
+ if (pfl->uniform_nb_blocs == 0 && pfl->nb_blocs[0] == 0) {
+ error_setg(errp, "attribute \"num-blocks\" not specified or zero.");
+ return;
+ }
+ if (pfl->name == NULL) {
+ error_setg(errp, "attribute \"name\" not specified.");
+ return;
+ }
+
+ int nb_regions;
+ pfl->chip_len = 0;
+ pfl->total_sectors = 0;
+ for (nb_regions = 0; nb_regions < PFLASH_MAX_ERASE_REGIONS; ++nb_regions) {
+ if (pfl->nb_blocs[nb_regions] == 0) {
+ break;
+ }
+ pfl->total_sectors += pfl->nb_blocs[nb_regions];
+ uint64_t sector_len_per_device = pfl->sector_len[nb_regions];
+
+ /*
+ * The size of each flash sector must be a power of 2 and it must be
+ * aligned at the same power of 2.
+ */
+ if (sector_len_per_device & 0xff ||
+ sector_len_per_device >= (1 << 24) ||
+ !is_power_of_2(sector_len_per_device))
+ {
+ error_setg(errp, "unsupported configuration: "
+ "sector length[%d] per device = %" PRIx64 ".",
+ nb_regions, sector_len_per_device);
+ return;
+ }
+ if (pfl->chip_len & (sector_len_per_device - 1)) {
+ error_setg(errp, "unsupported configuration: "
+ "flash region %d not correctly aligned.",
+ nb_regions);
+ return;
+ }
+
+ pfl->chip_len += (uint64_t)pfl->sector_len[nb_regions] *
+ pfl->nb_blocs[nb_regions];
+ }
+
+ uint64_t uniform_len = (uint64_t)pfl->uniform_nb_blocs *
+ pfl->uniform_sector_len;
+ if (nb_regions == 0) {
+ nb_regions = 1;
+ pfl->nb_blocs[0] = pfl->uniform_nb_blocs;
+ pfl->sector_len[0] = pfl->uniform_sector_len;
+ pfl->chip_len = uniform_len;
+ pfl->total_sectors = pfl->uniform_nb_blocs;
+ } else if (uniform_len != 0 && uniform_len != pfl->chip_len) {
+ error_setg(errp, "\"num-blocks\"*\"sector-length\" "
+ "different from \"num-blocks0\"*\'sector-length0\" + ... + "
+ "\"num-blocks3\"*\"sector-length3\"");
+ return;
+ }
+
+ memory_region_init_rom_device(&pfl->orig_mem, OBJECT(pfl),
+ &pflash_cfi02_ops, pfl, pfl->name,
+ pfl->chip_len, errp);
+ if (*errp) {
+ return;
+ }
+
+ pfl->storage = memory_region_get_ram_ptr(&pfl->orig_mem);
+
+ if (pfl->blk) {
+ uint64_t perm;
+ pfl->ro = !blk_supports_write_perm(pfl->blk);
+ perm = BLK_PERM_CONSISTENT_READ | (pfl->ro ? 0 : BLK_PERM_WRITE);
+ ret = blk_set_perm(pfl->blk, perm, BLK_PERM_ALL, errp);
+ if (ret < 0) {
+ return;
+ }
+ } else {
+ pfl->ro = 0;
+ }
+
+ if (pfl->blk) {
+ if (!blk_check_size_and_read_all(pfl->blk, pfl->storage,
+ pfl->chip_len, errp)) {
+ vmstate_unregister_ram(&pfl->orig_mem, DEVICE(pfl));
+ return;
+ }
+ }
+
+ /* Only 11 bits are used in the comparison. */
+ pfl->unlock_addr0 &= 0x7FF;
+ pfl->unlock_addr1 &= 0x7FF;
+
+ /* Allocate memory for a bitmap for sectors being erased. */
+ pfl->sector_erase_map = bitmap_new(pfl->total_sectors);
+
+ pfl->rom_mode = true;
+ if (pfl->mappings > 1) {
+ pflash_setup_mappings(pfl);
+ sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem);
+ } else {
+ sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->orig_mem);
+ }
+
+ timer_init_ns(&pfl->timer, QEMU_CLOCK_VIRTUAL, pflash_timer, pfl);
+ pfl->status = 0;
+
+ pflash_cfi02_fill_cfi_table(pfl, nb_regions);
+}
+
+static void pflash_cfi02_reset(DeviceState *dev)
+{
+ PFlashCFI02 *pfl = PFLASH_CFI02(dev);
+
+ pflash_reset_state_machine(pfl);
+}
+
+static Property pflash_cfi02_properties[] = {
+ DEFINE_PROP_DRIVE("drive", PFlashCFI02, blk),
+ DEFINE_PROP_UINT32("num-blocks", PFlashCFI02, uniform_nb_blocs, 0),
+ DEFINE_PROP_UINT32("sector-length", PFlashCFI02, uniform_sector_len, 0),
+ DEFINE_PROP_UINT32("num-blocks0", PFlashCFI02, nb_blocs[0], 0),
+ DEFINE_PROP_UINT32("sector-length0", PFlashCFI02, sector_len[0], 0),
+ DEFINE_PROP_UINT32("num-blocks1", PFlashCFI02, nb_blocs[1], 0),
+ DEFINE_PROP_UINT32("sector-length1", PFlashCFI02, sector_len[1], 0),
+ DEFINE_PROP_UINT32("num-blocks2", PFlashCFI02, nb_blocs[2], 0),
+ DEFINE_PROP_UINT32("sector-length2", PFlashCFI02, sector_len[2], 0),
+ DEFINE_PROP_UINT32("num-blocks3", PFlashCFI02, nb_blocs[3], 0),
+ DEFINE_PROP_UINT32("sector-length3", PFlashCFI02, sector_len[3], 0),
+ DEFINE_PROP_UINT8("width", PFlashCFI02, width, 0),
+ DEFINE_PROP_UINT8("mappings", PFlashCFI02, mappings, 0),
+ DEFINE_PROP_UINT8("big-endian", PFlashCFI02, be, 0),
+ DEFINE_PROP_UINT16("id0", PFlashCFI02, ident0, 0),
+ DEFINE_PROP_UINT16("id1", PFlashCFI02, ident1, 0),
+ DEFINE_PROP_UINT16("id2", PFlashCFI02, ident2, 0),
+ DEFINE_PROP_UINT16("id3", PFlashCFI02, ident3, 0),
+ DEFINE_PROP_UINT16("unlock-addr0", PFlashCFI02, unlock_addr0, 0),
+ DEFINE_PROP_UINT16("unlock-addr1", PFlashCFI02, unlock_addr1, 0),
+ DEFINE_PROP_STRING("name", PFlashCFI02, name),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void pflash_cfi02_unrealize(DeviceState *dev)
+{
+ PFlashCFI02 *pfl = PFLASH_CFI02(dev);
+ timer_del(&pfl->timer);
+ g_free(pfl->sector_erase_map);
+}
+
+static void pflash_cfi02_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ dc->realize = pflash_cfi02_realize;
+ dc->reset = pflash_cfi02_reset;
+ dc->unrealize = pflash_cfi02_unrealize;
+ device_class_set_props(dc, pflash_cfi02_properties);
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+}
+
+static const TypeInfo pflash_cfi02_info = {
+ .name = TYPE_PFLASH_CFI02,
+ .parent = TYPE_SYS_BUS_DEVICE,
+ .instance_size = sizeof(PFlashCFI02),
+ .class_init = pflash_cfi02_class_init,
+};
+
+static void pflash_cfi02_register_types(void)
+{
+ type_register_static(&pflash_cfi02_info);
+}
+
+type_init(pflash_cfi02_register_types)
+
+PFlashCFI02 *pflash_cfi02_register(hwaddr base,
+ const char *name,
+ hwaddr size,
+ BlockBackend *blk,
+ uint32_t sector_len,
+ int nb_mappings, int width,
+ uint16_t id0, uint16_t id1,
+ uint16_t id2, uint16_t id3,
+ uint16_t unlock_addr0,
+ uint16_t unlock_addr1,
+ int be)
+{
+ DeviceState *dev = qdev_new(TYPE_PFLASH_CFI02);
+
+ if (blk) {
+ qdev_prop_set_drive(dev, "drive", blk);
+ }
+ assert(QEMU_IS_ALIGNED(size, sector_len));
+ qdev_prop_set_uint32(dev, "num-blocks", size / sector_len);
+ qdev_prop_set_uint32(dev, "sector-length", sector_len);
+ qdev_prop_set_uint8(dev, "width", width);
+ qdev_prop_set_uint8(dev, "mappings", nb_mappings);
+ qdev_prop_set_uint8(dev, "big-endian", !!be);
+ qdev_prop_set_uint16(dev, "id0", id0);
+ qdev_prop_set_uint16(dev, "id1", id1);
+ qdev_prop_set_uint16(dev, "id2", id2);
+ qdev_prop_set_uint16(dev, "id3", id3);
+ qdev_prop_set_uint16(dev, "unlock-addr0", unlock_addr0);
+ qdev_prop_set_uint16(dev, "unlock-addr1", unlock_addr1);
+ qdev_prop_set_string(dev, "name", name);
+ sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);
+
+ sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base);
+ return PFLASH_CFI02(dev);
+}
diff --git a/hw/block/swim.c b/hw/block/swim.c
new file mode 100644
index 00000000..333da08c
--- /dev/null
+++ b/hw/block/swim.c
@@ -0,0 +1,491 @@
+/*
+ * QEMU Macintosh floppy disk controller emulator (SWIM)
+ *
+ * Copyright (c) 2014-2018 Laurent Vivier <laurent@vivier.eu>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Only the basic support: it allows to switch from IWM (Integrated WOZ
+ * Machine) mode to the SWIM mode and makes the linux driver happy.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/main-loop.h"
+#include "qapi/error.h"
+#include "sysemu/block-backend.h"
+#include "hw/sysbus.h"
+#include "migration/vmstate.h"
+#include "hw/block/block.h"
+#include "hw/block/swim.h"
+#include "hw/qdev-properties.h"
+
+/* IWM registers */
+
+#define IWM_PH0L 0
+#define IWM_PH0H 1
+#define IWM_PH1L 2
+#define IWM_PH1H 3
+#define IWM_PH2L 4
+#define IWM_PH2H 5
+#define IWM_PH3L 6
+#define IWM_PH3H 7
+#define IWM_MTROFF 8
+#define IWM_MTRON 9
+#define IWM_INTDRIVE 10
+#define IWM_EXTDRIVE 11
+#define IWM_Q6L 12
+#define IWM_Q6H 13
+#define IWM_Q7L 14
+#define IWM_Q7H 15
+
+/* SWIM registers */
+
+#define SWIM_WRITE_DATA 0
+#define SWIM_WRITE_MARK 1
+#define SWIM_WRITE_CRC 2
+#define SWIM_WRITE_PARAMETER 3
+#define SWIM_WRITE_PHASE 4
+#define SWIM_WRITE_SETUP 5
+#define SWIM_WRITE_MODE0 6
+#define SWIM_WRITE_MODE1 7
+
+#define SWIM_READ_DATA 8
+#define SWIM_READ_MARK 9
+#define SWIM_READ_ERROR 10
+#define SWIM_READ_PARAMETER 11
+#define SWIM_READ_PHASE 12
+#define SWIM_READ_SETUP 13
+#define SWIM_READ_STATUS 14
+#define SWIM_READ_HANDSHAKE 15
+
+#define REG_SHIFT 9
+
+#define SWIM_MODE_IWM 0
+#define SWIM_MODE_SWIM 1
+
+/* bits in phase register */
+
+#define SWIM_SEEK_NEGATIVE 0x074
+#define SWIM_STEP 0x071
+#define SWIM_MOTOR_ON 0x072
+#define SWIM_MOTOR_OFF 0x076
+#define SWIM_INDEX 0x073
+#define SWIM_EJECT 0x077
+#define SWIM_SETMFM 0x171
+#define SWIM_SETGCR 0x175
+#define SWIM_RELAX 0x033
+#define SWIM_LSTRB 0x008
+#define SWIM_CA_MASK 0x077
+
+/* Select values for swim_select and swim_readbit */
+
+#define SWIM_READ_DATA_0 0x074
+#define SWIM_TWOMEG_DRIVE 0x075
+#define SWIM_SINGLE_SIDED 0x076
+#define SWIM_DRIVE_PRESENT 0x077
+#define SWIM_DISK_IN 0x170
+#define SWIM_WRITE_PROT 0x171
+#define SWIM_TRACK_ZERO 0x172
+#define SWIM_TACHO 0x173
+#define SWIM_READ_DATA_1 0x174
+#define SWIM_MFM_MODE 0x175
+#define SWIM_SEEK_COMPLETE 0x176
+#define SWIM_ONEMEG_MEDIA 0x177
+
+/* Bits in handshake register */
+
+#define SWIM_MARK_BYTE 0x01
+#define SWIM_CRC_ZERO 0x02
+#define SWIM_RDDATA 0x04
+#define SWIM_SENSE 0x08
+#define SWIM_MOTEN 0x10
+#define SWIM_ERROR 0x20
+#define SWIM_DAT2BYTE 0x40
+#define SWIM_DAT1BYTE 0x80
+
+/* bits in setup register */
+
+#define SWIM_S_INV_WDATA 0x01
+#define SWIM_S_3_5_SELECT 0x02
+#define SWIM_S_GCR 0x04
+#define SWIM_S_FCLK_DIV2 0x08
+#define SWIM_S_ERROR_CORR 0x10
+#define SWIM_S_IBM_DRIVE 0x20
+#define SWIM_S_GCR_WRITE 0x40
+#define SWIM_S_TIMEOUT 0x80
+
+/* bits in mode register */
+
+#define SWIM_CLFIFO 0x01
+#define SWIM_ENBL1 0x02
+#define SWIM_ENBL2 0x04
+#define SWIM_ACTION 0x08
+#define SWIM_WRITE_MODE 0x10
+#define SWIM_HEDSEL 0x20
+#define SWIM_MOTON 0x80
+
+static void fd_recalibrate(FDrive *drive)
+{
+}
+
+static void swim_change_cb(void *opaque, bool load, Error **errp)
+{
+ FDrive *drive = opaque;
+
+ if (!load) {
+ blk_set_perm(drive->blk, 0, BLK_PERM_ALL, &error_abort);
+ } else {
+ if (!blkconf_apply_backend_options(drive->conf,
+ !blk_supports_write_perm(drive->blk),
+ false, errp)) {
+ return;
+ }
+ }
+}
+
+static const BlockDevOps swim_block_ops = {
+ .change_media_cb = swim_change_cb,
+};
+
+static Property swim_drive_properties[] = {
+ DEFINE_PROP_INT32("unit", SWIMDrive, unit, -1),
+ DEFINE_BLOCK_PROPERTIES(SWIMDrive, conf),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void swim_drive_realize(DeviceState *qdev, Error **errp)
+{
+ SWIMDrive *dev = SWIM_DRIVE(qdev);
+ SWIMBus *bus = SWIM_BUS(qdev->parent_bus);
+ FDrive *drive;
+ int ret;
+
+ if (dev->unit == -1) {
+ for (dev->unit = 0; dev->unit < SWIM_MAX_FD; dev->unit++) {
+ drive = &bus->ctrl->drives[dev->unit];
+ if (!drive->blk) {
+ break;
+ }
+ }
+ }
+
+ if (dev->unit >= SWIM_MAX_FD) {
+ error_setg(errp, "Can't create floppy unit %d, bus supports "
+ "only %d units", dev->unit, SWIM_MAX_FD);
+ return;
+ }
+
+ drive = &bus->ctrl->drives[dev->unit];
+ if (drive->blk) {
+ error_setg(errp, "Floppy unit %d is in use", dev->unit);
+ return;
+ }
+
+ if (!dev->conf.blk) {
+ /* Anonymous BlockBackend for an empty drive */
+ dev->conf.blk = blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL);
+ ret = blk_attach_dev(dev->conf.blk, qdev);
+ assert(ret == 0);
+ }
+
+ if (!blkconf_blocksizes(&dev->conf, errp)) {
+ return;
+ }
+
+ if (dev->conf.logical_block_size != 512 ||
+ dev->conf.physical_block_size != 512)
+ {
+ error_setg(errp, "Physical and logical block size must "
+ "be 512 for floppy");
+ return;
+ }
+
+ /*
+ * rerror/werror aren't supported by fdc and therefore not even registered
+ * with qdev. So set the defaults manually before they are used in
+ * blkconf_apply_backend_options().
+ */
+ dev->conf.rerror = BLOCKDEV_ON_ERROR_AUTO;
+ dev->conf.werror = BLOCKDEV_ON_ERROR_AUTO;
+
+ if (!blkconf_apply_backend_options(&dev->conf,
+ !blk_supports_write_perm(dev->conf.blk),
+ false, errp)) {
+ return;
+ }
+
+ /*
+ * 'enospc' is the default for -drive, 'report' is what blk_new() gives us
+ * for empty drives.
+ */
+ if (blk_get_on_error(dev->conf.blk, 0) != BLOCKDEV_ON_ERROR_ENOSPC &&
+ blk_get_on_error(dev->conf.blk, 0) != BLOCKDEV_ON_ERROR_REPORT) {
+ error_setg(errp, "fdc doesn't support drive option werror");
+ return;
+ }
+ if (blk_get_on_error(dev->conf.blk, 1) != BLOCKDEV_ON_ERROR_REPORT) {
+ error_setg(errp, "fdc doesn't support drive option rerror");
+ return;
+ }
+
+ drive->conf = &dev->conf;
+ drive->blk = dev->conf.blk;
+ drive->swimctrl = bus->ctrl;
+
+ blk_set_dev_ops(drive->blk, &swim_block_ops, drive);
+}
+
+static void swim_drive_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *k = DEVICE_CLASS(klass);
+ k->realize = swim_drive_realize;
+ set_bit(DEVICE_CATEGORY_STORAGE, k->categories);
+ k->bus_type = TYPE_SWIM_BUS;
+ device_class_set_props(k, swim_drive_properties);
+ k->desc = "virtual SWIM drive";
+}
+
+static const TypeInfo swim_drive_info = {
+ .name = TYPE_SWIM_DRIVE,
+ .parent = TYPE_DEVICE,
+ .instance_size = sizeof(SWIMDrive),
+ .class_init = swim_drive_class_init,
+};
+
+static const TypeInfo swim_bus_info = {
+ .name = TYPE_SWIM_BUS,
+ .parent = TYPE_BUS,
+ .instance_size = sizeof(SWIMBus),
+};
+
+static void iwmctrl_write(void *opaque, hwaddr reg, uint64_t value,
+ unsigned size)
+{
+ SWIMCtrl *swimctrl = opaque;
+
+ reg >>= REG_SHIFT;
+
+ swimctrl->regs[reg >> 1] = reg & 1;
+
+ if (swimctrl->regs[IWM_Q6] &&
+ swimctrl->regs[IWM_Q7]) {
+ if (swimctrl->regs[IWM_MTR]) {
+ /* data register */
+ swimctrl->iwm_data = value;
+ } else {
+ /* mode register */
+ swimctrl->iwm_mode = value;
+ /* detect sequence to switch from IWM mode to SWIM mode */
+ switch (swimctrl->iwm_switch) {
+ case 0:
+ if (value == 0x57) {
+ swimctrl->iwm_switch++;
+ }
+ break;
+ case 1:
+ if (value == 0x17) {
+ swimctrl->iwm_switch++;
+ }
+ break;
+ case 2:
+ if (value == 0x57) {
+ swimctrl->iwm_switch++;
+ }
+ break;
+ case 3:
+ if (value == 0x57) {
+ swimctrl->mode = SWIM_MODE_SWIM;
+ swimctrl->iwm_switch = 0;
+ }
+ break;
+ }
+ }
+ }
+}
+
+static uint64_t iwmctrl_read(void *opaque, hwaddr reg, unsigned size)
+{
+ SWIMCtrl *swimctrl = opaque;
+
+ reg >>= REG_SHIFT;
+
+ swimctrl->regs[reg >> 1] = reg & 1;
+
+ return 0;
+}
+
+static void swimctrl_write(void *opaque, hwaddr reg, uint64_t value,
+ unsigned size)
+{
+ SWIMCtrl *swimctrl = opaque;
+
+ if (swimctrl->mode == SWIM_MODE_IWM) {
+ iwmctrl_write(opaque, reg, value, size);
+ return;
+ }
+
+ reg >>= REG_SHIFT;
+
+ switch (reg) {
+ case SWIM_WRITE_PHASE:
+ swimctrl->swim_phase = value;
+ break;
+ case SWIM_WRITE_MODE0:
+ swimctrl->swim_mode &= ~value;
+ break;
+ case SWIM_WRITE_MODE1:
+ swimctrl->swim_mode |= value;
+ break;
+ case SWIM_WRITE_DATA:
+ case SWIM_WRITE_MARK:
+ case SWIM_WRITE_CRC:
+ case SWIM_WRITE_PARAMETER:
+ case SWIM_WRITE_SETUP:
+ break;
+ }
+}
+
+static uint64_t swimctrl_read(void *opaque, hwaddr reg, unsigned size)
+{
+ SWIMCtrl *swimctrl = opaque;
+ uint32_t value = 0;
+
+ if (swimctrl->mode == SWIM_MODE_IWM) {
+ return iwmctrl_read(opaque, reg, size);
+ }
+
+ reg >>= REG_SHIFT;
+
+ switch (reg) {
+ case SWIM_READ_PHASE:
+ value = swimctrl->swim_phase;
+ break;
+ case SWIM_READ_HANDSHAKE:
+ if (swimctrl->swim_phase == SWIM_DRIVE_PRESENT) {
+ /* always answer "no drive present" */
+ value = SWIM_SENSE;
+ }
+ break;
+ case SWIM_READ_DATA:
+ case SWIM_READ_MARK:
+ case SWIM_READ_ERROR:
+ case SWIM_READ_PARAMETER:
+ case SWIM_READ_SETUP:
+ case SWIM_READ_STATUS:
+ break;
+ }
+
+ return value;
+}
+
+static const MemoryRegionOps swimctrl_mem_ops = {
+ .write = swimctrl_write,
+ .read = swimctrl_read,
+ .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static void sysbus_swim_reset(DeviceState *d)
+{
+ Swim *sys = SWIM(d);
+ SWIMCtrl *ctrl = &sys->ctrl;
+ int i;
+
+ ctrl->mode = 0;
+ ctrl->iwm_switch = 0;
+ for (i = 0; i < 8; i++) {
+ ctrl->regs[i] = 0;
+ }
+ ctrl->iwm_data = 0;
+ ctrl->iwm_mode = 0;
+ ctrl->swim_phase = 0;
+ ctrl->swim_mode = 0;
+ for (i = 0; i < SWIM_MAX_FD; i++) {
+ fd_recalibrate(&ctrl->drives[i]);
+ }
+}
+
+static void sysbus_swim_init(Object *obj)
+{
+ SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
+ Swim *sbs = SWIM(obj);
+ SWIMCtrl *swimctrl = &sbs->ctrl;
+
+ memory_region_init_io(&swimctrl->iomem, obj, &swimctrl_mem_ops, swimctrl,
+ "swim", 0x2000);
+ sysbus_init_mmio(sbd, &swimctrl->iomem);
+}
+
+static void sysbus_swim_realize(DeviceState *dev, Error **errp)
+{
+ Swim *sys = SWIM(dev);
+ SWIMCtrl *swimctrl = &sys->ctrl;
+
+ qbus_init(&swimctrl->bus, sizeof(SWIMBus), TYPE_SWIM_BUS, dev, NULL);
+ swimctrl->bus.ctrl = swimctrl;
+}
+
+static const VMStateDescription vmstate_fdrive = {
+ .name = "fdrive",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .fields = (VMStateField[]) {
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+static const VMStateDescription vmstate_swim = {
+ .name = "swim",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .fields = (VMStateField[]) {
+ VMSTATE_INT32(mode, SWIMCtrl),
+ /* IWM mode */
+ VMSTATE_INT32(iwm_switch, SWIMCtrl),
+ VMSTATE_UINT16_ARRAY(regs, SWIMCtrl, 8),
+ VMSTATE_UINT8(iwm_data, SWIMCtrl),
+ VMSTATE_UINT8(iwm_mode, SWIMCtrl),
+ /* SWIM mode */
+ VMSTATE_UINT8(swim_phase, SWIMCtrl),
+ VMSTATE_UINT8(swim_mode, SWIMCtrl),
+ /* Drives */
+ VMSTATE_STRUCT_ARRAY(drives, SWIMCtrl, SWIM_MAX_FD, 1,
+ vmstate_fdrive, FDrive),
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+static const VMStateDescription vmstate_sysbus_swim = {
+ .name = "SWIM",
+ .version_id = 1,
+ .fields = (VMStateField[]) {
+ VMSTATE_STRUCT(ctrl, Swim, 0, vmstate_swim, SWIMCtrl),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static void sysbus_swim_class_init(ObjectClass *oc, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(oc);
+
+ dc->realize = sysbus_swim_realize;
+ dc->reset = sysbus_swim_reset;
+ dc->vmsd = &vmstate_sysbus_swim;
+}
+
+static const TypeInfo sysbus_swim_info = {
+ .name = TYPE_SWIM,
+ .parent = TYPE_SYS_BUS_DEVICE,
+ .instance_size = sizeof(Swim),
+ .instance_init = sysbus_swim_init,
+ .class_init = sysbus_swim_class_init,
+};
+
+static void swim_register_types(void)
+{
+ type_register_static(&sysbus_swim_info);
+ type_register_static(&swim_bus_info);
+ type_register_static(&swim_drive_info);
+}
+
+type_init(swim_register_types)
diff --git a/hw/block/tc58128.c b/hw/block/tc58128.c
new file mode 100644
index 00000000..bfc27ad8
--- /dev/null
+++ b/hw/block/tc58128.c
@@ -0,0 +1,208 @@
+/*
+ * TC58128 NAND EEPROM emulation
+ *
+ * Copyright (c) 2005 Samuel Tardieu
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ * SPDX-License-Identifier: MIT
+ */
+#include "qemu/osdep.h"
+#include "qemu/units.h"
+#include "hw/sh4/sh.h"
+#include "hw/loader.h"
+#include "sysemu/qtest.h"
+#include "qemu/error-report.h"
+
+#define CE1 0x0100
+#define CE2 0x0200
+#define RE 0x0400
+#define WE 0x0800
+#define ALE 0x1000
+#define CLE 0x2000
+#define RDY1 0x4000
+#define RDY2 0x8000
+#define RDY(n) ((n) == 0 ? RDY1 : RDY2)
+
+typedef enum { WAIT, READ1, READ2, READ3 } state_t;
+
+typedef struct {
+ uint8_t *flash_contents;
+ state_t state;
+ uint32_t address;
+ uint8_t address_cycle;
+} tc58128_dev;
+
+static tc58128_dev tc58128_devs[2];
+
+#define FLASH_SIZE (16 * MiB)
+
+static void init_dev(tc58128_dev * dev, const char *filename)
+{
+ int ret, blocks;
+
+ dev->state = WAIT;
+ dev->flash_contents = g_malloc(FLASH_SIZE);
+ memset(dev->flash_contents, 0xff, FLASH_SIZE);
+ if (filename) {
+ /* Load flash image skipping the first block */
+ ret = load_image_size(filename, dev->flash_contents + 528 * 32,
+ FLASH_SIZE - 528 * 32);
+ if (ret < 0) {
+ if (!qtest_enabled()) {
+ error_report("Could not load flash image %s", filename);
+ exit(1);
+ }
+ } else {
+ /* Build first block with number of blocks */
+ blocks = DIV_ROUND_UP(ret, 528 * 32);
+ dev->flash_contents[0] = blocks & 0xff;
+ dev->flash_contents[1] = (blocks >> 8) & 0xff;
+ dev->flash_contents[2] = (blocks >> 16) & 0xff;
+ dev->flash_contents[3] = (blocks >> 24) & 0xff;
+ fprintf(stderr, "loaded %d bytes for %s into flash\n", ret,
+ filename);
+ }
+ }
+}
+
+static void handle_command(tc58128_dev * dev, uint8_t command)
+{
+ switch (command) {
+ case 0xff:
+ fprintf(stderr, "reset flash device\n");
+ dev->state = WAIT;
+ break;
+ case 0x00:
+ fprintf(stderr, "read mode 1\n");
+ dev->state = READ1;
+ dev->address_cycle = 0;
+ break;
+ case 0x01:
+ fprintf(stderr, "read mode 2\n");
+ dev->state = READ2;
+ dev->address_cycle = 0;
+ break;
+ case 0x50:
+ fprintf(stderr, "read mode 3\n");
+ dev->state = READ3;
+ dev->address_cycle = 0;
+ break;
+ default:
+ fprintf(stderr, "unknown flash command 0x%02x\n", command);
+ abort();
+ }
+}
+
+static void handle_address(tc58128_dev * dev, uint8_t data)
+{
+ switch (dev->state) {
+ case READ1:
+ case READ2:
+ case READ3:
+ switch (dev->address_cycle) {
+ case 0:
+ dev->address = data;
+ if (dev->state == READ2)
+ dev->address |= 0x100;
+ else if (dev->state == READ3)
+ dev->address |= 0x200;
+ break;
+ case 1:
+ dev->address += data * 528 * 0x100;
+ break;
+ case 2:
+ dev->address += data * 528;
+ fprintf(stderr, "address pointer in flash: 0x%08x\n",
+ dev->address);
+ break;
+ default:
+ /* Invalid data */
+ abort();
+ }
+ dev->address_cycle++;
+ break;
+ default:
+ abort();
+ }
+}
+
+static uint8_t handle_read(tc58128_dev * dev)
+{
+#if 0
+ if (dev->address % 0x100000 == 0)
+ fprintf(stderr, "reading flash at address 0x%08x\n", dev->address);
+#endif
+ return dev->flash_contents[dev->address++];
+}
+
+/* We never mark the device as busy, so interrupts cannot be triggered
+ XXXXX */
+
+static int tc58128_cb(uint16_t porta, uint16_t portb,
+ uint16_t * periph_pdtra, uint16_t * periph_portadir,
+ uint16_t * periph_pdtrb, uint16_t * periph_portbdir)
+{
+ int dev;
+
+ if ((porta & CE1) == 0)
+ dev = 0;
+ else if ((porta & CE2) == 0)
+ dev = 1;
+ else
+ return 0; /* No device selected */
+
+ if ((porta & RE) && (porta & WE)) {
+ /* Nothing to do, assert ready and return to input state */
+ *periph_portadir &= 0xff00;
+ *periph_portadir |= RDY(dev);
+ *periph_pdtra |= RDY(dev);
+ return 1;
+ }
+
+ if (porta & CLE) {
+ /* Command */
+ assert((porta & WE) == 0);
+ handle_command(&tc58128_devs[dev], porta & 0x00ff);
+ } else if (porta & ALE) {
+ assert((porta & WE) == 0);
+ handle_address(&tc58128_devs[dev], porta & 0x00ff);
+ } else if ((porta & RE) == 0) {
+ *periph_portadir |= 0x00ff;
+ *periph_pdtra &= 0xff00;
+ *periph_pdtra |= handle_read(&tc58128_devs[dev]);
+ } else {
+ abort();
+ }
+ return 1;
+}
+
+static sh7750_io_device tc58128 = {
+ RE | WE, /* Port A triggers */
+ 0, /* Port B triggers */
+ tc58128_cb /* Callback */
+};
+
+int tc58128_init(struct SH7750State *s, const char *zone1, const char *zone2)
+{
+ init_dev(&tc58128_devs[0], zone1);
+ init_dev(&tc58128_devs[1], zone2);
+ return sh7750_register_io_device(s, &tc58128);
+}
diff --git a/hw/block/trace-events b/hw/block/trace-events
new file mode 100644
index 00000000..2c45a62b
--- /dev/null
+++ b/hw/block/trace-events
@@ -0,0 +1,85 @@
+# See docs/devel/tracing.rst for syntax documentation.
+
+# fdc.c
+fdc_ioport_read(uint8_t reg, uint8_t value) "read reg 0x%02x val 0x%02x"
+fdc_ioport_write(uint8_t reg, uint8_t value) "write reg 0x%02x val 0x%02x"
+
+# fdc-sysbus.c
+fdctrl_tc_pulse(int level) "TC pulse: %u"
+
+# pflash_cfi01.c
+# pflash_cfi02.c
+pflash_chip_erase_invalid(const char *name, uint64_t offset) "%s: chip erase: invalid address 0x%" PRIx64
+pflash_chip_erase_start(const char *name) "%s: start chip erase"
+pflash_data_read(const char *name, uint64_t offset, unsigned size, uint32_t value) "%s: data offset:0x%04"PRIx64" size:%u value:0x%04x"
+pflash_data_write(const char *name, uint64_t offset, unsigned size, uint32_t value, uint64_t counter) "%s: data offset:0x%04"PRIx64" size:%u value:0x%04x counter:0x%016"PRIx64
+pflash_device_id(const char *name, uint16_t id) "%s: read device ID: 0x%04x"
+pflash_device_info(const char *name, uint64_t offset) "%s: read device information offset:0x%04" PRIx64
+pflash_erase_complete(const char *name) "%s: sector erase complete"
+pflash_erase_timeout(const char *name, int count) "%s: erase timeout fired; erasing %d sectors"
+pflash_io_read(const char *name, uint64_t offset, unsigned int size, uint32_t value, uint8_t cmd, uint8_t wcycle) "%s: offset:0x%04" PRIx64 " size:%u value:0x%04x cmd:0x%02x wcycle:%u"
+pflash_io_write(const char *name, uint64_t offset, unsigned int size, uint32_t value, uint8_t wcycle) "%s: offset:0x%04"PRIx64" size:%u value:0x%04x wcycle:%u"
+pflash_manufacturer_id(const char *name, uint16_t id) "%s: read manufacturer ID: 0x%04x"
+pflash_mode_read_array(const char *name) "%s: read array mode"
+pflash_postload_cb(const char *name) "%s: updating bdrv"
+pflash_read_done(const char *name, uint64_t offset, uint64_t ret) "%s: ID:0x%" PRIx64 " ret:0x%" PRIx64
+pflash_read_status(const char *name, uint32_t ret) "%s: status:0x%x"
+pflash_read_unknown_state(const char *name, uint8_t cmd) "%s: unknown command state:0x%x"
+pflash_reset(const char *name) "%s: reset"
+pflash_sector_erase_start(const char *name, int width1, uint64_t start, int width2, uint64_t end) "%s: start sector erase at: 0x%0*" PRIx64 "-0x%0*" PRIx64
+pflash_timer_expired(const char *name, uint8_t cmd) "%s: command 0x%02x done"
+pflash_unlock0_failed(const char *name, uint64_t offset, uint8_t cmd, uint16_t addr0) "%s: unlock0 failed 0x%" PRIx64 " 0x%02x 0x%04x"
+pflash_unlock1_failed(const char *name, uint64_t offset, uint8_t cmd) "%s: unlock0 failed 0x%" PRIx64 " 0x%02x"
+pflash_unsupported_device_configuration(const char *name, uint8_t width, uint8_t max) "%s: unsupported device configuration: device_width:%d max_device_width:%d"
+pflash_write(const char *name, const char *str) "%s: %s"
+pflash_write_block(const char *name, uint32_t value) "%s: block write: bytes:0x%x"
+pflash_write_block_erase(const char *name, uint64_t offset, uint64_t len) "%s: block erase offset:0x%" PRIx64 " bytes:0x%" PRIx64
+pflash_write_failed(const char *name, uint64_t offset, uint8_t cmd) "%s: command failed 0x%" PRIx64 " 0x%02x"
+pflash_write_invalid(const char *name, uint8_t cmd) "%s: invalid write for command 0x%02x"
+pflash_write_invalid_command(const char *name, uint8_t cmd) "%s: invalid command 0x%02x (wc 5)"
+pflash_write_invalid_state(const char *name, uint8_t cmd, int wc) "%s: invalid command state 0x%02x (wc %d)"
+pflash_write_start(const char *name, uint8_t cmd) "%s: starting command 0x%02x"
+pflash_write_unknown(const char *name, uint8_t cmd) "%s: unknown command 0x%02x"
+
+# virtio-blk.c
+virtio_blk_req_complete(void *vdev, void *req, int status) "vdev %p req %p status %d"
+virtio_blk_rw_complete(void *vdev, void *req, int ret) "vdev %p req %p ret %d"
+virtio_blk_handle_write(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu"
+virtio_blk_handle_read(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu"
+virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint64_t offset, size_t size, bool is_write) "vdev %p mrb %p start %d num_reqs %d offset %"PRIu64" size %zu is_write %d"
+
+# hd-geometry.c
+hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d"
+hd_geometry_guess(void *blk, uint32_t cyls, uint32_t heads, uint32_t secs, int trans) "blk %p CHS %u %u %u trans %d"
+
+# xen-block.c
+xen_block_realize(const char *type, uint32_t disk, uint32_t partition) "%s d%up%u"
+xen_block_connect(const char *type, uint32_t disk, uint32_t partition) "%s d%up%u"
+xen_block_disconnect(const char *type, uint32_t disk, uint32_t partition) "%s d%up%u"
+xen_block_unrealize(const char *type, uint32_t disk, uint32_t partition) "%s d%up%u"
+xen_block_size(const char *type, uint32_t disk, uint32_t partition, int64_t sectors) "%s d%up%u %"PRIi64
+xen_disk_realize(void) ""
+xen_disk_unrealize(void) ""
+xen_cdrom_realize(void) ""
+xen_cdrom_unrealize(void) ""
+xen_block_blockdev_add(char *str) "%s"
+xen_block_blockdev_del(const char *node_name) "%s"
+xen_block_device_create(unsigned int number) "%u"
+xen_block_device_destroy(unsigned int number) "%u"
+
+# m25p80.c
+m25p80_flash_erase(void *s, int offset, uint32_t len) "[%p] offset = 0x%"PRIx32", len = %u"
+m25p80_programming_zero_to_one(void *s, uint32_t addr, uint8_t prev, uint8_t data) "[%p] programming zero to one! addr=0x%"PRIx32" 0x%"PRIx8" -> 0x%"PRIx8
+m25p80_reset_done(void *s) "[%p] Reset done."
+m25p80_command_decoded(void *s, uint32_t cmd) "[%p] new command:0x%"PRIx32
+m25p80_complete_collecting(void *s, uint32_t cmd, int n, uint8_t ear, uint32_t cur_addr) "[%p] decode cmd: 0x%"PRIx32" len %d ear 0x%"PRIx8" addr 0x%"PRIx32
+m25p80_populated_jedec(void *s) "[%p] populated jedec code"
+m25p80_chip_erase(void *s) "[%p] chip erase"
+m25p80_select(void *s, const char *what) "[%p] %sselect"
+m25p80_page_program(void *s, uint32_t addr, uint8_t tx) "[%p] page program cur_addr=0x%"PRIx32" data=0x%"PRIx8
+m25p80_transfer(void *s, uint8_t state, uint32_t len, uint8_t needed, uint32_t pos, uint32_t cur_addr, uint8_t t) "[%p] Transfer state 0x%"PRIx8" len 0x%"PRIx32" needed 0x%"PRIx8" pos 0x%"PRIx32" addr 0x%"PRIx32" tx 0x%"PRIx8
+m25p80_read_byte(void *s, uint32_t addr, uint8_t v) "[%p] Read byte 0x%"PRIx32"=0x%"PRIx8
+m25p80_read_data(void *s, uint32_t pos, uint8_t v) "[%p] Read data 0x%"PRIx32"=0x%"PRIx8
+m25p80_read_sfdp(void *s, uint32_t addr, uint8_t v) "[%p] Read SFDP 0x%"PRIx32"=0x%"PRIx8
+m25p80_binding(void *s) "[%p] Binding to IF_MTD drive"
+m25p80_binding_no_bdrv(void *s) "[%p] No BDRV - binding to RAM"
diff --git a/hw/block/trace.h b/hw/block/trace.h
new file mode 100644
index 00000000..cde210ae
--- /dev/null
+++ b/hw/block/trace.h
@@ -0,0 +1 @@
+#include "trace/trace-hw_block.h"
diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c
new file mode 100644
index 00000000..aff4d2b8
--- /dev/null
+++ b/hw/block/vhost-user-blk.c
@@ -0,0 +1,612 @@
+/*
+ * vhost-user-blk host device
+ *
+ * Copyright(C) 2017 Intel Corporation.
+ *
+ * Authors:
+ * Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * Largely based on the "vhost-user-scsi.c" and "vhost-scsi.c" implemented by:
+ * Felipe Franciosi <felipe@nutanix.com>
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Nicholas Bellinger <nab@risingtidesystems.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/cutils.h"
+#include "hw/qdev-core.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "hw/virtio/virtio-blk-common.h"
+#include "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-user-blk.h"
+#include "hw/virtio/virtio.h"
+#include "hw/virtio/virtio-bus.h"
+#include "hw/virtio/virtio-access.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/runstate.h"
+
+#define REALIZE_CONNECTION_RETRIES 3
+
+static const int user_feature_bits[] = {
+ VIRTIO_BLK_F_SIZE_MAX,
+ VIRTIO_BLK_F_SEG_MAX,
+ VIRTIO_BLK_F_GEOMETRY,
+ VIRTIO_BLK_F_BLK_SIZE,
+ VIRTIO_BLK_F_TOPOLOGY,
+ VIRTIO_BLK_F_MQ,
+ VIRTIO_BLK_F_RO,
+ VIRTIO_BLK_F_FLUSH,
+ VIRTIO_BLK_F_CONFIG_WCE,
+ VIRTIO_BLK_F_DISCARD,
+ VIRTIO_BLK_F_WRITE_ZEROES,
+ VIRTIO_F_VERSION_1,
+ VIRTIO_RING_F_INDIRECT_DESC,
+ VIRTIO_RING_F_EVENT_IDX,
+ VIRTIO_F_NOTIFY_ON_EMPTY,
+ VIRTIO_F_RING_PACKED,
+ VIRTIO_F_IOMMU_PLATFORM,
+ VIRTIO_F_RING_RESET,
+ VHOST_INVALID_FEATURE_BIT
+};
+
+static void vhost_user_blk_event(void *opaque, QEMUChrEvent event);
+
+static void vhost_user_blk_update_config(VirtIODevice *vdev, uint8_t *config)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+ /* Our num_queues overrides the device backend */
+ virtio_stw_p(vdev, &s->blkcfg.num_queues, s->num_queues);
+
+ memcpy(config, &s->blkcfg, vdev->config_len);
+}
+
+static void vhost_user_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ struct virtio_blk_config *blkcfg = (struct virtio_blk_config *)config;
+ int ret;
+
+ if (blkcfg->wce == s->blkcfg.wce) {
+ return;
+ }
+
+ ret = vhost_dev_set_config(&s->dev, &blkcfg->wce,
+ offsetof(struct virtio_blk_config, wce),
+ sizeof(blkcfg->wce),
+ VHOST_SET_CONFIG_TYPE_MASTER);
+ if (ret) {
+ error_report("set device config space failed");
+ return;
+ }
+
+ s->blkcfg.wce = blkcfg->wce;
+}
+
+static int vhost_user_blk_handle_config_change(struct vhost_dev *dev)
+{
+ int ret;
+ struct virtio_blk_config blkcfg;
+ VirtIODevice *vdev = dev->vdev;
+ VHostUserBlk *s = VHOST_USER_BLK(dev->vdev);
+ Error *local_err = NULL;
+
+ if (!dev->started) {
+ return 0;
+ }
+
+ ret = vhost_dev_get_config(dev, (uint8_t *)&blkcfg,
+ vdev->config_len, &local_err);
+ if (ret < 0) {
+ error_report_err(local_err);
+ return ret;
+ }
+
+ /* valid for resize only */
+ if (blkcfg.capacity != s->blkcfg.capacity) {
+ s->blkcfg.capacity = blkcfg.capacity;
+ memcpy(dev->vdev->config, &s->blkcfg, vdev->config_len);
+ virtio_notify_config(dev->vdev);
+ }
+
+ return 0;
+}
+
+const VhostDevConfigOps blk_ops = {
+ .vhost_dev_config_notifier = vhost_user_blk_handle_config_change,
+};
+
+static int vhost_user_blk_start(VirtIODevice *vdev, Error **errp)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+ VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+ int i, ret;
+
+ if (!k->set_guest_notifiers) {
+ error_setg(errp, "binding does not support guest notifiers");
+ return -ENOSYS;
+ }
+
+ ret = vhost_dev_enable_notifiers(&s->dev, vdev);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Error enabling host notifiers");
+ return ret;
+ }
+
+ ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Error binding guest notifier");
+ goto err_host_notifiers;
+ }
+
+ s->dev.acked_features = vdev->guest_features;
+
+ ret = vhost_dev_prepare_inflight(&s->dev, vdev);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Error setting inflight format");
+ goto err_guest_notifiers;
+ }
+
+ if (!s->inflight->addr) {
+ ret = vhost_dev_get_inflight(&s->dev, s->queue_size, s->inflight);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Error getting inflight");
+ goto err_guest_notifiers;
+ }
+ }
+
+ ret = vhost_dev_set_inflight(&s->dev, s->inflight);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Error setting inflight");
+ goto err_guest_notifiers;
+ }
+
+ /* guest_notifier_mask/pending not used yet, so just unmask
+ * everything here. virtio-pci will do the right thing by
+ * enabling/disabling irqfd.
+ */
+ for (i = 0; i < s->dev.nvqs; i++) {
+ vhost_virtqueue_mask(&s->dev, vdev, i, false);
+ }
+
+ s->dev.vq_index_end = s->dev.nvqs;
+ ret = vhost_dev_start(&s->dev, vdev, true);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Error starting vhost");
+ goto err_guest_notifiers;
+ }
+ s->started_vu = true;
+
+ return ret;
+
+err_guest_notifiers:
+ for (i = 0; i < s->dev.nvqs; i++) {
+ vhost_virtqueue_mask(&s->dev, vdev, i, true);
+ }
+ k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
+err_host_notifiers:
+ vhost_dev_disable_notifiers(&s->dev, vdev);
+ return ret;
+}
+
+static void vhost_user_blk_stop(VirtIODevice *vdev)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+ VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+ int ret;
+
+ if (!s->started_vu) {
+ return;
+ }
+ s->started_vu = false;
+
+ if (!k->set_guest_notifiers) {
+ return;
+ }
+
+ vhost_dev_stop(&s->dev, vdev, true);
+
+ ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
+ if (ret < 0) {
+ error_report("vhost guest notifier cleanup failed: %d", ret);
+ return;
+ }
+
+ vhost_dev_disable_notifiers(&s->dev, vdev);
+}
+
+static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ bool should_start = virtio_device_should_start(vdev, status);
+ Error *local_err = NULL;
+ int ret;
+
+ if (!s->connected) {
+ return;
+ }
+
+ if (vhost_dev_is_started(&s->dev) == should_start) {
+ return;
+ }
+
+ if (should_start) {
+ ret = vhost_user_blk_start(vdev, &local_err);
+ if (ret < 0) {
+ error_reportf_err(local_err, "vhost-user-blk: vhost start failed: ");
+ qemu_chr_fe_disconnect(&s->chardev);
+ }
+ } else {
+ vhost_user_blk_stop(vdev);
+ }
+
+}
+
+static uint64_t vhost_user_blk_get_features(VirtIODevice *vdev,
+ uint64_t features,
+ Error **errp)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+ /* Turn on pre-defined features */
+ virtio_add_feature(&features, VIRTIO_BLK_F_SIZE_MAX);
+ virtio_add_feature(&features, VIRTIO_BLK_F_SEG_MAX);
+ virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
+ virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
+ virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
+ virtio_add_feature(&features, VIRTIO_BLK_F_FLUSH);
+ virtio_add_feature(&features, VIRTIO_BLK_F_RO);
+
+ if (s->num_queues > 1) {
+ virtio_add_feature(&features, VIRTIO_BLK_F_MQ);
+ }
+
+ return vhost_get_features(&s->dev, user_feature_bits, features);
+}
+
+static void vhost_user_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ Error *local_err = NULL;
+ int i, ret;
+
+ if (!vdev->start_on_kick) {
+ return;
+ }
+
+ if (!s->connected) {
+ return;
+ }
+
+ if (vhost_dev_is_started(&s->dev)) {
+ return;
+ }
+
+ /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
+ * vhost here instead of waiting for .set_status().
+ */
+ ret = vhost_user_blk_start(vdev, &local_err);
+ if (ret < 0) {
+ error_reportf_err(local_err, "vhost-user-blk: vhost start failed: ");
+ qemu_chr_fe_disconnect(&s->chardev);
+ return;
+ }
+
+ /* Kick right away to begin processing requests already in vring */
+ for (i = 0; i < s->dev.nvqs; i++) {
+ VirtQueue *kick_vq = virtio_get_queue(vdev, i);
+
+ if (!virtio_queue_get_desc_addr(vdev, i)) {
+ continue;
+ }
+ event_notifier_set(virtio_queue_get_host_notifier(kick_vq));
+ }
+}
+
+static void vhost_user_blk_reset(VirtIODevice *vdev)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+ vhost_dev_free_inflight(s->inflight);
+}
+
+static int vhost_user_blk_connect(DeviceState *dev, Error **errp)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ int ret = 0;
+
+ if (s->connected) {
+ return 0;
+ }
+ s->connected = true;
+
+ s->dev.num_queues = s->num_queues;
+ s->dev.nvqs = s->num_queues;
+ s->dev.vqs = s->vhost_vqs;
+ s->dev.vq_index = 0;
+ s->dev.backend_features = 0;
+
+ vhost_dev_set_config_notifier(&s->dev, &blk_ops);
+
+ s->vhost_user.supports_config = true;
+ ret = vhost_dev_init(&s->dev, &s->vhost_user, VHOST_BACKEND_TYPE_USER, 0,
+ errp);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* restore vhost state */
+ if (virtio_device_started(vdev, vdev->status)) {
+ ret = vhost_user_blk_start(vdev, errp);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static void vhost_user_blk_disconnect(DeviceState *dev)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+ if (!s->connected) {
+ return;
+ }
+ s->connected = false;
+
+ vhost_user_blk_stop(vdev);
+
+ vhost_dev_cleanup(&s->dev);
+
+ /* Re-instate the event handler for new connections */
+ qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, vhost_user_blk_event,
+ NULL, dev, NULL, true);
+}
+
+static void vhost_user_blk_event(void *opaque, QEMUChrEvent event)
+{
+ DeviceState *dev = opaque;
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ Error *local_err = NULL;
+
+ switch (event) {
+ case CHR_EVENT_OPENED:
+ if (vhost_user_blk_connect(dev, &local_err) < 0) {
+ error_report_err(local_err);
+ qemu_chr_fe_disconnect(&s->chardev);
+ return;
+ }
+ break;
+ case CHR_EVENT_CLOSED:
+ /* defer close until later to avoid circular close */
+ vhost_user_async_close(dev, &s->chardev, &s->dev,
+ vhost_user_blk_disconnect);
+ break;
+ case CHR_EVENT_BREAK:
+ case CHR_EVENT_MUX_IN:
+ case CHR_EVENT_MUX_OUT:
+ /* Ignore */
+ break;
+ }
+}
+
+static int vhost_user_blk_realize_connect(VHostUserBlk *s, Error **errp)
+{
+ DeviceState *dev = &s->parent_obj.parent_obj;
+ int ret;
+
+ s->connected = false;
+
+ ret = qemu_chr_fe_wait_connected(&s->chardev, errp);
+ if (ret < 0) {
+ return ret;
+ }
+
+ ret = vhost_user_blk_connect(dev, errp);
+ if (ret < 0) {
+ qemu_chr_fe_disconnect(&s->chardev);
+ return ret;
+ }
+ assert(s->connected);
+
+ ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg,
+ s->parent_obj.config_len, errp);
+ if (ret < 0) {
+ qemu_chr_fe_disconnect(&s->chardev);
+ vhost_dev_cleanup(&s->dev);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp)
+{
+ ERRP_GUARD();
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ size_t config_size;
+ int retries;
+ int i, ret;
+
+ if (!s->chardev.chr) {
+ error_setg(errp, "chardev is mandatory");
+ return;
+ }
+
+ if (s->num_queues == VHOST_USER_BLK_AUTO_NUM_QUEUES) {
+ s->num_queues = 1;
+ }
+ if (!s->num_queues || s->num_queues > VIRTIO_QUEUE_MAX) {
+ error_setg(errp, "invalid number of IO queues");
+ return;
+ }
+
+ if (!s->queue_size) {
+ error_setg(errp, "queue size must be non-zero");
+ return;
+ }
+ if (s->queue_size > VIRTQUEUE_MAX_SIZE) {
+ error_setg(errp, "queue size must not exceed %d",
+ VIRTQUEUE_MAX_SIZE);
+ return;
+ }
+
+ if (!vhost_user_init(&s->vhost_user, &s->chardev, errp)) {
+ return;
+ }
+
+ config_size = virtio_get_config_size(&virtio_blk_cfg_size_params,
+ vdev->host_features);
+ virtio_init(vdev, VIRTIO_ID_BLOCK, config_size);
+
+ s->virtqs = g_new(VirtQueue *, s->num_queues);
+ for (i = 0; i < s->num_queues; i++) {
+ s->virtqs[i] = virtio_add_queue(vdev, s->queue_size,
+ vhost_user_blk_handle_output);
+ }
+
+ s->inflight = g_new0(struct vhost_inflight, 1);
+ s->vhost_vqs = g_new0(struct vhost_virtqueue, s->num_queues);
+
+ retries = REALIZE_CONNECTION_RETRIES;
+ assert(!*errp);
+ do {
+ if (*errp) {
+ error_prepend(errp, "Reconnecting after error: ");
+ error_report_err(*errp);
+ *errp = NULL;
+ }
+ ret = vhost_user_blk_realize_connect(s, errp);
+ } while (ret < 0 && retries--);
+
+ if (ret < 0) {
+ goto virtio_err;
+ }
+
+ /* we're fully initialized, now we can operate, so add the handler */
+ qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL,
+ vhost_user_blk_event, NULL, (void *)dev,
+ NULL, true);
+ return;
+
+virtio_err:
+ g_free(s->vhost_vqs);
+ s->vhost_vqs = NULL;
+ g_free(s->inflight);
+ s->inflight = NULL;
+ for (i = 0; i < s->num_queues; i++) {
+ virtio_delete_queue(s->virtqs[i]);
+ }
+ g_free(s->virtqs);
+ virtio_cleanup(vdev);
+ vhost_user_cleanup(&s->vhost_user);
+}
+
+static void vhost_user_blk_device_unrealize(DeviceState *dev)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VHostUserBlk *s = VHOST_USER_BLK(dev);
+ int i;
+
+ virtio_set_status(vdev, 0);
+ qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, NULL,
+ NULL, NULL, NULL, false);
+ vhost_dev_cleanup(&s->dev);
+ vhost_dev_free_inflight(s->inflight);
+ g_free(s->vhost_vqs);
+ s->vhost_vqs = NULL;
+ g_free(s->inflight);
+ s->inflight = NULL;
+
+ for (i = 0; i < s->num_queues; i++) {
+ virtio_delete_queue(s->virtqs[i]);
+ }
+ g_free(s->virtqs);
+ virtio_cleanup(vdev);
+ vhost_user_cleanup(&s->vhost_user);
+}
+
+static void vhost_user_blk_instance_init(Object *obj)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(obj);
+
+ device_add_bootindex_property(obj, &s->bootindex, "bootindex",
+ "/disk@0,0", DEVICE(obj));
+}
+
+static struct vhost_dev *vhost_user_blk_get_vhost(VirtIODevice *vdev)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ return &s->dev;
+}
+
+static const VMStateDescription vmstate_vhost_user_blk = {
+ .name = "vhost-user-blk",
+ .minimum_version_id = 1,
+ .version_id = 1,
+ .fields = (VMStateField[]) {
+ VMSTATE_VIRTIO_DEVICE,
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+static Property vhost_user_blk_properties[] = {
+ DEFINE_PROP_CHR("chardev", VHostUserBlk, chardev),
+ DEFINE_PROP_UINT16("num-queues", VHostUserBlk, num_queues,
+ VHOST_USER_BLK_AUTO_NUM_QUEUES),
+ DEFINE_PROP_UINT32("queue-size", VHostUserBlk, queue_size, 128),
+ DEFINE_PROP_BIT64("config-wce", VHostUserBlk, parent_obj.host_features,
+ VIRTIO_BLK_F_CONFIG_WCE, true),
+ DEFINE_PROP_BIT64("discard", VHostUserBlk, parent_obj.host_features,
+ VIRTIO_BLK_F_DISCARD, true),
+ DEFINE_PROP_BIT64("write-zeroes", VHostUserBlk, parent_obj.host_features,
+ VIRTIO_BLK_F_WRITE_ZEROES, true),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vhost_user_blk_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+ VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
+
+ device_class_set_props(dc, vhost_user_blk_properties);
+ dc->vmsd = &vmstate_vhost_user_blk;
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+ vdc->realize = vhost_user_blk_device_realize;
+ vdc->unrealize = vhost_user_blk_device_unrealize;
+ vdc->get_config = vhost_user_blk_update_config;
+ vdc->set_config = vhost_user_blk_set_config;
+ vdc->get_features = vhost_user_blk_get_features;
+ vdc->set_status = vhost_user_blk_set_status;
+ vdc->reset = vhost_user_blk_reset;
+ vdc->get_vhost = vhost_user_blk_get_vhost;
+}
+
+static const TypeInfo vhost_user_blk_info = {
+ .name = TYPE_VHOST_USER_BLK,
+ .parent = TYPE_VIRTIO_DEVICE,
+ .instance_size = sizeof(VHostUserBlk),
+ .instance_init = vhost_user_blk_instance_init,
+ .class_init = vhost_user_blk_class_init,
+};
+
+static void virtio_register_types(void)
+{
+ type_register_static(&vhost_user_blk_info);
+}
+
+type_init(virtio_register_types)
diff --git a/hw/block/virtio-blk-common.c b/hw/block/virtio-blk-common.c
new file mode 100644
index 00000000..ac52d7c1
--- /dev/null
+++ b/hw/block/virtio-blk-common.c
@@ -0,0 +1,39 @@
+/*
+ * Virtio Block Device common helpers
+ *
+ * Copyright IBM, Corp. 2007
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+
+#include "standard-headers/linux/virtio_blk.h"
+#include "hw/virtio/virtio.h"
+#include "hw/virtio/virtio-blk-common.h"
+
+/* Config size before the discard support (hide associated config fields) */
+#define VIRTIO_BLK_CFG_SIZE offsetof(struct virtio_blk_config, \
+ max_discard_sectors)
+
+/*
+ * Starting from the discard feature, we can use this array to properly
+ * set the config size depending on the features enabled.
+ */
+static const VirtIOFeature feature_sizes[] = {
+ {.flags = 1ULL << VIRTIO_BLK_F_DISCARD,
+ .end = endof(struct virtio_blk_config, discard_sector_alignment)},
+ {.flags = 1ULL << VIRTIO_BLK_F_WRITE_ZEROES,
+ .end = endof(struct virtio_blk_config, write_zeroes_may_unmap)},
+ {}
+};
+
+const VirtIOConfigSizeParams virtio_blk_cfg_size_params = {
+ .min_size = VIRTIO_BLK_CFG_SIZE,
+ .max_size = sizeof(struct virtio_blk_config),
+ .feature_sizes = feature_sizes
+};
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
new file mode 100644
index 00000000..f717550f
--- /dev/null
+++ b/hw/block/virtio-blk.c
@@ -0,0 +1,1336 @@
+/*
+ * Virtio Block Device
+ *
+ * Copyright IBM, Corp. 2007
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/iov.h"
+#include "qemu/module.h"
+#include "qemu/error-report.h"
+#include "qemu/main-loop.h"
+#include "trace.h"
+#include "hw/block/block.h"
+#include "hw/qdev-properties.h"
+#include "sysemu/blockdev.h"
+#include "sysemu/block-ram-registrar.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/runstate.h"
+#include "hw/virtio/virtio-blk.h"
+#include "dataplane/virtio-blk.h"
+#include "scsi/constants.h"
+#ifdef __linux__
+# include <scsi/sg.h>
+#endif
+#include "hw/virtio/virtio-bus.h"
+#include "migration/qemu-file-types.h"
+#include "hw/virtio/virtio-access.h"
+#include "hw/virtio/virtio-blk-common.h"
+#include "qemu/coroutine.h"
+
+static void virtio_blk_init_request(VirtIOBlock *s, VirtQueue *vq,
+ VirtIOBlockReq *req)
+{
+ req->dev = s;
+ req->vq = vq;
+ req->qiov.size = 0;
+ req->in_len = 0;
+ req->next = NULL;
+ req->mr_next = NULL;
+}
+
+static void virtio_blk_free_request(VirtIOBlockReq *req)
+{
+ g_free(req);
+}
+
+static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
+{
+ VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+
+ trace_virtio_blk_req_complete(vdev, req, status);
+
+ stb_p(&req->in->status, status);
+ iov_discard_undo(&req->inhdr_undo);
+ iov_discard_undo(&req->outhdr_undo);
+ virtqueue_push(req->vq, &req->elem, req->in_len);
+ if (s->dataplane_started && !s->dataplane_disabled) {
+ virtio_blk_data_plane_notify(s->dataplane, req->vq);
+ } else {
+ virtio_notify(vdev, req->vq);
+ }
+}
+
+static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
+ bool is_read, bool acct_failed)
+{
+ VirtIOBlock *s = req->dev;
+ BlockErrorAction action = blk_get_error_action(s->blk, is_read, error);
+
+ if (action == BLOCK_ERROR_ACTION_STOP) {
+ /* Break the link as the next request is going to be parsed from the
+ * ring again. Otherwise we may end up doing a double completion! */
+ req->mr_next = NULL;
+ req->next = s->rq;
+ s->rq = req;
+ } else if (action == BLOCK_ERROR_ACTION_REPORT) {
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
+ if (acct_failed) {
+ block_acct_failed(blk_get_stats(s->blk), &req->acct);
+ }
+ virtio_blk_free_request(req);
+ }
+
+ blk_error_action(s->blk, action, is_read, error);
+ return action != BLOCK_ERROR_ACTION_IGNORE;
+}
+
+static void virtio_blk_rw_complete(void *opaque, int ret)
+{
+ VirtIOBlockReq *next = opaque;
+ VirtIOBlock *s = next->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ while (next) {
+ VirtIOBlockReq *req = next;
+ next = req->mr_next;
+ trace_virtio_blk_rw_complete(vdev, req, ret);
+
+ if (req->qiov.nalloc != -1) {
+ /* If nalloc is != -1 req->qiov is a local copy of the original
+ * external iovec. It was allocated in submit_requests to be
+ * able to merge requests. */
+ qemu_iovec_destroy(&req->qiov);
+ }
+
+ if (ret) {
+ int p = virtio_ldl_p(VIRTIO_DEVICE(s), &req->out.type);
+ bool is_read = !(p & VIRTIO_BLK_T_OUT);
+ /* Note that memory may be dirtied on read failure. If the
+ * virtio request is not completed here, as is the case for
+ * BLOCK_ERROR_ACTION_STOP, the memory may not be copied
+ * correctly during live migration. While this is ugly,
+ * it is acceptable because the device is free to write to
+ * the memory until the request is completed (which will
+ * happen on the other side of the migration).
+ */
+ if (virtio_blk_handle_rw_error(req, -ret, is_read, true)) {
+ continue;
+ }
+ }
+
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
+ block_acct_done(blk_get_stats(s->blk), &req->acct);
+ virtio_blk_free_request(req);
+ }
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+}
+
+static void virtio_blk_flush_complete(void *opaque, int ret)
+{
+ VirtIOBlockReq *req = opaque;
+ VirtIOBlock *s = req->dev;
+
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ if (ret) {
+ if (virtio_blk_handle_rw_error(req, -ret, 0, true)) {
+ goto out;
+ }
+ }
+
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
+ block_acct_done(blk_get_stats(s->blk), &req->acct);
+ virtio_blk_free_request(req);
+
+out:
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+}
+
+static void virtio_blk_discard_write_zeroes_complete(void *opaque, int ret)
+{
+ VirtIOBlockReq *req = opaque;
+ VirtIOBlock *s = req->dev;
+ bool is_write_zeroes = (virtio_ldl_p(VIRTIO_DEVICE(s), &req->out.type) &
+ ~VIRTIO_BLK_T_BARRIER) == VIRTIO_BLK_T_WRITE_ZEROES;
+
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ if (ret) {
+ if (virtio_blk_handle_rw_error(req, -ret, false, is_write_zeroes)) {
+ goto out;
+ }
+ }
+
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
+ if (is_write_zeroes) {
+ block_acct_done(blk_get_stats(s->blk), &req->acct);
+ }
+ virtio_blk_free_request(req);
+
+out:
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+}
+
+#ifdef __linux__
+
+typedef struct {
+ VirtIOBlockReq *req;
+ struct sg_io_hdr hdr;
+} VirtIOBlockIoctlReq;
+
+static void virtio_blk_ioctl_complete(void *opaque, int status)
+{
+ VirtIOBlockIoctlReq *ioctl_req = opaque;
+ VirtIOBlockReq *req = ioctl_req->req;
+ VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+ struct virtio_scsi_inhdr *scsi;
+ struct sg_io_hdr *hdr;
+
+ scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base;
+
+ if (status) {
+ status = VIRTIO_BLK_S_UNSUPP;
+ virtio_stl_p(vdev, &scsi->errors, 255);
+ goto out;
+ }
+
+ hdr = &ioctl_req->hdr;
+ /*
+ * From SCSI-Generic-HOWTO: "Some lower level drivers (e.g. ide-scsi)
+ * clear the masked_status field [hence status gets cleared too, see
+ * block/scsi_ioctl.c] even when a CHECK_CONDITION or COMMAND_TERMINATED
+ * status has occurred. However they do set DRIVER_SENSE in driver_status
+ * field. Also a (sb_len_wr > 0) indicates there is a sense buffer.
+ */
+ if (hdr->status == 0 && hdr->sb_len_wr > 0) {
+ hdr->status = CHECK_CONDITION;
+ }
+
+ virtio_stl_p(vdev, &scsi->errors,
+ hdr->status | (hdr->msg_status << 8) |
+ (hdr->host_status << 16) | (hdr->driver_status << 24));
+ virtio_stl_p(vdev, &scsi->residual, hdr->resid);
+ virtio_stl_p(vdev, &scsi->sense_len, hdr->sb_len_wr);
+ virtio_stl_p(vdev, &scsi->data_len, hdr->dxfer_len);
+
+out:
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ virtio_blk_req_complete(req, status);
+ virtio_blk_free_request(req);
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+ g_free(ioctl_req);
+}
+
+#endif
+
+static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s, VirtQueue *vq)
+{
+ VirtIOBlockReq *req = virtqueue_pop(vq, sizeof(VirtIOBlockReq));
+
+ if (req) {
+ virtio_blk_init_request(s, vq, req);
+ }
+ return req;
+}
+
+static int virtio_blk_handle_scsi_req(VirtIOBlockReq *req)
+{
+ int status = VIRTIO_BLK_S_OK;
+ struct virtio_scsi_inhdr *scsi = NULL;
+ VirtIOBlock *blk = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(blk);
+ VirtQueueElement *elem = &req->elem;
+
+#ifdef __linux__
+ int i;
+ VirtIOBlockIoctlReq *ioctl_req;
+ BlockAIOCB *acb;
+#endif
+
+ /*
+ * We require at least one output segment each for the virtio_blk_outhdr
+ * and the SCSI command block.
+ *
+ * We also at least require the virtio_blk_inhdr, the virtio_scsi_inhdr
+ * and the sense buffer pointer in the input segments.
+ */
+ if (elem->out_num < 2 || elem->in_num < 3) {
+ status = VIRTIO_BLK_S_IOERR;
+ goto fail;
+ }
+
+ /*
+ * The scsi inhdr is placed in the second-to-last input segment, just
+ * before the regular inhdr.
+ */
+ scsi = (void *)elem->in_sg[elem->in_num - 2].iov_base;
+
+ if (!virtio_has_feature(blk->host_features, VIRTIO_BLK_F_SCSI)) {
+ status = VIRTIO_BLK_S_UNSUPP;
+ goto fail;
+ }
+
+ /*
+ * No support for bidirection commands yet.
+ */
+ if (elem->out_num > 2 && elem->in_num > 3) {
+ status = VIRTIO_BLK_S_UNSUPP;
+ goto fail;
+ }
+
+#ifdef __linux__
+ ioctl_req = g_new0(VirtIOBlockIoctlReq, 1);
+ ioctl_req->req = req;
+ ioctl_req->hdr.interface_id = 'S';
+ ioctl_req->hdr.cmd_len = elem->out_sg[1].iov_len;
+ ioctl_req->hdr.cmdp = elem->out_sg[1].iov_base;
+ ioctl_req->hdr.dxfer_len = 0;
+
+ if (elem->out_num > 2) {
+ /*
+ * If there are more than the minimally required 2 output segments
+ * there is write payload starting from the third iovec.
+ */
+ ioctl_req->hdr.dxfer_direction = SG_DXFER_TO_DEV;
+ ioctl_req->hdr.iovec_count = elem->out_num - 2;
+
+ for (i = 0; i < ioctl_req->hdr.iovec_count; i++) {
+ ioctl_req->hdr.dxfer_len += elem->out_sg[i + 2].iov_len;
+ }
+
+ ioctl_req->hdr.dxferp = elem->out_sg + 2;
+
+ } else if (elem->in_num > 3) {
+ /*
+ * If we have more than 3 input segments the guest wants to actually
+ * read data.
+ */
+ ioctl_req->hdr.dxfer_direction = SG_DXFER_FROM_DEV;
+ ioctl_req->hdr.iovec_count = elem->in_num - 3;
+ for (i = 0; i < ioctl_req->hdr.iovec_count; i++) {
+ ioctl_req->hdr.dxfer_len += elem->in_sg[i].iov_len;
+ }
+
+ ioctl_req->hdr.dxferp = elem->in_sg;
+ } else {
+ /*
+ * Some SCSI commands don't actually transfer any data.
+ */
+ ioctl_req->hdr.dxfer_direction = SG_DXFER_NONE;
+ }
+
+ ioctl_req->hdr.sbp = elem->in_sg[elem->in_num - 3].iov_base;
+ ioctl_req->hdr.mx_sb_len = elem->in_sg[elem->in_num - 3].iov_len;
+
+ acb = blk_aio_ioctl(blk->blk, SG_IO, &ioctl_req->hdr,
+ virtio_blk_ioctl_complete, ioctl_req);
+ if (!acb) {
+ g_free(ioctl_req);
+ status = VIRTIO_BLK_S_UNSUPP;
+ goto fail;
+ }
+ return -EINPROGRESS;
+#else
+ abort();
+#endif
+
+fail:
+ /* Just put anything nonzero so that the ioctl fails in the guest. */
+ if (scsi) {
+ virtio_stl_p(vdev, &scsi->errors, 255);
+ }
+ return status;
+}
+
+static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
+{
+ int status;
+
+ status = virtio_blk_handle_scsi_req(req);
+ if (status != -EINPROGRESS) {
+ virtio_blk_req_complete(req, status);
+ virtio_blk_free_request(req);
+ }
+}
+
+static inline void submit_requests(VirtIOBlock *s, MultiReqBuffer *mrb,
+ int start, int num_reqs, int niov)
+{
+ BlockBackend *blk = s->blk;
+ QEMUIOVector *qiov = &mrb->reqs[start]->qiov;
+ int64_t sector_num = mrb->reqs[start]->sector_num;
+ bool is_write = mrb->is_write;
+ BdrvRequestFlags flags = 0;
+
+ if (num_reqs > 1) {
+ int i;
+ struct iovec *tmp_iov = qiov->iov;
+ int tmp_niov = qiov->niov;
+
+ /* mrb->reqs[start]->qiov was initialized from external so we can't
+ * modify it here. We need to initialize it locally and then add the
+ * external iovecs. */
+ qemu_iovec_init(qiov, niov);
+
+ for (i = 0; i < tmp_niov; i++) {
+ qemu_iovec_add(qiov, tmp_iov[i].iov_base, tmp_iov[i].iov_len);
+ }
+
+ for (i = start + 1; i < start + num_reqs; i++) {
+ qemu_iovec_concat(qiov, &mrb->reqs[i]->qiov, 0,
+ mrb->reqs[i]->qiov.size);
+ mrb->reqs[i - 1]->mr_next = mrb->reqs[i];
+ }
+
+ trace_virtio_blk_submit_multireq(VIRTIO_DEVICE(mrb->reqs[start]->dev),
+ mrb, start, num_reqs,
+ sector_num << BDRV_SECTOR_BITS,
+ qiov->size, is_write);
+ block_acct_merge_done(blk_get_stats(blk),
+ is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ,
+ num_reqs - 1);
+ }
+
+ if (blk_ram_registrar_ok(&s->blk_ram_registrar)) {
+ flags |= BDRV_REQ_REGISTERED_BUF;
+ }
+
+ if (is_write) {
+ blk_aio_pwritev(blk, sector_num << BDRV_SECTOR_BITS, qiov,
+ flags, virtio_blk_rw_complete,
+ mrb->reqs[start]);
+ } else {
+ blk_aio_preadv(blk, sector_num << BDRV_SECTOR_BITS, qiov,
+ flags, virtio_blk_rw_complete,
+ mrb->reqs[start]);
+ }
+}
+
+static int multireq_compare(const void *a, const void *b)
+{
+ const VirtIOBlockReq *req1 = *(VirtIOBlockReq **)a,
+ *req2 = *(VirtIOBlockReq **)b;
+
+ /*
+ * Note that we can't simply subtract sector_num1 from sector_num2
+ * here as that could overflow the return value.
+ */
+ if (req1->sector_num > req2->sector_num) {
+ return 1;
+ } else if (req1->sector_num < req2->sector_num) {
+ return -1;
+ } else {
+ return 0;
+ }
+}
+
+static void virtio_blk_submit_multireq(VirtIOBlock *s, MultiReqBuffer *mrb)
+{
+ int i = 0, start = 0, num_reqs = 0, niov = 0, nb_sectors = 0;
+ uint32_t max_transfer;
+ int64_t sector_num = 0;
+
+ if (mrb->num_reqs == 1) {
+ submit_requests(s, mrb, 0, 1, -1);
+ mrb->num_reqs = 0;
+ return;
+ }
+
+ max_transfer = blk_get_max_transfer(mrb->reqs[0]->dev->blk);
+
+ qsort(mrb->reqs, mrb->num_reqs, sizeof(*mrb->reqs),
+ &multireq_compare);
+
+ for (i = 0; i < mrb->num_reqs; i++) {
+ VirtIOBlockReq *req = mrb->reqs[i];
+ if (num_reqs > 0) {
+ /*
+ * NOTE: We cannot merge the requests in below situations:
+ * 1. requests are not sequential
+ * 2. merge would exceed maximum number of IOVs
+ * 3. merge would exceed maximum transfer length of backend device
+ */
+ if (sector_num + nb_sectors != req->sector_num ||
+ niov > blk_get_max_iov(s->blk) - req->qiov.niov ||
+ req->qiov.size > max_transfer ||
+ nb_sectors > (max_transfer -
+ req->qiov.size) / BDRV_SECTOR_SIZE) {
+ submit_requests(s, mrb, start, num_reqs, niov);
+ num_reqs = 0;
+ }
+ }
+
+ if (num_reqs == 0) {
+ sector_num = req->sector_num;
+ nb_sectors = niov = 0;
+ start = i;
+ }
+
+ nb_sectors += req->qiov.size / BDRV_SECTOR_SIZE;
+ niov += req->qiov.niov;
+ num_reqs++;
+ }
+
+ submit_requests(s, mrb, start, num_reqs, niov);
+ mrb->num_reqs = 0;
+}
+
+static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
+{
+ VirtIOBlock *s = req->dev;
+
+ block_acct_start(blk_get_stats(s->blk), &req->acct, 0,
+ BLOCK_ACCT_FLUSH);
+
+ /*
+ * Make sure all outstanding writes are posted to the backing device.
+ */
+ if (mrb->is_write && mrb->num_reqs > 0) {
+ virtio_blk_submit_multireq(s, mrb);
+ }
+ blk_aio_flush(s->blk, virtio_blk_flush_complete, req);
+}
+
+static bool virtio_blk_sect_range_ok(VirtIOBlock *dev,
+ uint64_t sector, size_t size)
+{
+ uint64_t nb_sectors = size >> BDRV_SECTOR_BITS;
+ uint64_t total_sectors;
+
+ if (nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
+ return false;
+ }
+ if (sector & dev->sector_mask) {
+ return false;
+ }
+ if (size % dev->conf.conf.logical_block_size) {
+ return false;
+ }
+ blk_get_geometry(dev->blk, &total_sectors);
+ if (sector > total_sectors || nb_sectors > total_sectors - sector) {
+ return false;
+ }
+ return true;
+}
+
+static uint8_t virtio_blk_handle_discard_write_zeroes(VirtIOBlockReq *req,
+ struct virtio_blk_discard_write_zeroes *dwz_hdr, bool is_write_zeroes)
+{
+ VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+ uint64_t sector;
+ uint32_t num_sectors, flags, max_sectors;
+ uint8_t err_status;
+ int bytes;
+
+ sector = virtio_ldq_p(vdev, &dwz_hdr->sector);
+ num_sectors = virtio_ldl_p(vdev, &dwz_hdr->num_sectors);
+ flags = virtio_ldl_p(vdev, &dwz_hdr->flags);
+ max_sectors = is_write_zeroes ? s->conf.max_write_zeroes_sectors :
+ s->conf.max_discard_sectors;
+
+ /*
+ * max_sectors is at most BDRV_REQUEST_MAX_SECTORS, this check
+ * make us sure that "num_sectors << BDRV_SECTOR_BITS" can fit in
+ * the integer variable.
+ */
+ if (unlikely(num_sectors > max_sectors)) {
+ err_status = VIRTIO_BLK_S_IOERR;
+ goto err;
+ }
+
+ bytes = num_sectors << BDRV_SECTOR_BITS;
+
+ if (unlikely(!virtio_blk_sect_range_ok(s, sector, bytes))) {
+ err_status = VIRTIO_BLK_S_IOERR;
+ goto err;
+ }
+
+ /*
+ * The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for discard
+ * and write zeroes commands if any unknown flag is set.
+ */
+ if (unlikely(flags & ~VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) {
+ err_status = VIRTIO_BLK_S_UNSUPP;
+ goto err;
+ }
+
+ if (is_write_zeroes) { /* VIRTIO_BLK_T_WRITE_ZEROES */
+ int blk_aio_flags = 0;
+
+ if (flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) {
+ blk_aio_flags |= BDRV_REQ_MAY_UNMAP;
+ }
+
+ block_acct_start(blk_get_stats(s->blk), &req->acct, bytes,
+ BLOCK_ACCT_WRITE);
+
+ blk_aio_pwrite_zeroes(s->blk, sector << BDRV_SECTOR_BITS,
+ bytes, blk_aio_flags,
+ virtio_blk_discard_write_zeroes_complete, req);
+ } else { /* VIRTIO_BLK_T_DISCARD */
+ /*
+ * The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for
+ * discard commands if the unmap flag is set.
+ */
+ if (unlikely(flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) {
+ err_status = VIRTIO_BLK_S_UNSUPP;
+ goto err;
+ }
+
+ blk_aio_pdiscard(s->blk, sector << BDRV_SECTOR_BITS, bytes,
+ virtio_blk_discard_write_zeroes_complete, req);
+ }
+
+ return VIRTIO_BLK_S_OK;
+
+err:
+ if (is_write_zeroes) {
+ block_acct_invalid(blk_get_stats(s->blk), BLOCK_ACCT_WRITE);
+ }
+ return err_status;
+}
+
+static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
+{
+ uint32_t type;
+ struct iovec *in_iov = req->elem.in_sg;
+ struct iovec *out_iov = req->elem.out_sg;
+ unsigned in_num = req->elem.in_num;
+ unsigned out_num = req->elem.out_num;
+ VirtIOBlock *s = req->dev;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+
+ if (req->elem.out_num < 1 || req->elem.in_num < 1) {
+ virtio_error(vdev, "virtio-blk missing headers");
+ return -1;
+ }
+
+ if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out,
+ sizeof(req->out)) != sizeof(req->out))) {
+ virtio_error(vdev, "virtio-blk request outhdr too short");
+ return -1;
+ }
+
+ iov_discard_front_undoable(&out_iov, &out_num, sizeof(req->out),
+ &req->outhdr_undo);
+
+ if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
+ virtio_error(vdev, "virtio-blk request inhdr too short");
+ iov_discard_undo(&req->outhdr_undo);
+ return -1;
+ }
+
+ /* We always touch the last byte, so just see how big in_iov is. */
+ req->in_len = iov_size(in_iov, in_num);
+ req->in = (void *)in_iov[in_num - 1].iov_base
+ + in_iov[in_num - 1].iov_len
+ - sizeof(struct virtio_blk_inhdr);
+ iov_discard_back_undoable(in_iov, &in_num, sizeof(struct virtio_blk_inhdr),
+ &req->inhdr_undo);
+
+ type = virtio_ldl_p(vdev, &req->out.type);
+
+ /* VIRTIO_BLK_T_OUT defines the command direction. VIRTIO_BLK_T_BARRIER
+ * is an optional flag. Although a guest should not send this flag if
+ * not negotiated we ignored it in the past. So keep ignoring it. */
+ switch (type & ~(VIRTIO_BLK_T_OUT | VIRTIO_BLK_T_BARRIER)) {
+ case VIRTIO_BLK_T_IN:
+ {
+ bool is_write = type & VIRTIO_BLK_T_OUT;
+ req->sector_num = virtio_ldq_p(vdev, &req->out.sector);
+
+ if (is_write) {
+ qemu_iovec_init_external(&req->qiov, out_iov, out_num);
+ trace_virtio_blk_handle_write(vdev, req, req->sector_num,
+ req->qiov.size / BDRV_SECTOR_SIZE);
+ } else {
+ qemu_iovec_init_external(&req->qiov, in_iov, in_num);
+ trace_virtio_blk_handle_read(vdev, req, req->sector_num,
+ req->qiov.size / BDRV_SECTOR_SIZE);
+ }
+
+ if (!virtio_blk_sect_range_ok(s, req->sector_num, req->qiov.size)) {
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
+ block_acct_invalid(blk_get_stats(s->blk),
+ is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
+ virtio_blk_free_request(req);
+ return 0;
+ }
+
+ block_acct_start(blk_get_stats(s->blk), &req->acct, req->qiov.size,
+ is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
+
+ /* merge would exceed maximum number of requests or IO direction
+ * changes */
+ if (mrb->num_reqs > 0 && (mrb->num_reqs == VIRTIO_BLK_MAX_MERGE_REQS ||
+ is_write != mrb->is_write ||
+ !s->conf.request_merging)) {
+ virtio_blk_submit_multireq(s, mrb);
+ }
+
+ assert(mrb->num_reqs < VIRTIO_BLK_MAX_MERGE_REQS);
+ mrb->reqs[mrb->num_reqs++] = req;
+ mrb->is_write = is_write;
+ break;
+ }
+ case VIRTIO_BLK_T_FLUSH:
+ virtio_blk_handle_flush(req, mrb);
+ break;
+ case VIRTIO_BLK_T_SCSI_CMD:
+ virtio_blk_handle_scsi(req);
+ break;
+ case VIRTIO_BLK_T_GET_ID:
+ {
+ /*
+ * NB: per existing s/n string convention the string is
+ * terminated by '\0' only when shorter than buffer.
+ */
+ const char *serial = s->conf.serial ? s->conf.serial : "";
+ size_t size = MIN(strlen(serial) + 1,
+ MIN(iov_size(in_iov, in_num),
+ VIRTIO_BLK_ID_BYTES));
+ iov_from_buf(in_iov, in_num, 0, serial, size);
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
+ virtio_blk_free_request(req);
+ break;
+ }
+ /*
+ * VIRTIO_BLK_T_DISCARD and VIRTIO_BLK_T_WRITE_ZEROES are defined with
+ * VIRTIO_BLK_T_OUT flag set. We masked this flag in the switch statement,
+ * so we must mask it for these requests, then we will check if it is set.
+ */
+ case VIRTIO_BLK_T_DISCARD & ~VIRTIO_BLK_T_OUT:
+ case VIRTIO_BLK_T_WRITE_ZEROES & ~VIRTIO_BLK_T_OUT:
+ {
+ struct virtio_blk_discard_write_zeroes dwz_hdr;
+ size_t out_len = iov_size(out_iov, out_num);
+ bool is_write_zeroes = (type & ~VIRTIO_BLK_T_BARRIER) ==
+ VIRTIO_BLK_T_WRITE_ZEROES;
+ uint8_t err_status;
+
+ /*
+ * Unsupported if VIRTIO_BLK_T_OUT is not set or the request contains
+ * more than one segment.
+ */
+ if (unlikely(!(type & VIRTIO_BLK_T_OUT) ||
+ out_len > sizeof(dwz_hdr))) {
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
+ virtio_blk_free_request(req);
+ return 0;
+ }
+
+ if (unlikely(iov_to_buf(out_iov, out_num, 0, &dwz_hdr,
+ sizeof(dwz_hdr)) != sizeof(dwz_hdr))) {
+ iov_discard_undo(&req->inhdr_undo);
+ iov_discard_undo(&req->outhdr_undo);
+ virtio_error(vdev, "virtio-blk discard/write_zeroes header"
+ " too short");
+ return -1;
+ }
+
+ err_status = virtio_blk_handle_discard_write_zeroes(req, &dwz_hdr,
+ is_write_zeroes);
+ if (err_status != VIRTIO_BLK_S_OK) {
+ virtio_blk_req_complete(req, err_status);
+ virtio_blk_free_request(req);
+ }
+
+ break;
+ }
+ default:
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
+ virtio_blk_free_request(req);
+ }
+ return 0;
+}
+
+void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq)
+{
+ VirtIOBlockReq *req;
+ MultiReqBuffer mrb = {};
+ bool suppress_notifications = virtio_queue_get_notification(vq);
+
+ aio_context_acquire(blk_get_aio_context(s->blk));
+ blk_io_plug(s->blk);
+
+ do {
+ if (suppress_notifications) {
+ virtio_queue_set_notification(vq, 0);
+ }
+
+ while ((req = virtio_blk_get_request(s, vq))) {
+ if (virtio_blk_handle_request(req, &mrb)) {
+ virtqueue_detach_element(req->vq, &req->elem, 0);
+ virtio_blk_free_request(req);
+ break;
+ }
+ }
+
+ if (suppress_notifications) {
+ virtio_queue_set_notification(vq, 1);
+ }
+ } while (!virtio_queue_empty(vq));
+
+ if (mrb.num_reqs) {
+ virtio_blk_submit_multireq(s, &mrb);
+ }
+
+ blk_io_unplug(s->blk);
+ aio_context_release(blk_get_aio_context(s->blk));
+}
+
+static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
+{
+ VirtIOBlock *s = (VirtIOBlock *)vdev;
+
+ if (s->dataplane && !s->dataplane_started) {
+ /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
+ * dataplane here instead of waiting for .set_status().
+ */
+ virtio_device_start_ioeventfd(vdev);
+ if (!s->dataplane_disabled) {
+ return;
+ }
+ }
+ virtio_blk_handle_vq(s, vq);
+}
+
+void virtio_blk_process_queued_requests(VirtIOBlock *s, bool is_bh)
+{
+ VirtIOBlockReq *req = s->rq;
+ MultiReqBuffer mrb = {};
+
+ s->rq = NULL;
+
+ aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+ while (req) {
+ VirtIOBlockReq *next = req->next;
+ if (virtio_blk_handle_request(req, &mrb)) {
+ /* Device is now broken and won't do any processing until it gets
+ * reset. Already queued requests will be lost: let's purge them.
+ */
+ while (req) {
+ next = req->next;
+ virtqueue_detach_element(req->vq, &req->elem, 0);
+ virtio_blk_free_request(req);
+ req = next;
+ }
+ break;
+ }
+ req = next;
+ }
+
+ if (mrb.num_reqs) {
+ virtio_blk_submit_multireq(s, &mrb);
+ }
+ if (is_bh) {
+ blk_dec_in_flight(s->conf.conf.blk);
+ }
+ aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+}
+
+static void virtio_blk_dma_restart_bh(void *opaque)
+{
+ VirtIOBlock *s = opaque;
+
+ qemu_bh_delete(s->bh);
+ s->bh = NULL;
+
+ virtio_blk_process_queued_requests(s, true);
+}
+
+static void virtio_blk_dma_restart_cb(void *opaque, bool running,
+ RunState state)
+{
+ VirtIOBlock *s = opaque;
+ BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s)));
+ VirtioBusState *bus = VIRTIO_BUS(qbus);
+
+ if (!running) {
+ return;
+ }
+
+ /*
+ * If ioeventfd is enabled, don't schedule the BH here as queued
+ * requests will be processed while starting the data plane.
+ */
+ if (!s->bh && !virtio_bus_ioeventfd_enabled(bus)) {
+ s->bh = aio_bh_new(blk_get_aio_context(s->conf.conf.blk),
+ virtio_blk_dma_restart_bh, s);
+ blk_inc_in_flight(s->conf.conf.blk);
+ qemu_bh_schedule(s->bh);
+ }
+}
+
+static void virtio_blk_reset(VirtIODevice *vdev)
+{
+ VirtIOBlock *s = VIRTIO_BLK(vdev);
+ AioContext *ctx;
+ VirtIOBlockReq *req;
+
+ ctx = blk_get_aio_context(s->blk);
+ aio_context_acquire(ctx);
+ blk_drain(s->blk);
+
+ /* We drop queued requests after blk_drain() because blk_drain() itself can
+ * produce them. */
+ while (s->rq) {
+ req = s->rq;
+ s->rq = req->next;
+ virtqueue_detach_element(req->vq, &req->elem, 0);
+ virtio_blk_free_request(req);
+ }
+
+ aio_context_release(ctx);
+
+ assert(!s->dataplane_started);
+ blk_set_enable_write_cache(s->blk, s->original_wce);
+}
+
+/* coalesce internal state, copy to pci i/o region 0
+ */
+static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
+{
+ VirtIOBlock *s = VIRTIO_BLK(vdev);
+ BlockConf *conf = &s->conf.conf;
+ struct virtio_blk_config blkcfg;
+ uint64_t capacity;
+ int64_t length;
+ int blk_size = conf->logical_block_size;
+
+ blk_get_geometry(s->blk, &capacity);
+ memset(&blkcfg, 0, sizeof(blkcfg));
+ virtio_stq_p(vdev, &blkcfg.capacity, capacity);
+ virtio_stl_p(vdev, &blkcfg.seg_max,
+ s->conf.seg_max_adjust ? s->conf.queue_size - 2 : 128 - 2);
+ virtio_stw_p(vdev, &blkcfg.geometry.cylinders, conf->cyls);
+ virtio_stl_p(vdev, &blkcfg.blk_size, blk_size);
+ virtio_stw_p(vdev, &blkcfg.min_io_size, conf->min_io_size / blk_size);
+ virtio_stl_p(vdev, &blkcfg.opt_io_size, conf->opt_io_size / blk_size);
+ blkcfg.geometry.heads = conf->heads;
+ /*
+ * We must ensure that the block device capacity is a multiple of
+ * the logical block size. If that is not the case, let's use
+ * sector_mask to adopt the geometry to have a correct picture.
+ * For those devices where the capacity is ok for the given geometry
+ * we don't touch the sector value of the geometry, since some devices
+ * (like s390 dasd) need a specific value. Here the capacity is already
+ * cyls*heads*secs*blk_size and the sector value is not block size
+ * divided by 512 - instead it is the amount of blk_size blocks
+ * per track (cylinder).
+ */
+ length = blk_getlength(s->blk);
+ if (length > 0 && length / conf->heads / conf->secs % blk_size) {
+ blkcfg.geometry.sectors = conf->secs & ~s->sector_mask;
+ } else {
+ blkcfg.geometry.sectors = conf->secs;
+ }
+ blkcfg.size_max = 0;
+ blkcfg.physical_block_exp = get_physical_block_exp(conf);
+ blkcfg.alignment_offset = 0;
+ blkcfg.wce = blk_enable_write_cache(s->blk);
+ virtio_stw_p(vdev, &blkcfg.num_queues, s->conf.num_queues);
+ if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_DISCARD)) {
+ uint32_t discard_granularity = conf->discard_granularity;
+ if (discard_granularity == -1 || !s->conf.report_discard_granularity) {
+ discard_granularity = blk_size;
+ }
+ virtio_stl_p(vdev, &blkcfg.max_discard_sectors,
+ s->conf.max_discard_sectors);
+ virtio_stl_p(vdev, &blkcfg.discard_sector_alignment,
+ discard_granularity >> BDRV_SECTOR_BITS);
+ /*
+ * We support only one segment per request since multiple segments
+ * are not widely used and there are no userspace APIs that allow
+ * applications to submit multiple segments in a single call.
+ */
+ virtio_stl_p(vdev, &blkcfg.max_discard_seg, 1);
+ }
+ if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_WRITE_ZEROES)) {
+ virtio_stl_p(vdev, &blkcfg.max_write_zeroes_sectors,
+ s->conf.max_write_zeroes_sectors);
+ blkcfg.write_zeroes_may_unmap = 1;
+ virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1);
+ }
+ memcpy(config, &blkcfg, s->config_size);
+}
+
+static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
+{
+ VirtIOBlock *s = VIRTIO_BLK(vdev);
+ struct virtio_blk_config blkcfg;
+
+ memcpy(&blkcfg, config, s->config_size);
+
+ aio_context_acquire(blk_get_aio_context(s->blk));
+ blk_set_enable_write_cache(s->blk, blkcfg.wce != 0);
+ aio_context_release(blk_get_aio_context(s->blk));
+}
+
+static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
+ Error **errp)
+{
+ VirtIOBlock *s = VIRTIO_BLK(vdev);
+
+ /* Firstly sync all virtio-blk possible supported features */
+ features |= s->host_features;
+
+ virtio_add_feature(&features, VIRTIO_BLK_F_SEG_MAX);
+ virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
+ virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
+ virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
+ if (virtio_has_feature(features, VIRTIO_F_VERSION_1)) {
+ if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_SCSI)) {
+ error_setg(errp, "Please set scsi=off for virtio-blk devices in order to use virtio 1.0");
+ return 0;
+ }
+ } else {
+ virtio_clear_feature(&features, VIRTIO_F_ANY_LAYOUT);
+ virtio_add_feature(&features, VIRTIO_BLK_F_SCSI);
+ }
+
+ if (blk_enable_write_cache(s->blk) ||
+ (s->conf.x_enable_wce_if_config_wce &&
+ virtio_has_feature(features, VIRTIO_BLK_F_CONFIG_WCE))) {
+ virtio_add_feature(&features, VIRTIO_BLK_F_WCE);
+ }
+ if (!blk_is_writable(s->blk)) {
+ virtio_add_feature(&features, VIRTIO_BLK_F_RO);
+ }
+ if (s->conf.num_queues > 1) {
+ virtio_add_feature(&features, VIRTIO_BLK_F_MQ);
+ }
+
+ return features;
+}
+
+static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
+{
+ VirtIOBlock *s = VIRTIO_BLK(vdev);
+
+ if (!(status & (VIRTIO_CONFIG_S_DRIVER | VIRTIO_CONFIG_S_DRIVER_OK))) {
+ assert(!s->dataplane_started);
+ }
+
+ if (!(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
+ return;
+ }
+
+ /* A guest that supports VIRTIO_BLK_F_CONFIG_WCE must be able to send
+ * cache flushes. Thus, the "auto writethrough" behavior is never
+ * necessary for guests that support the VIRTIO_BLK_F_CONFIG_WCE feature.
+ * Leaving it enabled would break the following sequence:
+ *
+ * Guest started with "-drive cache=writethrough"
+ * Guest sets status to 0
+ * Guest sets DRIVER bit in status field
+ * Guest reads host features (WCE=0, CONFIG_WCE=1)
+ * Guest writes guest features (WCE=0, CONFIG_WCE=1)
+ * Guest writes 1 to the WCE configuration field (writeback mode)
+ * Guest sets DRIVER_OK bit in status field
+ *
+ * s->blk would erroneously be placed in writethrough mode.
+ */
+ if (!virtio_vdev_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE)) {
+ aio_context_acquire(blk_get_aio_context(s->blk));
+ blk_set_enable_write_cache(s->blk,
+ virtio_vdev_has_feature(vdev,
+ VIRTIO_BLK_F_WCE));
+ aio_context_release(blk_get_aio_context(s->blk));
+ }
+}
+
+static void virtio_blk_save_device(VirtIODevice *vdev, QEMUFile *f)
+{
+ VirtIOBlock *s = VIRTIO_BLK(vdev);
+ VirtIOBlockReq *req = s->rq;
+
+ while (req) {
+ qemu_put_sbyte(f, 1);
+
+ if (s->conf.num_queues > 1) {
+ qemu_put_be32(f, virtio_get_queue_index(req->vq));
+ }
+
+ qemu_put_virtqueue_element(vdev, f, &req->elem);
+ req = req->next;
+ }
+ qemu_put_sbyte(f, 0);
+}
+
+static int virtio_blk_load_device(VirtIODevice *vdev, QEMUFile *f,
+ int version_id)
+{
+ VirtIOBlock *s = VIRTIO_BLK(vdev);
+
+ while (qemu_get_sbyte(f)) {
+ unsigned nvqs = s->conf.num_queues;
+ unsigned vq_idx = 0;
+ VirtIOBlockReq *req;
+
+ if (nvqs > 1) {
+ vq_idx = qemu_get_be32(f);
+
+ if (vq_idx >= nvqs) {
+ error_report("Invalid virtqueue index in request list: %#x",
+ vq_idx);
+ return -EINVAL;
+ }
+ }
+
+ req = qemu_get_virtqueue_element(vdev, f, sizeof(VirtIOBlockReq));
+ virtio_blk_init_request(s, virtio_get_queue(vdev, vq_idx), req);
+ req->next = s->rq;
+ s->rq = req;
+ }
+
+ return 0;
+}
+
+static void virtio_resize_cb(void *opaque)
+{
+ VirtIODevice *vdev = opaque;
+
+ assert(qemu_get_current_aio_context() == qemu_get_aio_context());
+ virtio_notify_config(vdev);
+}
+
+static void virtio_blk_resize(void *opaque)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
+
+ /*
+ * virtio_notify_config() needs to acquire the global mutex,
+ * so it can't be called from an iothread. Instead, schedule
+ * it to be run in the main context BH.
+ */
+ aio_bh_schedule_oneshot(qemu_get_aio_context(), virtio_resize_cb, vdev);
+}
+
+static const BlockDevOps virtio_block_ops = {
+ .resize_cb = virtio_blk_resize,
+};
+
+static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VirtIOBlock *s = VIRTIO_BLK(dev);
+ VirtIOBlkConf *conf = &s->conf;
+ Error *err = NULL;
+ unsigned i;
+
+ if (!conf->conf.blk) {
+ error_setg(errp, "drive property not set");
+ return;
+ }
+ if (!blk_is_inserted(conf->conf.blk)) {
+ error_setg(errp, "Device needs media, but drive is empty");
+ return;
+ }
+ if (conf->num_queues == VIRTIO_BLK_AUTO_NUM_QUEUES) {
+ conf->num_queues = 1;
+ }
+ if (!conf->num_queues) {
+ error_setg(errp, "num-queues property must be larger than 0");
+ return;
+ }
+ if (conf->queue_size <= 2) {
+ error_setg(errp, "invalid queue-size property (%" PRIu16 "), "
+ "must be > 2", conf->queue_size);
+ return;
+ }
+ if (!is_power_of_2(conf->queue_size) ||
+ conf->queue_size > VIRTQUEUE_MAX_SIZE) {
+ error_setg(errp, "invalid queue-size property (%" PRIu16 "), "
+ "must be a power of 2 (max %d)",
+ conf->queue_size, VIRTQUEUE_MAX_SIZE);
+ return;
+ }
+
+ if (!blkconf_apply_backend_options(&conf->conf,
+ !blk_supports_write_perm(conf->conf.blk),
+ true, errp)) {
+ return;
+ }
+ s->original_wce = blk_enable_write_cache(conf->conf.blk);
+ if (!blkconf_geometry(&conf->conf, NULL, 65535, 255, 255, errp)) {
+ return;
+ }
+
+ if (!blkconf_blocksizes(&conf->conf, errp)) {
+ return;
+ }
+
+ if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_DISCARD) &&
+ (!conf->max_discard_sectors ||
+ conf->max_discard_sectors > BDRV_REQUEST_MAX_SECTORS)) {
+ error_setg(errp, "invalid max-discard-sectors property (%" PRIu32 ")"
+ ", must be between 1 and %d",
+ conf->max_discard_sectors, (int)BDRV_REQUEST_MAX_SECTORS);
+ return;
+ }
+
+ if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_WRITE_ZEROES) &&
+ (!conf->max_write_zeroes_sectors ||
+ conf->max_write_zeroes_sectors > BDRV_REQUEST_MAX_SECTORS)) {
+ error_setg(errp, "invalid max-write-zeroes-sectors property (%" PRIu32
+ "), must be between 1 and %d",
+ conf->max_write_zeroes_sectors,
+ (int)BDRV_REQUEST_MAX_SECTORS);
+ return;
+ }
+
+ s->config_size = virtio_get_config_size(&virtio_blk_cfg_size_params,
+ s->host_features);
+ virtio_init(vdev, VIRTIO_ID_BLOCK, s->config_size);
+
+ s->blk = conf->conf.blk;
+ s->rq = NULL;
+ s->sector_mask = (s->conf.conf.logical_block_size / BDRV_SECTOR_SIZE) - 1;
+
+ for (i = 0; i < conf->num_queues; i++) {
+ virtio_add_queue(vdev, conf->queue_size, virtio_blk_handle_output);
+ }
+ qemu_coroutine_inc_pool_size(conf->num_queues * conf->queue_size / 2);
+ virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err);
+ if (err != NULL) {
+ error_propagate(errp, err);
+ for (i = 0; i < conf->num_queues; i++) {
+ virtio_del_queue(vdev, i);
+ }
+ virtio_cleanup(vdev);
+ return;
+ }
+
+ s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
+ blk_ram_registrar_init(&s->blk_ram_registrar, s->blk);
+ blk_set_dev_ops(s->blk, &virtio_block_ops, s);
+
+ blk_iostatus_enable(s->blk);
+
+ add_boot_device_lchs(dev, "/disk@0,0",
+ conf->conf.lcyls,
+ conf->conf.lheads,
+ conf->conf.lsecs);
+}
+
+static void virtio_blk_device_unrealize(DeviceState *dev)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VirtIOBlock *s = VIRTIO_BLK(dev);
+ VirtIOBlkConf *conf = &s->conf;
+ unsigned i;
+
+ blk_drain(s->blk);
+ del_boot_device_lchs(dev, "/disk@0,0");
+ virtio_blk_data_plane_destroy(s->dataplane);
+ s->dataplane = NULL;
+ for (i = 0; i < conf->num_queues; i++) {
+ virtio_del_queue(vdev, i);
+ }
+ qemu_coroutine_dec_pool_size(conf->num_queues * conf->queue_size / 2);
+ blk_ram_registrar_destroy(&s->blk_ram_registrar);
+ qemu_del_vm_change_state_handler(s->change);
+ blockdev_mark_auto_del(s->blk);
+ virtio_cleanup(vdev);
+}
+
+static void virtio_blk_instance_init(Object *obj)
+{
+ VirtIOBlock *s = VIRTIO_BLK(obj);
+
+ device_add_bootindex_property(obj, &s->conf.conf.bootindex,
+ "bootindex", "/disk@0,0",
+ DEVICE(obj));
+}
+
+static const VMStateDescription vmstate_virtio_blk = {
+ .name = "virtio-blk",
+ .minimum_version_id = 2,
+ .version_id = 2,
+ .fields = (VMStateField[]) {
+ VMSTATE_VIRTIO_DEVICE,
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+static Property virtio_blk_properties[] = {
+ DEFINE_BLOCK_PROPERTIES(VirtIOBlock, conf.conf),
+ DEFINE_BLOCK_ERROR_PROPERTIES(VirtIOBlock, conf.conf),
+ DEFINE_BLOCK_CHS_PROPERTIES(VirtIOBlock, conf.conf),
+ DEFINE_PROP_STRING("serial", VirtIOBlock, conf.serial),
+ DEFINE_PROP_BIT64("config-wce", VirtIOBlock, host_features,
+ VIRTIO_BLK_F_CONFIG_WCE, true),
+#ifdef __linux__
+ DEFINE_PROP_BIT64("scsi", VirtIOBlock, host_features,
+ VIRTIO_BLK_F_SCSI, false),
+#endif
+ DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0,
+ true),
+ DEFINE_PROP_UINT16("num-queues", VirtIOBlock, conf.num_queues,
+ VIRTIO_BLK_AUTO_NUM_QUEUES),
+ DEFINE_PROP_UINT16("queue-size", VirtIOBlock, conf.queue_size, 256),
+ DEFINE_PROP_BOOL("seg-max-adjust", VirtIOBlock, conf.seg_max_adjust, true),
+ DEFINE_PROP_LINK("iothread", VirtIOBlock, conf.iothread, TYPE_IOTHREAD,
+ IOThread *),
+ DEFINE_PROP_BIT64("discard", VirtIOBlock, host_features,
+ VIRTIO_BLK_F_DISCARD, true),
+ DEFINE_PROP_BOOL("report-discard-granularity", VirtIOBlock,
+ conf.report_discard_granularity, true),
+ DEFINE_PROP_BIT64("write-zeroes", VirtIOBlock, host_features,
+ VIRTIO_BLK_F_WRITE_ZEROES, true),
+ DEFINE_PROP_UINT32("max-discard-sectors", VirtIOBlock,
+ conf.max_discard_sectors, BDRV_REQUEST_MAX_SECTORS),
+ DEFINE_PROP_UINT32("max-write-zeroes-sectors", VirtIOBlock,
+ conf.max_write_zeroes_sectors, BDRV_REQUEST_MAX_SECTORS),
+ DEFINE_PROP_BOOL("x-enable-wce-if-config-wce", VirtIOBlock,
+ conf.x_enable_wce_if_config_wce, true),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void virtio_blk_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+ VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
+
+ device_class_set_props(dc, virtio_blk_properties);
+ dc->vmsd = &vmstate_virtio_blk;
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+ vdc->realize = virtio_blk_device_realize;
+ vdc->unrealize = virtio_blk_device_unrealize;
+ vdc->get_config = virtio_blk_update_config;
+ vdc->set_config = virtio_blk_set_config;
+ vdc->get_features = virtio_blk_get_features;
+ vdc->set_status = virtio_blk_set_status;
+ vdc->reset = virtio_blk_reset;
+ vdc->save = virtio_blk_save_device;
+ vdc->load = virtio_blk_load_device;
+ vdc->start_ioeventfd = virtio_blk_data_plane_start;
+ vdc->stop_ioeventfd = virtio_blk_data_plane_stop;
+}
+
+static const TypeInfo virtio_blk_info = {
+ .name = TYPE_VIRTIO_BLK,
+ .parent = TYPE_VIRTIO_DEVICE,
+ .instance_size = sizeof(VirtIOBlock),
+ .instance_init = virtio_blk_instance_init,
+ .class_init = virtio_blk_class_init,
+};
+
+static void virtio_register_types(void)
+{
+ type_register_static(&virtio_blk_info);
+}
+
+type_init(virtio_register_types)
diff --git a/hw/block/xen-block.c b/hw/block/xen-block.c
new file mode 100644
index 00000000..345b284d
--- /dev/null
+++ b/hw/block/xen-block.c
@@ -0,0 +1,1023 @@
+/*
+ * Copyright (c) 2018 Citrix Systems Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/cutils.h"
+#include "qemu/main-loop.h"
+#include "qemu/module.h"
+#include "qemu/option.h"
+#include "qapi/error.h"
+#include "qapi/qapi-commands-block-core.h"
+#include "qapi/qapi-commands-qom.h"
+#include "qapi/qapi-visit-block-core.h"
+#include "qapi/qobject-input-visitor.h"
+#include "qapi/visitor.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qstring.h"
+#include "qom/object_interfaces.h"
+#include "hw/xen/xen_common.h"
+#include "hw/block/xen_blkif.h"
+#include "hw/qdev-properties.h"
+#include "hw/xen/xen-block.h"
+#include "hw/xen/xen-backend.h"
+#include "sysemu/blockdev.h"
+#include "sysemu/block-backend.h"
+#include "sysemu/iothread.h"
+#include "dataplane/xen-block.h"
+#include "trace.h"
+
+static char *xen_block_get_name(XenDevice *xendev, Error **errp)
+{
+ XenBlockDevice *blockdev = XEN_BLOCK_DEVICE(xendev);
+ XenBlockVdev *vdev = &blockdev->props.vdev;
+
+ return g_strdup_printf("%lu", vdev->number);
+}
+
+static void xen_block_disconnect(XenDevice *xendev, Error **errp)
+{
+ XenBlockDevice *blockdev = XEN_BLOCK_DEVICE(xendev);
+ const char *type = object_get_typename(OBJECT(blockdev));
+ XenBlockVdev *vdev = &blockdev->props.vdev;
+
+ trace_xen_block_disconnect(type, vdev->disk, vdev->partition);
+
+ xen_block_dataplane_stop(blockdev->dataplane);
+}
+
+static void xen_block_connect(XenDevice *xendev, Error **errp)
+{
+ XenBlockDevice *blockdev = XEN_BLOCK_DEVICE(xendev);
+ const char *type = object_get_typename(OBJECT(blockdev));
+ XenBlockVdev *vdev = &blockdev->props.vdev;
+ BlockConf *conf = &blockdev->props.conf;
+ unsigned int feature_large_sector_size;
+ unsigned int order, nr_ring_ref, *ring_ref, event_channel, protocol;
+ char *str;
+
+ trace_xen_block_connect(type, vdev->disk, vdev->partition);
+
+ if (xen_device_frontend_scanf(xendev, "feature-large-sector-size", "%u",
+ &feature_large_sector_size) != 1) {
+ feature_large_sector_size = 0;
+ }
+
+ if (feature_large_sector_size != 1 &&
+ conf->logical_block_size != XEN_BLKIF_SECTOR_SIZE) {
+ error_setg(errp, "logical_block_size != %u not supported by frontend",
+ XEN_BLKIF_SECTOR_SIZE);
+ return;
+ }
+
+ if (xen_device_frontend_scanf(xendev, "ring-page-order", "%u",
+ &order) != 1) {
+ nr_ring_ref = 1;
+ ring_ref = g_new(unsigned int, nr_ring_ref);
+
+ if (xen_device_frontend_scanf(xendev, "ring-ref", "%u",
+ &ring_ref[0]) != 1) {
+ error_setg(errp, "failed to read ring-ref");
+ g_free(ring_ref);
+ return;
+ }
+ } else if (order <= blockdev->props.max_ring_page_order) {
+ unsigned int i;
+
+ nr_ring_ref = 1 << order;
+ ring_ref = g_new(unsigned int, nr_ring_ref);
+
+ for (i = 0; i < nr_ring_ref; i++) {
+ const char *key = g_strdup_printf("ring-ref%u", i);
+
+ if (xen_device_frontend_scanf(xendev, key, "%u",
+ &ring_ref[i]) != 1) {
+ error_setg(errp, "failed to read %s", key);
+ g_free((gpointer)key);
+ g_free(ring_ref);
+ return;
+ }
+
+ g_free((gpointer)key);
+ }
+ } else {
+ error_setg(errp, "invalid ring-page-order (%d)", order);
+ return;
+ }
+
+ if (xen_device_frontend_scanf(xendev, "event-channel", "%u",
+ &event_channel) != 1) {
+ error_setg(errp, "failed to read event-channel");
+ g_free(ring_ref);
+ return;
+ }
+
+ if (xen_device_frontend_scanf(xendev, "protocol", "%ms",
+ &str) != 1) {
+ protocol = BLKIF_PROTOCOL_NATIVE;
+ } else {
+ if (strcmp(str, XEN_IO_PROTO_ABI_X86_32) == 0) {
+ protocol = BLKIF_PROTOCOL_X86_32;
+ } else if (strcmp(str, XEN_IO_PROTO_ABI_X86_64) == 0) {
+ protocol = BLKIF_PROTOCOL_X86_64;
+ } else {
+ protocol = BLKIF_PROTOCOL_NATIVE;
+ }
+
+ free(str);
+ }
+
+ xen_block_dataplane_start(blockdev->dataplane, ring_ref, nr_ring_ref,
+ event_channel, protocol, errp);
+
+ g_free(ring_ref);
+}
+
+static void xen_block_unrealize(XenDevice *xendev)
+{
+ XenBlockDevice *blockdev = XEN_BLOCK_DEVICE(xendev);
+ XenBlockDeviceClass *blockdev_class =
+ XEN_BLOCK_DEVICE_GET_CLASS(xendev);
+ const char *type = object_get_typename(OBJECT(blockdev));
+ XenBlockVdev *vdev = &blockdev->props.vdev;
+
+ if (vdev->type == XEN_BLOCK_VDEV_TYPE_INVALID) {
+ return;
+ }
+
+ trace_xen_block_unrealize(type, vdev->disk, vdev->partition);
+
+ /* Disconnect from the frontend in case this has not already happened */
+ xen_block_disconnect(xendev, NULL);
+
+ xen_block_dataplane_destroy(blockdev->dataplane);
+ blockdev->dataplane = NULL;
+
+ if (blockdev_class->unrealize) {
+ blockdev_class->unrealize(blockdev);
+ }
+}
+
+static void xen_block_set_size(XenBlockDevice *blockdev)
+{
+ const char *type = object_get_typename(OBJECT(blockdev));
+ XenBlockVdev *vdev = &blockdev->props.vdev;
+ BlockConf *conf = &blockdev->props.conf;
+ int64_t sectors = blk_getlength(conf->blk) / conf->logical_block_size;
+ XenDevice *xendev = XEN_DEVICE(blockdev);
+
+ trace_xen_block_size(type, vdev->disk, vdev->partition, sectors);
+
+ xen_device_backend_printf(xendev, "sectors", "%"PRIi64, sectors);
+}
+
+static void xen_block_resize_cb(void *opaque)
+{
+ XenBlockDevice *blockdev = opaque;
+ XenDevice *xendev = XEN_DEVICE(blockdev);
+ enum xenbus_state state = xen_device_backend_get_state(xendev);
+
+ xen_block_set_size(blockdev);
+
+ /*
+ * Mimic the behaviour of Linux xen-blkback and re-write the state
+ * to trigger the frontend watch.
+ */
+ xen_device_backend_printf(xendev, "state", "%u", state);
+}
+
+static const BlockDevOps xen_block_dev_ops = {
+ .resize_cb = xen_block_resize_cb,
+};
+
+static void xen_block_realize(XenDevice *xendev, Error **errp)
+{
+ ERRP_GUARD();
+ XenBlockDevice *blockdev = XEN_BLOCK_DEVICE(xendev);
+ XenBlockDeviceClass *blockdev_class =
+ XEN_BLOCK_DEVICE_GET_CLASS(xendev);
+ const char *type = object_get_typename(OBJECT(blockdev));
+ XenBlockVdev *vdev = &blockdev->props.vdev;
+ BlockConf *conf = &blockdev->props.conf;
+ BlockBackend *blk = conf->blk;
+
+ if (vdev->type == XEN_BLOCK_VDEV_TYPE_INVALID) {
+ error_setg(errp, "vdev property not set");
+ return;
+ }
+
+ trace_xen_block_realize(type, vdev->disk, vdev->partition);
+
+ if (blockdev_class->realize) {
+ blockdev_class->realize(blockdev, errp);
+ if (*errp) {
+ return;
+ }
+ }
+
+ /*
+ * The blkif protocol does not deal with removable media, so it must
+ * always be present, even for CDRom devices.
+ */
+ assert(blk);
+ if (!blk_is_inserted(blk)) {
+ error_setg(errp, "device needs media, but drive is empty");
+ return;
+ }
+
+ if (!blkconf_apply_backend_options(conf, blockdev->info & VDISK_READONLY,
+ true, errp)) {
+ return;
+ }
+
+ if (!(blockdev->info & VDISK_CDROM) &&
+ !blkconf_geometry(conf, NULL, 65535, 255, 255, errp)) {
+ return;
+ }
+
+ if (!blkconf_blocksizes(conf, errp)) {
+ return;
+ }
+
+ blk_set_dev_ops(blk, &xen_block_dev_ops, blockdev);
+
+ if (conf->discard_granularity == -1) {
+ conf->discard_granularity = conf->physical_block_size;
+ }
+
+ if (blk_get_flags(blk) & BDRV_O_UNMAP) {
+ xen_device_backend_printf(xendev, "feature-discard", "%u", 1);
+ xen_device_backend_printf(xendev, "discard-granularity", "%u",
+ conf->discard_granularity);
+ xen_device_backend_printf(xendev, "discard-alignment", "%u", 0);
+ }
+
+ xen_device_backend_printf(xendev, "feature-flush-cache", "%u", 1);
+ xen_device_backend_printf(xendev, "max-ring-page-order", "%u",
+ blockdev->props.max_ring_page_order);
+ xen_device_backend_printf(xendev, "info", "%u", blockdev->info);
+
+ xen_device_frontend_printf(xendev, "virtual-device", "%lu",
+ vdev->number);
+ xen_device_frontend_printf(xendev, "device-type", "%s",
+ blockdev->device_type);
+
+ xen_device_backend_printf(xendev, "sector-size", "%u",
+ conf->logical_block_size);
+
+ xen_block_set_size(blockdev);
+
+ blockdev->dataplane =
+ xen_block_dataplane_create(xendev, blk, conf->logical_block_size,
+ blockdev->props.iothread);
+}
+
+static void xen_block_frontend_changed(XenDevice *xendev,
+ enum xenbus_state frontend_state,
+ Error **errp)
+{
+ ERRP_GUARD();
+ enum xenbus_state backend_state = xen_device_backend_get_state(xendev);
+
+ switch (frontend_state) {
+ case XenbusStateInitialised:
+ case XenbusStateConnected:
+ if (backend_state == XenbusStateConnected) {
+ break;
+ }
+
+ xen_block_disconnect(xendev, errp);
+ if (*errp) {
+ break;
+ }
+
+ xen_block_connect(xendev, errp);
+ if (*errp) {
+ break;
+ }
+
+ xen_device_backend_set_state(xendev, XenbusStateConnected);
+ break;
+
+ case XenbusStateClosing:
+ xen_device_backend_set_state(xendev, XenbusStateClosing);
+ break;
+
+ case XenbusStateClosed:
+ case XenbusStateUnknown:
+ xen_block_disconnect(xendev, errp);
+ if (*errp) {
+ break;
+ }
+
+ xen_device_backend_set_state(xendev, XenbusStateClosed);
+ break;
+
+ default:
+ break;
+ }
+}
+
+static char *disk_to_vbd_name(unsigned int disk)
+{
+ char *name, *prefix = (disk >= 26) ?
+ disk_to_vbd_name((disk / 26) - 1) : g_strdup("");
+
+ name = g_strdup_printf("%s%c", prefix, 'a' + disk % 26);
+ g_free(prefix);
+
+ return name;
+}
+
+static void xen_block_get_vdev(Object *obj, Visitor *v, const char *name,
+ void *opaque, Error **errp)
+{
+ Property *prop = opaque;
+ XenBlockVdev *vdev = object_field_prop_ptr(obj, prop);
+ char *str;
+
+ switch (vdev->type) {
+ case XEN_BLOCK_VDEV_TYPE_DP:
+ str = g_strdup_printf("d%lup%lu", vdev->disk, vdev->partition);
+ break;
+
+ case XEN_BLOCK_VDEV_TYPE_XVD:
+ case XEN_BLOCK_VDEV_TYPE_HD:
+ case XEN_BLOCK_VDEV_TYPE_SD: {
+ char *name = disk_to_vbd_name(vdev->disk);
+
+ str = g_strdup_printf("%s%s%lu",
+ (vdev->type == XEN_BLOCK_VDEV_TYPE_XVD) ?
+ "xvd" :
+ (vdev->type == XEN_BLOCK_VDEV_TYPE_HD) ?
+ "hd" :
+ "sd",
+ name, vdev->partition);
+ g_free(name);
+ break;
+ }
+ default:
+ error_setg(errp, "invalid vdev type");
+ return;
+ }
+
+ visit_type_str(v, name, &str, errp);
+ g_free(str);
+}
+
+static int vbd_name_to_disk(const char *name, const char **endp,
+ unsigned long *disk)
+{
+ unsigned int n = 0;
+
+ while (*name != '\0') {
+ if (!g_ascii_isalpha(*name) || !g_ascii_islower(*name)) {
+ break;
+ }
+
+ n *= 26;
+ n += *name++ - 'a' + 1;
+ }
+ *endp = name;
+
+ if (!n) {
+ return -1;
+ }
+
+ *disk = n - 1;
+
+ return 0;
+}
+
+static void xen_block_set_vdev(Object *obj, Visitor *v, const char *name,
+ void *opaque, Error **errp)
+{
+ Property *prop = opaque;
+ XenBlockVdev *vdev = object_field_prop_ptr(obj, prop);
+ char *str, *p;
+ const char *end;
+
+ if (!visit_type_str(v, name, &str, errp)) {
+ return;
+ }
+
+ p = strchr(str, 'd');
+ if (!p) {
+ goto invalid;
+ }
+
+ *p++ = '\0';
+ if (*str == '\0') {
+ vdev->type = XEN_BLOCK_VDEV_TYPE_DP;
+ } else if (strcmp(str, "xv") == 0) {
+ vdev->type = XEN_BLOCK_VDEV_TYPE_XVD;
+ } else if (strcmp(str, "h") == 0) {
+ vdev->type = XEN_BLOCK_VDEV_TYPE_HD;
+ } else if (strcmp(str, "s") == 0) {
+ vdev->type = XEN_BLOCK_VDEV_TYPE_SD;
+ } else {
+ goto invalid;
+ }
+
+ if (vdev->type == XEN_BLOCK_VDEV_TYPE_DP) {
+ if (qemu_strtoul(p, &end, 10, &vdev->disk)) {
+ goto invalid;
+ }
+
+ if (*end == 'p') {
+ if (*(++end) == '\0') {
+ goto invalid;
+ }
+ }
+ } else {
+ if (vbd_name_to_disk(p, &end, &vdev->disk)) {
+ goto invalid;
+ }
+ }
+
+ if (*end != '\0') {
+ p = (char *)end;
+
+ if (qemu_strtoul(p, &end, 10, &vdev->partition)) {
+ goto invalid;
+ }
+
+ if (*end != '\0') {
+ goto invalid;
+ }
+ } else {
+ vdev->partition = 0;
+ }
+
+ switch (vdev->type) {
+ case XEN_BLOCK_VDEV_TYPE_DP:
+ case XEN_BLOCK_VDEV_TYPE_XVD:
+ if (vdev->disk < (1 << 4) && vdev->partition < (1 << 4)) {
+ vdev->number = (202 << 8) | (vdev->disk << 4) |
+ vdev->partition;
+ } else if (vdev->disk < (1 << 20) && vdev->partition < (1 << 8)) {
+ vdev->number = (1 << 28) | (vdev->disk << 8) |
+ vdev->partition;
+ } else {
+ goto invalid;
+ }
+ break;
+
+ case XEN_BLOCK_VDEV_TYPE_HD:
+ if ((vdev->disk == 0 || vdev->disk == 1) &&
+ vdev->partition < (1 << 6)) {
+ vdev->number = (3 << 8) | (vdev->disk << 6) | vdev->partition;
+ } else if ((vdev->disk == 2 || vdev->disk == 3) &&
+ vdev->partition < (1 << 6)) {
+ vdev->number = (22 << 8) | ((vdev->disk - 2) << 6) |
+ vdev->partition;
+ } else {
+ goto invalid;
+ }
+ break;
+
+ case XEN_BLOCK_VDEV_TYPE_SD:
+ if (vdev->disk < (1 << 4) && vdev->partition < (1 << 4)) {
+ vdev->number = (8 << 8) | (vdev->disk << 4) | vdev->partition;
+ } else {
+ goto invalid;
+ }
+ break;
+
+ default:
+ goto invalid;
+ }
+
+ g_free(str);
+ return;
+
+invalid:
+ error_setg(errp, "invalid virtual disk specifier");
+
+ vdev->type = XEN_BLOCK_VDEV_TYPE_INVALID;
+ g_free(str);
+}
+
+/*
+ * This property deals with 'vdev' names adhering to the Xen VBD naming
+ * scheme described in:
+ *
+ * https://xenbits.xen.org/docs/unstable/man/xen-vbd-interface.7.html
+ */
+const PropertyInfo xen_block_prop_vdev = {
+ .name = "str",
+ .description = "Virtual Disk specifier: d*p*/xvd*/hd*/sd*",
+ .get = xen_block_get_vdev,
+ .set = xen_block_set_vdev,
+};
+
+static Property xen_block_props[] = {
+ DEFINE_PROP("vdev", XenBlockDevice, props.vdev,
+ xen_block_prop_vdev, XenBlockVdev),
+ DEFINE_BLOCK_PROPERTIES(XenBlockDevice, props.conf),
+ DEFINE_PROP_UINT32("max-ring-page-order", XenBlockDevice,
+ props.max_ring_page_order, 4),
+ DEFINE_PROP_LINK("iothread", XenBlockDevice, props.iothread,
+ TYPE_IOTHREAD, IOThread *),
+ DEFINE_PROP_END_OF_LIST()
+};
+
+static void xen_block_class_init(ObjectClass *class, void *data)
+{
+ DeviceClass *dev_class = DEVICE_CLASS(class);
+ XenDeviceClass *xendev_class = XEN_DEVICE_CLASS(class);
+
+ xendev_class->backend = "qdisk";
+ xendev_class->device = "vbd";
+ xendev_class->get_name = xen_block_get_name;
+ xendev_class->realize = xen_block_realize;
+ xendev_class->frontend_changed = xen_block_frontend_changed;
+ xendev_class->unrealize = xen_block_unrealize;
+
+ device_class_set_props(dev_class, xen_block_props);
+}
+
+static const TypeInfo xen_block_type_info = {
+ .name = TYPE_XEN_BLOCK_DEVICE,
+ .parent = TYPE_XEN_DEVICE,
+ .instance_size = sizeof(XenBlockDevice),
+ .abstract = true,
+ .class_size = sizeof(XenBlockDeviceClass),
+ .class_init = xen_block_class_init,
+};
+
+static void xen_disk_unrealize(XenBlockDevice *blockdev)
+{
+ trace_xen_disk_unrealize();
+}
+
+static void xen_disk_realize(XenBlockDevice *blockdev, Error **errp)
+{
+ BlockConf *conf = &blockdev->props.conf;
+
+ trace_xen_disk_realize();
+
+ blockdev->device_type = "disk";
+
+ if (!conf->blk) {
+ error_setg(errp, "drive property not set");
+ return;
+ }
+
+ blockdev->info = blk_supports_write_perm(conf->blk) ? 0 : VDISK_READONLY;
+}
+
+static void xen_disk_class_init(ObjectClass *class, void *data)
+{
+ DeviceClass *dev_class = DEVICE_CLASS(class);
+ XenBlockDeviceClass *blockdev_class = XEN_BLOCK_DEVICE_CLASS(class);
+
+ blockdev_class->realize = xen_disk_realize;
+ blockdev_class->unrealize = xen_disk_unrealize;
+
+ dev_class->desc = "Xen Disk Device";
+}
+
+static const TypeInfo xen_disk_type_info = {
+ .name = TYPE_XEN_DISK_DEVICE,
+ .parent = TYPE_XEN_BLOCK_DEVICE,
+ .instance_size = sizeof(XenDiskDevice),
+ .class_init = xen_disk_class_init,
+};
+
+static void xen_cdrom_unrealize(XenBlockDevice *blockdev)
+{
+ trace_xen_cdrom_unrealize();
+}
+
+static void xen_cdrom_realize(XenBlockDevice *blockdev, Error **errp)
+{
+ BlockConf *conf = &blockdev->props.conf;
+
+ trace_xen_cdrom_realize();
+
+ blockdev->device_type = "cdrom";
+
+ if (!conf->blk) {
+ int rc;
+
+ /* Set up an empty drive */
+ conf->blk = blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL);
+
+ rc = blk_attach_dev(conf->blk, DEVICE(blockdev));
+ if (!rc) {
+ error_setg_errno(errp, -rc, "failed to create drive");
+ return;
+ }
+ }
+
+ blockdev->info = VDISK_READONLY | VDISK_CDROM;
+}
+
+static void xen_cdrom_class_init(ObjectClass *class, void *data)
+{
+ DeviceClass *dev_class = DEVICE_CLASS(class);
+ XenBlockDeviceClass *blockdev_class = XEN_BLOCK_DEVICE_CLASS(class);
+
+ blockdev_class->realize = xen_cdrom_realize;
+ blockdev_class->unrealize = xen_cdrom_unrealize;
+
+ dev_class->desc = "Xen CD-ROM Device";
+}
+
+static const TypeInfo xen_cdrom_type_info = {
+ .name = TYPE_XEN_CDROM_DEVICE,
+ .parent = TYPE_XEN_BLOCK_DEVICE,
+ .instance_size = sizeof(XenCDRomDevice),
+ .class_init = xen_cdrom_class_init,
+};
+
+static void xen_block_register_types(void)
+{
+ type_register_static(&xen_block_type_info);
+ type_register_static(&xen_disk_type_info);
+ type_register_static(&xen_cdrom_type_info);
+}
+
+type_init(xen_block_register_types)
+
+static void xen_block_blockdev_del(const char *node_name, Error **errp)
+{
+ trace_xen_block_blockdev_del(node_name);
+
+ qmp_blockdev_del(node_name, errp);
+}
+
+static char *xen_block_blockdev_add(const char *id, QDict *qdict,
+ Error **errp)
+{
+ ERRP_GUARD();
+ const char *driver = qdict_get_try_str(qdict, "driver");
+ BlockdevOptions *options = NULL;
+ char *node_name;
+ Visitor *v;
+
+ if (!driver) {
+ error_setg(errp, "no 'driver' parameter");
+ return NULL;
+ }
+
+ node_name = g_strdup_printf("%s-%s", id, driver);
+ qdict_put_str(qdict, "node-name", node_name);
+
+ trace_xen_block_blockdev_add(node_name);
+
+ v = qobject_input_visitor_new(QOBJECT(qdict));
+ visit_type_BlockdevOptions(v, NULL, &options, errp);
+ visit_free(v);
+ if (!options) {
+ goto fail;
+ }
+
+ qmp_blockdev_add(options, errp);
+
+ if (*errp) {
+ goto fail;
+ }
+
+ qapi_free_BlockdevOptions(options);
+
+ return node_name;
+
+fail:
+ if (options) {
+ qapi_free_BlockdevOptions(options);
+ }
+ g_free(node_name);
+
+ return NULL;
+}
+
+static void xen_block_drive_destroy(XenBlockDrive *drive, Error **errp)
+{
+ ERRP_GUARD();
+ char *node_name = drive->node_name;
+
+ if (node_name) {
+ xen_block_blockdev_del(node_name, errp);
+ if (*errp) {
+ return;
+ }
+ g_free(node_name);
+ drive->node_name = NULL;
+ }
+ g_free(drive->id);
+ g_free(drive);
+}
+
+static XenBlockDrive *xen_block_drive_create(const char *id,
+ const char *device_type,
+ QDict *opts, Error **errp)
+{
+ ERRP_GUARD();
+ const char *params = qdict_get_try_str(opts, "params");
+ const char *mode = qdict_get_try_str(opts, "mode");
+ const char *direct_io_safe = qdict_get_try_str(opts, "direct-io-safe");
+ const char *discard_enable = qdict_get_try_str(opts, "discard-enable");
+ char *driver = NULL;
+ char *filename = NULL;
+ XenBlockDrive *drive = NULL;
+ QDict *file_layer;
+ QDict *driver_layer;
+ struct stat st;
+ int rc;
+
+ if (params) {
+ char **v = g_strsplit(params, ":", 2);
+
+ if (v[1] == NULL) {
+ filename = g_strdup(v[0]);
+ driver = g_strdup("raw");
+ } else {
+ if (strcmp(v[0], "aio") == 0) {
+ driver = g_strdup("raw");
+ } else if (strcmp(v[0], "vhd") == 0) {
+ driver = g_strdup("vpc");
+ } else {
+ driver = g_strdup(v[0]);
+ }
+ filename = g_strdup(v[1]);
+ }
+
+ g_strfreev(v);
+ } else {
+ error_setg(errp, "no params");
+ goto done;
+ }
+
+ assert(filename);
+ assert(driver);
+
+ drive = g_new0(XenBlockDrive, 1);
+ drive->id = g_strdup(id);
+
+ file_layer = qdict_new();
+ driver_layer = qdict_new();
+
+ rc = stat(filename, &st);
+ if (rc) {
+ error_setg_errno(errp, errno, "Could not stat file '%s'", filename);
+ goto done;
+ }
+ if (S_ISBLK(st.st_mode)) {
+ qdict_put_str(file_layer, "driver", "host_device");
+ } else {
+ qdict_put_str(file_layer, "driver", "file");
+ }
+
+ qdict_put_str(file_layer, "filename", filename);
+ g_free(filename);
+
+ if (mode && *mode != 'w') {
+ qdict_put_bool(file_layer, "read-only", true);
+ }
+
+ if (direct_io_safe) {
+ unsigned long value;
+
+ if (!qemu_strtoul(direct_io_safe, NULL, 2, &value) && !!value) {
+ QDict *cache_qdict = qdict_new();
+
+ qdict_put_bool(cache_qdict, "direct", true);
+ qdict_put(file_layer, "cache", cache_qdict);
+
+ qdict_put_str(file_layer, "aio", "native");
+ }
+ }
+
+ if (discard_enable) {
+ unsigned long value;
+
+ if (!qemu_strtoul(discard_enable, NULL, 2, &value) && !!value) {
+ qdict_put_str(file_layer, "discard", "unmap");
+ qdict_put_str(driver_layer, "discard", "unmap");
+ }
+ }
+
+ /*
+ * It is necessary to turn file locking off as an emulated device
+ * may have already opened the same image file.
+ */
+ qdict_put_str(file_layer, "locking", "off");
+
+ qdict_put_str(driver_layer, "driver", driver);
+ g_free(driver);
+
+ qdict_put(driver_layer, "file", file_layer);
+
+ g_assert(!drive->node_name);
+ drive->node_name = xen_block_blockdev_add(drive->id, driver_layer,
+ errp);
+
+ qobject_unref(driver_layer);
+
+done:
+ if (*errp) {
+ xen_block_drive_destroy(drive, NULL);
+ return NULL;
+ }
+
+ return drive;
+}
+
+static const char *xen_block_drive_get_node_name(XenBlockDrive *drive)
+{
+ return drive->node_name ? drive->node_name : "";
+}
+
+static void xen_block_iothread_destroy(XenBlockIOThread *iothread,
+ Error **errp)
+{
+ qmp_object_del(iothread->id, errp);
+
+ g_free(iothread->id);
+ g_free(iothread);
+}
+
+static XenBlockIOThread *xen_block_iothread_create(const char *id,
+ Error **errp)
+{
+ ERRP_GUARD();
+ XenBlockIOThread *iothread = g_new(XenBlockIOThread, 1);
+ ObjectOptions *opts;
+
+ iothread->id = g_strdup(id);
+
+ opts = g_new(ObjectOptions, 1);
+ *opts = (ObjectOptions) {
+ .qom_type = OBJECT_TYPE_IOTHREAD,
+ .id = g_strdup(id),
+ };
+ qmp_object_add(opts, errp);
+ qapi_free_ObjectOptions(opts);
+
+ if (*errp) {
+ g_free(iothread->id);
+ g_free(iothread);
+ return NULL;
+ }
+
+ return iothread;
+}
+
+static void xen_block_device_create(XenBackendInstance *backend,
+ QDict *opts, Error **errp)
+{
+ ERRP_GUARD();
+ XenBus *xenbus = xen_backend_get_bus(backend);
+ const char *name = xen_backend_get_name(backend);
+ unsigned long number;
+ const char *vdev, *device_type;
+ XenBlockDrive *drive = NULL;
+ XenBlockIOThread *iothread = NULL;
+ XenDevice *xendev = NULL;
+ const char *type;
+ XenBlockDevice *blockdev;
+
+ if (qemu_strtoul(name, NULL, 10, &number)) {
+ error_setg(errp, "failed to parse name '%s'", name);
+ goto fail;
+ }
+
+ trace_xen_block_device_create(number);
+
+ vdev = qdict_get_try_str(opts, "dev");
+ if (!vdev) {
+ error_setg(errp, "no dev parameter");
+ goto fail;
+ }
+
+ device_type = qdict_get_try_str(opts, "device-type");
+ if (!device_type) {
+ error_setg(errp, "no device-type parameter");
+ goto fail;
+ }
+
+ if (!strcmp(device_type, "disk")) {
+ type = TYPE_XEN_DISK_DEVICE;
+ } else if (!strcmp(device_type, "cdrom")) {
+ type = TYPE_XEN_CDROM_DEVICE;
+ } else {
+ error_setg(errp, "invalid device-type parameter '%s'", device_type);
+ goto fail;
+ }
+
+ drive = xen_block_drive_create(vdev, device_type, opts, errp);
+ if (!drive) {
+ error_prepend(errp, "failed to create drive: ");
+ goto fail;
+ }
+
+ iothread = xen_block_iothread_create(vdev, errp);
+ if (*errp) {
+ error_prepend(errp, "failed to create iothread: ");
+ goto fail;
+ }
+
+ xendev = XEN_DEVICE(qdev_new(type));
+ blockdev = XEN_BLOCK_DEVICE(xendev);
+
+ if (!object_property_set_str(OBJECT(xendev), "vdev", vdev,
+ errp)) {
+ error_prepend(errp, "failed to set 'vdev': ");
+ goto fail;
+ }
+
+ if (!object_property_set_str(OBJECT(xendev), "drive",
+ xen_block_drive_get_node_name(drive),
+ errp)) {
+ error_prepend(errp, "failed to set 'drive': ");
+ goto fail;
+ }
+
+ if (!object_property_set_str(OBJECT(xendev), "iothread", iothread->id,
+ errp)) {
+ error_prepend(errp, "failed to set 'iothread': ");
+ goto fail;
+ }
+
+ blockdev->iothread = iothread;
+ blockdev->drive = drive;
+
+ if (!qdev_realize_and_unref(DEVICE(xendev), BUS(xenbus), errp)) {
+ error_prepend(errp, "realization of device %s failed: ", type);
+ goto fail;
+ }
+
+ xen_backend_set_device(backend, xendev);
+ return;
+
+fail:
+ if (xendev) {
+ object_unparent(OBJECT(xendev));
+ }
+
+ if (iothread) {
+ xen_block_iothread_destroy(iothread, NULL);
+ }
+
+ if (drive) {
+ xen_block_drive_destroy(drive, NULL);
+ }
+}
+
+static void xen_block_device_destroy(XenBackendInstance *backend,
+ Error **errp)
+{
+ ERRP_GUARD();
+ XenDevice *xendev = xen_backend_get_device(backend);
+ XenBlockDevice *blockdev = XEN_BLOCK_DEVICE(xendev);
+ XenBlockVdev *vdev = &blockdev->props.vdev;
+ XenBlockDrive *drive = blockdev->drive;
+ XenBlockIOThread *iothread = blockdev->iothread;
+
+ trace_xen_block_device_destroy(vdev->number);
+
+ object_unparent(OBJECT(xendev));
+
+ /*
+ * Drain all pending RCU callbacks as object_unparent() frees `xendev'
+ * in a RCU callback.
+ * And due to the property "drive" still existing in `xendev', we
+ * can't destroy the XenBlockDrive associated with `xendev' with
+ * xen_block_drive_destroy() below.
+ */
+ drain_call_rcu();
+
+ if (iothread) {
+ xen_block_iothread_destroy(iothread, errp);
+ if (*errp) {
+ error_prepend(errp, "failed to destroy iothread: ");
+ return;
+ }
+ }
+
+ if (drive) {
+ xen_block_drive_destroy(drive, errp);
+ if (*errp) {
+ error_prepend(errp, "failed to destroy drive: ");
+ return;
+ }
+ }
+}
+
+static const XenBackendInfo xen_block_backend_info = {
+ .type = "qdisk",
+ .create = xen_block_device_create,
+ .destroy = xen_block_device_destroy,
+};
+
+static void xen_block_register_backend(void)
+{
+ xen_backend_register(&xen_block_backend_info);
+}
+
+xen_backend_init(xen_block_register_backend);
diff --git a/hw/block/xen_blkif.h b/hw/block/xen_blkif.h
new file mode 100644
index 00000000..99733529
--- /dev/null
+++ b/hw/block/xen_blkif.h
@@ -0,0 +1,147 @@
+#ifndef XEN_BLKIF_H
+#define XEN_BLKIF_H
+
+#include "hw/xen/interface/io/blkif.h"
+#include "hw/xen/interface/io/protocols.h"
+
+/*
+ * Not a real protocol. Used to generate ring structs which contain
+ * the elements common to all protocols only. This way we get a
+ * compiler-checkable way to use common struct elements, so we can
+ * avoid using switch(protocol) in a number of places.
+ */
+struct blkif_common_request {
+ char dummy;
+};
+struct blkif_common_response {
+ char dummy;
+};
+
+/* i386 protocol version */
+#pragma pack(push, 4)
+struct blkif_x86_32_request {
+ uint8_t operation; /* BLKIF_OP_??? */
+ uint8_t nr_segments; /* number of segments */
+ blkif_vdev_t handle; /* only for read/write requests */
+ uint64_t id; /* private guest value, echoed in resp */
+ blkif_sector_t sector_number; /* start sector idx on disk (r/w only) */
+ struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+};
+struct blkif_x86_32_request_discard {
+ uint8_t operation; /* BLKIF_OP_DISCARD */
+ uint8_t flag; /* nr_segments in request struct */
+ blkif_vdev_t handle; /* only for read/write requests */
+ uint64_t id; /* private guest value, echoed in resp */
+ blkif_sector_t sector_number; /* start sector idx on disk (r/w only) */
+ uint64_t nr_sectors; /* # of contiguous sectors to discard */
+};
+struct blkif_x86_32_response {
+ uint64_t id; /* copied from request */
+ uint8_t operation; /* copied from request */
+ int16_t status; /* BLKIF_RSP_??? */
+};
+typedef struct blkif_x86_32_request blkif_x86_32_request_t;
+typedef struct blkif_x86_32_response blkif_x86_32_response_t;
+#pragma pack(pop)
+
+/* x86_64 protocol version */
+struct blkif_x86_64_request {
+ uint8_t operation; /* BLKIF_OP_??? */
+ uint8_t nr_segments; /* number of segments */
+ blkif_vdev_t handle; /* only for read/write requests */
+ uint64_t __attribute__((__aligned__(8))) id;
+ blkif_sector_t sector_number; /* start sector idx on disk (r/w only) */
+ struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+};
+struct blkif_x86_64_request_discard {
+ uint8_t operation; /* BLKIF_OP_DISCARD */
+ uint8_t flag; /* nr_segments in request struct */
+ blkif_vdev_t handle; /* only for read/write requests */
+ uint64_t __attribute__((__aligned__(8))) id;
+ blkif_sector_t sector_number; /* start sector idx on disk (r/w only) */
+ uint64_t nr_sectors; /* # of contiguous sectors to discard */
+};
+struct blkif_x86_64_response {
+ uint64_t __attribute__((__aligned__(8))) id;
+ uint8_t operation; /* copied from request */
+ int16_t status; /* BLKIF_RSP_??? */
+};
+typedef struct blkif_x86_64_request blkif_x86_64_request_t;
+typedef struct blkif_x86_64_response blkif_x86_64_response_t;
+
+DEFINE_RING_TYPES(blkif_common, struct blkif_common_request,
+ struct blkif_common_response);
+DEFINE_RING_TYPES(blkif_x86_32, struct blkif_x86_32_request,
+ struct blkif_x86_32_response);
+DEFINE_RING_TYPES(blkif_x86_64, struct blkif_x86_64_request,
+ struct blkif_x86_64_response);
+
+union blkif_back_rings {
+ blkif_back_ring_t native;
+ blkif_common_back_ring_t common;
+ blkif_x86_32_back_ring_t x86_32_part;
+ blkif_x86_64_back_ring_t x86_64_part;
+};
+typedef union blkif_back_rings blkif_back_rings_t;
+
+enum blkif_protocol {
+ BLKIF_PROTOCOL_NATIVE = 1,
+ BLKIF_PROTOCOL_X86_32 = 2,
+ BLKIF_PROTOCOL_X86_64 = 3,
+};
+
+static inline void blkif_get_x86_32_req(blkif_request_t *dst,
+ blkif_x86_32_request_t *src)
+{
+ int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+ dst->operation = src->operation;
+ dst->nr_segments = src->nr_segments;
+ dst->handle = src->handle;
+ dst->id = src->id;
+ dst->sector_number = src->sector_number;
+ /* Prevent the compiler from using src->... instead. */
+ barrier();
+ if (dst->operation == BLKIF_OP_DISCARD) {
+ struct blkif_x86_32_request_discard *s = (void *)src;
+ struct blkif_request_discard *d = (void *)dst;
+ d->nr_sectors = s->nr_sectors;
+ return;
+ }
+ if (n > dst->nr_segments) {
+ n = dst->nr_segments;
+ }
+ for (i = 0; i < n; i++) {
+ dst->seg[i] = src->seg[i];
+ }
+}
+
+static inline void blkif_get_x86_64_req(blkif_request_t *dst,
+ blkif_x86_64_request_t *src)
+{
+ int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+ dst->operation = src->operation;
+ dst->nr_segments = src->nr_segments;
+ dst->handle = src->handle;
+ dst->id = src->id;
+ dst->sector_number = src->sector_number;
+ /* Prevent the compiler from using src->... instead. */
+ barrier();
+ if (dst->operation == BLKIF_OP_DISCARD) {
+ struct blkif_x86_64_request_discard *s = (void *)src;
+ struct blkif_request_discard *d = (void *)dst;
+ d->nr_sectors = s->nr_sectors;
+ return;
+ }
+ if (n > dst->nr_segments) {
+ n = dst->nr_segments;
+ }
+ for (i = 0; i < n; i++) {
+ dst->seg[i] = src->seg[i];
+ }
+}
+
+#define XEN_BLKIF_SECTOR_SIZE 512
+
+#endif /* XEN_BLKIF_H */