Merge remote-tracking branch 'remotes/riku/tags/pull-linux-user-20141101' into staging
linux-user pull for 2.2
Two minor fixes and new a feature, addition of QEMU_RAND_SEED for
testing needs.
# gpg: Signature made Mon 03 Nov 2014 11:49:39 GMT using RSA key ID DE3C9BC0
# gpg: Good signature from "Riku Voipio <riku.voipio@iki.fi>"
# gpg: aka "Riku Voipio <riku.voipio@linaro.org>"
* remotes/riku/tags/pull-linux-user-20141101:
elf: take phdr offset into account when calculating the program load address
linux-user: Fix fault address truncation AArch64
linux-user: Let user specify random seed
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/MAINTAINERS b/MAINTAINERS
index 94366ef..dd02d96 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -583,12 +583,13 @@
sim
M: Max Filippov <jcmvbkbc@gmail.com>
S: Maintained
-F: hw/xtensa/xtensa_sim.c
+F: hw/xtensa/sim.c
-Avnet LX60
+XTFPGA (LX60, LX200, ML605, KC705)
M: Max Filippov <jcmvbkbc@gmail.com>
S: Maintained
-F: hw/xtensa/xtensa_lx60.c
+F: hw/xtensa/xtfpga.c
+F: hw/net/opencores_eth.c
Devices
-------
diff --git a/block.c b/block.c
index 88f6d9b..dacd881 100644
--- a/block.c
+++ b/block.c
@@ -519,6 +519,7 @@
return;
}
bs->bl.opt_transfer_length = bs->file->bl.opt_transfer_length;
+ bs->bl.max_transfer_length = bs->file->bl.max_transfer_length;
bs->bl.opt_mem_alignment = bs->file->bl.opt_mem_alignment;
} else {
bs->bl.opt_mem_alignment = 512;
@@ -533,6 +534,9 @@
bs->bl.opt_transfer_length =
MAX(bs->bl.opt_transfer_length,
bs->backing_hd->bl.opt_transfer_length);
+ bs->bl.max_transfer_length =
+ MIN_NON_ZERO(bs->bl.max_transfer_length,
+ bs->backing_hd->bl.max_transfer_length);
bs->bl.opt_mem_alignment =
MAX(bs->bl.opt_mem_alignment,
bs->backing_hd->bl.opt_mem_alignment);
@@ -1900,6 +1904,34 @@
return false;
}
+static bool bdrv_drain_one(BlockDriverState *bs)
+{
+ bool bs_busy;
+
+ bdrv_flush_io_queue(bs);
+ bdrv_start_throttled_reqs(bs);
+ bs_busy = bdrv_requests_pending(bs);
+ bs_busy |= aio_poll(bdrv_get_aio_context(bs), bs_busy);
+ return bs_busy;
+}
+
+/*
+ * Wait for pending requests to complete on a single BlockDriverState subtree
+ *
+ * See the warning in bdrv_drain_all(). This function can only be called if
+ * you are sure nothing can generate I/O because you have op blockers
+ * installed.
+ *
+ * Note that unlike bdrv_drain_all(), the caller must hold the BlockDriverState
+ * AioContext.
+ */
+void bdrv_drain(BlockDriverState *bs)
+{
+ while (bdrv_drain_one(bs)) {
+ /* Keep iterating */
+ }
+}
+
/*
* Wait for pending requests to complete across all BlockDriverStates
*
@@ -1923,16 +1955,10 @@
QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
AioContext *aio_context = bdrv_get_aio_context(bs);
- bool bs_busy;
aio_context_acquire(aio_context);
- bdrv_flush_io_queue(bs);
- bdrv_start_throttled_reqs(bs);
- bs_busy = bdrv_requests_pending(bs);
- bs_busy |= aio_poll(aio_context, bs_busy);
+ busy |= bdrv_drain_one(bs);
aio_context_release(aio_context);
-
- busy |= bs_busy;
}
}
}
@@ -3540,10 +3566,10 @@
BlockErrorAction action,
bool is_read, int error)
{
- BlockErrorAction ac;
+ IoOperationType optype;
- ac = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
- qapi_event_send_block_io_error(bdrv_get_device_name(bs), ac, action,
+ optype = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
+ qapi_event_send_block_io_error(bdrv_get_device_name(bs), optype, action,
bdrv_iostatus_is_enabled(bs),
error == ENOSPC, strerror(error),
&error_abort);
@@ -4442,6 +4468,11 @@
merge = 0;
}
+ if (bs->bl.max_transfer_length && reqs[outidx].nb_sectors +
+ reqs[i].nb_sectors > bs->bl.max_transfer_length) {
+ merge = 0;
+ }
+
if (merge) {
size_t size;
QEMUIOVector *qiov = g_malloc0(sizeof(*qiov));
@@ -5750,12 +5781,13 @@
notifier_with_return_list_add(&bs->before_write_notifiers, notifier);
}
-int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts)
+int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts,
+ BlockDriverAmendStatusCB *status_cb)
{
if (!bs->drv->bdrv_amend_options) {
return -ENOTSUP;
}
- return bs->drv->bdrv_amend_options(bs, opts);
+ return bs->drv->bdrv_amend_options(bs, opts, status_cb);
}
/* This function will be called by the bdrv_recurse_is_first_non_filter method
@@ -5818,13 +5850,19 @@
BlockDriverState *check_to_replace_node(const char *node_name, Error **errp)
{
BlockDriverState *to_replace_bs = bdrv_find_node(node_name);
+ AioContext *aio_context;
+
if (!to_replace_bs) {
error_setg(errp, "Node name '%s' not found", node_name);
return NULL;
}
+ aio_context = bdrv_get_aio_context(to_replace_bs);
+ aio_context_acquire(aio_context);
+
if (bdrv_op_is_blocked(to_replace_bs, BLOCK_OP_TYPE_REPLACE, errp)) {
- return NULL;
+ to_replace_bs = NULL;
+ goto out;
}
/* We don't want arbitrary node of the BDS chain to be replaced only the top
@@ -5834,9 +5872,12 @@
*/
if (!bdrv_is_first_non_filter(to_replace_bs)) {
error_setg(errp, "Only top most non filter can be replaced");
- return NULL;
+ to_replace_bs = NULL;
+ goto out;
}
+out:
+ aio_context_release(aio_context);
return to_replace_bs;
}
diff --git a/block/Makefile.objs b/block/Makefile.objs
index 27911b6..04b0e43 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -9,7 +9,7 @@
block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
block-obj-$(CONFIG_POSIX) += raw-posix.o
block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
-block-obj-y += null.o
+block-obj-y += null.o mirror.o
block-obj-y += nbd.o nbd-client.o sheepdog.o
block-obj-$(CONFIG_LIBISCSI) += iscsi.o
@@ -23,7 +23,6 @@
common-obj-y += stream.o
common-obj-y += commit.o
-common-obj-y += mirror.o
common-obj-y += backup.o
iscsi.o-cflags := $(LIBISCSI_CFLAGS)
diff --git a/block/backup.c b/block/backup.c
index e334740..792e655 100644
--- a/block/backup.c
+++ b/block/backup.c
@@ -227,9 +227,25 @@
}
}
+typedef struct {
+ int ret;
+} BackupCompleteData;
+
+static void backup_complete(BlockJob *job, void *opaque)
+{
+ BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+ BackupCompleteData *data = opaque;
+
+ bdrv_unref(s->target);
+
+ block_job_completed(job, data->ret);
+ g_free(data);
+}
+
static void coroutine_fn backup_run(void *opaque)
{
BackupBlockJob *job = opaque;
+ BackupCompleteData *data;
BlockDriverState *bs = job->common.bs;
BlockDriverState *target = job->target;
BlockdevOnError on_target_error = job->on_target_error;
@@ -344,9 +360,10 @@
hbitmap_free(job->bitmap);
bdrv_iostatus_disable(target);
- bdrv_unref(target);
- block_job_completed(&job->common, ret);
+ data = g_malloc(sizeof(*data));
+ data->ret = ret;
+ block_job_defer_to_main_loop(&job->common, backup_complete, data);
}
void backup_start(BlockDriverState *bs, BlockDriverState *target,
diff --git a/block/blkdebug.c b/block/blkdebug.c
index e046b92..862d93b 100644
--- a/block/blkdebug.c
+++ b/block/blkdebug.c
@@ -195,6 +195,8 @@
[BLKDBG_PWRITEV] = "pwritev",
[BLKDBG_PWRITEV_ZERO] = "pwritev_zero",
[BLKDBG_PWRITEV_DONE] = "pwritev_done",
+
+ [BLKDBG_EMPTY_IMAGE_PREPARE] = "empty_image_prepare",
};
static int get_event_by_name(const char *name, BlkDebugEvent *event)
diff --git a/block/commit.c b/block/commit.c
index 60a2acc..cfa2bbe 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -60,17 +60,50 @@
return 0;
}
-static void coroutine_fn commit_run(void *opaque)
+typedef struct {
+ int ret;
+} CommitCompleteData;
+
+static void commit_complete(BlockJob *job, void *opaque)
{
- CommitBlockJob *s = opaque;
+ CommitBlockJob *s = container_of(job, CommitBlockJob, common);
+ CommitCompleteData *data = opaque;
BlockDriverState *active = s->active;
BlockDriverState *top = s->top;
BlockDriverState *base = s->base;
BlockDriverState *overlay_bs;
+ int ret = data->ret;
+
+ if (!block_job_is_cancelled(&s->common) && ret == 0) {
+ /* success */
+ ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
+ }
+
+ /* restore base open flags here if appropriate (e.g., change the base back
+ * to r/o). These reopens do not need to be atomic, since we won't abort
+ * even on failure here */
+ if (s->base_flags != bdrv_get_flags(base)) {
+ bdrv_reopen(base, s->base_flags, NULL);
+ }
+ overlay_bs = bdrv_find_overlay(active, top);
+ if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
+ bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
+ }
+ g_free(s->backing_file_str);
+ block_job_completed(&s->common, ret);
+ g_free(data);
+}
+
+static void coroutine_fn commit_run(void *opaque)
+{
+ CommitBlockJob *s = opaque;
+ CommitCompleteData *data;
+ BlockDriverState *top = s->top;
+ BlockDriverState *base = s->base;
int64_t sector_num, end;
int ret = 0;
int n = 0;
- void *buf;
+ void *buf = NULL;
int bytes_written = 0;
int64_t base_len;
@@ -78,18 +111,18 @@
if (s->common.len < 0) {
- goto exit_restore_reopen;
+ goto out;
}
ret = base_len = bdrv_getlength(base);
if (base_len < 0) {
- goto exit_restore_reopen;
+ goto out;
}
if (base_len < s->common.len) {
ret = bdrv_truncate(base, s->common.len);
if (ret) {
- goto exit_restore_reopen;
+ goto out;
}
}
@@ -128,7 +161,7 @@
if (s->on_error == BLOCKDEV_ON_ERROR_STOP ||
s->on_error == BLOCKDEV_ON_ERROR_REPORT||
(s->on_error == BLOCKDEV_ON_ERROR_ENOSPC && ret == -ENOSPC)) {
- goto exit_free_buf;
+ goto out;
} else {
n = 0;
continue;
@@ -140,27 +173,12 @@
ret = 0;
- if (!block_job_is_cancelled(&s->common) && sector_num == end) {
- /* success */
- ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
- }
-
-exit_free_buf:
+out:
qemu_vfree(buf);
-exit_restore_reopen:
- /* restore base open flags here if appropriate (e.g., change the base back
- * to r/o). These reopens do not need to be atomic, since we won't abort
- * even on failure here */
- if (s->base_flags != bdrv_get_flags(base)) {
- bdrv_reopen(base, s->base_flags, NULL);
- }
- overlay_bs = bdrv_find_overlay(active, top);
- if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
- bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
- }
- g_free(s->backing_file_str);
- block_job_completed(&s->common, ret);
+ data = g_malloc(sizeof(*data));
+ data->ret = ret;
+ block_job_defer_to_main_loop(&s->common, commit_complete, data);
}
static void commit_set_speed(BlockJob *job, int64_t speed, Error **errp)
diff --git a/block/curl.c b/block/curl.c
index b4157cc..bbee3ca 100644
--- a/block/curl.c
+++ b/block/curl.c
@@ -64,6 +64,7 @@
#define SECTOR_SIZE 512
#define READ_AHEAD_DEFAULT (256 * 1024)
#define CURL_TIMEOUT_DEFAULT 5
+#define CURL_TIMEOUT_MAX 10000
#define FIND_RET_NONE 0
#define FIND_RET_OK 1
@@ -112,7 +113,7 @@
char *url;
size_t readahead_size;
bool sslverify;
- int timeout;
+ uint64_t timeout;
char *cookie;
bool accept_range;
AioContext *aio_context;
@@ -390,7 +391,7 @@
if (s->cookie) {
curl_easy_setopt(state->curl, CURLOPT_COOKIE, s->cookie);
}
- curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, s->timeout);
+ curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, (long)s->timeout);
curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION,
(void *)curl_read_cb);
curl_easy_setopt(state->curl, CURLOPT_WRITEDATA, (void *)state);
@@ -546,6 +547,10 @@
s->timeout = qemu_opt_get_number(opts, CURL_BLOCK_OPT_TIMEOUT,
CURL_TIMEOUT_DEFAULT);
+ if (s->timeout > CURL_TIMEOUT_MAX) {
+ error_setg(errp, "timeout parameter is too large or negative");
+ goto out_noclean;
+ }
s->sslverify = qemu_opt_get_bool(opts, CURL_BLOCK_OPT_SSLVERIFY, true);
diff --git a/block/iscsi.c b/block/iscsi.c
index 233f462..ed375fc 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -362,6 +362,12 @@
return -EINVAL;
}
+ if (bs->bl.max_transfer_length && nb_sectors > bs->bl.max_transfer_length) {
+ error_report("iSCSI Error: Write of %d sectors exceeds max_xfer_len "
+ "of %d sectors", nb_sectors, bs->bl.max_transfer_length);
+ return -EINVAL;
+ }
+
lba = sector_qemu2lun(sector_num, iscsilun);
num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
iscsi_co_init_iscsitask(iscsilun, &iTask);
@@ -529,6 +535,12 @@
return -EINVAL;
}
+ if (bs->bl.max_transfer_length && nb_sectors > bs->bl.max_transfer_length) {
+ error_report("iSCSI Error: Read of %d sectors exceeds max_xfer_len "
+ "of %d sectors", nb_sectors, bs->bl.max_transfer_length);
+ return -EINVAL;
+ }
+
if (iscsilun->lbprz && nb_sectors >= ISCSI_CHECKALLOC_THRES &&
!iscsi_allocationmap_is_allocated(iscsilun, sector_num, nb_sectors)) {
int64_t ret;
@@ -1219,6 +1231,40 @@
qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);
}
+static bool iscsi_is_write_protected(IscsiLun *iscsilun)
+{
+ struct scsi_task *task;
+ struct scsi_mode_sense *ms = NULL;
+ bool wrprotected = false;
+
+ task = iscsi_modesense6_sync(iscsilun->iscsi, iscsilun->lun,
+ 1, SCSI_MODESENSE_PC_CURRENT,
+ 0x3F, 0, 255);
+ if (task == NULL) {
+ error_report("iSCSI: Failed to send MODE_SENSE(6) command: %s",
+ iscsi_get_error(iscsilun->iscsi));
+ goto out;
+ }
+
+ if (task->status != SCSI_STATUS_GOOD) {
+ error_report("iSCSI: Failed MODE_SENSE(6), LUN assumed writable");
+ goto out;
+ }
+ ms = scsi_datain_unmarshall(task);
+ if (!ms) {
+ error_report("iSCSI: Failed to unmarshall MODE_SENSE(6) data: %s",
+ iscsi_get_error(iscsilun->iscsi));
+ goto out;
+ }
+ wrprotected = ms->device_specific_parameter & 0x80;
+
+out:
+ if (task) {
+ scsi_free_scsi_task(task);
+ }
+ return wrprotected;
+}
+
/*
* We support iscsi url's on the form
* iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun>
@@ -1339,6 +1385,14 @@
scsi_free_scsi_task(task);
task = NULL;
+ /* Check the write protect flag of the LUN if we want to write */
+ if (iscsilun->type == TYPE_DISK && (flags & BDRV_O_RDWR) &&
+ iscsi_is_write_protected(iscsilun)) {
+ error_setg(errp, "Cannot open a write protected LUN as read-write");
+ ret = -EACCES;
+ goto out;
+ }
+
iscsi_readcapacity_sync(iscsilun, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
@@ -1447,31 +1501,44 @@
memset(iscsilun, 0, sizeof(IscsiLun));
}
+static int sector_limits_lun2qemu(int64_t sector, IscsiLun *iscsilun)
+{
+ return MIN(sector_lun2qemu(sector, iscsilun), INT_MAX / 2 + 1);
+}
+
static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp)
{
- IscsiLun *iscsilun = bs->opaque;
-
/* We don't actually refresh here, but just return data queried in
* iscsi_open(): iscsi targets don't change their limits. */
+
+ IscsiLun *iscsilun = bs->opaque;
+ uint32_t max_xfer_len = iscsilun->use_16_for_rw ? 0xffffffff : 0xffff;
+
+ if (iscsilun->bl.max_xfer_len) {
+ max_xfer_len = MIN(max_xfer_len, iscsilun->bl.max_xfer_len);
+ }
+
+ bs->bl.max_transfer_length = sector_limits_lun2qemu(max_xfer_len, iscsilun);
+
if (iscsilun->lbp.lbpu) {
if (iscsilun->bl.max_unmap < 0xffffffff) {
- bs->bl.max_discard = sector_lun2qemu(iscsilun->bl.max_unmap,
- iscsilun);
+ bs->bl.max_discard =
+ sector_limits_lun2qemu(iscsilun->bl.max_unmap, iscsilun);
}
- bs->bl.discard_alignment = sector_lun2qemu(iscsilun->bl.opt_unmap_gran,
- iscsilun);
+ bs->bl.discard_alignment =
+ sector_limits_lun2qemu(iscsilun->bl.opt_unmap_gran, iscsilun);
}
if (iscsilun->bl.max_ws_len < 0xffffffff) {
- bs->bl.max_write_zeroes = sector_lun2qemu(iscsilun->bl.max_ws_len,
- iscsilun);
+ bs->bl.max_write_zeroes =
+ sector_limits_lun2qemu(iscsilun->bl.max_ws_len, iscsilun);
}
if (iscsilun->lbp.lbpws) {
- bs->bl.write_zeroes_alignment = sector_lun2qemu(iscsilun->bl.opt_unmap_gran,
- iscsilun);
+ bs->bl.write_zeroes_alignment =
+ sector_limits_lun2qemu(iscsilun->bl.opt_unmap_gran, iscsilun);
}
- bs->bl.opt_transfer_length = sector_lun2qemu(iscsilun->bl.opt_xfer_len,
- iscsilun);
+ bs->bl.opt_transfer_length =
+ sector_limits_lun2qemu(iscsilun->bl.opt_xfer_len, iscsilun);
}
/* Since iscsi_open() ignores bdrv_flags, there is nothing to do here in
diff --git a/block/mirror.c b/block/mirror.c
index e8a43eb..2c6dd2a 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -45,6 +45,7 @@
int64_t sector_num;
int64_t granularity;
size_t buf_size;
+ int64_t bdev_length;
unsigned long *cow_bitmap;
BdrvDirtyBitmap *dirty_bitmap;
HBitmapIter hbi;
@@ -54,6 +55,7 @@
unsigned long *in_flight_bitmap;
int in_flight;
+ int sectors_in_flight;
int ret;
} MirrorBlockJob;
@@ -87,6 +89,7 @@
trace_mirror_iteration_done(s, op->sector_num, op->nb_sectors, ret);
s->in_flight--;
+ s->sectors_in_flight -= op->nb_sectors;
iov = op->qiov.iov;
for (i = 0; i < op->qiov.niov; i++) {
MirrorBuffer *buf = (MirrorBuffer *) iov[i].iov_base;
@@ -98,8 +101,11 @@
chunk_num = op->sector_num / sectors_per_chunk;
nb_chunks = op->nb_sectors / sectors_per_chunk;
bitmap_clear(s->in_flight_bitmap, chunk_num, nb_chunks);
- if (s->cow_bitmap && ret >= 0) {
- bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
+ if (ret >= 0) {
+ if (s->cow_bitmap) {
+ bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
+ }
+ s->common.offset += (uint64_t)op->nb_sectors * BDRV_SECTOR_SIZE;
}
qemu_iovec_destroy(&op->qiov);
@@ -172,7 +178,7 @@
hbitmap_next_sector = s->sector_num;
sector_num = s->sector_num;
sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
- end = s->common.len >> BDRV_SECTOR_BITS;
+ end = s->bdev_length / BDRV_SECTOR_SIZE;
/* Extend the QEMUIOVector to include all adjacent blocks that will
* be copied in this operation.
@@ -284,6 +290,7 @@
/* Copy the dirty cluster. */
s->in_flight++;
+ s->sectors_in_flight += nb_sectors;
trace_mirror_one_iteration(s, sector_num, nb_sectors);
bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
mirror_read_complete, op);
@@ -314,9 +321,56 @@
}
}
+typedef struct {
+ int ret;
+} MirrorExitData;
+
+static void mirror_exit(BlockJob *job, void *opaque)
+{
+ MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
+ MirrorExitData *data = opaque;
+ AioContext *replace_aio_context = NULL;
+
+ if (s->to_replace) {
+ replace_aio_context = bdrv_get_aio_context(s->to_replace);
+ aio_context_acquire(replace_aio_context);
+ }
+
+ if (s->should_complete && data->ret == 0) {
+ BlockDriverState *to_replace = s->common.bs;
+ if (s->to_replace) {
+ to_replace = s->to_replace;
+ }
+ if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
+ bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
+ }
+ bdrv_swap(s->target, to_replace);
+ if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
+ /* drop the bs loop chain formed by the swap: break the loop then
+ * trigger the unref from the top one */
+ BlockDriverState *p = s->base->backing_hd;
+ bdrv_set_backing_hd(s->base, NULL);
+ bdrv_unref(p);
+ }
+ }
+ if (s->to_replace) {
+ bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
+ error_free(s->replace_blocker);
+ bdrv_unref(s->to_replace);
+ }
+ if (replace_aio_context) {
+ aio_context_release(replace_aio_context);
+ }
+ g_free(s->replaces);
+ bdrv_unref(s->target);
+ block_job_completed(&s->common, data->ret);
+ g_free(data);
+}
+
static void coroutine_fn mirror_run(void *opaque)
{
MirrorBlockJob *s = opaque;
+ MirrorExitData *data;
BlockDriverState *bs = s->common.bs;
int64_t sector_num, end, sectors_per_chunk, length;
uint64_t last_pause_ns;
@@ -329,11 +383,11 @@
goto immediate_exit;
}
- s->common.len = bdrv_getlength(bs);
- if (s->common.len < 0) {
- ret = s->common.len;
+ s->bdev_length = bdrv_getlength(bs);
+ if (s->bdev_length < 0) {
+ ret = s->bdev_length;
goto immediate_exit;
- } else if (s->common.len == 0) {
+ } else if (s->bdev_length == 0) {
/* Report BLOCK_JOB_READY and wait for complete. */
block_job_event_ready(&s->common);
s->synced = true;
@@ -344,7 +398,7 @@
goto immediate_exit;
}
- length = DIV_ROUND_UP(s->common.len, s->granularity);
+ length = DIV_ROUND_UP(s->bdev_length, s->granularity);
s->in_flight_bitmap = bitmap_new(length);
/* If we have no backing file yet in the destination, we cannot let
@@ -364,7 +418,7 @@
}
}
- end = s->common.len >> BDRV_SECTOR_BITS;
+ end = s->bdev_length / BDRV_SECTOR_SIZE;
s->buf = qemu_try_blockalign(bs, s->buf_size);
if (s->buf == NULL) {
ret = -ENOMEM;
@@ -409,6 +463,12 @@
}
cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
+ /* s->common.offset contains the number of bytes already processed so
+ * far, cnt is the number of dirty sectors remaining and
+ * s->sectors_in_flight is the number of sectors currently being
+ * processed; together those are the current total operation length */
+ s->common.len = s->common.offset +
+ (cnt + s->sectors_in_flight) * BDRV_SECTOR_SIZE;
/* Note that even when no rate limit is applied we need to yield
* periodically with no pending I/O so that qemu_aio_flush() returns.
@@ -445,7 +505,6 @@
* report completion. This way, block-job-cancel will leave
* the target in a consistent state.
*/
- s->common.offset = end * BDRV_SECTOR_SIZE;
if (!s->synced) {
block_job_event_ready(&s->common);
s->synced = true;
@@ -467,15 +526,13 @@
* mirror_populate runs.
*/
trace_mirror_before_drain(s, cnt);
- bdrv_drain_all();
+ bdrv_drain(bs);
cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
}
ret = 0;
trace_mirror_before_sleep(s, cnt, s->synced, delay_ns);
if (!s->synced) {
- /* Publish progress */
- s->common.offset = (end - cnt) * BDRV_SECTOR_SIZE;
block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
if (block_job_is_cancelled(&s->common)) {
break;
@@ -510,31 +567,10 @@
g_free(s->in_flight_bitmap);
bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
bdrv_iostatus_disable(s->target);
- if (s->should_complete && ret == 0) {
- BlockDriverState *to_replace = s->common.bs;
- if (s->to_replace) {
- to_replace = s->to_replace;
- }
- if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
- bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
- }
- bdrv_swap(s->target, to_replace);
- if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
- /* drop the bs loop chain formed by the swap: break the loop then
- * trigger the unref from the top one */
- BlockDriverState *p = s->base->backing_hd;
- bdrv_set_backing_hd(s->base, NULL);
- bdrv_unref(p);
- }
- }
- if (s->to_replace) {
- bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
- error_free(s->replace_blocker);
- bdrv_unref(s->to_replace);
- }
- g_free(s->replaces);
- bdrv_unref(s->target);
- block_job_completed(&s->common, ret);
+
+ data = g_malloc(sizeof(*data));
+ data->ret = ret;
+ block_job_defer_to_main_loop(&s->common, mirror_exit, data);
}
static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -574,16 +610,23 @@
/* check the target bs is not blocked and block all operations on it */
if (s->replaces) {
+ AioContext *replace_aio_context;
+
s->to_replace = check_to_replace_node(s->replaces, &local_err);
if (!s->to_replace) {
error_propagate(errp, local_err);
return;
}
+ replace_aio_context = bdrv_get_aio_context(s->to_replace);
+ aio_context_acquire(replace_aio_context);
+
error_setg(&s->replace_blocker,
"block device is in use by block-job-complete");
bdrv_op_block_all(s->to_replace, s->replace_blocker);
bdrv_ref(s->to_replace);
+
+ aio_context_release(replace_aio_context);
}
s->should_complete = true;
diff --git a/block/parallels.c b/block/parallels.c
index 2a814f3..4f9cd8d 100644
--- a/block/parallels.c
+++ b/block/parallels.c
@@ -155,7 +155,7 @@
offset = sector_num % s->tracks;
/* not allocated */
- if ((index > s->catalog_size) || (s->catalog_bitmap[index] == 0))
+ if ((index >= s->catalog_size) || (s->catalog_bitmap[index] == 0))
return -1;
return
((uint64_t)s->catalog_bitmap[index] * s->off_multiplier + offset) * 512;
diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index 4d888c7..df0b2c9 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -1414,7 +1414,7 @@
* clusters.
*/
static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
- unsigned int nb_clusters, enum qcow2_discard_type type)
+ unsigned int nb_clusters, enum qcow2_discard_type type, bool full_discard)
{
BDRVQcowState *s = bs->opaque;
uint64_t *l2_table;
@@ -1436,23 +1436,30 @@
old_l2_entry = be64_to_cpu(l2_table[l2_index + i]);
/*
- * Make sure that a discarded area reads back as zeroes for v3 images
- * (we cannot do it for v2 without actually writing a zero-filled
- * buffer). We can skip the operation if the cluster is already marked
- * as zero, or if it's unallocated and we don't have a backing file.
+ * If full_discard is false, make sure that a discarded area reads back
+ * as zeroes for v3 images (we cannot do it for v2 without actually
+ * writing a zero-filled buffer). We can skip the operation if the
+ * cluster is already marked as zero, or if it's unallocated and we
+ * don't have a backing file.
*
* TODO We might want to use bdrv_get_block_status(bs) here, but we're
* holding s->lock, so that doesn't work today.
+ *
+ * If full_discard is true, the sector should not read back as zeroes,
+ * but rather fall through to the backing file.
*/
switch (qcow2_get_cluster_type(old_l2_entry)) {
case QCOW2_CLUSTER_UNALLOCATED:
- if (!bs->backing_hd) {
+ if (full_discard || !bs->backing_hd) {
continue;
}
break;
case QCOW2_CLUSTER_ZERO:
- continue;
+ if (!full_discard) {
+ continue;
+ }
+ break;
case QCOW2_CLUSTER_NORMAL:
case QCOW2_CLUSTER_COMPRESSED:
@@ -1464,7 +1471,7 @@
/* First remove L2 entries */
qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
- if (s->qcow_version >= 3) {
+ if (!full_discard && s->qcow_version >= 3) {
l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
} else {
l2_table[l2_index + i] = cpu_to_be64(0);
@@ -1483,7 +1490,7 @@
}
int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
- int nb_sectors, enum qcow2_discard_type type)
+ int nb_sectors, enum qcow2_discard_type type, bool full_discard)
{
BDRVQcowState *s = bs->opaque;
uint64_t end_offset;
@@ -1506,7 +1513,7 @@
/* Each L2 table is handled by its own loop iteration */
while (nb_clusters > 0) {
- ret = discard_single_l2(bs, offset, nb_clusters, type);
+ ret = discard_single_l2(bs, offset, nb_clusters, type, full_discard);
if (ret < 0) {
goto fail;
}
@@ -1606,15 +1613,14 @@
* Expands all zero clusters in a specific L1 table (or deallocates them, for
* non-backed non-pre-allocated zero clusters).
*
- * expanded_clusters is a bitmap where every bit corresponds to one cluster in
- * the image file; a bit gets set if the corresponding cluster has been used for
- * zero expansion (i.e., has been filled with zeroes and is referenced from an
- * L2 table). nb_clusters contains the total cluster count of the image file,
- * i.e., the number of bits in expanded_clusters.
+ * l1_entries and *visited_l1_entries are used to keep track of progress for
+ * status_cb(). l1_entries contains the total number of L1 entries and
+ * *visited_l1_entries counts all visited L1 entries.
*/
static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
- int l1_size, uint8_t **expanded_clusters,
- uint64_t *nb_clusters)
+ int l1_size, int64_t *visited_l1_entries,
+ int64_t l1_entries,
+ BlockDriverAmendStatusCB *status_cb)
{
BDRVQcowState *s = bs->opaque;
bool is_active_l1 = (l1_table == s->l1_table);
@@ -1634,9 +1640,14 @@
for (i = 0; i < l1_size; i++) {
uint64_t l2_offset = l1_table[i] & L1E_OFFSET_MASK;
bool l2_dirty = false;
+ int l2_refcount;
if (!l2_offset) {
/* unallocated */
+ (*visited_l1_entries)++;
+ if (status_cb) {
+ status_cb(bs, *visited_l1_entries, l1_entries);
+ }
continue;
}
@@ -1653,33 +1664,19 @@
goto fail;
}
+ l2_refcount = qcow2_get_refcount(bs, l2_offset >> s->cluster_bits);
+ if (l2_refcount < 0) {
+ ret = l2_refcount;
+ goto fail;
+ }
+
for (j = 0; j < s->l2_size; j++) {
uint64_t l2_entry = be64_to_cpu(l2_table[j]);
- int64_t offset = l2_entry & L2E_OFFSET_MASK, cluster_index;
+ int64_t offset = l2_entry & L2E_OFFSET_MASK;
int cluster_type = qcow2_get_cluster_type(l2_entry);
bool preallocated = offset != 0;
- if (cluster_type == QCOW2_CLUSTER_NORMAL) {
- cluster_index = offset >> s->cluster_bits;
- assert((cluster_index >= 0) && (cluster_index < *nb_clusters));
- if ((*expanded_clusters)[cluster_index / 8] &
- (1 << (cluster_index % 8))) {
- /* Probably a shared L2 table; this cluster was a zero
- * cluster which has been expanded, its refcount
- * therefore most likely requires an update. */
- ret = qcow2_update_cluster_refcount(bs, cluster_index, 1,
- QCOW2_DISCARD_NEVER);
- if (ret < 0) {
- goto fail;
- }
- /* Since we just increased the refcount, the COPIED flag may
- * no longer be set. */
- l2_table[j] = cpu_to_be64(l2_entry & ~QCOW_OFLAG_COPIED);
- l2_dirty = true;
- }
- continue;
- }
- else if (qcow2_get_cluster_type(l2_entry) != QCOW2_CLUSTER_ZERO) {
+ if (cluster_type != QCOW2_CLUSTER_ZERO) {
continue;
}
@@ -1697,6 +1694,19 @@
ret = offset;
goto fail;
}
+
+ if (l2_refcount > 1) {
+ /* For shared L2 tables, set the refcount accordingly (it is
+ * already 1 and needs to be l2_refcount) */
+ ret = qcow2_update_cluster_refcount(bs,
+ offset >> s->cluster_bits, l2_refcount - 1,
+ QCOW2_DISCARD_OTHER);
+ if (ret < 0) {
+ qcow2_free_clusters(bs, offset, s->cluster_size,
+ QCOW2_DISCARD_OTHER);
+ goto fail;
+ }
+ }
}
ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
@@ -1718,29 +1728,12 @@
goto fail;
}
- l2_table[j] = cpu_to_be64(offset | QCOW_OFLAG_COPIED);
- l2_dirty = true;
-
- cluster_index = offset >> s->cluster_bits;
-
- if (cluster_index >= *nb_clusters) {
- uint64_t old_bitmap_size = (*nb_clusters + 7) / 8;
- uint64_t new_bitmap_size;
- /* The offset may lie beyond the old end of the underlying image
- * file for growable files only */
- assert(bs->file->growable);
- *nb_clusters = size_to_clusters(s, bs->file->total_sectors *
- BDRV_SECTOR_SIZE);
- new_bitmap_size = (*nb_clusters + 7) / 8;
- *expanded_clusters = g_realloc(*expanded_clusters,
- new_bitmap_size);
- /* clear the newly allocated space */
- memset(&(*expanded_clusters)[old_bitmap_size], 0,
- new_bitmap_size - old_bitmap_size);
+ if (l2_refcount == 1) {
+ l2_table[j] = cpu_to_be64(offset | QCOW_OFLAG_COPIED);
+ } else {
+ l2_table[j] = cpu_to_be64(offset);
}
-
- assert((cluster_index >= 0) && (cluster_index < *nb_clusters));
- (*expanded_clusters)[cluster_index / 8] |= 1 << (cluster_index % 8);
+ l2_dirty = true;
}
if (is_active_l1) {
@@ -1769,6 +1762,11 @@
}
}
}
+
+ (*visited_l1_entries)++;
+ if (status_cb) {
+ status_cb(bs, *visited_l1_entries, l1_entries);
+ }
}
ret = 0;
@@ -1795,25 +1793,25 @@
* allocation for pre-allocated ones). This is important for downgrading to a
* qcow2 version which doesn't yet support metadata zero clusters.
*/
-int qcow2_expand_zero_clusters(BlockDriverState *bs)
+int qcow2_expand_zero_clusters(BlockDriverState *bs,
+ BlockDriverAmendStatusCB *status_cb)
{
BDRVQcowState *s = bs->opaque;
uint64_t *l1_table = NULL;
- uint64_t nb_clusters;
- uint8_t *expanded_clusters;
+ int64_t l1_entries = 0, visited_l1_entries = 0;
int ret;
int i, j;
- nb_clusters = size_to_clusters(s, bs->file->total_sectors *
- BDRV_SECTOR_SIZE);
- expanded_clusters = g_try_malloc0((nb_clusters + 7) / 8);
- if (expanded_clusters == NULL) {
- ret = -ENOMEM;
- goto fail;
+ if (status_cb) {
+ l1_entries = s->l1_size;
+ for (i = 0; i < s->nb_snapshots; i++) {
+ l1_entries += s->snapshots[i].l1_size;
+ }
}
ret = expand_zero_clusters_in_l1(bs, s->l1_table, s->l1_size,
- &expanded_clusters, &nb_clusters);
+ &visited_l1_entries, l1_entries,
+ status_cb);
if (ret < 0) {
goto fail;
}
@@ -1847,7 +1845,8 @@
}
ret = expand_zero_clusters_in_l1(bs, l1_table, s->snapshots[i].l1_size,
- &expanded_clusters, &nb_clusters);
+ &visited_l1_entries, l1_entries,
+ status_cb);
if (ret < 0) {
goto fail;
}
@@ -1856,7 +1855,6 @@
ret = 0;
fail:
- g_free(expanded_clusters);
g_free(l1_table);
return ret;
}
diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
index 1477031..9afdb40 100644
--- a/block/qcow2-refcount.c
+++ b/block/qcow2-refcount.c
@@ -91,7 +91,7 @@
* return value is the refcount of the cluster, negative values are -errno
* and indicate an error.
*/
-static int get_refcount(BlockDriverState *bs, int64_t cluster_index)
+int qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index)
{
BDRVQcowState *s = bs->opaque;
uint64_t refcount_table_index, block_index;
@@ -629,8 +629,7 @@
}
/*
- * Increases or decreases the refcount of a given cluster by one.
- * addend must be 1 or -1.
+ * Increases or decreases the refcount of a given cluster.
*
* If the return value is non-negative, it is the new refcount of the cluster.
* If it is negative, it is -errno and indicates an error.
@@ -649,7 +648,7 @@
return ret;
}
- return get_refcount(bs, cluster_index);
+ return qcow2_get_refcount(bs, cluster_index);
}
@@ -670,7 +669,7 @@
retry:
for(i = 0; i < nb_clusters; i++) {
uint64_t next_cluster_index = s->free_cluster_index++;
- refcount = get_refcount(bs, next_cluster_index);
+ refcount = qcow2_get_refcount(bs, next_cluster_index);
if (refcount < 0) {
return refcount;
@@ -734,7 +733,7 @@
/* Check how many clusters there are free */
cluster_index = offset >> s->cluster_bits;
for(i = 0; i < nb_clusters; i++) {
- refcount = get_refcount(bs, cluster_index++);
+ refcount = qcow2_get_refcount(bs, cluster_index++);
if (refcount < 0) {
return refcount;
@@ -981,7 +980,7 @@
cluster_index, addend,
QCOW2_DISCARD_SNAPSHOT);
} else {
- refcount = get_refcount(bs, cluster_index);
+ refcount = qcow2_get_refcount(bs, cluster_index);
}
if (refcount < 0) {
@@ -1021,7 +1020,7 @@
refcount = qcow2_update_cluster_refcount(bs, l2_offset >>
s->cluster_bits, addend, QCOW2_DISCARD_SNAPSHOT);
} else {
- refcount = get_refcount(bs, l2_offset >> s->cluster_bits);
+ refcount = qcow2_get_refcount(bs, l2_offset >> s->cluster_bits);
}
if (refcount < 0) {
ret = refcount;
@@ -1332,8 +1331,8 @@
* Checks the OFLAG_COPIED flag for all L1 and L2 entries.
*
* This function does not print an error message nor does it increment
- * check_errors if get_refcount fails (this is because such an error will have
- * been already detected and sufficiently signaled by the calling function
+ * check_errors if qcow2_get_refcount fails (this is because such an error will
+ * have been already detected and sufficiently signaled by the calling function
* (qcow2_check_refcounts) by the time this function is called).
*/
static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res,
@@ -1354,7 +1353,7 @@
continue;
}
- refcount = get_refcount(bs, l2_offset >> s->cluster_bits);
+ refcount = qcow2_get_refcount(bs, l2_offset >> s->cluster_bits);
if (refcount < 0) {
/* don't print message nor increment check_errors */
continue;
@@ -1396,7 +1395,8 @@
if ((cluster_type == QCOW2_CLUSTER_NORMAL) ||
((cluster_type == QCOW2_CLUSTER_ZERO) && (data_offset != 0))) {
- refcount = get_refcount(bs, data_offset >> s->cluster_bits);
+ refcount = qcow2_get_refcount(bs,
+ data_offset >> s->cluster_bits);
if (refcount < 0) {
/* don't print message nor increment check_errors */
continue;
@@ -1632,7 +1632,7 @@
int refcount1, refcount2, ret;
for (i = 0, *highest_cluster = 0; i < nb_clusters; i++) {
- refcount1 = get_refcount(bs, i);
+ refcount1 = qcow2_get_refcount(bs, i);
if (refcount1 < 0) {
fprintf(stderr, "Can't get refcount for cluster %" PRId64 ": %s\n",
i, strerror(-refcount1));
diff --git a/block/qcow2-snapshot.c b/block/qcow2-snapshot.c
index f52d7fd..5b3903c 100644
--- a/block/qcow2-snapshot.c
+++ b/block/qcow2-snapshot.c
@@ -441,7 +441,7 @@
qcow2_discard_clusters(bs, qcow2_vm_state_offset(s),
align_offset(sn->vm_state_size, s->cluster_size)
>> BDRV_SECTOR_BITS,
- QCOW2_DISCARD_NEVER);
+ QCOW2_DISCARD_NEVER, false);
#ifdef DEBUG_ALLOC
{
diff --git a/block/qcow2.c b/block/qcow2.c
index d031515..d120494 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -2089,7 +2089,7 @@
qemu_co_mutex_lock(&s->lock);
ret = qcow2_discard_clusters(bs, sector_num << BDRV_SECTOR_BITS,
- nb_sectors, QCOW2_DISCARD_REQUEST);
+ nb_sectors, QCOW2_DISCARD_REQUEST, false);
qemu_co_mutex_unlock(&s->lock);
return ret;
}
@@ -2230,6 +2230,195 @@
return ret;
}
+static int make_completely_empty(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret, l1_clusters;
+ int64_t offset;
+ uint64_t *new_reftable = NULL;
+ uint64_t rt_entry, l1_size2;
+ struct {
+ uint64_t l1_offset;
+ uint64_t reftable_offset;
+ uint32_t reftable_clusters;
+ } QEMU_PACKED l1_ofs_rt_ofs_cls;
+
+ ret = qcow2_cache_empty(bs, s->l2_table_cache);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ ret = qcow2_cache_empty(bs, s->refcount_block_cache);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Refcounts will be broken utterly */
+ ret = qcow2_mark_dirty(bs);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE);
+
+ l1_clusters = DIV_ROUND_UP(s->l1_size, s->cluster_size / sizeof(uint64_t));
+ l1_size2 = (uint64_t)s->l1_size * sizeof(uint64_t);
+
+ /* After this call, neither the in-memory nor the on-disk refcount
+ * information accurately describe the actual references */
+
+ ret = bdrv_write_zeroes(bs->file, s->l1_table_offset / BDRV_SECTOR_SIZE,
+ l1_clusters * s->cluster_sectors, 0);
+ if (ret < 0) {
+ goto fail_broken_refcounts;
+ }
+ memset(s->l1_table, 0, l1_size2);
+
+ BLKDBG_EVENT(bs->file, BLKDBG_EMPTY_IMAGE_PREPARE);
+
+ /* Overwrite enough clusters at the beginning of the sectors to place
+ * the refcount table, a refcount block and the L1 table in; this may
+ * overwrite parts of the existing refcount and L1 table, which is not
+ * an issue because the dirty flag is set, complete data loss is in fact
+ * desired and partial data loss is consequently fine as well */
+ ret = bdrv_write_zeroes(bs->file, s->cluster_size / BDRV_SECTOR_SIZE,
+ (2 + l1_clusters) * s->cluster_size /
+ BDRV_SECTOR_SIZE, 0);
+ /* This call (even if it failed overall) may have overwritten on-disk
+ * refcount structures; in that case, the in-memory refcount information
+ * will probably differ from the on-disk information which makes the BDS
+ * unusable */
+ if (ret < 0) {
+ goto fail_broken_refcounts;
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE);
+ BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_UPDATE);
+
+ /* "Create" an empty reftable (one cluster) directly after the image
+ * header and an empty L1 table three clusters after the image header;
+ * the cluster between those two will be used as the first refblock */
+ cpu_to_be64w(&l1_ofs_rt_ofs_cls.l1_offset, 3 * s->cluster_size);
+ cpu_to_be64w(&l1_ofs_rt_ofs_cls.reftable_offset, s->cluster_size);
+ cpu_to_be32w(&l1_ofs_rt_ofs_cls.reftable_clusters, 1);
+ ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_table_offset),
+ &l1_ofs_rt_ofs_cls, sizeof(l1_ofs_rt_ofs_cls));
+ if (ret < 0) {
+ goto fail_broken_refcounts;
+ }
+
+ s->l1_table_offset = 3 * s->cluster_size;
+
+ new_reftable = g_try_new0(uint64_t, s->cluster_size / sizeof(uint64_t));
+ if (!new_reftable) {
+ ret = -ENOMEM;
+ goto fail_broken_refcounts;
+ }
+
+ s->refcount_table_offset = s->cluster_size;
+ s->refcount_table_size = s->cluster_size / sizeof(uint64_t);
+
+ g_free(s->refcount_table);
+ s->refcount_table = new_reftable;
+ new_reftable = NULL;
+
+ /* Now the in-memory refcount information again corresponds to the on-disk
+ * information (reftable is empty and no refblocks (the refblock cache is
+ * empty)); however, this means some clusters (e.g. the image header) are
+ * referenced, but not refcounted, but the normal qcow2 code assumes that
+ * the in-memory information is always correct */
+
+ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC);
+
+ /* Enter the first refblock into the reftable */
+ rt_entry = cpu_to_be64(2 * s->cluster_size);
+ ret = bdrv_pwrite_sync(bs->file, s->cluster_size,
+ &rt_entry, sizeof(rt_entry));
+ if (ret < 0) {
+ goto fail_broken_refcounts;
+ }
+ s->refcount_table[0] = 2 * s->cluster_size;
+
+ s->free_cluster_index = 0;
+ assert(3 + l1_clusters <= s->refcount_block_size);
+ offset = qcow2_alloc_clusters(bs, 3 * s->cluster_size + l1_size2);
+ if (offset < 0) {
+ ret = offset;
+ goto fail_broken_refcounts;
+ } else if (offset > 0) {
+ error_report("First cluster in emptied image is in use");
+ abort();
+ }
+
+ /* Now finally the in-memory information corresponds to the on-disk
+ * structures and is correct */
+ ret = qcow2_mark_clean(bs);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ ret = bdrv_truncate(bs->file, (3 + l1_clusters) * s->cluster_size);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ return 0;
+
+fail_broken_refcounts:
+ /* The BDS is unusable at this point. If we wanted to make it usable, we
+ * would have to call qcow2_refcount_close(), qcow2_refcount_init(),
+ * qcow2_check_refcounts(), qcow2_refcount_close() and qcow2_refcount_init()
+ * again. However, because the functions which could have caused this error
+ * path to be taken are used by those functions as well, it's very likely
+ * that that sequence will fail as well. Therefore, just eject the BDS. */
+ bs->drv = NULL;
+
+fail:
+ g_free(new_reftable);
+ return ret;
+}
+
+static int qcow2_make_empty(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t start_sector;
+ int sector_step = INT_MAX / BDRV_SECTOR_SIZE;
+ int l1_clusters, ret = 0;
+
+ l1_clusters = DIV_ROUND_UP(s->l1_size, s->cluster_size / sizeof(uint64_t));
+
+ if (s->qcow_version >= 3 && !s->snapshots &&
+ 3 + l1_clusters <= s->refcount_block_size) {
+ /* The following function only works for qcow2 v3 images (it requires
+ * the dirty flag) and only as long as there are no snapshots (because
+ * it completely empties the image). Furthermore, the L1 table and three
+ * additional clusters (image header, refcount table, one refcount
+ * block) have to fit inside one refcount block. */
+ return make_completely_empty(bs);
+ }
+
+ /* This fallback code simply discards every active cluster; this is slow,
+ * but works in all cases */
+ for (start_sector = 0; start_sector < bs->total_sectors;
+ start_sector += sector_step)
+ {
+ /* As this function is generally used after committing an external
+ * snapshot, QCOW2_DISCARD_SNAPSHOT seems appropriate. Also, the
+ * default action for this kind of discard is to pass the discard,
+ * which will ideally result in an actually smaller image file, as
+ * is probably desired. */
+ ret = qcow2_discard_clusters(bs, start_sector * BDRV_SECTOR_SIZE,
+ MIN(sector_step,
+ bs->total_sectors - start_sector),
+ QCOW2_DISCARD_SNAPSHOT, true);
+ if (ret < 0) {
+ break;
+ }
+ }
+
+ return ret;
+}
+
static coroutine_fn int qcow2_co_flush_to_os(BlockDriverState *bs)
{
BDRVQcowState *s = bs->opaque;
@@ -2361,7 +2550,8 @@
* Downgrades an image's version. To achieve this, any incompatible features
* have to be removed.
*/
-static int qcow2_downgrade(BlockDriverState *bs, int target_version)
+static int qcow2_downgrade(BlockDriverState *bs, int target_version,
+ BlockDriverAmendStatusCB *status_cb)
{
BDRVQcowState *s = bs->opaque;
int current_version = s->qcow_version;
@@ -2410,7 +2600,7 @@
/* clearing autoclear features is trivial */
s->autoclear_features = 0;
- ret = qcow2_expand_zero_clusters(bs);
+ ret = qcow2_expand_zero_clusters(bs, status_cb);
if (ret < 0) {
return ret;
}
@@ -2424,7 +2614,8 @@
return 0;
}
-static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts)
+static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
+ BlockDriverAmendStatusCB *status_cb)
{
BDRVQcowState *s = bs->opaque;
int old_version = s->qcow_version, new_version = old_version;
@@ -2502,7 +2693,7 @@
return ret;
}
} else {
- ret = qcow2_downgrade(bs, new_version);
+ ret = qcow2_downgrade(bs, new_version, status_cb);
if (ret < 0) {
return ret;
}
@@ -2676,6 +2867,7 @@
.bdrv_co_discard = qcow2_co_discard,
.bdrv_truncate = qcow2_truncate,
.bdrv_write_compressed = qcow2_write_compressed,
+ .bdrv_make_empty = qcow2_make_empty,
.bdrv_snapshot_create = qcow2_snapshot_create,
.bdrv_snapshot_goto = qcow2_snapshot_goto,
diff --git a/block/qcow2.h b/block/qcow2.h
index 577ccd1..6e39a1b 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -487,6 +487,8 @@
int qcow2_refcount_init(BlockDriverState *bs);
void qcow2_refcount_close(BlockDriverState *bs);
+int qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index);
+
int qcow2_update_cluster_refcount(BlockDriverState *bs, int64_t cluster_index,
int addend, enum qcow2_discard_type type);
@@ -534,10 +536,11 @@
int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
- int nb_sectors, enum qcow2_discard_type type);
+ int nb_sectors, enum qcow2_discard_type type, bool full_discard);
int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
-int qcow2_expand_zero_clusters(BlockDriverState *bs);
+int qcow2_expand_zero_clusters(BlockDriverState *bs,
+ BlockDriverAmendStatusCB *status_cb);
/* qcow2-snapshot.c functions */
int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);
diff --git a/block/raw-posix.c b/block/raw-posix.c
index 475cf74..e100ae2 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -1481,12 +1481,12 @@
return result;
}
-static int64_t try_fiemap(BlockDriverState *bs, off_t start, off_t *data,
- off_t *hole, int nb_sectors, int *pnum)
+static int try_fiemap(BlockDriverState *bs, off_t start, off_t *data,
+ off_t *hole, int nb_sectors)
{
#ifdef CONFIG_FIEMAP
BDRVRawState *s = bs->opaque;
- int64_t ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
+ int ret = 0;
struct {
struct fiemap fm;
struct fiemap_extent fe;
@@ -1527,18 +1527,14 @@
#endif
}
-static int64_t try_seek_hole(BlockDriverState *bs, off_t start, off_t *data,
- off_t *hole, int *pnum)
+static int try_seek_hole(BlockDriverState *bs, off_t start, off_t *data,
+ off_t *hole)
{
#if defined SEEK_HOLE && defined SEEK_DATA
BDRVRawState *s = bs->opaque;
*hole = lseek(s->fd, start, SEEK_HOLE);
if (*hole == -1) {
- /* -ENXIO indicates that sector_num was past the end of the file.
- * There is a virtual hole there. */
- assert(errno != -ENXIO);
-
return -errno;
}
@@ -1552,7 +1548,7 @@
}
}
- return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
+ return 0;
#else
return -ENOTSUP;
#endif
@@ -1578,7 +1574,8 @@
int nb_sectors, int *pnum)
{
off_t start, data = 0, hole = 0;
- int64_t ret;
+ int64_t total_size;
+ int ret;
ret = fd_open(bs);
if (ret < 0) {
@@ -1586,29 +1583,38 @@
}
start = sector_num * BDRV_SECTOR_SIZE;
+ total_size = bdrv_getlength(bs);
+ if (total_size < 0) {
+ return total_size;
+ } else if (start >= total_size) {
+ *pnum = 0;
+ return 0;
+ } else if (start + nb_sectors * BDRV_SECTOR_SIZE > total_size) {
+ nb_sectors = DIV_ROUND_UP(total_size - start, BDRV_SECTOR_SIZE);
+ }
- ret = try_seek_hole(bs, start, &data, &hole, pnum);
+ ret = try_seek_hole(bs, start, &data, &hole);
if (ret < 0) {
- ret = try_fiemap(bs, start, &data, &hole, nb_sectors, pnum);
+ ret = try_fiemap(bs, start, &data, &hole, nb_sectors);
if (ret < 0) {
/* Assume everything is allocated. */
data = 0;
hole = start + nb_sectors * BDRV_SECTOR_SIZE;
- ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
+ ret = 0;
}
}
+ assert(ret >= 0);
+
if (data <= start) {
/* On a data extent, compute sectors to the end of the extent. */
*pnum = MIN(nb_sectors, (hole - start) / BDRV_SECTOR_SIZE);
+ return ret | BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
} else {
/* On a hole, compute sectors to the beginning of the next extent. */
*pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
- ret &= ~BDRV_BLOCK_DATA;
- ret |= BDRV_BLOCK_ZERO;
+ return ret | BDRV_BLOCK_ZERO | BDRV_BLOCK_OFFSET_VALID | start;
}
-
- return ret;
}
static coroutine_fn BlockAIOCB *raw_aio_discard(BlockDriverState *bs,
diff --git a/block/rbd.c b/block/rbd.c
index 47cab8b..5b5a64a 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -887,6 +887,18 @@
}
#endif
+#ifdef LIBRBD_SUPPORTS_INVALIDATE
+static void qemu_rbd_invalidate_cache(BlockDriverState *bs,
+ Error **errp)
+{
+ BDRVRBDState *s = bs->opaque;
+ int r = rbd_invalidate_cache(s->image);
+ if (r < 0) {
+ error_setg_errno(errp, -r, "Failed to invalidate the cache");
+ }
+}
+#endif
+
static QemuOptsList qemu_rbd_create_opts = {
.name = "rbd-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(qemu_rbd_create_opts.head),
@@ -936,6 +948,9 @@
.bdrv_snapshot_delete = qemu_rbd_snap_remove,
.bdrv_snapshot_list = qemu_rbd_snap_list,
.bdrv_snapshot_goto = qemu_rbd_snap_rollback,
+#ifdef LIBRBD_SUPPORTS_INVALIDATE
+ .bdrv_invalidate_cache = qemu_rbd_invalidate_cache,
+#endif
};
static void bdrv_rbd_init(void)
diff --git a/block/snapshot.c b/block/snapshot.c
index 85c52ff..698e1a1 100644
--- a/block/snapshot.c
+++ b/block/snapshot.c
@@ -236,6 +236,10 @@
error_setg(errp, "snapshot_id and name are both NULL");
return -EINVAL;
}
+
+ /* drain all pending i/o before deleting snapshot */
+ bdrv_drain_all();
+
if (drv->bdrv_snapshot_delete) {
return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
}
diff --git a/block/stream.c b/block/stream.c
index a1dc8da..a628901 100644
--- a/block/stream.c
+++ b/block/stream.c
@@ -79,9 +79,39 @@
bdrv_refresh_limits(top, NULL);
}
+typedef struct {
+ int ret;
+ bool reached_end;
+} StreamCompleteData;
+
+static void stream_complete(BlockJob *job, void *opaque)
+{
+ StreamBlockJob *s = container_of(job, StreamBlockJob, common);
+ StreamCompleteData *data = opaque;
+ BlockDriverState *base = s->base;
+
+ if (!block_job_is_cancelled(&s->common) && data->reached_end &&
+ data->ret == 0) {
+ const char *base_id = NULL, *base_fmt = NULL;
+ if (base) {
+ base_id = s->backing_file_str;
+ if (base->drv) {
+ base_fmt = base->drv->format_name;
+ }
+ }
+ data->ret = bdrv_change_backing_file(job->bs, base_id, base_fmt);
+ close_unused_images(job->bs, base, base_id);
+ }
+
+ g_free(s->backing_file_str);
+ block_job_completed(&s->common, data->ret);
+ g_free(data);
+}
+
static void coroutine_fn stream_run(void *opaque)
{
StreamBlockJob *s = opaque;
+ StreamCompleteData *data;
BlockDriverState *bs = s->common.bs;
BlockDriverState *base = s->base;
int64_t sector_num, end;
@@ -183,21 +213,13 @@
/* Do not remove the backing file if an error was there but ignored. */
ret = error;
- if (!block_job_is_cancelled(&s->common) && sector_num == end && ret == 0) {
- const char *base_id = NULL, *base_fmt = NULL;
- if (base) {
- base_id = s->backing_file_str;
- if (base->drv) {
- base_fmt = base->drv->format_name;
- }
- }
- ret = bdrv_change_backing_file(bs, base_id, base_fmt);
- close_unused_images(bs, base, base_id);
- }
-
qemu_vfree(buf);
- g_free(s->backing_file_str);
- block_job_completed(&s->common, ret);
+
+ /* Modify backing chain and close BDSes in main loop */
+ data = g_malloc(sizeof(*data));
+ data->ret = ret;
+ data->reached_end = sector_num == end;
+ block_job_defer_to_main_loop(&s->common, stream_complete, data);
}
static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
diff --git a/block/vdi.c b/block/vdi.c
index 19701ee..e1d211c 100644
--- a/block/vdi.c
+++ b/block/vdi.c
@@ -137,12 +137,14 @@
return memcmp(uu, null_uuid, sizeof(uuid_t)) == 0;
}
+# if defined(CONFIG_VDI_DEBUG)
static inline void uuid_unparse(const uuid_t uu, char *out)
{
snprintf(out, 37, UUID_FMT,
uu[0], uu[1], uu[2], uu[3], uu[4], uu[5], uu[6], uu[7],
uu[8], uu[9], uu[10], uu[11], uu[12], uu[13], uu[14], uu[15]);
}
+# endif
#endif
typedef struct {
diff --git a/blockdev.c b/blockdev.c
index eb743a9..57910b8 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -115,14 +115,21 @@
{
DriveInfo *dinfo = blk_legacy_dinfo(blk);
BlockDriverState *bs = blk_bs(blk);
+ AioContext *aio_context;
if (!dinfo) {
return;
}
+ aio_context = bdrv_get_aio_context(bs);
+ aio_context_acquire(aio_context);
+
if (bs->job) {
block_job_cancel(bs->job);
}
+
+ aio_context_release(aio_context);
+
dinfo->auto_del = 1;
}
@@ -1922,6 +1929,11 @@
static void block_job_cb(void *opaque, int ret)
{
+ /* Note that this function may be executed from another AioContext besides
+ * the QEMU main loop. If you need to access anything that assumes the
+ * QEMU global mutex, use a BH or introduce a mutex.
+ */
+
BlockDriverState *bs = opaque;
const char *msg = NULL;
@@ -1951,6 +1963,7 @@
{
BlockDriverState *bs;
BlockDriverState *base_bs = NULL;
+ AioContext *aio_context;
Error *local_err = NULL;
const char *base_name = NULL;
@@ -1964,16 +1977,20 @@
return;
}
+ aio_context = bdrv_get_aio_context(bs);
+ aio_context_acquire(aio_context);
+
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_STREAM, errp)) {
- return;
+ goto out;
}
if (has_base) {
base_bs = bdrv_find_backing_image(bs, base);
if (base_bs == NULL) {
error_set(errp, QERR_BASE_NOT_FOUND, base);
- return;
+ goto out;
}
+ assert(bdrv_get_aio_context(base_bs) == aio_context);
base_name = base;
}
@@ -1982,7 +1999,7 @@
if (base_bs == NULL && has_backing_file) {
error_setg(errp, "backing file specified, but streaming the "
"entire chain");
- return;
+ goto out;
}
/* backing_file string overrides base bs filename */
@@ -1992,10 +2009,13 @@
on_error, block_job_cb, bs, &local_err);
if (local_err) {
error_propagate(errp, local_err);
- return;
+ goto out;
}
trace_qmp_block_stream(bs, bs->job);
+
+out:
+ aio_context_release(aio_context);
}
void qmp_block_commit(const char *device,
@@ -2007,6 +2027,7 @@
{
BlockDriverState *bs;
BlockDriverState *base_bs, *top_bs;
+ AioContext *aio_context;
Error *local_err = NULL;
/* This will be part of the QMP command, if/when the
* BlockdevOnError change for blkmirror makes it in
@@ -2017,9 +2038,6 @@
speed = 0;
}
- /* drain all i/o before commits */
- bdrv_drain_all();
-
/* Important Note:
* libvirt relies on the DeviceNotFound error class in order to probe for
* live commit feature versions; for this to work, we must make sure to
@@ -2031,8 +2049,14 @@
return;
}
+ aio_context = bdrv_get_aio_context(bs);
+ aio_context_acquire(aio_context);
+
+ /* drain all i/o before commits */
+ bdrv_drain_all();
+
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT, errp)) {
- return;
+ goto out;
}
/* default top_bs is the active layer */
@@ -2046,9 +2070,11 @@
if (top_bs == NULL) {
error_setg(errp, "Top image file %s not found", top ? top : "NULL");
- return;
+ goto out;
}
+ assert(bdrv_get_aio_context(top_bs) == aio_context);
+
if (has_base && base) {
base_bs = bdrv_find_backing_image(top_bs, base);
} else {
@@ -2057,20 +2083,22 @@
if (base_bs == NULL) {
error_set(errp, QERR_BASE_NOT_FOUND, base ? base : "NULL");
- return;
+ goto out;
}
+ assert(bdrv_get_aio_context(base_bs) == aio_context);
+
/* Do not allow attempts to commit an image into itself */
if (top_bs == base_bs) {
error_setg(errp, "cannot commit an image into itself");
- return;
+ goto out;
}
if (top_bs == bs) {
if (has_backing_file) {
error_setg(errp, "'backing-file' specified,"
" but 'top' is the active layer");
- return;
+ goto out;
}
commit_active_start(bs, base_bs, speed, on_error, block_job_cb,
bs, &local_err);
@@ -2080,8 +2108,11 @@
}
if (local_err != NULL) {
error_propagate(errp, local_err);
- return;
+ goto out;
}
+
+out:
+ aio_context_release(aio_context);
}
void qmp_drive_backup(const char *device, const char *target,
@@ -2096,6 +2127,7 @@
BlockDriverState *bs;
BlockDriverState *target_bs;
BlockDriverState *source = NULL;
+ AioContext *aio_context;
BlockDriver *drv = NULL;
Error *local_err = NULL;
int flags;
@@ -2121,9 +2153,12 @@
return;
}
+ aio_context = bdrv_get_aio_context(bs);
+ aio_context_acquire(aio_context);
+
if (!bdrv_is_inserted(bs)) {
error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
- return;
+ goto out;
}
if (!has_format) {
@@ -2133,12 +2168,12 @@
drv = bdrv_find_format(format);
if (!drv) {
error_set(errp, QERR_INVALID_BLOCK_FORMAT, format);
- return;
+ goto out;
}
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
- return;
+ goto out;
}
flags = bs->open_flags | BDRV_O_RDWR;
@@ -2158,7 +2193,7 @@
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "bdrv_getlength failed");
- return;
+ goto out;
}
if (mode != NEW_IMAGE_MODE_EXISTING) {
@@ -2175,23 +2210,28 @@
if (local_err) {
error_propagate(errp, local_err);
- return;
+ goto out;
}
target_bs = NULL;
ret = bdrv_open(&target_bs, target, NULL, NULL, flags, drv, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
- return;
+ goto out;
}
+ bdrv_set_aio_context(target_bs, aio_context);
+
backup_start(bs, target_bs, speed, sync, on_source_error, on_target_error,
block_job_cb, bs, &local_err);
if (local_err != NULL) {
bdrv_unref(target_bs);
error_propagate(errp, local_err);
- return;
+ goto out;
}
+
+out:
+ aio_context_release(aio_context);
}
BlockDeviceInfoList *qmp_query_named_block_nodes(Error **errp)
@@ -2216,6 +2256,7 @@
{
BlockDriverState *bs;
BlockDriverState *source, *target_bs;
+ AioContext *aio_context;
BlockDriver *drv = NULL;
Error *local_err = NULL;
QDict *options = NULL;
@@ -2258,9 +2299,12 @@
return;
}
+ aio_context = bdrv_get_aio_context(bs);
+ aio_context_acquire(aio_context);
+
if (!bdrv_is_inserted(bs)) {
error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
- return;
+ goto out;
}
if (!has_format) {
@@ -2270,12 +2314,12 @@
drv = bdrv_find_format(format);
if (!drv) {
error_set(errp, QERR_INVALID_BLOCK_FORMAT, format);
- return;
+ goto out;
}
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_MIRROR, errp)) {
- return;
+ goto out;
}
flags = bs->open_flags | BDRV_O_RDWR;
@@ -2290,29 +2334,36 @@
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "bdrv_getlength failed");
- return;
+ goto out;
}
if (has_replaces) {
BlockDriverState *to_replace_bs;
+ AioContext *replace_aio_context;
+ int64_t replace_size;
if (!has_node_name) {
error_setg(errp, "a node-name must be provided when replacing a"
" named node of the graph");
- return;
+ goto out;
}
to_replace_bs = check_to_replace_node(replaces, &local_err);
if (!to_replace_bs) {
error_propagate(errp, local_err);
- return;
+ goto out;
}
- if (size != bdrv_getlength(to_replace_bs)) {
+ replace_aio_context = bdrv_get_aio_context(to_replace_bs);
+ aio_context_acquire(replace_aio_context);
+ replace_size = bdrv_getlength(to_replace_bs);
+ aio_context_release(replace_aio_context);
+
+ if (size != replace_size) {
error_setg(errp, "cannot replace image with a mirror image of "
"different size");
- return;
+ goto out;
}
}
@@ -2341,7 +2392,7 @@
if (local_err) {
error_propagate(errp, local_err);
- return;
+ goto out;
}
if (has_node_name) {
@@ -2357,9 +2408,11 @@
flags | BDRV_O_NO_BACKING, drv, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
- return;
+ goto out;
}
+ bdrv_set_aio_context(target_bs, aio_context);
+
/* pass the node name to replace to mirror start since it's loose coupling
* and will allow to check whether the node still exist at mirror completion
*/
@@ -2371,24 +2424,42 @@
if (local_err != NULL) {
bdrv_unref(target_bs);
error_propagate(errp, local_err);
- return;
+ goto out;
}
+
+out:
+ aio_context_release(aio_context);
}
-static BlockJob *find_block_job(const char *device)
+/* Get the block job for a given device name and acquire its AioContext */
+static BlockJob *find_block_job(const char *device, AioContext **aio_context)
{
BlockDriverState *bs;
bs = bdrv_find(device);
- if (!bs || !bs->job) {
- return NULL;
+ if (!bs) {
+ goto notfound;
}
+
+ *aio_context = bdrv_get_aio_context(bs);
+ aio_context_acquire(*aio_context);
+
+ if (!bs->job) {
+ aio_context_release(*aio_context);
+ goto notfound;
+ }
+
return bs->job;
+
+notfound:
+ *aio_context = NULL;
+ return NULL;
}
void qmp_block_job_set_speed(const char *device, int64_t speed, Error **errp)
{
- BlockJob *job = find_block_job(device);
+ AioContext *aio_context;
+ BlockJob *job = find_block_job(device, &aio_context);
if (!job) {
error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
@@ -2396,34 +2467,40 @@
}
block_job_set_speed(job, speed, errp);
+ aio_context_release(aio_context);
}
void qmp_block_job_cancel(const char *device,
bool has_force, bool force, Error **errp)
{
- BlockJob *job = find_block_job(device);
-
- if (!has_force) {
- force = false;
- }
+ AioContext *aio_context;
+ BlockJob *job = find_block_job(device, &aio_context);
if (!job) {
error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
return;
}
+
+ if (!has_force) {
+ force = false;
+ }
+
if (job->paused && !force) {
error_setg(errp, "The block job for device '%s' is currently paused",
device);
- return;
+ goto out;
}
trace_qmp_block_job_cancel(job);
block_job_cancel(job);
+out:
+ aio_context_release(aio_context);
}
void qmp_block_job_pause(const char *device, Error **errp)
{
- BlockJob *job = find_block_job(device);
+ AioContext *aio_context;
+ BlockJob *job = find_block_job(device, &aio_context);
if (!job) {
error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
@@ -2432,11 +2509,13 @@
trace_qmp_block_job_pause(job);
block_job_pause(job);
+ aio_context_release(aio_context);
}
void qmp_block_job_resume(const char *device, Error **errp)
{
- BlockJob *job = find_block_job(device);
+ AioContext *aio_context;
+ BlockJob *job = find_block_job(device, &aio_context);
if (!job) {
error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
@@ -2445,11 +2524,13 @@
trace_qmp_block_job_resume(job);
block_job_resume(job);
+ aio_context_release(aio_context);
}
void qmp_block_job_complete(const char *device, Error **errp)
{
- BlockJob *job = find_block_job(device);
+ AioContext *aio_context;
+ BlockJob *job = find_block_job(device, &aio_context);
if (!job) {
error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
@@ -2458,6 +2539,7 @@
trace_qmp_block_job_complete(job);
block_job_complete(job, errp);
+ aio_context_release(aio_context);
}
void qmp_change_backing_file(const char *device,
@@ -2602,12 +2684,18 @@
BlockDriverState *bs;
for (bs = bdrv_next(NULL); bs; bs = bdrv_next(bs)) {
+ AioContext *aio_context = bdrv_get_aio_context(bs);
+
+ aio_context_acquire(aio_context);
+
if (bs->job) {
BlockJobInfoList *elem = g_new0(BlockJobInfoList, 1);
elem->value = block_job_query(bs->job);
*p_next = elem;
p_next = &elem->next;
}
+
+ aio_context_release(aio_context);
}
return head;
diff --git a/blockjob.c b/blockjob.c
index ff0908a..ba2255d 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -50,6 +50,7 @@
error_setg(&job->blocker, "block device is in use by block job: %s",
BlockJobType_lookup[driver->job_type]);
bdrv_op_block_all(bs, job->blocker);
+ bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);
job->driver = driver;
job->bs = bs;
@@ -153,7 +154,7 @@
}
}
-struct BlockCancelData {
+struct BlockFinishData {
BlockJob *job;
BlockCompletionFunc *cb;
void *opaque;
@@ -161,19 +162,22 @@
int ret;
};
-static void block_job_cancel_cb(void *opaque, int ret)
+static void block_job_finish_cb(void *opaque, int ret)
{
- struct BlockCancelData *data = opaque;
+ struct BlockFinishData *data = opaque;
data->cancelled = block_job_is_cancelled(data->job);
data->ret = ret;
data->cb(data->opaque, ret);
}
-int block_job_cancel_sync(BlockJob *job)
+static int block_job_finish_sync(BlockJob *job,
+ void (*finish)(BlockJob *, Error **errp),
+ Error **errp)
{
- struct BlockCancelData data;
+ struct BlockFinishData data;
BlockDriverState *bs = job->bs;
+ Error *local_err = NULL;
assert(bs->job == job);
@@ -184,15 +188,37 @@
data.cb = job->cb;
data.opaque = job->opaque;
data.ret = -EINPROGRESS;
- job->cb = block_job_cancel_cb;
+ job->cb = block_job_finish_cb;
job->opaque = &data;
- block_job_cancel(job);
+ finish(job, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return -EBUSY;
+ }
while (data.ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(bs), true);
}
return (data.cancelled && data.ret == 0) ? -ECANCELED : data.ret;
}
+/* A wrapper around block_job_cancel() taking an Error ** parameter so it may be
+ * used with block_job_finish_sync() without the need for (rather nasty)
+ * function pointer casts there. */
+static void block_job_cancel_err(BlockJob *job, Error **errp)
+{
+ block_job_cancel(job);
+}
+
+int block_job_cancel_sync(BlockJob *job)
+{
+ return block_job_finish_sync(job, &block_job_cancel_err, NULL);
+}
+
+int block_job_complete_sync(BlockJob *job, Error **errp)
+{
+ return block_job_finish_sync(job, &block_job_complete, errp);
+}
+
void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns)
{
assert(job->busy);
@@ -236,6 +262,7 @@
info->offset = job->offset;
info->speed = job->speed;
info->io_status = job->iostatus;
+ info->ready = job->ready;
return info;
}
@@ -271,6 +298,8 @@
void block_job_event_ready(BlockJob *job)
{
+ job->ready = true;
+
qapi_event_send_block_job_ready(job->driver->job_type,
bdrv_get_device_name(job->bs),
job->len,
@@ -314,3 +343,48 @@
}
return action;
}
+
+typedef struct {
+ BlockJob *job;
+ QEMUBH *bh;
+ AioContext *aio_context;
+ BlockJobDeferToMainLoopFn *fn;
+ void *opaque;
+} BlockJobDeferToMainLoopData;
+
+static void block_job_defer_to_main_loop_bh(void *opaque)
+{
+ BlockJobDeferToMainLoopData *data = opaque;
+ AioContext *aio_context;
+
+ qemu_bh_delete(data->bh);
+
+ /* Prevent race with block_job_defer_to_main_loop() */
+ aio_context_acquire(data->aio_context);
+
+ /* Fetch BDS AioContext again, in case it has changed */
+ aio_context = bdrv_get_aio_context(data->job->bs);
+ aio_context_acquire(aio_context);
+
+ data->fn(data->job, data->opaque);
+
+ aio_context_release(aio_context);
+
+ aio_context_release(data->aio_context);
+
+ g_free(data);
+}
+
+void block_job_defer_to_main_loop(BlockJob *job,
+ BlockJobDeferToMainLoopFn *fn,
+ void *opaque)
+{
+ BlockJobDeferToMainLoopData *data = g_malloc(sizeof(*data));
+ data->job = job;
+ data->bh = qemu_bh_new(block_job_defer_to_main_loop_bh, data);
+ data->aio_context = bdrv_get_aio_context(job->bs);
+ data->fn = fn;
+ data->opaque = opaque;
+
+ qemu_bh_schedule(data->bh);
+}
diff --git a/configure b/configure
index a9e4d49..2f17bf3 100755
--- a/configure
+++ b/configure
@@ -4908,6 +4908,7 @@
echo "QEMU_INCLUDES=$QEMU_INCLUDES" >> $config_host_mak
if test "$sparse" = "yes" ; then
echo "CC := REAL_CC=\"\$(CC)\" cgcc" >> $config_host_mak
+ echo "CXX := REAL_CC=\"\$(CXX)\" cgcc" >> $config_host_mak
echo "HOST_CC := REAL_CC=\"\$(HOST_CC)\" cgcc" >> $config_host_mak
echo "QEMU_CFLAGS += -Wbitwise -Wno-transparent-union -Wno-old-initializer -Wno-non-pointer-null" >> $config_host_mak
fi
diff --git a/dump.c b/dump.c
index 06a4915..9c7dad8 100644
--- a/dump.c
+++ b/dump.c
@@ -604,10 +604,9 @@
{
GuestPhysBlock *block;
int64_t size;
- int ret;
Error *local_err = NULL;
- while (1) {
+ do {
block = s->next_block;
size = block->target_end - block->target_start;
@@ -623,11 +622,9 @@
return;
}
- ret = get_next_block(s, block);
- if (ret == 1) {
- dump_completed(s);
- }
- }
+ } while (!get_next_block(s, block));
+
+ dump_completed(s);
}
static void create_vmcore(DumpState *s, Error **errp)
diff --git a/hw/9pfs/virtio-9p-proxy.c b/hw/9pfs/virtio-9p-proxy.c
index b57966d..59c7445 100644
--- a/hw/9pfs/virtio-9p-proxy.c
+++ b/hw/9pfs/virtio-9p-proxy.c
@@ -1104,14 +1104,15 @@
sockfd = socket(AF_UNIX, SOCK_STREAM, 0);
if (sockfd < 0) {
- fprintf(stderr, "socket %s\n", strerror(errno));
+ fprintf(stderr, "failed to create socket: %s\n", strerror(errno));
return -1;
}
strcpy(helper.sun_path, path);
helper.sun_family = AF_UNIX;
size = strlen(helper.sun_path) + sizeof(helper.sun_family);
if (connect(sockfd, (struct sockaddr *)&helper, size) < 0) {
- fprintf(stderr, "socket error\n");
+ fprintf(stderr, "failed to connect to %s: %s\n", path, strerror(errno));
+ close(sockfd);
return -1;
}
@@ -1154,10 +1155,12 @@
sock_id = atoi(ctx->fs_root);
if (sock_id < 0) {
fprintf(stderr, "socket descriptor not initialized\n");
- g_free(proxy);
- return -1;
}
}
+ if (sock_id < 0) {
+ g_free(proxy);
+ return -1;
+ }
g_free(ctx->fs_root);
ctx->fs_root = NULL;
diff --git a/hw/arm/boot.c b/hw/arm/boot.c
index bffbea5..0014c34 100644
--- a/hw/arm/boot.c
+++ b/hw/arm/boot.c
@@ -580,7 +580,7 @@
entry = elf_entry;
if (kernel_size < 0) {
kernel_size = load_uimage(info->kernel_filename, &entry, NULL,
- &is_linux);
+ &is_linux, NULL, NULL);
}
/* On aarch64, it's the bootloader's job to uncompress the kernel. */
if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64) && kernel_size < 0) {
diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index 45b1164..1222a37 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -196,6 +196,11 @@
blk_op_block_all(conf->conf.blk, s->blocker);
blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_RESIZE, s->blocker);
blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_DRIVE_DEL, s->blocker);
+ blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_BACKUP_SOURCE, s->blocker);
+ blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_COMMIT, s->blocker);
+ blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_MIRROR, s->blocker);
+ blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_STREAM, s->blocker);
+ blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_REPLACE, s->blocker);
*dataplane = s;
}
diff --git a/hw/core/loader.c b/hw/core/loader.c
index 5f3a859..bbe6eb3 100644
--- a/hw/core/loader.c
+++ b/hw/core/loader.c
@@ -477,7 +477,9 @@
/* Load a U-Boot image. */
static int load_uboot_image(const char *filename, hwaddr *ep, hwaddr *loadaddr,
- int *is_linux, uint8_t image_type)
+ int *is_linux, uint8_t image_type,
+ uint64_t (*translate_fn)(void *, uint64_t),
+ void *translate_opaque)
{
int fd;
int size;
@@ -511,6 +513,9 @@
switch (hdr->ih_type) {
case IH_TYPE_KERNEL:
address = hdr->ih_load;
+ if (translate_fn) {
+ address = translate_fn(translate_opaque, address);
+ }
if (loadaddr) {
*loadaddr = hdr->ih_load;
}
@@ -587,15 +592,19 @@
}
int load_uimage(const char *filename, hwaddr *ep, hwaddr *loadaddr,
- int *is_linux)
+ int *is_linux,
+ uint64_t (*translate_fn)(void *, uint64_t),
+ void *translate_opaque)
{
- return load_uboot_image(filename, ep, loadaddr, is_linux, IH_TYPE_KERNEL);
+ return load_uboot_image(filename, ep, loadaddr, is_linux, IH_TYPE_KERNEL,
+ translate_fn, translate_opaque);
}
/* Load a ramdisk. */
int load_ramdisk(const char *filename, hwaddr addr, uint64_t max_sz)
{
- return load_uboot_image(filename, NULL, &addr, NULL, IH_TYPE_RAMDISK);
+ return load_uboot_image(filename, NULL, &addr, NULL, IH_TYPE_RAMDISK,
+ NULL, NULL);
}
/* This simply prevents g_malloc in the function below from allocating
diff --git a/hw/i386/kvmvapic.c b/hw/i386/kvmvapic.c
index 2dc362b..c6d34b2 100644
--- a/hw/i386/kvmvapic.c
+++ b/hw/i386/kvmvapic.c
@@ -405,7 +405,6 @@
}
if (!kvm_enabled()) {
- cpu_restore_state(cs, cs->mem_io_pc);
cpu_get_tb_cpu_state(env, ¤t_pc, ¤t_cs_base,
¤t_flags);
}
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 61aba9f..889e888 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1688,6 +1688,20 @@
pcms->max_ram_below_4g = value;
}
+static bool pc_machine_get_vmport(Object *obj, Error **errp)
+{
+ PCMachineState *pcms = PC_MACHINE(obj);
+
+ return pcms->vmport;
+}
+
+static void pc_machine_set_vmport(Object *obj, bool value, Error **errp)
+{
+ PCMachineState *pcms = PC_MACHINE(obj);
+
+ pcms->vmport = value;
+}
+
static void pc_machine_initfn(Object *obj)
{
PCMachineState *pcms = PC_MACHINE(obj);
@@ -1700,6 +1714,11 @@
pc_machine_get_max_ram_below_4g,
pc_machine_set_max_ram_below_4g,
NULL, NULL, NULL);
+ pcms->vmport = !xen_enabled();
+ object_property_add_bool(obj, PC_MACHINE_VMPORT,
+ pc_machine_get_vmport,
+ pc_machine_set_vmport,
+ NULL);
}
static void pc_machine_class_init(ObjectClass *oc, void *data)
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 91a20cb..1cda5dd 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -234,8 +234,8 @@
pc_vga_init(isa_bus, pci_enabled ? pci_bus : NULL);
/* init basic PC hardware */
- pc_basic_device_init(isa_bus, gsi, &rtc_state, &floppy, xen_enabled(),
- 0x4);
+ pc_basic_device_init(isa_bus, gsi, &rtc_state, &floppy,
+ !pc_machine->vmport, 0x4);
pc_nic_init(isa_bus, pci_bus);
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index e225c6d..4d9e3cd 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -242,7 +242,8 @@
pc_register_ferr_irq(gsi[13]);
/* init basic PC hardware */
- pc_basic_device_init(isa_bus, gsi, &rtc_state, &floppy, false, 0xff0104);
+ pc_basic_device_init(isa_bus, gsi, &rtc_state, &floppy,
+ !pc_machine->vmport, 0xff0104);
/* connect pm stuff to lpc */
ich9_lpc_pm_init(lpc);
diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
index 70958e3..61dbed1 100644
--- a/hw/ide/ahci.c
+++ b/hw/ide/ahci.c
@@ -49,6 +49,9 @@
static void ahci_reset_port(AHCIState *s, int port);
static void ahci_write_fis_d2h(AHCIDevice *ad, uint8_t *cmd_fis);
static void ahci_init_d2h(AHCIDevice *ad);
+static int ahci_dma_prepare_buf(IDEDMA *dma, int is_write);
+static void ahci_commit_buf(IDEDMA *dma, uint32_t tx_bytes);
+
static uint32_t ahci_port_read(AHCIState *s, int port, int offset)
{
@@ -567,24 +570,24 @@
AHCIDevice *ad = &s->dev[port];
AHCIPortRegs *pr = &ad->port_regs;
IDEState *ide_state;
- uint8_t *sdb_fis;
+ SDBFIS *sdb_fis;
if (!s->dev[port].res_fis ||
!(pr->cmd & PORT_CMD_FIS_RX)) {
return;
}
- sdb_fis = &ad->res_fis[RES_FIS_SDBFIS];
+ sdb_fis = (SDBFIS *)&ad->res_fis[RES_FIS_SDBFIS];
ide_state = &ad->port.ifs[0];
- /* clear memory */
- *(uint32_t*)sdb_fis = 0;
-
- /* write values */
- sdb_fis[0] = ide_state->error;
- sdb_fis[2] = ide_state->status & 0x77;
+ sdb_fis->type = 0xA1;
+ /* Interrupt pending & Notification bit */
+ sdb_fis->flags = (ad->hba->control_regs.irqstatus ? (1 << 6) : 0);
+ sdb_fis->status = ide_state->status & 0x77;
+ sdb_fis->error = ide_state->error;
+ /* update SAct field in SDB_FIS */
s->dev[port].finished |= finished;
- *(uint32_t*)(sdb_fis + 4) = cpu_to_le32(ad->finished);
+ sdb_fis->payload = cpu_to_le32(ad->finished);
/* Update shadow registers (except BSY 0x80 and DRQ 0x08) */
pr->tfdata = (ad->port.ifs[0].error << 8) |
@@ -600,6 +603,7 @@
uint8_t *pio_fis, *cmd_fis;
uint64_t tbl_addr;
dma_addr_t cmd_len = 0x80;
+ IDEState *s = &ad->port.ifs[0];
if (!ad->res_fis || !(pr->cmd & PORT_CMD_FIS_RX)) {
return;
@@ -629,21 +633,21 @@
pio_fis[0] = 0x5f;
pio_fis[1] = (ad->hba->control_regs.irqstatus ? (1 << 6) : 0);
- pio_fis[2] = ad->port.ifs[0].status;
- pio_fis[3] = ad->port.ifs[0].error;
+ pio_fis[2] = s->status;
+ pio_fis[3] = s->error;
- pio_fis[4] = cmd_fis[4];
- pio_fis[5] = cmd_fis[5];
- pio_fis[6] = cmd_fis[6];
- pio_fis[7] = cmd_fis[7];
- pio_fis[8] = cmd_fis[8];
- pio_fis[9] = cmd_fis[9];
- pio_fis[10] = cmd_fis[10];
- pio_fis[11] = cmd_fis[11];
+ pio_fis[4] = s->sector;
+ pio_fis[5] = s->lcyl;
+ pio_fis[6] = s->hcyl;
+ pio_fis[7] = s->select;
+ pio_fis[8] = s->hob_sector;
+ pio_fis[9] = s->hob_lcyl;
+ pio_fis[10] = s->hob_hcyl;
+ pio_fis[11] = 0;
pio_fis[12] = cmd_fis[12];
pio_fis[13] = cmd_fis[13];
pio_fis[14] = 0;
- pio_fis[15] = ad->port.ifs[0].status;
+ pio_fis[15] = s->status;
pio_fis[16] = len & 255;
pio_fis[17] = len >> 8;
pio_fis[18] = 0;
@@ -670,6 +674,7 @@
int i;
dma_addr_t cmd_len = 0x80;
int cmd_mapped = 0;
+ IDEState *s = &ad->port.ifs[0];
if (!ad->res_fis || !(pr->cmd & PORT_CMD_FIS_RX)) {
return;
@@ -687,17 +692,17 @@
d2h_fis[0] = 0x34;
d2h_fis[1] = (ad->hba->control_regs.irqstatus ? (1 << 6) : 0);
- d2h_fis[2] = ad->port.ifs[0].status;
- d2h_fis[3] = ad->port.ifs[0].error;
+ d2h_fis[2] = s->status;
+ d2h_fis[3] = s->error;
- d2h_fis[4] = cmd_fis[4];
- d2h_fis[5] = cmd_fis[5];
- d2h_fis[6] = cmd_fis[6];
- d2h_fis[7] = cmd_fis[7];
- d2h_fis[8] = cmd_fis[8];
- d2h_fis[9] = cmd_fis[9];
- d2h_fis[10] = cmd_fis[10];
- d2h_fis[11] = cmd_fis[11];
+ d2h_fis[4] = s->sector;
+ d2h_fis[5] = s->lcyl;
+ d2h_fis[6] = s->hcyl;
+ d2h_fis[7] = s->select;
+ d2h_fis[8] = s->hob_sector;
+ d2h_fis[9] = s->hob_lcyl;
+ d2h_fis[10] = s->hob_hcyl;
+ d2h_fis[11] = 0;
d2h_fis[12] = cmd_fis[12];
d2h_fis[13] = cmd_fis[13];
for (i = 14; i < 20; i++) {
@@ -1103,16 +1108,12 @@
}
}
- /* update number of transferred bytes */
- ad->cur_cmd->status = cpu_to_le32(le32_to_cpu(ad->cur_cmd->status) + size);
-
out:
/* declare that we processed everything */
s->data_ptr = s->data_end;
- if (has_sglist) {
- qemu_sglist_destroy(&s->sg);
- }
+ /* Update number of transferred bytes, destroy sglist */
+ ahci_commit_buf(dma, size);
s->end_transfer_func(s);
@@ -1133,6 +1134,11 @@
dma_cb(s, 0);
}
+/**
+ * Called in DMA R/W chains to read the PRDT, utilizing ahci_populate_sglist.
+ * Not currently invoked by PIO R/W chains,
+ * which invoke ahci_populate_sglist via ahci_start_transfer.
+ */
static int ahci_dma_prepare_buf(IDEDMA *dma, int is_write)
{
AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
@@ -1145,6 +1151,24 @@
return s->io_buffer_size != 0;
}
+/**
+ * Destroys the scatter-gather list,
+ * and updates the command header with a bytes-read value.
+ * called explicitly via ahci_dma_rw_buf (ATAPI DMA),
+ * and ahci_start_transfer (PIO R/W),
+ * and called via callback from ide_dma_cb for DMA R/W paths.
+ */
+static void ahci_commit_buf(IDEDMA *dma, uint32_t tx_bytes)
+{
+ AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
+ IDEState *s = &ad->port.ifs[0];
+
+ tx_bytes += le32_to_cpu(ad->cur_cmd->status);
+ ad->cur_cmd->status = cpu_to_le32(tx_bytes);
+
+ qemu_sglist_destroy(&s->sg);
+}
+
static int ahci_dma_rw_buf(IDEDMA *dma, int is_write)
{
AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
@@ -1162,11 +1186,9 @@
dma_buf_write(p, l, &s->sg);
}
- /* free sglist that was created in ahci_populate_sglist() */
- qemu_sglist_destroy(&s->sg);
+ /* free sglist, update byte count */
+ ahci_commit_buf(dma, l);
- /* update number of transferred bytes */
- ad->cur_cmd->status = cpu_to_le32(le32_to_cpu(ad->cur_cmd->status) + l);
s->io_buffer_index += l;
s->io_buffer_offset += l;
@@ -1209,6 +1231,7 @@
.start_dma = ahci_start_dma,
.start_transfer = ahci_start_transfer,
.prepare_buf = ahci_dma_prepare_buf,
+ .commit_buf = ahci_commit_buf,
.rw_buf = ahci_dma_rw_buf,
.set_unit = ahci_dma_set_unit,
.cmd_done = ahci_cmd_done,
diff --git a/hw/ide/ahci.h b/hw/ide/ahci.h
index e8ea34a..b123237 100644
--- a/hw/ide/ahci.h
+++ b/hw/ide/ahci.h
@@ -327,6 +327,14 @@
uint8_t reserved10;
} QEMU_PACKED NCQFrame;
+typedef struct SDBFIS {
+ uint8_t type;
+ uint8_t flags;
+ uint8_t status;
+ uint8_t error;
+ uint32_t payload;
+} QEMU_PACKED SDBFIS;
+
void ahci_init(AHCIState *s, DeviceState *qdev, AddressSpace *as, int ports);
void ahci_uninit(AHCIState *s);
diff --git a/hw/ide/core.c b/hw/ide/core.c
index 44e3d50..d316ccf 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -634,8 +634,11 @@
ide_sector_read_cb, s);
}
-static void dma_buf_commit(IDEState *s)
+static void dma_buf_commit(IDEState *s, uint32_t tx_bytes)
{
+ if (s->bus->dma->ops->commit_buf) {
+ s->bus->dma->ops->commit_buf(s->bus->dma, tx_bytes);
+ }
qemu_sglist_destroy(&s->sg);
}
@@ -650,6 +653,7 @@
void ide_dma_error(IDEState *s)
{
+ dma_buf_commit(s, 0);
ide_abort_command(s);
ide_set_inactive(s, false);
ide_set_irq(s->bus);
@@ -665,7 +669,6 @@
s->bus->error_status = op;
} else if (action == BLOCK_ERROR_ACTION_REPORT) {
if (op & IDE_RETRY_DMA) {
- dma_buf_commit(s);
ide_dma_error(s);
} else {
ide_rw_error(s);
@@ -709,7 +712,8 @@
sector_num = ide_get_sector(s);
if (n > 0) {
- dma_buf_commit(s);
+ assert(s->io_buffer_size == s->sg.size);
+ dma_buf_commit(s, s->io_buffer_size);
sector_num += n;
ide_set_sector(s, sector_num);
s->nsector -= n;
@@ -740,7 +744,6 @@
if ((s->dma_cmd == IDE_DMA_READ || s->dma_cmd == IDE_DMA_WRITE) &&
!ide_sect_range_ok(s, sector_num, n)) {
- dma_buf_commit(s);
ide_dma_error(s);
return;
}
diff --git a/hw/ide/internal.h b/hw/ide/internal.h
index 68ac610..907493d 100644
--- a/hw/ide/internal.h
+++ b/hw/ide/internal.h
@@ -322,6 +322,7 @@
typedef void DMAStartFunc(IDEDMA *, IDEState *, BlockCompletionFunc *);
typedef void DMAVoidFunc(IDEDMA *);
typedef int DMAIntFunc(IDEDMA *, int);
+typedef void DMAu32Func(IDEDMA *, uint32_t);
typedef void DMAStopFunc(IDEDMA *, bool);
typedef void DMARestartFunc(void *, int, RunState);
@@ -430,6 +431,7 @@
DMAStartFunc *start_dma;
DMAVoidFunc *start_transfer;
DMAIntFunc *prepare_buf;
+ DMAu32Func *commit_buf;
DMAIntFunc *rw_buf;
DMAIntFunc *set_unit;
DMAStopFunc *set_inactive;
diff --git a/hw/m68k/an5206.c b/hw/m68k/an5206.c
index a9ac270..f1f1350 100644
--- a/hw/m68k/an5206.c
+++ b/hw/m68k/an5206.c
@@ -74,7 +74,8 @@
NULL, NULL, 1, ELF_MACHINE, 0);
entry = elf_entry;
if (kernel_size < 0) {
- kernel_size = load_uimage(kernel_filename, &entry, NULL, NULL);
+ kernel_size = load_uimage(kernel_filename, &entry, NULL, NULL,
+ NULL, NULL);
}
if (kernel_size < 0) {
kernel_size = load_image_targphys(kernel_filename, KERNEL_LOAD_ADDR,
diff --git a/hw/m68k/dummy_m68k.c b/hw/m68k/dummy_m68k.c
index 957ef82..facd561 100644
--- a/hw/m68k/dummy_m68k.c
+++ b/hw/m68k/dummy_m68k.c
@@ -50,7 +50,8 @@
NULL, NULL, 1, ELF_MACHINE, 0);
entry = elf_entry;
if (kernel_size < 0) {
- kernel_size = load_uimage(kernel_filename, &entry, NULL, NULL);
+ kernel_size = load_uimage(kernel_filename, &entry, NULL, NULL,
+ NULL, NULL);
}
if (kernel_size < 0) {
kernel_size = load_image_targphys(kernel_filename,
diff --git a/hw/m68k/mcf5208.c b/hw/m68k/mcf5208.c
index 188230f..a01a445 100644
--- a/hw/m68k/mcf5208.c
+++ b/hw/m68k/mcf5208.c
@@ -279,7 +279,8 @@
NULL, NULL, 1, ELF_MACHINE, 0);
entry = elf_entry;
if (kernel_size < 0) {
- kernel_size = load_uimage(kernel_filename, &entry, NULL, NULL);
+ kernel_size = load_uimage(kernel_filename, &entry, NULL, NULL,
+ NULL, NULL);
}
if (kernel_size < 0) {
kernel_size = load_image_targphys(kernel_filename, 0x40000000,
diff --git a/hw/microblaze/boot.c b/hw/microblaze/boot.c
index 6bf36d0..a2843cd 100644
--- a/hw/microblaze/boot.c
+++ b/hw/microblaze/boot.c
@@ -154,7 +154,8 @@
if (kernel_size < 0) {
hwaddr uentry, loadaddr;
- kernel_size = load_uimage(kernel_filename, &uentry, &loadaddr, 0);
+ kernel_size = load_uimage(kernel_filename, &uentry, &loadaddr, 0,
+ NULL, NULL);
boot_info.bootstrap_pc = uentry;
high = (loadaddr + kernel_size + 3) & ~3;
}
diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c
index bd9d718..5d272c8 100644
--- a/hw/misc/ivshmem.c
+++ b/hw/misc/ivshmem.c
@@ -24,10 +24,12 @@
#include "migration/migration.h"
#include "qapi/qmp/qerror.h"
#include "qemu/event_notifier.h"
+#include "qemu/fifo8.h"
#include "sysemu/char.h"
#include <sys/mman.h>
#include <sys/types.h>
+#include <limits.h>
#define PCI_VENDOR_ID_IVSHMEM PCI_VENDOR_ID_REDHAT_QUMRANET
#define PCI_DEVICE_ID_IVSHMEM 0x1110
@@ -73,6 +75,7 @@
CharDriverState **eventfd_chr;
CharDriverState *server_chr;
+ Fifo8 incoming_fifo;
MemoryRegion ivshmem_mmio;
/* We might need to register the BAR before we actually have the memory.
@@ -130,7 +133,7 @@
/* don't print ISR resets */
if (isr) {
IVSHMEM_DPRINTF("Set IRQ to %d (%04x %04x)\n",
- isr ? 1 : 0, s->intrstatus, s->intrmask);
+ isr ? 1 : 0, s->intrstatus, s->intrmask);
}
pci_set_irq(d, (isr != 0));
@@ -297,8 +300,8 @@
chr = qemu_chr_open_eventfd(eventfd);
if (chr == NULL) {
- fprintf(stderr, "creating eventfd for eventfd %d failed\n", eventfd);
- exit(-1);
+ error_report("creating eventfd for eventfd %d failed", eventfd);
+ exit(1);
}
qemu_chr_fe_claim_no_fail(chr);
@@ -325,16 +328,15 @@
struct stat buf;
if (fstat(fd, &buf) < 0) {
- fprintf(stderr, "ivshmem: exiting: fstat on fd %d failed: %s\n",
- fd, strerror(errno));
+ error_report("exiting: fstat on fd %d failed: %s",
+ fd, strerror(errno));
return -1;
}
if (s->ivshmem_size > buf.st_size) {
- fprintf(stderr,
- "IVSHMEM ERROR: Requested memory size greater"
- " than shared object size (%" PRIu64 " > %" PRIu64")\n",
- s->ivshmem_size, (uint64_t)buf.st_size);
+ error_report("Requested memory size greater"
+ " than shared object size (%" PRIu64 " > %" PRIu64")",
+ s->ivshmem_size, (uint64_t)buf.st_size);
return -1;
} else {
return 0;
@@ -387,6 +389,9 @@
if (!ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
return;
}
+ if (posn < 0 || posn >= s->nb_peers) {
+ return;
+ }
guest_curr_max = s->peers[posn].nb_eventfds;
@@ -405,14 +410,24 @@
/* this function increase the dynamic storage need to store data about other
* guests */
-static void increase_dynamic_storage(IVShmemState *s, int new_min_size) {
+static int increase_dynamic_storage(IVShmemState *s, int new_min_size)
+{
int j, old_nb_alloc;
+ /* check for integer overflow */
+ if (new_min_size >= INT_MAX / sizeof(Peer) - 1 || new_min_size <= 0) {
+ return -1;
+ }
+
old_nb_alloc = s->nb_peers;
- while (new_min_size >= s->nb_peers)
- s->nb_peers = s->nb_peers * 2;
+ if (new_min_size >= s->nb_peers) {
+ /* +1 because #new_min_size is used as last array index */
+ s->nb_peers = new_min_size + 1;
+ } else {
+ return 0;
+ }
IVSHMEM_DPRINTF("bumping storage to %d guests\n", s->nb_peers);
s->peers = g_realloc(s->peers, s->nb_peers * sizeof(Peer));
@@ -422,23 +437,57 @@
s->peers[j].eventfds = NULL;
s->peers[j].nb_eventfds = 0;
}
+
+ return 0;
}
-static void ivshmem_read(void *opaque, const uint8_t * buf, int flags)
+static void ivshmem_read(void *opaque, const uint8_t *buf, int size)
{
IVShmemState *s = opaque;
int incoming_fd, tmp_fd;
int guest_max_eventfd;
long incoming_posn;
- memcpy(&incoming_posn, buf, sizeof(long));
+ if (fifo8_is_empty(&s->incoming_fifo) && size == sizeof(incoming_posn)) {
+ memcpy(&incoming_posn, buf, size);
+ } else {
+ const uint8_t *p;
+ uint32_t num;
+
+ IVSHMEM_DPRINTF("short read of %d bytes\n", size);
+ num = MAX(size, sizeof(long) - fifo8_num_used(&s->incoming_fifo));
+ fifo8_push_all(&s->incoming_fifo, buf, num);
+ if (fifo8_num_used(&s->incoming_fifo) < sizeof(incoming_posn)) {
+ return;
+ }
+ size -= num;
+ buf += num;
+ p = fifo8_pop_buf(&s->incoming_fifo, sizeof(incoming_posn), &num);
+ g_assert(num == sizeof(incoming_posn));
+ memcpy(&incoming_posn, p, sizeof(incoming_posn));
+ if (size > 0) {
+ fifo8_push_all(&s->incoming_fifo, buf, size);
+ }
+ }
+
+ if (incoming_posn < -1) {
+ IVSHMEM_DPRINTF("invalid incoming_posn %ld\n", incoming_posn);
+ return;
+ }
+
/* pick off s->server_chr->msgfd and store it, posn should accompany msg */
tmp_fd = qemu_chr_fe_get_msgfd(s->server_chr);
IVSHMEM_DPRINTF("posn is %ld, fd is %d\n", incoming_posn, tmp_fd);
/* make sure we have enough space for this guest */
if (incoming_posn >= s->nb_peers) {
- increase_dynamic_storage(s, incoming_posn);
+ if (increase_dynamic_storage(s, incoming_posn) < 0) {
+ error_report("increase_dynamic_storage() failed");
+ if (tmp_fd != -1) {
+ close(tmp_fd);
+ }
+ return;
+ }
}
if (tmp_fd == -1) {
@@ -460,8 +509,8 @@
incoming_fd = dup(tmp_fd);
if (incoming_fd == -1) {
- fprintf(stderr, "could not allocate file descriptor %s\n",
- strerror(errno));
+ error_report("could not allocate file descriptor %s", strerror(errno));
+ close(tmp_fd);
return;
}
@@ -473,7 +522,7 @@
s->max_peer = 0;
if (check_shm_size(s, incoming_fd) == -1) {
- exit(-1);
+ exit(1);
}
/* mmap the region and map into the BAR2 */
@@ -484,7 +533,7 @@
vmstate_register_ram(&s->ivshmem, DEVICE(s));
IVSHMEM_DPRINTF("guest h/w addr = %p, size = %" PRIu64 "\n",
- map_ptr, s->ivshmem_size);
+ map_ptr, s->ivshmem_size);
memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
@@ -505,7 +554,7 @@
/* this is an eventfd for a particular guest VM */
IVSHMEM_DPRINTF("eventfds[%ld][%d] = %d\n", incoming_posn,
- guest_max_eventfd, incoming_fd);
+ guest_max_eventfd, incoming_fd);
event_notifier_init_fd(&s->peers[incoming_posn].eventfds[guest_max_eventfd],
incoming_fd);
@@ -567,13 +616,13 @@
value <<= 30;
break;
default:
- fprintf(stderr, "qemu: invalid ram size: %s\n", s->sizearg);
+ error_report("invalid ram size: %s", s->sizearg);
exit(1);
}
/* BARs must be a power of 2 */
if (!is_power_of_two(value)) {
- fprintf(stderr, "ivshmem: size must be power of 2\n");
+ error_report("size must be power of 2");
exit(1);
}
@@ -625,7 +674,7 @@
}
if (proxy->role_val == IVSHMEM_PEER) {
- fprintf(stderr, "ivshmem: 'peer' devices are not migratable\n");
+ error_report("'peer' devices are not migratable");
return -EINVAL;
}
@@ -663,13 +712,15 @@
s->ivshmem_size = ivshmem_get_size(s);
}
+ fifo8_create(&s->incoming_fifo, sizeof(long));
+
register_savevm(DEVICE(dev), "ivshmem", 0, 0, ivshmem_save, ivshmem_load,
dev);
/* IRQFD requires MSI */
if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) &&
!ivshmem_has_feature(s, IVSHMEM_MSI)) {
- fprintf(stderr, "ivshmem: ioeventfd/irqfd requires MSI\n");
+ error_report("ioeventfd/irqfd requires MSI");
exit(1);
}
@@ -680,7 +731,7 @@
} else if (strncmp(s->role, "master", 7) == 0) {
s->role_val = IVSHMEM_MASTER;
} else {
- fprintf(stderr, "ivshmem: 'role' must be 'peer' or 'master'\n");
+ error_report("'role' must be 'peer' or 'master'");
exit(1);
}
} else {
@@ -720,12 +771,12 @@
* to the ivshmem server to receive the memory region */
if (s->shmobj != NULL) {
- fprintf(stderr, "WARNING: do not specify both 'chardev' "
- "and 'shm' with ivshmem\n");
+ error_report("WARNING: do not specify both 'chardev' "
+ "and 'shm' with ivshmem");
}
IVSHMEM_DPRINTF("using shared memory server (socket = %s)\n",
- s->server_chr->filename);
+ s->server_chr->filename);
if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
ivshmem_setup_msi(s);
@@ -749,7 +800,7 @@
int fd;
if (s->shmobj == NULL) {
- fprintf(stderr, "Must specify 'chardev' or 'shm' to ivshmem\n");
+ error_report("Must specify 'chardev' or 'shm' to ivshmem");
exit(1);
}
@@ -761,18 +812,18 @@
S_IRWXU|S_IRWXG|S_IRWXO)) > 0) {
/* truncate file to length PCI device's memory */
if (ftruncate(fd, s->ivshmem_size) != 0) {
- fprintf(stderr, "ivshmem: could not truncate shared file\n");
+ error_report("could not truncate shared file");
}
} else if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR,
S_IRWXU|S_IRWXG|S_IRWXO)) < 0) {
- fprintf(stderr, "ivshmem: could not open shared file\n");
- exit(-1);
+ error_report("could not open shared file");
+ exit(1);
}
if (check_shm_size(s, fd) == -1) {
- exit(-1);
+ exit(1);
}
create_shared_memory_BAR(s, fd);
@@ -796,6 +847,7 @@
memory_region_del_subregion(&s->bar, &s->ivshmem);
vmstate_unregister_ram(&s->ivshmem, DEVICE(dev));
unregister_savevm(DEVICE(dev), "ivshmem", s);
+ fifo8_destroy(&s->incoming_fifo);
}
static Property ivshmem_properties[] = {
diff --git a/hw/misc/vfio.c b/hw/misc/vfio.c
index b5e7981..fd318a1 100644
--- a/hw/misc/vfio.c
+++ b/hw/misc/vfio.c
@@ -2911,6 +2911,7 @@
}
memory_region_init_ram_ptr(submem, OBJECT(vdev), name, size, *map);
+ memory_region_set_skip_dump(submem);
} else {
empty_region:
/* Create a zero sized sub-region to make cleanup easy. */
diff --git a/hw/openrisc/openrisc_sim.c b/hw/openrisc/openrisc_sim.c
index c110033..1da0657 100644
--- a/hw/openrisc/openrisc_sim.c
+++ b/hw/openrisc/openrisc_sim.c
@@ -72,7 +72,7 @@
entry = elf_entry;
if (kernel_size < 0) {
kernel_size = load_uimage(kernel_filename,
- &entry, NULL, NULL);
+ &entry, NULL, NULL, NULL, NULL);
}
if (kernel_size < 0) {
kernel_size = load_image_targphys(kernel_filename,
diff --git a/hw/ppc/e500.c b/hw/ppc/e500.c
index 16c85ef..2157d87 100644
--- a/hw/ppc/e500.c
+++ b/hw/ppc/e500.c
@@ -830,7 +830,8 @@
* Hrm. No ELF image? Try a uImage, maybe someone is giving us an
* ePAPR compliant kernel
*/
- kernel_size = load_uimage(filename, &bios_entry, &loadaddr, NULL);
+ kernel_size = load_uimage(filename, &bios_entry, &loadaddr, NULL,
+ NULL, NULL);
if (kernel_size < 0) {
fprintf(stderr, "qemu: could not load firmware '%s'\n", filename);
exit(1);
diff --git a/hw/ppc/ppc440_bamboo.c b/hw/ppc/ppc440_bamboo.c
index 81a06d3..778970a 100644
--- a/hw/ppc/ppc440_bamboo.c
+++ b/hw/ppc/ppc440_bamboo.c
@@ -253,7 +253,8 @@
/* Load kernel. */
if (kernel_filename) {
- success = load_uimage(kernel_filename, &entry, &loadaddr, NULL);
+ success = load_uimage(kernel_filename, &entry, &loadaddr, NULL,
+ NULL, NULL);
if (success < 0) {
success = load_elf(kernel_filename, NULL, NULL, &elf_entry,
&elf_lowaddr, NULL, 1, ELF_MACHINE, 0);
diff --git a/hw/scsi/megasas.c b/hw/scsi/megasas.c
index 36a04f3..604252a 100644
--- a/hw/scsi/megasas.c
+++ b/hw/scsi/megasas.c
@@ -31,9 +31,11 @@
#include "mfi.h"
-#define MEGASAS_VERSION "1.70"
+#define MEGASAS_VERSION_GEN1 "1.70"
+#define MEGASAS_VERSION_GEN2 "1.80"
#define MEGASAS_MAX_FRAMES 2048 /* Firmware limit at 65535 */
#define MEGASAS_DEFAULT_FRAMES 1000 /* Windows requires this */
+#define MEGASAS_GEN2_DEFAULT_FRAMES 1008 /* Windows requires this */
#define MEGASAS_MAX_SGE 128 /* Firmware limit */
#define MEGASAS_DEFAULT_SGE 80
#define MEGASAS_MAX_SECTORS 0xFFFF /* No real limit */
@@ -91,6 +93,8 @@
int intr_mask;
int doorbell;
int busy;
+ int diag;
+ int adp_reset;
MegasasCmd *event_cmd;
int event_locale;
@@ -111,14 +115,30 @@
uint64_t producer_pa;
MegasasCmd frames[MEGASAS_MAX_FRAMES];
-
+ DECLARE_BITMAP(frame_map, MEGASAS_MAX_FRAMES);
SCSIBus bus;
} MegasasState;
-#define TYPE_MEGASAS "megasas"
+typedef struct MegasasBaseClass {
+ PCIDeviceClass parent_class;
+ const char *product_name;
+ const char *product_version;
+ int mmio_bar;
+ int ioport_bar;
+ int osts;
+} MegasasBaseClass;
+
+#define TYPE_MEGASAS_BASE "megasas-base"
+#define TYPE_MEGASAS_GEN1 "megasas"
+#define TYPE_MEGASAS_GEN2 "megasas-gen2"
#define MEGASAS(obj) \
- OBJECT_CHECK(MegasasState, (obj), TYPE_MEGASAS)
+ OBJECT_CHECK(MegasasState, (obj), TYPE_MEGASAS_BASE)
+
+#define MEGASAS_DEVICE_CLASS(oc) \
+ OBJECT_CLASS_CHECK(MegasasBaseClass, (oc), TYPE_MEGASAS_BASE)
+#define MEGASAS_DEVICE_GET_CLASS(oc) \
+ OBJECT_GET_CLASS(MegasasBaseClass, (oc), TYPE_MEGASAS_BASE)
#define MEGASAS_INTR_DISABLED_MASK 0xFFFFFFFF
@@ -443,34 +463,20 @@
return cmd;
}
-static MegasasCmd *megasas_next_frame(MegasasState *s,
- hwaddr frame)
+static void megasas_unmap_frame(MegasasState *s, MegasasCmd *cmd)
{
- MegasasCmd *cmd = NULL;
- int num = 0, index;
+ PCIDevice *p = PCI_DEVICE(s);
- cmd = megasas_lookup_frame(s, frame);
- if (cmd) {
- trace_megasas_qf_found(cmd->index, cmd->pa);
- return cmd;
- }
- index = s->reply_queue_head;
- num = 0;
- while (num < s->fw_cmds) {
- if (!s->frames[index].pa) {
- cmd = &s->frames[index];
- break;
- }
- index = megasas_next_index(s, index, s->fw_cmds);
- num++;
- }
- if (!cmd) {
- trace_megasas_qf_failed(frame);
- }
- trace_megasas_qf_new(index, cmd);
- return cmd;
+ pci_dma_unmap(p, cmd->frame, cmd->pa_size, 0, 0);
+ cmd->frame = NULL;
+ cmd->pa = 0;
+ clear_bit(cmd->index, s->frame_map);
}
+/*
+ * This absolutely needs to be locked if
+ * qemu ever goes multithreaded.
+ */
static MegasasCmd *megasas_enqueue_frame(MegasasState *s,
hwaddr frame, uint64_t context, int count)
{
@@ -478,37 +484,50 @@
MegasasCmd *cmd = NULL;
int frame_size = MFI_FRAME_SIZE * 16;
hwaddr frame_size_p = frame_size;
+ unsigned long index;
- cmd = megasas_next_frame(s, frame);
- /* All frames busy */
- if (!cmd) {
+ index = 0;
+ while (index < s->fw_cmds) {
+ index = find_next_zero_bit(s->frame_map, s->fw_cmds, index);
+ if (!s->frames[index].pa)
+ break;
+ /* Busy frame found */
+ trace_megasas_qf_mapped(index);
+ }
+ if (index >= s->fw_cmds) {
+ /* All frames busy */
+ trace_megasas_qf_busy(frame);
return NULL;
}
- if (!cmd->pa) {
- cmd->pa = frame;
- /* Map all possible frames */
- cmd->frame = pci_dma_map(pcid, frame, &frame_size_p, 0);
- if (frame_size_p != frame_size) {
- trace_megasas_qf_map_failed(cmd->index, (unsigned long)frame);
- if (cmd->frame) {
- pci_dma_unmap(pcid, cmd->frame, frame_size_p, 0, 0);
- cmd->frame = NULL;
- cmd->pa = 0;
- }
- s->event_count++;
- return NULL;
+ cmd = &s->frames[index];
+ set_bit(index, s->frame_map);
+ trace_megasas_qf_new(index, frame);
+
+ cmd->pa = frame;
+ /* Map all possible frames */
+ cmd->frame = pci_dma_map(pcid, frame, &frame_size_p, 0);
+ if (frame_size_p != frame_size) {
+ trace_megasas_qf_map_failed(cmd->index, (unsigned long)frame);
+ if (cmd->frame) {
+ megasas_unmap_frame(s, cmd);
}
- cmd->pa_size = frame_size_p;
- cmd->context = context;
- if (!megasas_use_queue64(s)) {
- cmd->context &= (uint64_t)0xFFFFFFFF;
- }
+ s->event_count++;
+ return NULL;
+ }
+ cmd->pa_size = frame_size_p;
+ cmd->context = context;
+ if (!megasas_use_queue64(s)) {
+ cmd->context &= (uint64_t)0xFFFFFFFF;
}
cmd->count = count;
s->busy++;
+ if (s->consumer_pa) {
+ s->reply_queue_tail = ldl_le_phys(&address_space_memory,
+ s->consumer_pa);
+ }
trace_megasas_qf_enqueue(cmd->index, cmd->count, cmd->context,
- s->reply_queue_head, s->busy);
+ s->reply_queue_head, s->reply_queue_tail, s->busy);
return cmd;
}
@@ -520,39 +539,47 @@
/* Decrement busy count */
s->busy--;
-
if (s->reply_queue_pa) {
/*
* Put command on the reply queue.
* Context is opaque, but emulation is running in
* little endian. So convert it.
*/
- tail = s->reply_queue_head;
if (megasas_use_queue64(s)) {
- queue_offset = tail * sizeof(uint64_t);
+ queue_offset = s->reply_queue_head * sizeof(uint64_t);
stq_le_phys(&address_space_memory,
s->reply_queue_pa + queue_offset, context);
} else {
- queue_offset = tail * sizeof(uint32_t);
+ queue_offset = s->reply_queue_head * sizeof(uint32_t);
stl_le_phys(&address_space_memory,
s->reply_queue_pa + queue_offset, context);
}
- s->reply_queue_head = megasas_next_index(s, tail, s->fw_cmds);
- trace_megasas_qf_complete(context, tail, queue_offset,
- s->busy, s->doorbell);
+ s->reply_queue_tail = ldl_le_phys(&address_space_memory,
+ s->consumer_pa);
+ trace_megasas_qf_complete(context, s->reply_queue_head,
+ s->reply_queue_tail, s->busy);
}
if (megasas_intr_enabled(s)) {
+ /* Update reply queue pointer */
+ s->reply_queue_tail = ldl_le_phys(&address_space_memory,
+ s->consumer_pa);
+ tail = s->reply_queue_head;
+ s->reply_queue_head = megasas_next_index(s, tail, s->fw_cmds);
+ trace_megasas_qf_update(s->reply_queue_head, s->reply_queue_tail,
+ s->busy);
+ stl_le_phys(&address_space_memory,
+ s->producer_pa, s->reply_queue_head);
/* Notify HBA */
- s->doorbell++;
- if (s->doorbell == 1) {
- if (msix_enabled(pci_dev)) {
- trace_megasas_msix_raise(0);
- msix_notify(pci_dev, 0);
- } else if (msi_enabled(pci_dev)) {
- trace_megasas_msi_raise(0);
- msi_notify(pci_dev, 0);
- } else {
+ if (msix_enabled(pci_dev)) {
+ trace_megasas_msix_raise(0);
+ msix_notify(pci_dev, 0);
+ } else if (msi_enabled(pci_dev)) {
+ trace_megasas_msi_raise(0);
+ msi_notify(pci_dev, 0);
+ } else {
+ s->doorbell++;
+ if (s->doorbell == 1) {
trace_megasas_irq_raise();
pci_irq_assert(pci_dev);
}
@@ -564,18 +591,16 @@
static void megasas_reset_frames(MegasasState *s)
{
- PCIDevice *pcid = PCI_DEVICE(s);
int i;
MegasasCmd *cmd;
for (i = 0; i < s->fw_cmds; i++) {
cmd = &s->frames[i];
if (cmd->pa) {
- pci_dma_unmap(pcid, cmd->frame, cmd->pa_size, 0, 0);
- cmd->frame = NULL;
- cmd->pa = 0;
+ megasas_unmap_frame(s, cmd);
}
}
+ bitmap_zero(s->frame_map, MEGASAS_MAX_FRAMES);
}
static void megasas_abort_command(MegasasCmd *cmd)
@@ -590,16 +615,19 @@
{
PCIDevice *pcid = PCI_DEVICE(s);
uint32_t pa_hi, pa_lo;
- hwaddr iq_pa, initq_size;
- struct mfi_init_qinfo *initq;
+ hwaddr iq_pa, initq_size = sizeof(struct mfi_init_qinfo);
+ struct mfi_init_qinfo *initq = NULL;
uint32_t flags;
int ret = MFI_STAT_OK;
+ if (s->reply_queue_pa) {
+ trace_megasas_initq_mapped(s->reply_queue_pa);
+ goto out;
+ }
pa_lo = le32_to_cpu(cmd->frame->init.qinfo_new_addr_lo);
pa_hi = le32_to_cpu(cmd->frame->init.qinfo_new_addr_hi);
iq_pa = (((uint64_t) pa_hi << 32) | pa_lo);
trace_megasas_init_firmware((uint64_t)iq_pa);
- initq_size = sizeof(*initq);
initq = pci_dma_map(pcid, iq_pa, &initq_size, 0);
if (!initq || initq_size != sizeof(*initq)) {
trace_megasas_initq_map_failed(cmd->index);
@@ -686,11 +714,12 @@
static int megasas_ctrl_get_info(MegasasState *s, MegasasCmd *cmd)
{
PCIDevice *pci_dev = PCI_DEVICE(s);
+ PCIDeviceClass *pci_class = PCI_DEVICE_GET_CLASS(pci_dev);
+ MegasasBaseClass *base_class = MEGASAS_DEVICE_GET_CLASS(s);
struct mfi_ctrl_info info;
size_t dcmd_size = sizeof(info);
BusChild *kid;
- int num_ld_disks = 0;
- uint16_t sdev_id;
+ int num_pd_disks = 0;
memset(&info, 0x0, cmd->iov_size);
if (cmd->iov_size < dcmd_size) {
@@ -699,10 +728,10 @@
return MFI_STAT_INVALID_PARAMETER;
}
- info.pci.vendor = cpu_to_le16(PCI_VENDOR_ID_LSI_LOGIC);
- info.pci.device = cpu_to_le16(PCI_DEVICE_ID_LSI_SAS1078);
- info.pci.subvendor = cpu_to_le16(PCI_VENDOR_ID_LSI_LOGIC);
- info.pci.subdevice = cpu_to_le16(0x1013);
+ info.pci.vendor = cpu_to_le16(pci_class->vendor_id);
+ info.pci.device = cpu_to_le16(pci_class->device_id);
+ info.pci.subvendor = cpu_to_le16(pci_class->subsystem_vendor_id);
+ info.pci.subdevice = cpu_to_le16(pci_class->subsystem_id);
/*
* For some reason the firmware supports
@@ -719,20 +748,22 @@
info.device.port_count = 8;
QTAILQ_FOREACH(kid, &s->bus.qbus.children, sibling) {
SCSIDevice *sdev = DO_UPCAST(SCSIDevice, qdev, kid->child);
+ uint16_t pd_id;
- if (num_ld_disks < 8) {
- sdev_id = ((sdev->id & 0xFF) >> 8) | (sdev->lun & 0xFF);
- info.device.port_addr[num_ld_disks] =
- cpu_to_le64(megasas_get_sata_addr(sdev_id));
+ if (num_pd_disks < 8) {
+ pd_id = ((sdev->id & 0xFF) << 8) | (sdev->lun & 0xFF);
+ info.device.port_addr[num_pd_disks] =
+ cpu_to_le64(megasas_get_sata_addr(pd_id));
}
- num_ld_disks++;
+ num_pd_disks++;
}
- memcpy(info.product_name, "MegaRAID SAS 8708EM2", 20);
+ memcpy(info.product_name, base_class->product_name, 24);
snprintf(info.serial_number, 32, "%s", s->hba_serial);
snprintf(info.package_version, 0x60, "%s-QEMU", QEMU_VERSION);
memcpy(info.image_component[0].name, "APP", 3);
- memcpy(info.image_component[0].version, MEGASAS_VERSION "-QEMU", 9);
+ snprintf(info.image_component[0].version, 10, "%s-QEMU",
+ base_class->product_version);
memcpy(info.image_component[0].build_date, "Apr 1 2014", 11);
memcpy(info.image_component[0].build_time, "12:34:56", 8);
info.image_component_count = 1;
@@ -751,13 +782,14 @@
info.max_arms = 32;
info.max_spans = 8;
info.max_arrays = MEGASAS_MAX_ARRAYS;
- info.max_lds = s->fw_luns;
+ info.max_lds = MFI_MAX_LD;
info.max_cmds = cpu_to_le16(s->fw_cmds);
info.max_sg_elements = cpu_to_le16(s->fw_sge);
info.max_request_size = cpu_to_le32(MEGASAS_MAX_SECTORS);
- info.lds_present = cpu_to_le16(num_ld_disks);
- info.pd_present = cpu_to_le16(num_ld_disks);
- info.pd_disks_present = cpu_to_le16(num_ld_disks);
+ if (!megasas_is_jbod(s))
+ info.lds_present = cpu_to_le16(num_pd_disks);
+ info.pd_present = cpu_to_le16(num_pd_disks);
+ info.pd_disks_present = cpu_to_le16(num_pd_disks);
info.hw_present = cpu_to_le32(MFI_INFO_HW_NVRAM |
MFI_INFO_HW_MEM |
MFI_INFO_HW_FLASH);
@@ -916,7 +948,6 @@
size_t dcmd_size = sizeof(info);
BusChild *kid;
uint32_t offset, dcmd_limit, num_pd_disks = 0, max_pd_disks;
- uint16_t sdev_id;
memset(&info, 0, dcmd_size);
offset = 8;
@@ -928,22 +959,25 @@
}
max_pd_disks = (cmd->iov_size - offset) / sizeof(struct mfi_pd_address);
- if (max_pd_disks > s->fw_luns) {
- max_pd_disks = s->fw_luns;
+ if (max_pd_disks > MFI_MAX_SYS_PDS) {
+ max_pd_disks = MFI_MAX_SYS_PDS;
}
-
QTAILQ_FOREACH(kid, &s->bus.qbus.children, sibling) {
SCSIDevice *sdev = DO_UPCAST(SCSIDevice, qdev, kid->child);
+ uint16_t pd_id;
- sdev_id = ((sdev->id & 0xFF) >> 8) | (sdev->lun & 0xFF);
- info.addr[num_pd_disks].device_id = cpu_to_le16(sdev_id);
+ if (num_pd_disks >= max_pd_disks)
+ break;
+
+ pd_id = ((sdev->id & 0xFF) << 8) | (sdev->lun & 0xFF);
+ info.addr[num_pd_disks].device_id = cpu_to_le16(pd_id);
info.addr[num_pd_disks].encl_device_id = 0xFFFF;
info.addr[num_pd_disks].encl_index = 0;
- info.addr[num_pd_disks].slot_number = (sdev->id & 0xFF);
+ info.addr[num_pd_disks].slot_number = sdev->id & 0xFF;
info.addr[num_pd_disks].scsi_dev_type = sdev->type;
info.addr[num_pd_disks].connect_port_bitmap = 0x1;
info.addr[num_pd_disks].sas_addr[0] =
- cpu_to_le64(megasas_get_sata_addr(sdev_id));
+ cpu_to_le64(megasas_get_sata_addr(pd_id));
num_pd_disks++;
offset += sizeof(struct mfi_pd_address);
}
@@ -978,7 +1012,7 @@
struct mfi_pd_info *info = cmd->iov_buf;
size_t dcmd_size = sizeof(struct mfi_pd_info);
uint64_t pd_size;
- uint16_t sdev_id = ((sdev->id & 0xFF) >> 8) | (lun & 0xFF);
+ uint16_t pd_id = ((sdev->id & 0xFF) << 8) | (lun & 0xFF);
uint8_t cmdbuf[6];
SCSIRequest *req;
size_t len, resid;
@@ -1034,7 +1068,7 @@
info->fw_state = cpu_to_le16(MFI_PD_STATE_OFFLINE);
}
- info->ref.v.device_id = cpu_to_le16(sdev_id);
+ info->ref.v.device_id = cpu_to_le16(pd_id);
info->state.ddf.pd_type = cpu_to_le16(MFI_PD_DDF_TYPE_IN_VD|
MFI_PD_DDF_TYPE_INTF_SAS);
blk_get_geometry(sdev->conf.blk, &pd_size);
@@ -1045,7 +1079,7 @@
info->slot_number = (sdev->id & 0xFF);
info->path_info.count = 1;
info->path_info.sas_addr[0] =
- cpu_to_le64(megasas_get_sata_addr(sdev_id));
+ cpu_to_le64(megasas_get_sata_addr(pd_id));
info->connected_port_bitmap = 0x1;
info->device_speed = 1;
info->link_speed = 1;
@@ -1060,6 +1094,7 @@
{
size_t dcmd_size = sizeof(struct mfi_pd_info);
uint16_t pd_id;
+ uint8_t target_id, lun_id;
SCSIDevice *sdev = NULL;
int retval = MFI_STAT_DEVICE_NOT_FOUND;
@@ -1069,7 +1104,9 @@
/* mbox0 has the ID */
pd_id = le16_to_cpu(cmd->frame->dcmd.mbox[0]);
- sdev = scsi_device_find(&s->bus, 0, pd_id, 0);
+ target_id = (pd_id >> 8) & 0xFF;
+ lun_id = pd_id & 0xFF;
+ sdev = scsi_device_find(&s->bus, 0, target_id, lun_id);
trace_megasas_dcmd_pd_get_info(cmd->index, pd_id);
if (sdev) {
@@ -1084,20 +1121,24 @@
{
struct mfi_ld_list info;
size_t dcmd_size = sizeof(info), resid;
- uint32_t num_ld_disks = 0, max_ld_disks = s->fw_luns;
+ uint32_t num_ld_disks = 0, max_ld_disks;
uint64_t ld_size;
BusChild *kid;
memset(&info, 0, dcmd_size);
- if (cmd->iov_size < dcmd_size) {
+ if (cmd->iov_size > dcmd_size) {
trace_megasas_dcmd_invalid_xfer_len(cmd->index, cmd->iov_size,
dcmd_size);
return MFI_STAT_INVALID_PARAMETER;
}
+ max_ld_disks = (cmd->iov_size - 8) / 16;
if (megasas_is_jbod(s)) {
max_ld_disks = 0;
}
+ if (max_ld_disks > MFI_MAX_LD) {
+ max_ld_disks = MFI_MAX_LD;
+ }
QTAILQ_FOREACH(kid, &s->bus.qbus.children, sibling) {
SCSIDevice *sdev = DO_UPCAST(SCSIDevice, qdev, kid->child);
@@ -1107,7 +1148,6 @@
/* Logical device size is in blocks */
blk_get_geometry(sdev->conf.blk, &ld_size);
info.ld_list[num_ld_disks].ld.v.target_id = sdev->id;
- info.ld_list[num_ld_disks].ld.v.lun_id = sdev->lun;
info.ld_list[num_ld_disks].state = MFI_LD_STATE_OPTIMAL;
info.ld_list[num_ld_disks].size = cpu_to_le64(ld_size);
num_ld_disks++;
@@ -1123,15 +1163,49 @@
static int megasas_dcmd_ld_list_query(MegasasState *s, MegasasCmd *cmd)
{
uint16_t flags;
+ struct mfi_ld_targetid_list info;
+ size_t dcmd_size = sizeof(info), resid;
+ uint32_t num_ld_disks = 0, max_ld_disks = s->fw_luns;
+ BusChild *kid;
/* mbox0 contains flags */
flags = le16_to_cpu(cmd->frame->dcmd.mbox[0]);
trace_megasas_dcmd_ld_list_query(cmd->index, flags);
- if (flags == MR_LD_QUERY_TYPE_ALL ||
- flags == MR_LD_QUERY_TYPE_EXPOSED_TO_HOST) {
- return megasas_dcmd_ld_get_list(s, cmd);
+ if (flags != MR_LD_QUERY_TYPE_ALL &&
+ flags != MR_LD_QUERY_TYPE_EXPOSED_TO_HOST) {
+ max_ld_disks = 0;
}
+ memset(&info, 0, dcmd_size);
+ if (cmd->iov_size < 12) {
+ trace_megasas_dcmd_invalid_xfer_len(cmd->index, cmd->iov_size,
+ dcmd_size);
+ return MFI_STAT_INVALID_PARAMETER;
+ }
+ dcmd_size = sizeof(uint32_t) * 2 + 3;
+ max_ld_disks = cmd->iov_size - dcmd_size;
+ if (megasas_is_jbod(s)) {
+ max_ld_disks = 0;
+ }
+ if (max_ld_disks > MFI_MAX_LD) {
+ max_ld_disks = MFI_MAX_LD;
+ }
+ QTAILQ_FOREACH(kid, &s->bus.qbus.children, sibling) {
+ SCSIDevice *sdev = DO_UPCAST(SCSIDevice, qdev, kid->child);
+
+ if (num_ld_disks >= max_ld_disks) {
+ break;
+ }
+ info.targetid[num_ld_disks] = sdev->lun;
+ num_ld_disks++;
+ dcmd_size++;
+ }
+ info.ld_count = cpu_to_le32(num_ld_disks);
+ info.size = dcmd_size;
+ trace_megasas_dcmd_ld_get_list(cmd->index, num_ld_disks, max_ld_disks);
+
+ resid = dma_buf_read((uint8_t *)&info, dcmd_size, &cmd->qsg);
+ cmd->iov_size = dcmd_size - resid;
return MFI_STAT_OK;
}
@@ -1143,7 +1217,7 @@
uint8_t cdb[6];
SCSIRequest *req;
ssize_t len, resid;
- uint16_t sdev_id = ((sdev->id & 0xFF) >> 8) | (lun & 0xFF);
+ uint16_t sdev_id = ((sdev->id & 0xFF) << 8) | (lun & 0xFF);
uint64_t ld_size;
if (!cmd->iov_buf) {
@@ -1259,7 +1333,7 @@
QTAILQ_FOREACH(kid, &s->bus.qbus.children, sibling) {
SCSIDevice *sdev = DO_UPCAST(SCSIDevice, qdev, kid->child);
- uint16_t sdev_id = ((sdev->id & 0xFF) >> 8) | (sdev->lun & 0xFF);
+ uint16_t sdev_id = ((sdev->id & 0xFF) << 8) | (sdev->lun & 0xFF);
struct mfi_array *array;
struct mfi_ld_config *ld;
uint64_t pd_size;
@@ -1285,7 +1359,7 @@
array_offset += sizeof(struct mfi_array);
ld = (struct mfi_ld_config *)(data + ld_offset);
memset(ld, 0, sizeof(struct mfi_ld_config));
- ld->properties.ld.v.target_id = (sdev->id & 0xFF);
+ ld->properties.ld.v.target_id = sdev->id;
ld->properties.default_cache_policy = MR_LD_CACHE_READ_AHEAD |
MR_LD_CACHE_READ_ADAPTIVE;
ld->properties.current_cache_policy = MR_LD_CACHE_READ_AHEAD |
@@ -1347,9 +1421,23 @@
return MFI_STAT_OK;
}
+/* Some implementations use CLUSTER RESET LD to simulate a device reset */
static int megasas_cluster_reset_ld(MegasasState *s, MegasasCmd *cmd)
{
- return MFI_STAT_INVALID_DCMD;
+ uint16_t target_id;
+ int i;
+
+ /* mbox0 contains the device index */
+ target_id = le16_to_cpu(cmd->frame->dcmd.mbox[0]);
+ trace_megasas_dcmd_reset_ld(cmd->index, target_id);
+ for (i = 0; i < s->fw_cmds; i++) {
+ MegasasCmd *tmp_cmd = &s->frames[i];
+ if (tmp_cmd->req && tmp_cmd->req->dev->id == target_id) {
+ SCSIDevice *d = tmp_cmd->req->dev;
+ qdev_reset_all(&d->qdev);
+ }
+ }
+ return MFI_STAT_OK;
}
static int megasas_dcmd_set_properties(MegasasState *s, MegasasCmd *cmd)
@@ -1566,16 +1654,23 @@
bool is_logical)
{
uint8_t *cdb;
- int len;
bool is_write;
struct SCSIDevice *sdev = NULL;
cdb = cmd->frame->pass.cdb;
- if (cmd->frame->header.target_id < s->fw_luns) {
- sdev = scsi_device_find(&s->bus, 0, cmd->frame->header.target_id,
- cmd->frame->header.lun_id);
+ if (is_logical) {
+ if (cmd->frame->header.target_id >= MFI_MAX_LD ||
+ cmd->frame->header.lun_id != 0) {
+ trace_megasas_scsi_target_not_present(
+ mfi_frame_desc[cmd->frame->header.frame_cmd], is_logical,
+ cmd->frame->header.target_id, cmd->frame->header.lun_id);
+ return MFI_STAT_DEVICE_NOT_FOUND;
+ }
}
+ sdev = scsi_device_find(&s->bus, 0, cmd->frame->header.target_id,
+ cmd->frame->header.lun_id);
+
cmd->iov_size = le32_to_cpu(cmd->frame->header.data_len);
trace_megasas_handle_scsi(mfi_frame_desc[cmd->frame->header.frame_cmd],
is_logical, cmd->frame->header.target_id,
@@ -1619,16 +1714,16 @@
}
is_write = (cmd->req->cmd.mode == SCSI_XFER_TO_DEV);
- len = megasas_enqueue_req(cmd, is_write);
- if (len > 0) {
+ if (cmd->iov_size) {
if (is_write) {
- trace_megasas_scsi_write_start(cmd->index, len);
+ trace_megasas_scsi_write_start(cmd->index, cmd->iov_size);
} else {
- trace_megasas_scsi_read_start(cmd->index, len);
+ trace_megasas_scsi_read_start(cmd->index, cmd->iov_size);
}
} else {
trace_megasas_scsi_nodata(cmd->index);
}
+ megasas_enqueue_req(cmd, is_write);
return MFI_STAT_INVALID_STATUS;
}
@@ -1646,7 +1741,8 @@
lba_start_hi = le32_to_cpu(cmd->frame->io.lba_hi);
lba_start = ((uint64_t)lba_start_hi << 32) | lba_start_lo;
- if (cmd->frame->header.target_id < s->fw_luns) {
+ if (cmd->frame->header.target_id < MFI_MAX_LD &&
+ cmd->frame->header.lun_id == 0) {
sdev = scsi_device_find(&s->bus, 0, cmd->frame->header.target_id,
cmd->frame->header.lun_id);
}
@@ -1797,6 +1893,7 @@
cmd->req = NULL;
}
cmd->frame->header.cmd_status = cmd_status;
+ megasas_unmap_frame(cmd->state, cmd);
megasas_complete_frame(cmd->state, cmd->context);
}
@@ -1900,6 +1997,7 @@
} else {
megasas_frame_set_cmd_status(frame_addr, frame_status);
}
+ megasas_unmap_frame(s, cmd);
megasas_complete_frame(s, cmd->context);
}
}
@@ -1908,38 +2006,55 @@
unsigned size)
{
MegasasState *s = opaque;
+ PCIDevice *pci_dev = PCI_DEVICE(s);
+ MegasasBaseClass *base_class = MEGASAS_DEVICE_GET_CLASS(s);
uint32_t retval = 0;
switch (addr) {
case MFI_IDB:
retval = 0;
+ trace_megasas_mmio_readl("MFI_IDB", retval);
break;
case MFI_OMSG0:
case MFI_OSP0:
- retval = (megasas_use_msix(s) ? MFI_FWSTATE_MSIX_SUPPORTED : 0) |
+ retval = (msix_present(pci_dev) ? MFI_FWSTATE_MSIX_SUPPORTED : 0) |
(s->fw_state & MFI_FWSTATE_MASK) |
((s->fw_sge & 0xff) << 16) |
(s->fw_cmds & 0xFFFF);
+ trace_megasas_mmio_readl(addr == MFI_OMSG0 ? "MFI_OMSG0" : "MFI_OSP0",
+ retval);
break;
case MFI_OSTS:
if (megasas_intr_enabled(s) && s->doorbell) {
- retval = MFI_1078_RM | 1;
+ retval = base_class->osts;
}
+ trace_megasas_mmio_readl("MFI_OSTS", retval);
break;
case MFI_OMSK:
retval = s->intr_mask;
+ trace_megasas_mmio_readl("MFI_OMSK", retval);
break;
case MFI_ODCR0:
- retval = s->doorbell;
+ retval = s->doorbell ? 1 : 0;
+ trace_megasas_mmio_readl("MFI_ODCR0", retval);
+ break;
+ case MFI_DIAG:
+ retval = s->diag;
+ trace_megasas_mmio_readl("MFI_DIAG", retval);
+ break;
+ case MFI_OSP1:
+ retval = 15;
+ trace_megasas_mmio_readl("MFI_OSP1", retval);
break;
default:
trace_megasas_mmio_invalid_readl(addr);
break;
}
- trace_megasas_mmio_readl(addr, retval);
return retval;
}
+static int adp_reset_seq[] = {0x00, 0x04, 0x0b, 0x02, 0x07, 0x0d};
+
static void megasas_mmio_write(void *opaque, hwaddr addr,
uint64_t val, unsigned size)
{
@@ -1949,9 +2064,9 @@
uint32_t frame_count;
int i;
- trace_megasas_mmio_writel(addr, val);
switch (addr) {
case MFI_IDB:
+ trace_megasas_mmio_writel("MFI_IDB", val);
if (val & MFI_FWINIT_ABORT) {
/* Abort all pending cmds */
for (i = 0; i < s->fw_cmds; i++) {
@@ -1965,8 +2080,13 @@
if (val & MFI_FWINIT_MFIMODE) {
/* discard MFIs */
}
+ if (val & MFI_FWINIT_STOP_ADP) {
+ /* Terminal error, stop processing */
+ s->fw_state = MFI_FWSTATE_FAULT;
+ }
break;
case MFI_OMSK:
+ trace_megasas_mmio_writel("MFI_OMSK", val);
s->intr_mask = val;
if (!megasas_intr_enabled(s) &&
!msi_enabled(pci_dev) &&
@@ -1984,29 +2104,34 @@
}
} else {
trace_megasas_intr_disabled();
+ megasas_soft_reset(s);
}
break;
case MFI_ODCR0:
+ trace_megasas_mmio_writel("MFI_ODCR0", val);
s->doorbell = 0;
- if (s->producer_pa && megasas_intr_enabled(s)) {
- /* Update reply queue pointer */
- trace_megasas_qf_update(s->reply_queue_head, s->busy);
- stl_le_phys(&address_space_memory,
- s->producer_pa, s->reply_queue_head);
- if (!msix_enabled(pci_dev)) {
+ if (megasas_intr_enabled(s)) {
+ if (!msix_enabled(pci_dev) && !msi_enabled(pci_dev)) {
trace_megasas_irq_lower();
pci_irq_deassert(pci_dev);
}
}
break;
case MFI_IQPH:
+ trace_megasas_mmio_writel("MFI_IQPH", val);
/* Received high 32 bits of a 64 bit MFI frame address */
s->frame_hi = val;
break;
case MFI_IQPL:
+ trace_megasas_mmio_writel("MFI_IQPL", val);
/* Received low 32 bits of a 64 bit MFI frame address */
+ /* Fallthrough */
case MFI_IQP:
- /* Received 32 bit MFI frame address */
+ if (addr == MFI_IQP) {
+ trace_megasas_mmio_writel("MFI_IQP", val);
+ /* Received 64 bit MFI frame address */
+ s->frame_hi = 0;
+ }
frame_addr = (val & ~0x1F);
/* Add possible 64 bit offset */
frame_addr |= ((uint64_t)s->frame_hi << 32);
@@ -2014,6 +2139,30 @@
frame_count = (val >> 1) & 0xF;
megasas_handle_frame(s, frame_addr, frame_count);
break;
+ case MFI_SEQ:
+ trace_megasas_mmio_writel("MFI_SEQ", val);
+ /* Magic sequence to start ADP reset */
+ if (adp_reset_seq[s->adp_reset] == val) {
+ s->adp_reset++;
+ } else {
+ s->adp_reset = 0;
+ s->diag = 0;
+ }
+ if (s->adp_reset == 6) {
+ s->diag = MFI_DIAG_WRITE_ENABLE;
+ }
+ break;
+ case MFI_DIAG:
+ trace_megasas_mmio_writel("MFI_DIAG", val);
+ /* ADP reset */
+ if ((s->diag & MFI_DIAG_WRITE_ENABLE) &&
+ (val & MFI_DIAG_RESET_ADP)) {
+ s->diag |= MFI_DIAG_RESET_ADP;
+ megasas_soft_reset(s);
+ s->adp_reset = 0;
+ s->diag = 0;
+ }
+ break;
default:
trace_megasas_mmio_invalid_writel(addr, val);
break;
@@ -2072,11 +2221,26 @@
int i;
MegasasCmd *cmd;
- trace_megasas_reset();
+ trace_megasas_reset(s->fw_state);
for (i = 0; i < s->fw_cmds; i++) {
cmd = &s->frames[i];
megasas_abort_command(cmd);
}
+ if (s->fw_state == MFI_FWSTATE_READY) {
+ BusChild *kid;
+
+ /*
+ * The EFI firmware doesn't handle UA,
+ * so we need to clear the Power On/Reset UA
+ * after the initial reset.
+ */
+ QTAILQ_FOREACH(kid, &s->bus.qbus.children, sibling) {
+ SCSIDevice *sdev = DO_UPCAST(SCSIDevice, qdev, kid->child);
+
+ sdev->unit_attention = SENSE_CODE(NO_SENSE);
+ scsi_device_unit_attention_reported(sdev);
+ }
+ }
megasas_reset_frames(s);
s->reply_queue_len = s->fw_cmds;
s->reply_queue_pa = 0;
@@ -2098,7 +2262,7 @@
megasas_soft_reset(s);
}
-static const VMStateDescription vmstate_megasas = {
+static const VMStateDescription vmstate_megasas_gen1 = {
.name = "megasas",
.version_id = 0,
.minimum_version_id = 0,
@@ -2116,6 +2280,25 @@
}
};
+static const VMStateDescription vmstate_megasas_gen2 = {
+ .name = "megasas-gen2",
+ .version_id = 0,
+ .minimum_version_id = 0,
+ .minimum_version_id_old = 0,
+ .fields = (VMStateField[]) {
+ VMSTATE_PCIE_DEVICE(parent_obj, MegasasState),
+ VMSTATE_MSIX(parent_obj, MegasasState),
+
+ VMSTATE_INT32(fw_state, MegasasState),
+ VMSTATE_INT32(intr_mask, MegasasState),
+ VMSTATE_INT32(doorbell, MegasasState),
+ VMSTATE_UINT64(reply_queue_pa, MegasasState),
+ VMSTATE_UINT64(consumer_pa, MegasasState),
+ VMSTATE_UINT64(producer_pa, MegasasState),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
static void megasas_scsi_uninit(PCIDevice *d)
{
MegasasState *s = MEGASAS(d);
@@ -2143,6 +2326,7 @@
{
DeviceState *d = DEVICE(dev);
MegasasState *s = MEGASAS(dev);
+ MegasasBaseClass *b = MEGASAS_DEVICE_GET_CLASS(s);
uint8_t *pci_conf;
int i, bar_type;
Error *err = NULL;
@@ -2166,20 +2350,25 @@
s->flags &= ~MEGASAS_MASK_USE_MSI;
}
if (megasas_use_msix(s) &&
- msix_init(dev, 15, &s->mmio_io, 0, 0x2000,
- &s->mmio_io, 0, 0x3800, 0x68)) {
+ msix_init(dev, 15, &s->mmio_io, b->mmio_bar, 0x2000,
+ &s->mmio_io, b->mmio_bar, 0x3800, 0x68)) {
s->flags &= ~MEGASAS_MASK_USE_MSIX;
}
+ if (pci_is_express(dev)) {
+ pcie_endpoint_cap_init(dev, 0xa0);
+ }
bar_type = PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64;
- pci_register_bar(dev, 0, bar_type, &s->mmio_io);
- pci_register_bar(dev, 2, PCI_BASE_ADDRESS_SPACE_IO, &s->port_io);
+ pci_register_bar(dev, b->ioport_bar,
+ PCI_BASE_ADDRESS_SPACE_IO, &s->port_io);
+ pci_register_bar(dev, b->mmio_bar, bar_type, &s->mmio_io);
pci_register_bar(dev, 3, bar_type, &s->queue_io);
if (megasas_use_msix(s)) {
msix_vector_use(dev, 0);
}
+ s->fw_state = MFI_FWSTATE_READY;
if (!s->sas_addr) {
s->sas_addr = ((NAA_LOCALLY_ASSIGNED_ID << 24) |
IEEE_COMPANY_LOCALLY_ASSIGNED) << 36;
@@ -2202,8 +2391,12 @@
}
trace_megasas_init(s->fw_sge, s->fw_cmds,
megasas_is_jbod(s) ? "jbod" : "raid");
- s->fw_luns = (MFI_MAX_LD > MAX_SCSI_DEVS) ?
- MAX_SCSI_DEVS : MFI_MAX_LD;
+
+ if (megasas_is_jbod(s)) {
+ s->fw_luns = MFI_MAX_SYS_PDS;
+ } else {
+ s->fw_luns = MFI_MAX_LD;
+ }
s->producer_pa = 0;
s->consumer_pa = 0;
for (i = 0; i < s->fw_cmds; i++) {
@@ -2232,7 +2425,7 @@
msi_write_config(pci, addr, val, len);
}
-static Property megasas_properties[] = {
+static Property megasas_properties_gen1[] = {
DEFINE_PROP_UINT32("max_sge", MegasasState, fw_sge,
MEGASAS_DEFAULT_SGE),
DEFINE_PROP_UINT32("max_cmds", MegasasState, fw_cmds,
@@ -2248,36 +2441,119 @@
DEFINE_PROP_END_OF_LIST(),
};
+static Property megasas_properties_gen2[] = {
+ DEFINE_PROP_UINT32("max_sge", MegasasState, fw_sge,
+ MEGASAS_DEFAULT_SGE),
+ DEFINE_PROP_UINT32("max_cmds", MegasasState, fw_cmds,
+ MEGASAS_GEN2_DEFAULT_FRAMES),
+ DEFINE_PROP_STRING("hba_serial", MegasasState, hba_serial),
+ DEFINE_PROP_UINT64("sas_address", MegasasState, sas_addr, 0),
+ DEFINE_PROP_BIT("use_msi", MegasasState, flags,
+ MEGASAS_FLAG_USE_MSI, true),
+ DEFINE_PROP_BIT("use_msix", MegasasState, flags,
+ MEGASAS_FLAG_USE_MSIX, true),
+ DEFINE_PROP_BIT("use_jbod", MegasasState, flags,
+ MEGASAS_FLAG_USE_JBOD, false),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+typedef struct MegasasInfo {
+ const char *name;
+ const char *desc;
+ const char *product_name;
+ const char *product_version;
+ uint16_t device_id;
+ uint16_t subsystem_id;
+ int ioport_bar;
+ int mmio_bar;
+ bool is_express;
+ int osts;
+ const VMStateDescription *vmsd;
+ Property *props;
+} MegasasInfo;
+
+static struct MegasasInfo megasas_devices[] = {
+ {
+ .name = TYPE_MEGASAS_GEN1,
+ .desc = "LSI MegaRAID SAS 1078",
+ .product_name = "LSI MegaRAID SAS 8708EM2",
+ .product_version = MEGASAS_VERSION_GEN1,
+ .device_id = PCI_DEVICE_ID_LSI_SAS1078,
+ .subsystem_id = 0x1013,
+ .ioport_bar = 2,
+ .mmio_bar = 0,
+ .osts = MFI_1078_RM | 1,
+ .is_express = false,
+ .vmsd = &vmstate_megasas_gen1,
+ .props = megasas_properties_gen1,
+ },{
+ .name = TYPE_MEGASAS_GEN2,
+ .desc = "LSI MegaRAID SAS 2108",
+ .product_name = "LSI MegaRAID SAS 9260-8i",
+ .product_version = MEGASAS_VERSION_GEN2,
+ .device_id = PCI_DEVICE_ID_LSI_SAS0079,
+ .subsystem_id = 0x9261,
+ .ioport_bar = 0,
+ .mmio_bar = 1,
+ .osts = MFI_GEN2_RM,
+ .is_express = true,
+ .vmsd = &vmstate_megasas_gen2,
+ .props = megasas_properties_gen2,
+ }
+};
+
static void megasas_class_init(ObjectClass *oc, void *data)
{
DeviceClass *dc = DEVICE_CLASS(oc);
PCIDeviceClass *pc = PCI_DEVICE_CLASS(oc);
+ MegasasBaseClass *e = MEGASAS_DEVICE_CLASS(oc);
+ const MegasasInfo *info = data;
pc->init = megasas_scsi_init;
pc->exit = megasas_scsi_uninit;
pc->vendor_id = PCI_VENDOR_ID_LSI_LOGIC;
- pc->device_id = PCI_DEVICE_ID_LSI_SAS1078;
+ pc->device_id = info->device_id;
pc->subsystem_vendor_id = PCI_VENDOR_ID_LSI_LOGIC;
- pc->subsystem_id = 0x1013;
+ pc->subsystem_id = info->subsystem_id;
pc->class_id = PCI_CLASS_STORAGE_RAID;
- dc->props = megasas_properties;
+ pc->is_express = info->is_express;
+ e->mmio_bar = info->mmio_bar;
+ e->ioport_bar = info->ioport_bar;
+ e->osts = info->osts;
+ e->product_name = info->product_name;
+ e->product_version = info->product_version;
+ dc->props = info->props;
dc->reset = megasas_scsi_reset;
- dc->vmsd = &vmstate_megasas;
+ dc->vmsd = info->vmsd;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
- dc->desc = "LSI MegaRAID SAS 1078";
+ dc->desc = info->desc;
pc->config_write = megasas_write_config;
}
static const TypeInfo megasas_info = {
- .name = TYPE_MEGASAS,
+ .name = TYPE_MEGASAS_BASE,
.parent = TYPE_PCI_DEVICE,
.instance_size = sizeof(MegasasState),
- .class_init = megasas_class_init,
+ .class_size = sizeof(MegasasBaseClass),
+ .abstract = true,
};
static void megasas_register_types(void)
{
+ int i;
+
type_register_static(&megasas_info);
+ for (i = 0; i < ARRAY_SIZE(megasas_devices); i++) {
+ const MegasasInfo *info = &megasas_devices[i];
+ TypeInfo type_info = {};
+
+ type_info.name = info->name;
+ type_info.parent = TYPE_MEGASAS_BASE;
+ type_info.class_data = (void *)info;
+ type_info.class_init = megasas_class_init;
+
+ type_register(&type_info);
+ }
}
type_init(megasas_register_types)
diff --git a/hw/scsi/mfi.h b/hw/scsi/mfi.h
index a3034f6..29d4177 100644
--- a/hw/scsi/mfi.h
+++ b/hw/scsi/mfi.h
@@ -60,6 +60,7 @@
#define MFI_ODR0 0x9c /* outbound doorbell register0 */
#define MFI_ODCR0 0xa0 /* outbound doorbell clear register0 */
#define MFI_OSP0 0xb0 /* outbound scratch pad0 */
+#define MFI_OSP1 0xb4 /* outbound scratch pad1 */
#define MFI_IQPL 0xc0 /* Inbound queue port (low bytes) */
#define MFI_IQPH 0xc4 /* Inbound queue port (high bytes) */
#define MFI_DIAG 0xf8 /* Host diag */
@@ -116,6 +117,12 @@
#define MFI_FWINIT_STOP_ADP 0x00000020 /* Move to operational, stop */
#define MFI_FWINIT_ADP_RESET 0x00000040 /* Reset ADP */
+/*
+ * Control bits for the DIAG register
+ */
+#define MFI_DIAG_WRITE_ENABLE 0x00000080
+#define MFI_DIAG_RESET_ADP 0x00000004
+
/* MFI Commands */
typedef enum {
MFI_CMD_INIT = 0x00,
@@ -1094,7 +1101,7 @@
union mfi_ld_ref {
struct {
uint8_t target_id;
- uint8_t lun_id;
+ uint8_t reserved;
uint16_t seq;
} v;
uint32_t ref;
@@ -1111,6 +1118,13 @@
} ld_list[MFI_MAX_LD];
} QEMU_PACKED;
+struct mfi_ld_targetid_list {
+ uint32_t size;
+ uint32_t ld_count;
+ uint8_t pad[3];
+ uint8_t targetid[MFI_MAX_LD];
+} QEMU_PACKED;
+
enum mfi_ld_access {
MFI_LD_ACCESS_RW = 0,
MFI_LD_ACCSSS_RO = 2,
diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
index af7707c..24f7b74 100644
--- a/hw/scsi/scsi-bus.c
+++ b/hw/scsi/scsi-bus.c
@@ -51,14 +51,6 @@
}
}
-static void scsi_device_unrealize(SCSIDevice *s, Error **errp)
-{
- SCSIDeviceClass *sc = SCSI_DEVICE_GET_CLASS(s);
- if (sc->unrealize) {
- sc->unrealize(s, errp);
- }
-}
-
int scsi_bus_parse_cdb(SCSIDevice *dev, SCSICommand *cmd, uint8_t *buf,
void *hba_private)
{
@@ -84,7 +76,7 @@
return NULL;
}
-static void scsi_device_unit_attention_reported(SCSIDevice *s)
+void scsi_device_unit_attention_reported(SCSIDevice *s)
{
SCSIDeviceClass *sc = SCSI_DEVICE_GET_CLASS(s);
if (sc->unit_attention_reported) {
@@ -218,7 +210,9 @@
if (dev->vmsentry) {
qemu_del_vm_change_state_handler(dev->vmsentry);
}
- scsi_device_unrealize(dev, errp);
+
+ scsi_device_purge_requests(dev, SENSE_CODE(NO_SENSE));
+ blockdev_mark_auto_del(dev->conf.blk);
}
/* handle legacy '-drive if=scsi,...' cmd line args */
@@ -826,7 +820,7 @@
return xfer_unit;
}
-static int ata_passthrough_12_xfer_size(SCSIDevice *dev, uint8_t *buf)
+static int ata_passthrough_12_xfer(SCSIDevice *dev, uint8_t *buf)
{
int length = buf[2] & 0x3;
int xfer;
@@ -849,7 +843,7 @@
return xfer * unit;
}
-static int ata_passthrough_16_xfer_size(SCSIDevice *dev, uint8_t *buf)
+static int ata_passthrough_16_xfer(SCSIDevice *dev, uint8_t *buf)
{
int extend = buf[1] & 0x1;
int length = buf[2] & 0x3;
@@ -875,16 +869,16 @@
return xfer * unit;
}
-uint32_t scsi_data_cdb_length(uint8_t *buf)
+uint32_t scsi_data_cdb_xfer(uint8_t *buf)
{
if ((buf[0] >> 5) == 0 && buf[4] == 0) {
return 256;
} else {
- return scsi_cdb_length(buf);
+ return scsi_cdb_xfer(buf);
}
}
-uint32_t scsi_cdb_length(uint8_t *buf)
+uint32_t scsi_cdb_xfer(uint8_t *buf)
{
switch (buf[0] >> 5) {
case 0:
@@ -905,9 +899,9 @@
}
}
-static int scsi_req_length(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf)
+static int scsi_req_xfer(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf)
{
- cmd->xfer = scsi_cdb_length(buf);
+ cmd->xfer = scsi_cdb_xfer(buf);
switch (buf[0]) {
case TEST_UNIT_READY:
case REWIND:
@@ -1038,17 +1032,17 @@
/* BLANK command of MMC */
cmd->xfer = 0;
} else {
- cmd->xfer = ata_passthrough_12_xfer_size(dev, buf);
+ cmd->xfer = ata_passthrough_12_xfer(dev, buf);
}
break;
case ATA_PASSTHROUGH_16:
- cmd->xfer = ata_passthrough_16_xfer_size(dev, buf);
+ cmd->xfer = ata_passthrough_16_xfer(dev, buf);
break;
}
return 0;
}
-static int scsi_req_stream_length(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf)
+static int scsi_req_stream_xfer(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf)
{
switch (buf[0]) {
/* stream commands */
@@ -1103,12 +1097,12 @@
break;
/* generic commands */
default:
- return scsi_req_length(cmd, dev, buf);
+ return scsi_req_xfer(cmd, dev, buf);
}
return 0;
}
-static int scsi_req_medium_changer_length(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf)
+static int scsi_req_medium_changer_xfer(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf)
{
switch (buf[0]) {
/* medium changer commands */
@@ -1125,7 +1119,7 @@
/* generic commands */
default:
- return scsi_req_length(cmd, dev, buf);
+ return scsi_req_xfer(cmd, dev, buf);
}
return 0;
}
@@ -1214,38 +1208,45 @@
return lba;
}
+int scsi_cdb_length(uint8_t *buf) {
+ int cdb_len;
+
+ switch (buf[0] >> 5) {
+ case 0:
+ cdb_len = 6;
+ break;
+ case 1:
+ case 2:
+ cdb_len = 10;
+ break;
+ case 4:
+ cdb_len = 16;
+ break;
+ case 5:
+ cdb_len = 12;
+ break;
+ default:
+ cdb_len = -1;
+ }
+ return cdb_len;
+}
+
int scsi_req_parse_cdb(SCSIDevice *dev, SCSICommand *cmd, uint8_t *buf)
{
int rc;
cmd->lba = -1;
- switch (buf[0] >> 5) {
- case 0:
- cmd->len = 6;
- break;
- case 1:
- case 2:
- cmd->len = 10;
- break;
- case 4:
- cmd->len = 16;
- break;
- case 5:
- cmd->len = 12;
- break;
- default:
- return -1;
- }
+ cmd->len = scsi_cdb_length(buf);
switch (dev->type) {
case TYPE_TAPE:
- rc = scsi_req_stream_length(cmd, dev, buf);
+ rc = scsi_req_stream_xfer(cmd, dev, buf);
break;
case TYPE_MEDIUM_CHANGER:
- rc = scsi_req_medium_changer_length(cmd, dev, buf);
+ rc = scsi_req_medium_changer_xfer(cmd, dev, buf);
break;
default:
- rc = scsi_req_length(cmd, dev, buf);
+ rc = scsi_req_xfer(cmd, dev, buf);
break;
}
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index 010eefd..2f75d7d 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -1666,7 +1666,7 @@
{
SCSIRequest *req = &r->req;
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, req->dev);
- uint32_t nb_sectors = scsi_data_cdb_length(r->req.cmd.buf);
+ uint32_t nb_sectors = scsi_data_cdb_xfer(r->req.cmd.buf);
WriteSameCBData *data;
uint8_t *buf;
int i;
@@ -2061,7 +2061,7 @@
return 0;
}
- len = scsi_data_cdb_length(r->req.cmd.buf);
+ len = scsi_data_cdb_xfer(r->req.cmd.buf);
switch (command) {
case READ_6:
case READ_10:
@@ -2138,14 +2138,6 @@
s->tray_open = 0;
}
-static void scsi_unrealize(SCSIDevice *dev, Error **errp)
-{
- SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, dev);
-
- scsi_device_purge_requests(&s->qdev, SENSE_CODE(NO_SENSE));
- blockdev_mark_auto_del(s->qdev.conf.blk);
-}
-
static void scsi_disk_resize_cb(void *opaque)
{
SCSIDiskState *s = opaque;
@@ -2396,7 +2388,7 @@
DPRINTF("Command: lun=%d tag=0x%x data=0x%02x", lun, tag, buf[0]);
{
int i;
- for (i = 1; i < req->cmd.len; i++) {
+ for (i = 1; i < scsi_cdb_length(buf); i++) {
printf(" 0x%02x", buf[i]);
}
printf("\n");
@@ -2612,7 +2604,6 @@
SCSIDeviceClass *sc = SCSI_DEVICE_CLASS(klass);
sc->realize = scsi_hd_realize;
- sc->unrealize = scsi_unrealize;
sc->alloc_req = scsi_new_request;
sc->unit_attention_reported = scsi_disk_unit_attention_reported;
dc->fw_name = "disk";
@@ -2643,7 +2634,6 @@
SCSIDeviceClass *sc = SCSI_DEVICE_CLASS(klass);
sc->realize = scsi_cd_realize;
- sc->unrealize = scsi_unrealize;
sc->alloc_req = scsi_new_request;
sc->unit_attention_reported = scsi_disk_unit_attention_reported;
dc->fw_name = "disk";
@@ -2672,7 +2662,6 @@
SCSIDeviceClass *sc = SCSI_DEVICE_CLASS(klass);
sc->realize = scsi_block_realize;
- sc->unrealize = scsi_unrealize;
sc->alloc_req = scsi_block_new_request;
sc->parse_cdb = scsi_block_parse_cdb;
dc->fw_name = "disk";
@@ -2710,7 +2699,6 @@
SCSIDeviceClass *sc = SCSI_DEVICE_CLASS(klass);
sc->realize = scsi_disk_realize;
- sc->unrealize = scsi_unrealize;
sc->alloc_req = scsi_new_request;
sc->unit_attention_reported = scsi_disk_unit_attention_reported;
dc->fw_name = "disk";
diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
index f2e53af..6b9e4e1 100644
--- a/hw/scsi/scsi-generic.c
+++ b/hw/scsi/scsi-generic.c
@@ -368,12 +368,6 @@
scsi_device_purge_requests(s, SENSE_CODE(RESET));
}
-static void scsi_unrealize(SCSIDevice *s, Error **errp)
-{
- scsi_device_purge_requests(s, SENSE_CODE(NO_SENSE));
- blockdev_mark_auto_del(s->conf.blk);
-}
-
static void scsi_generic_realize(SCSIDevice *s, Error **errp)
{
int rc;
@@ -478,7 +472,6 @@
SCSIDeviceClass *sc = SCSI_DEVICE_CLASS(klass);
sc->realize = scsi_generic_realize;
- sc->unrealize = scsi_unrealize;
sc->alloc_req = scsi_new_request;
sc->parse_cdb = scsi_generic_parse_cdb;
dc->fw_name = "disk";
diff --git a/hw/scsi/virtio-scsi-dataplane.c b/hw/scsi/virtio-scsi-dataplane.c
index 3097d54..9651e6f 100644
--- a/hw/scsi/virtio-scsi-dataplane.c
+++ b/hw/scsi/virtio-scsi-dataplane.c
@@ -241,9 +241,10 @@
}
}
- aio_context_release(s->ctx);
s->dataplane_starting = false;
s->dataplane_started = true;
+ aio_context_release(s->ctx);
+ return;
fail_vrings:
virtio_scsi_clear_aio(s);
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 7d40ecc..fdcacfd 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -804,10 +804,12 @@
virtio_init(vdev, "virtio-scsi", VIRTIO_ID_SCSI,
sizeof(VirtIOSCSIConfig));
- if (s->conf.num_queues <= 0 || s->conf.num_queues > VIRTIO_PCI_QUEUE_MAX) {
- error_setg(errp, "Invalid number of queues (= %" PRId32 "), "
+ if (s->conf.num_queues == 0 ||
+ s->conf.num_queues > VIRTIO_PCI_QUEUE_MAX - 2) {
+ error_setg(errp, "Invalid number of queues (= %" PRIu32 "), "
"must be a positive integer less than %d.",
- s->conf.num_queues, VIRTIO_PCI_QUEUE_MAX);
+ s->conf.num_queues, VIRTIO_PCI_QUEUE_MAX - 2);
+ virtio_cleanup(vdev);
return;
}
s->cmd_vqs = g_malloc0(s->conf.num_queues * sizeof(VirtQueue *));
diff --git a/hw/tricore/tricore_testboard.c b/hw/tricore/tricore_testboard.c
index eeb4922..a059a20 100644
--- a/hw/tricore/tricore_testboard.c
+++ b/hw/tricore/tricore_testboard.c
@@ -71,11 +71,11 @@
machine->cpu_model = "tc1796";
}
cpu = cpu_tricore_init(machine->cpu_model);
- env = &cpu->env;
if (!cpu) {
error_report("Unable to find CPU definition");
exit(1);
}
+ env = &cpu->env;
memory_region_init_ram(ext_cram, NULL, "powerlink_ext_c.ram", 2*1024*1024, &error_abort);
vmstate_register_ram_global(ext_cram);
memory_region_init_ram(ext_dram, NULL, "powerlink_ext_d.ram", 4*1024*1024, &error_abort);
diff --git a/hw/xtensa/pic_cpu.c b/hw/xtensa/pic_cpu.c
index e2005bd..18825d1 100644
--- a/hw/xtensa/pic_cpu.c
+++ b/hw/xtensa/pic_cpu.c
@@ -31,14 +31,14 @@
void xtensa_advance_ccount(CPUXtensaState *env, uint32_t d)
{
- uint32_t old_ccount = env->sregs[CCOUNT];
+ uint32_t old_ccount = env->sregs[CCOUNT] + 1;
env->sregs[CCOUNT] += d;
if (xtensa_option_enabled(env->config, XTENSA_OPTION_TIMER_INTERRUPT)) {
int i;
for (i = 0; i < env->config->nccompare; ++i) {
- if (env->sregs[CCOMPARE + i] - old_ccount <= d) {
+ if (env->sregs[CCOMPARE + i] - old_ccount < d) {
xtensa_timer_irq(env, i, 1);
}
}
diff --git a/hw/xtensa/xtfpga.c b/hw/xtensa/xtfpga.c
index 0100c31..e5a6bba 100644
--- a/hw/xtensa/xtfpga.c
+++ b/hw/xtensa/xtfpga.c
@@ -328,7 +328,8 @@
} else {
hwaddr ep;
int is_linux;
- success = load_uimage(kernel_filename, &ep, NULL, &is_linux);
+ success = load_uimage(kernel_filename, &ep, NULL, &is_linux,
+ translate_phys_addr, cpu);
if (success > 0 && is_linux) {
entry_point = ep;
} else {
diff --git a/include/block/block.h b/include/block/block.h
index 341054d..13e4537 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -268,7 +268,13 @@
int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix);
-int bdrv_amend_options(BlockDriverState *bs_new, QemuOpts *opts);
+/* The units of offset and total_work_size may be chosen arbitrarily by the
+ * block driver; total_work_size may change during the course of the amendment
+ * operation */
+typedef void BlockDriverAmendStatusCB(BlockDriverState *bs, int64_t offset,
+ int64_t total_work_size);
+int bdrv_amend_options(BlockDriverState *bs_new, QemuOpts *opts,
+ BlockDriverAmendStatusCB *status_cb);
/* external snapshots */
bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs,
@@ -328,6 +334,7 @@
int coroutine_fn bdrv_co_flush(BlockDriverState *bs);
int bdrv_flush_all(void);
void bdrv_close_all(void);
+void bdrv_drain(BlockDriverState *bs);
void bdrv_drain_all(void);
int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors);
@@ -498,6 +505,8 @@
BLKDBG_PWRITEV_ZERO,
BLKDBG_PWRITEV_DONE,
+ BLKDBG_EMPTY_IMAGE_PREPARE,
+
BLKDBG_EVENT_MAX,
} BlkDebugEvent;
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 8898c6c..a1c17b9 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -232,7 +232,8 @@
int (*bdrv_check)(BlockDriverState* bs, BdrvCheckResult *result,
BdrvCheckMode fix);
- int (*bdrv_amend_options)(BlockDriverState *bs, QemuOpts *opts);
+ int (*bdrv_amend_options)(BlockDriverState *bs, QemuOpts *opts,
+ BlockDriverAmendStatusCB *status_cb);
void (*bdrv_debug_event)(BlockDriverState *bs, BlkDebugEvent event);
@@ -289,6 +290,9 @@
/* optimal transfer length in sectors */
int opt_transfer_length;
+ /* maximal transfer length in sectors */
+ int max_transfer_length;
+
/* memory alignment so that no bounce buffer is needed */
size_t opt_mem_alignment;
} BlockLimits;
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index acb399f..b6d4ebb 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -91,6 +91,11 @@
*/
bool busy;
+ /**
+ * Set to true when the job is ready to be completed.
+ */
+ bool ready;
+
/** Status that is published by the query-block-jobs QMP API */
BlockDeviceIoStatus iostatus;
@@ -273,6 +278,21 @@
int block_job_cancel_sync(BlockJob *job);
/**
+ * block_job_complete_sync:
+ * @job: The job to be completed.
+ * @errp: Error object which may be set by block_job_complete(); this is not
+ * necessarily set on every error, the job return value has to be
+ * checked as well.
+ *
+ * Synchronously complete the job. The completion callback is called before the
+ * function returns, unless it is NULL (which is permissible when using this
+ * function).
+ *
+ * Returns the return value from the job.
+ */
+int block_job_complete_sync(BlockJob *job, Error **errp);
+
+/**
* block_job_iostatus_reset:
* @job: The job whose I/O status should be reset.
*
@@ -295,4 +315,23 @@
BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
BlockdevOnError on_err,
int is_read, int error);
+
+typedef void BlockJobDeferToMainLoopFn(BlockJob *job, void *opaque);
+
+/**
+ * block_job_defer_to_main_loop:
+ * @job: The job
+ * @fn: The function to run in the main loop
+ * @opaque: The opaque value that is passed to @fn
+ *
+ * Execute a given function in the main loop with the BlockDriverState
+ * AioContext acquired. Block jobs must call bdrv_unref(), bdrv_close(), and
+ * anything that uses bdrv_drain_all() in the main loop.
+ *
+ * The @job AioContext is held while @fn executes.
+ */
+void block_job_defer_to_main_loop(BlockJob *job,
+ BlockJobDeferToMainLoopFn *fn,
+ void *opaque);
+
#endif
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 072aad2..74a58b4 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -150,6 +150,7 @@
bool terminates;
bool romd_mode;
bool ram;
+ bool skip_dump;
bool readonly; /* For RAM regions */
bool enabled;
bool rom_device;
@@ -457,6 +458,24 @@
bool memory_region_is_ram(MemoryRegion *mr);
/**
+ * memory_region_is_skip_dump: check whether a memory region should not be
+ * dumped
+ *
+ * Returns %true is a memory region should not be dumped(e.g. VFIO BAR MMAP).
+ *
+ * @mr: the memory region being queried
+ */
+bool memory_region_is_skip_dump(MemoryRegion *mr);
+
+/**
+ * memory_region_set_skip_dump: Set skip_dump flag, dump will ignore this memory
+ * region
+ *
+ * @mr: the memory region being queried
+ */
+void memory_region_set_skip_dump(MemoryRegion *mr);
+
+/**
* memory_region_is_romd: check whether a memory region is in ROMD mode
*
* Returns %true if a memory region is a ROM device and currently set to allow
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index c4ee520..2545268 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -35,11 +35,13 @@
HotplugHandler *acpi_dev;
uint64_t max_ram_below_4g;
+ bool vmport;
};
#define PC_MACHINE_ACPI_DEVICE_PROP "acpi-device"
#define PC_MACHINE_MEMHP_REGION_SIZE "hotplug-memory-region-size"
#define PC_MACHINE_MAX_RAM_BELOW_4G "max-ram-below-4g"
+#define PC_MACHINE_VMPORT "vmport"
/**
* PCMachineClass:
diff --git a/include/hw/loader.h b/include/hw/loader.h
index 9190387..054c6a2 100644
--- a/include/hw/loader.h
+++ b/include/hw/loader.h
@@ -30,7 +30,9 @@
int load_aout(const char *filename, hwaddr addr, int max_sz,
int bswap_needed, hwaddr target_page_size);
int load_uimage(const char *filename, hwaddr *ep,
- hwaddr *loadaddr, int *is_linux);
+ hwaddr *loadaddr, int *is_linux,
+ uint64_t (*translate_fn)(void *, uint64_t),
+ void *translate_opaque);
/**
* load_ramdisk:
diff --git a/include/hw/pci/pci_ids.h b/include/hw/pci/pci_ids.h
index e597070..321d622 100644
--- a/include/hw/pci/pci_ids.h
+++ b/include/hw/pci/pci_ids.h
@@ -56,6 +56,7 @@
#define PCI_DEVICE_ID_LSI_53C810 0x0001
#define PCI_DEVICE_ID_LSI_53C895A 0x0012
#define PCI_DEVICE_ID_LSI_SAS1078 0x0060
+#define PCI_DEVICE_ID_LSI_SAS0079 0x0079
#define PCI_VENDOR_ID_DEC 0x1011
#define PCI_DEVICE_ID_DEC_21154 0x0026
diff --git a/include/hw/scsi/scsi.h b/include/hw/scsi/scsi.h
index 6bc841a..cdaf0f8 100644
--- a/include/hw/scsi/scsi.h
+++ b/include/hw/scsi/scsi.h
@@ -84,7 +84,6 @@
typedef struct SCSIDeviceClass {
DeviceClass parent_class;
void (*realize)(SCSIDevice *dev, Error **errp);
- void (*unrealize)(SCSIDevice *dev, Error **errp);
int (*parse_cdb)(SCSIDevice *dev, SCSICommand *cmd, uint8_t *buf,
void *hba_private);
SCSIRequest *(*alloc_req)(SCSIDevice *s, uint32_t tag, uint32_t lun,
@@ -239,8 +238,9 @@
#define SENSE_CODE(x) sense_code_ ## x
-uint32_t scsi_data_cdb_length(uint8_t *buf);
-uint32_t scsi_cdb_length(uint8_t *buf);
+uint32_t scsi_data_cdb_xfer(uint8_t *buf);
+uint32_t scsi_cdb_xfer(uint8_t *buf);
+int scsi_cdb_length(uint8_t *buf);
int scsi_sense_valid(SCSISense sense);
int scsi_build_sense(uint8_t *in_buf, int in_len,
uint8_t *buf, int len, bool fixed);
@@ -271,6 +271,7 @@
void scsi_device_purge_requests(SCSIDevice *sdev, SCSISense sense);
void scsi_device_set_ua(SCSIDevice *sdev, SCSISense sense);
void scsi_device_report_change(SCSIDevice *dev, SCSISense sense);
+void scsi_device_unit_attention_reported(SCSIDevice *dev);
int scsi_device_get_sense(SCSIDevice *dev, uint8_t *buf, int len, bool fixed);
SCSIDevice *scsi_device_find(SCSIBus *bus, int channel, int target, int lun);
diff --git a/include/qemu-common.h b/include/qemu-common.h
index b87e9c2..f862214 100644
--- a/include/qemu-common.h
+++ b/include/qemu-common.h
@@ -357,7 +357,6 @@
void os_setup_early_signal_handling(void);
char *os_find_datadir(void);
void os_parse_cmd_args(int index, const char *optarg);
-void os_pidfile_error(void);
/* Convert a byte between binary and BCD. */
static inline uint8_t to_bcd(uint8_t val)
diff --git a/include/qemu/bitmap.h b/include/qemu/bitmap.h
index edf4f17..f0273c9 100644
--- a/include/qemu/bitmap.h
+++ b/include/qemu/bitmap.h
@@ -12,7 +12,11 @@
#ifndef BITMAP_H
#define BITMAP_H
-#include "qemu-common.h"
+#include <glib.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "qemu/osdep.h"
#include "qemu/bitops.h"
/*
diff --git a/include/qemu/bitops.h b/include/qemu/bitops.h
index 7e2d5c9..181bd46 100644
--- a/include/qemu/bitops.h
+++ b/include/qemu/bitops.h
@@ -12,7 +12,9 @@
#ifndef BITOPS_H
#define BITOPS_H
-#include "qemu-common.h"
+#include <stdint.h>
+#include <assert.h>
+
#include "host-utils.h"
#define BITS_PER_BYTE CHAR_BIT
diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
index 1565404..c032434 100644
--- a/include/qemu/osdep.h
+++ b/include/qemu/osdep.h
@@ -68,6 +68,12 @@
#define MAX(a, b) (((a) > (b)) ? (a) : (b))
#endif
+/* Minimum function that returns zero only iff both values are zero.
+ * Intended for use with unsigned values only. */
+#ifndef MIN_NON_ZERO
+#define MIN_NON_ZERO(a, b) (((a) != 0 && (a) < (b)) ? (a) : (b))
+#endif
+
#ifndef ROUND_UP
#define ROUND_UP(n,d) (((n) + (d) - 1) & -(d))
#endif
diff --git a/memory.c b/memory.c
index 30f77b2..0f4fdc7 100644
--- a/memory.c
+++ b/memory.c
@@ -1185,6 +1185,11 @@
mr->ram_addr = qemu_ram_alloc_from_ptr(size, ptr, mr, &error_abort);
}
+void memory_region_set_skip_dump(MemoryRegion *mr)
+{
+ mr->skip_dump = true;
+}
+
void memory_region_init_alias(MemoryRegion *mr,
Object *owner,
const char *name,
@@ -1306,6 +1311,11 @@
return mr->ram;
}
+bool memory_region_is_skip_dump(MemoryRegion *mr)
+{
+ return mr->skip_dump;
+}
+
bool memory_region_is_logging(MemoryRegion *mr)
{
return mr->dirty_log_mask;
diff --git a/memory_mapping.c b/memory_mapping.c
index 87a6ed5..7b69801 100644
--- a/memory_mapping.c
+++ b/memory_mapping.c
@@ -203,7 +203,8 @@
GuestPhysBlock *predecessor;
/* we only care about RAM */
- if (!memory_region_is_ram(section->mr)) {
+ if (!memory_region_is_ram(section->mr) ||
+ memory_region_is_skip_dump(section->mr)) {
return;
}
diff --git a/net/slirp.c b/net/slirp.c
index c171119..920af30 100644
--- a/net/slirp.c
+++ b/net/slirp.c
@@ -549,8 +549,8 @@
);
fclose(f);
- snprintf(smb_cmdline, sizeof(smb_cmdline), "%s -s %s",
- CONFIG_SMBD_COMMAND, smb_conf);
+ snprintf(smb_cmdline, sizeof(smb_cmdline), "%s -l %s -s %s",
+ CONFIG_SMBD_COMMAND, s->smb_dir, smb_conf);
if (slirp_add_exec(s->slirp, 0, smb_cmdline, &vserver_addr, 139) < 0 ||
slirp_add_exec(s->slirp, 0, smb_cmdline, &vserver_addr, 445) < 0) {
diff --git a/net/tap.c b/net/tap.c
index a40f7f0..bde6b58 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -598,7 +598,6 @@
s = net_tap_fd_init(peer, model, name, fd, vnet_hdr);
if (!s) {
- close(fd);
return -1;
}
@@ -797,6 +796,7 @@
if (net_init_tap_one(tap, peer, "bridge", name, ifname,
script, downscript, vhostfdname,
vnet_hdr, fd)) {
+ close(fd);
return -1;
}
} else {
@@ -824,6 +824,7 @@
if (queues > 1 && i == 0 && !tap->has_ifname) {
if (tap_fd_get_ifname(fd, ifname)) {
error_report("Fail to get ifname");
+ close(fd);
return -1;
}
}
@@ -832,6 +833,7 @@
i >= 1 ? "no" : script,
i >= 1 ? "no" : downscript,
vhostfdname, vnet_hdr, fd)) {
+ close(fd);
return -1;
}
}
diff --git a/net/tap_int.h b/net/tap_int.h
index 86bb224..79afdf2 100644
--- a/net/tap_int.h
+++ b/net/tap_int.h
@@ -29,9 +29,6 @@
#include "qemu-common.h"
#include "qapi-types.h"
-#define DEFAULT_NETWORK_SCRIPT "/etc/qemu-ifup"
-#define DEFAULT_NETWORK_DOWN_SCRIPT "/etc/qemu-ifdown"
-
int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
int vnet_hdr_required, int mq_required);
diff --git a/os-posix.c b/os-posix.c
index 4898ebf..ba091f1 100644
--- a/os-posix.c
+++ b/os-posix.c
@@ -47,7 +47,7 @@
static struct passwd *user_pwd;
static const char *chroot_dir;
static int daemonize;
-static int fds[2];
+static int daemon_pipe;
void os_setup_early_signal_handling(void)
{
@@ -205,6 +205,7 @@
{
if (daemonize) {
pid_t pid;
+ int fds[2];
if (pipe(fds) == -1) {
exit(1);
@@ -217,26 +218,21 @@
close(fds[1]);
- again:
- len = read(fds[0], &status, 1);
- if (len == -1 && (errno == EINTR)) {
- goto again;
- }
- if (len != 1) {
- exit(1);
- }
- else if (status == 1) {
- fprintf(stderr, "Could not acquire pidfile\n");
- exit(1);
- } else {
- exit(0);
- }
- } else if (pid < 0) {
- exit(1);
- }
+ do {
+ len = read(fds[0], &status, 1);
+ } while (len < 0 && errno == EINTR);
+
+ /* only exit successfully if our child actually wrote
+ * a one-byte zero to our pipe, upon successful init */
+ exit(len == 1 && status == 0 ? 0 : 1);
+
+ } else if (pid < 0) {
+ exit(1);
+ }
close(fds[0]);
- qemu_set_cloexec(fds[1]);
+ daemon_pipe = fds[1];
+ qemu_set_cloexec(daemon_pipe);
setsid();
@@ -259,17 +255,6 @@
int fd = 0;
if (daemonize) {
- uint8_t status = 0;
- ssize_t len;
-
- again1:
- len = write(fds[1], &status, 1);
- if (len == -1 && (errno == EINTR)) {
- goto again1;
- }
- if (len != 1) {
- exit(1);
- }
if (chdir("/")) {
perror("not able to chdir to /");
exit(1);
@@ -284,23 +269,22 @@
change_process_uid();
if (daemonize) {
+ uint8_t status = 0;
+ ssize_t len;
+
dup2(fd, 0);
dup2(fd, 1);
dup2(fd, 2);
close(fd);
- }
-}
-void os_pidfile_error(void)
-{
- if (daemonize) {
- uint8_t status = 1;
- if (write(fds[1], &status, 1) != 1) {
- perror("daemonize. Writing to pipe\n");
+ do {
+ len = write(daemon_pipe, &status, 1);
+ } while (len < 0 && errno == EINTR);
+ if (len != 1) {
+ exit(1);
}
- } else
- fprintf(stderr, "Could not acquire pid file: %s\n", strerror(errno));
+ }
}
void os_set_line_buffering(void)
@@ -319,8 +303,6 @@
return -1;
}
if (lockf(fd, F_TLOCK, 0) == -1) {
- fprintf(stderr, "lock file '%s' failed: %s\n",
- filename, strerror(errno));
close(fd);
return -1;
}
diff --git a/os-win32.c b/os-win32.c
index 5f95caa..c0daf8e 100644
--- a/os-win32.c
+++ b/os-win32.c
@@ -104,11 +104,6 @@
return;
}
-void os_pidfile_error(void)
-{
- fprintf(stderr, "Could not acquire pid file: %s\n", strerror(errno));
-}
-
int qemu_create_pidfile(const char *filename)
{
char buffer[128];
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 8f7089e..77a0cfb 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -514,12 +514,14 @@
#
# @io-status: the status of the job (since 1.3)
#
+# @ready: true if the job may be completed (since 2.2)
+#
# Since: 1.1
##
{ 'type': 'BlockJobInfo',
'data': {'type': 'str', 'device': 'str', 'len': 'int',
'offset': 'int', 'busy': 'bool', 'paused': 'bool', 'speed': 'int',
- 'io-status': 'BlockDeviceIoStatus'} }
+ 'io-status': 'BlockDeviceIoStatus', 'ready': 'bool'} }
##
# @query-block-jobs:
diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx
index 55aec6b..9567774 100644
--- a/qemu-img-cmds.hx
+++ b/qemu-img-cmds.hx
@@ -22,9 +22,9 @@
ETEXI
DEF("commit", img_commit,
- "commit [-q] [-f fmt] [-t cache] filename")
+ "commit [-q] [-f fmt] [-t cache] [-b base] [-d] [-p] filename")
STEXI
-@item commit [-q] [-f @var{fmt}] [-t @var{cache}] @var{filename}
+@item commit [-q] [-f @var{fmt}] [-t @var{cache}] [-b @var{base}] [-d] [-p] @var{filename}
ETEXI
DEF("compare", img_compare,
@@ -70,8 +70,8 @@
ETEXI
DEF("amend", img_amend,
- "amend [-q] [-f fmt] [-t cache] -o options filename")
+ "amend [-p] [-q] [-f fmt] [-t cache] -o options filename")
STEXI
-@item amend [-q] [-f @var{fmt}] [-t @var{cache}] -o @var{options} @var{filename}
+@item amend [-p] [-q] [-f @var{fmt}] [-t @var{cache}] -o @var{options} @var{filename}
@end table
ETEXI
diff --git a/qemu-img.c b/qemu-img.c
index 731502c..66a7eb4 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -31,6 +31,7 @@
#include "sysemu/sysemu.h"
#include "sysemu/block-backend.h"
#include "block/block_int.h"
+#include "block/blockjob.h"
#include "block/qapi.h"
#include <getopt.h>
@@ -722,18 +723,54 @@
return ret;
}
+typedef struct CommonBlockJobCBInfo {
+ BlockDriverState *bs;
+ Error **errp;
+} CommonBlockJobCBInfo;
+
+static void common_block_job_cb(void *opaque, int ret)
+{
+ CommonBlockJobCBInfo *cbi = opaque;
+
+ if (ret < 0) {
+ error_setg_errno(cbi->errp, -ret, "Block job failed");
+ }
+
+ /* Drop this block job's reference */
+ bdrv_unref(cbi->bs);
+}
+
+static void run_block_job(BlockJob *job, Error **errp)
+{
+ AioContext *aio_context = bdrv_get_aio_context(job->bs);
+
+ do {
+ aio_poll(aio_context, true);
+ qemu_progress_print((float)job->offset / job->len * 100.f, 0);
+ } while (!job->ready);
+
+ block_job_complete_sync(job, errp);
+
+ /* A block job may finish instantaneously without publishing any progress,
+ * so just signal completion here */
+ qemu_progress_print(100.f, 0);
+}
+
static int img_commit(int argc, char **argv)
{
int c, ret, flags;
- const char *filename, *fmt, *cache;
+ const char *filename, *fmt, *cache, *base;
BlockBackend *blk;
- BlockDriverState *bs;
- bool quiet = false;
+ BlockDriverState *bs, *base_bs;
+ bool progress = false, quiet = false, drop = false;
+ Error *local_err = NULL;
+ CommonBlockJobCBInfo cbi;
fmt = NULL;
cache = BDRV_DEFAULT_CACHE;
+ base = NULL;
for(;;) {
- c = getopt(argc, argv, "f:ht:q");
+ c = getopt(argc, argv, "f:ht:b:dpq");
if (c == -1) {
break;
}
@@ -748,17 +785,34 @@
case 't':
cache = optarg;
break;
+ case 'b':
+ base = optarg;
+ /* -b implies -d */
+ drop = true;
+ break;
+ case 'd':
+ drop = true;
+ break;
+ case 'p':
+ progress = true;
+ break;
case 'q':
quiet = true;
break;
}
}
+
+ /* Progress is not shown in Quiet mode */
+ if (quiet) {
+ progress = false;
+ }
+
if (optind != argc - 1) {
error_exit("Expecting one image file name");
}
filename = argv[optind++];
- flags = BDRV_O_RDWR;
+ flags = BDRV_O_RDWR | BDRV_O_UNMAP;
ret = bdrv_parse_cache_flags(cache, &flags);
if (ret < 0) {
error_report("Invalid cache option: %s", cache);
@@ -771,29 +825,76 @@
}
bs = blk_bs(blk);
- ret = bdrv_commit(bs);
- switch(ret) {
- case 0:
- qprintf(quiet, "Image committed.\n");
- break;
- case -ENOENT:
- error_report("No disk inserted");
- break;
- case -EACCES:
- error_report("Image is read-only");
- break;
- case -ENOTSUP:
- error_report("Image is already committed");
- break;
- default:
- error_report("Error while committing image");
- break;
+ qemu_progress_init(progress, 1.f);
+ qemu_progress_print(0.f, 100);
+
+ if (base) {
+ base_bs = bdrv_find_backing_image(bs, base);
+ if (!base_bs) {
+ error_set(&local_err, QERR_BASE_NOT_FOUND, base);
+ goto done;
+ }
+ } else {
+ /* This is different from QMP, which by default uses the deepest file in
+ * the backing chain (i.e., the very base); however, the traditional
+ * behavior of qemu-img commit is using the immediate backing file. */
+ base_bs = bs->backing_hd;
+ if (!base_bs) {
+ error_setg(&local_err, "Image does not have a backing file");
+ goto done;
+ }
}
+ cbi = (CommonBlockJobCBInfo){
+ .errp = &local_err,
+ .bs = bs,
+ };
+
+ commit_active_start(bs, base_bs, 0, BLOCKDEV_ON_ERROR_REPORT,
+ common_block_job_cb, &cbi, &local_err);
+ if (local_err) {
+ goto done;
+ }
+
+ /* The block job will swap base_bs and bs (which is not what we really want
+ * here, but okay) and unref base_bs (after the swap, i.e., the old top
+ * image). In order to still be able to empty that top image afterwards,
+ * increment the reference counter here preemptively. */
+ if (!drop) {
+ bdrv_ref(base_bs);
+ }
+
+ run_block_job(bs->job, &local_err);
+ if (local_err) {
+ goto unref_backing;
+ }
+
+ if (!drop && base_bs->drv->bdrv_make_empty) {
+ ret = base_bs->drv->bdrv_make_empty(base_bs);
+ if (ret) {
+ error_setg_errno(&local_err, -ret, "Could not empty %s",
+ filename);
+ goto unref_backing;
+ }
+ }
+
+unref_backing:
+ if (!drop) {
+ bdrv_unref(base_bs);
+ }
+
+done:
+ qemu_progress_end();
+
blk_unref(blk);
- if (ret) {
+
+ if (local_err) {
+ qerror_report_err(local_err);
+ error_free(local_err);
return 1;
}
+
+ qprintf(quiet, "Image committed.\n");
return 0;
}
@@ -2770,6 +2871,12 @@
return 0;
}
+static void amend_status_cb(BlockDriverState *bs,
+ int64_t offset, int64_t total_work_size)
+{
+ qemu_progress_print(100.f * offset / total_work_size, 0);
+}
+
static int img_amend(int argc, char **argv)
{
int c, ret = 0;
@@ -2778,13 +2885,13 @@
QemuOpts *opts = NULL;
const char *fmt = NULL, *filename, *cache;
int flags;
- bool quiet = false;
+ bool quiet = false, progress = false;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
cache = BDRV_DEFAULT_CACHE;
for (;;) {
- c = getopt(argc, argv, "ho:f:t:q");
+ c = getopt(argc, argv, "ho:f:t:pq");
if (c == -1) {
break;
}
@@ -2814,6 +2921,9 @@
case 't':
cache = optarg;
break;
+ case 'p':
+ progress = true;
+ break;
case 'q':
quiet = true;
break;
@@ -2824,6 +2934,11 @@
error_exit("Must specify options (-o)");
}
+ if (quiet) {
+ progress = false;
+ }
+ qemu_progress_init(progress, 1.0);
+
filename = (optind == argc - 1) ? argv[argc - 1] : NULL;
if (fmt && has_help_option(options)) {
/* If a format is explicitly specified (and possibly no filename is
@@ -2833,7 +2948,9 @@
}
if (optind != argc - 1) {
- error_exit("Expecting one image file name");
+ error_report("Expecting one image file name");
+ ret = -1;
+ goto out;
}
flags = BDRV_O_FLAGS | BDRV_O_RDWR;
@@ -2867,13 +2984,18 @@
goto out;
}
- ret = bdrv_amend_options(bs, opts);
+ /* In case the driver does not call amend_status_cb() */
+ qemu_progress_print(0.f, 0);
+ ret = bdrv_amend_options(bs, opts, &amend_status_cb);
+ qemu_progress_print(100.f, 0);
if (ret < 0) {
error_report("Error while amending options: %s", strerror(-ret));
goto out;
}
out:
+ qemu_progress_end();
+
blk_unref(blk);
qemu_opts_del(opts);
qemu_opts_free(create_opts);
diff --git a/qemu-img.texi b/qemu-img.texi
index e3ef4a0..0a1ab35 100644
--- a/qemu-img.texi
+++ b/qemu-img.texi
@@ -167,7 +167,7 @@
The size can also be specified using the @var{size} option with @code{-o},
it doesn't need to be specified separately in this case.
-@item commit [-f @var{fmt}] [-t @var{cache}] @var{filename}
+@item commit [-q] [-f @var{fmt}] [-t @var{cache}] [-b @var{base}] [-d] [-p] @var{filename}
Commit the changes recorded in @var{filename} in its base image or backing file.
If the backing file is smaller than the snapshot, then the backing file will be
@@ -176,6 +176,20 @@
backing file to match the size of the smaller snapshot, you can safely truncate
it yourself once the commit operation successfully completes.
+The image @var{filename} is emptied after the operation has succeeded. If you do
+not need @var{filename} afterwards and intend to drop it, you may skip emptying
+@var{filename} by specifying the @code{-d} flag.
+
+If the backing chain of the given image file @var{filename} has more than one
+layer, the backing file into which the changes will be committed may be
+specified as @var{base} (which has to be part of @var{filename}'s backing
+chain). If @var{base} is not specified, the immediate backing file of the top
+image (which is @var{filename}) will be used. For reasons of consistency,
+explicitly specifying @var{base} will always imply @code{-d} (since emptying an
+image after committing to an indirect backing file would lead to different data
+being read from the image due to content in the intermediate backing chain
+overruling the commit target).
+
@item compare [-f @var{fmt}] [-F @var{fmt}] [-T @var{src_cache}] [-p] [-s] [-q] @var{filename1} @var{filename2}
Check if two images have the same content. You can compare images with
@@ -398,7 +412,7 @@
partitioning tools inside the VM to actually begin using the new space on the
device.
-@item amend [-f @var{fmt}] [-t @var{cache}] -o @var{options} @var{filename}
+@item amend [-p] [-f @var{fmt}] [-t @var{cache}] -o @var{options} @var{filename}
Amends the image format specific @var{options} for the image file
@var{filename}. Not all file formats support this operation.
diff --git a/qemu-options.hx b/qemu-options.hx
index 1e7d5b8..da9851d 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -33,6 +33,7 @@
" property accel=accel1[:accel2[:...]] selects accelerator\n"
" supported accelerators are kvm, xen, tcg (default: tcg)\n"
" kernel_irqchip=on|off controls accelerated irqchip support\n"
+ " vmport=on|off controls emulation of vmport (default: on)\n"
" kvm_shadow_mem=size of KVM shadow MMU\n"
" dump-guest-core=on|off include guest memory in a core dump (default=on)\n"
" mem-merge=on|off controls memory merge support (default: on)\n"
@@ -51,6 +52,8 @@
to initialize.
@item kernel_irqchip=on|off
Enables in-kernel irqchip support for the chosen accelerator when available.
+@item vmport=on|off
+Enables emulation of VMWare IO port, for vmmouse etc. (enabled by default)
@item kvm_shadow_mem=size
Defines the size of the KVM shadow MMU.
@item dump-guest-core=on|off
diff --git a/rules.mak b/rules.mak
index cf76b88..f500fef 100644
--- a/rules.mak
+++ b/rules.mak
@@ -362,4 +362,9 @@
# Include all the .d files
$(eval -include $(addsuffix *.d, $(sort $(dir $($v)))))
$(eval $v := $(filter-out %/,$($v))))
+
+ # For all %.mo objects that are directly added into -y, expand them to %.mo-objs
+ $(foreach v,$2,
+ $(eval $v := $(foreach o,$($v),$(if $($o-objs),$($o-objs),$o))))
+
endef
diff --git a/savevm.c b/savevm.c
index 2d8eb96..08ec678 100644
--- a/savevm.c
+++ b/savevm.c
@@ -1246,7 +1246,7 @@
void do_delvm(Monitor *mon, const QDict *qdict)
{
BlockDriverState *bs;
- Error *err = NULL;
+ Error *err;
const char *name = qdict_get_str(qdict, "name");
if (!find_vmstate_bs()) {
@@ -1257,6 +1257,7 @@
bs = NULL;
while ((bs = bdrv_next(bs))) {
if (bdrv_can_snapshot(bs)) {
+ err = NULL;
bdrv_snapshot_delete_by_id_or_name(bs, name, &err);
if (err) {
monitor_printf(mon,
diff --git a/scripts/kvm/kvm_stat b/scripts/kvm/kvm_stat
index d7e97e7..7b1437c 100755
--- a/scripts/kvm/kvm_stat
+++ b/scripts/kvm/kvm_stat
@@ -12,7 +12,7 @@
# the COPYING file in the top-level directory.
import curses
-import sys, os, time, optparse
+import sys, os, time, optparse, ctypes
class DebugfsProvider(object):
def __init__(self):
@@ -141,61 +141,97 @@
0x400: 'NPF',
}
-s390_exit_reasons = {
- 0x000: 'UNKNOWN',
- 0x001: 'EXCEPTION',
- 0x002: 'IO',
- 0x003: 'HYPERCALL',
- 0x004: 'DEBUG',
- 0x005: 'HLT',
- 0x006: 'MMIO',
- 0x007: 'IRQ_WINDOW_OPEN',
- 0x008: 'SHUTDOWN',
- 0x009: 'FAIL_ENTRY',
- 0x010: 'INTR',
- 0x011: 'SET_TPR',
- 0x012: 'TPR_ACCESS',
- 0x013: 'S390_SIEIC',
- 0x014: 'S390_RESET',
- 0x015: 'DCR',
- 0x016: 'NMI',
- 0x017: 'INTERNAL_ERROR',
- 0x018: 'OSI',
- 0x019: 'PAPR_HCALL',
+# From include/uapi/linux/kvm.h, KVM_EXIT_xxx
+userspace_exit_reasons = {
+ 0: 'UNKNOWN',
+ 1: 'EXCEPTION',
+ 2: 'IO',
+ 3: 'HYPERCALL',
+ 4: 'DEBUG',
+ 5: 'HLT',
+ 6: 'MMIO',
+ 7: 'IRQ_WINDOW_OPEN',
+ 8: 'SHUTDOWN',
+ 9: 'FAIL_ENTRY',
+ 10: 'INTR',
+ 11: 'SET_TPR',
+ 12: 'TPR_ACCESS',
+ 13: 'S390_SIEIC',
+ 14: 'S390_RESET',
+ 15: 'DCR',
+ 16: 'NMI',
+ 17: 'INTERNAL_ERROR',
+ 18: 'OSI',
+ 19: 'PAPR_HCALL',
+ 20: 'S390_UCONTROL',
+ 21: 'WATCHDOG',
+ 22: 'S390_TSCH',
+ 23: 'EPR',
}
-vendor_exit_reasons = {
+x86_exit_reasons = {
'vmx': vmx_exit_reasons,
'svm': svm_exit_reasons,
- 'IBM/S390': s390_exit_reasons,
}
-syscall_numbers = {
- 'IBM/S390': 331,
-}
-
-sc_perf_evt_open = 298
-
+sc_perf_evt_open = None
exit_reasons = None
-for line in file('/proc/cpuinfo').readlines():
- if line.startswith('flags') or line.startswith('vendor_id'):
- for flag in line.split():
- if flag in vendor_exit_reasons:
- exit_reasons = vendor_exit_reasons[flag]
- if flag in syscall_numbers:
- sc_perf_evt_open = syscall_numbers[flag]
-filters = {
- 'kvm_exit': ('exit_reason', exit_reasons)
+ioctl_numbers = {
+ 'SET_FILTER' : 0x40082406,
+ 'ENABLE' : 0x00002400,
+ 'DISABLE' : 0x00002401,
}
+def x86_init(flag):
+ globals().update({
+ 'sc_perf_evt_open' : 298,
+ 'exit_reasons' : x86_exit_reasons[flag],
+ })
+
+def s390_init():
+ globals().update({
+ 'sc_perf_evt_open' : 331
+ })
+
+def ppc_init():
+ globals().update({
+ 'sc_perf_evt_open' : 319,
+ 'ioctl_numbers' : {
+ 'SET_FILTER' : 0x80002406 | (ctypes.sizeof(ctypes.c_char_p) << 16),
+ 'ENABLE' : 0x20002400,
+ 'DISABLE' : 0x20002401,
+ }
+ })
+
+def detect_platform():
+ if os.uname()[4].startswith('ppc'):
+ ppc_init()
+ return
+
+ for line in file('/proc/cpuinfo').readlines():
+ if line.startswith('flags'):
+ for flag in line.split():
+ if flag in x86_exit_reasons:
+ x86_init(flag)
+ return
+ elif line.startswith('vendor_id'):
+ for flag in line.split():
+ if flag == 'IBM/S390':
+ s390_init()
+ return
+
+detect_platform()
+
def invert(d):
return dict((x[1], x[0]) for x in d.iteritems())
-for f in filters:
- filters[f] = (filters[f][0], invert(filters[f][1]))
+filters = {}
+filters['kvm_userspace_exit'] = ('reason', invert(userspace_exit_reasons))
+if exit_reasons:
+ filters['kvm_exit'] = ('exit_reason', invert(exit_reasons))
-import ctypes, struct, array
+import struct, array
libc = ctypes.CDLL('libc.so.6')
syscall = libc.syscall
@@ -285,14 +321,14 @@
raise Exception('perf_event_open failed')
if filter:
import fcntl
- fcntl.ioctl(fd, 0x40082406, filter)
+ fcntl.ioctl(fd, ioctl_numbers['SET_FILTER'], filter)
self.fd = fd
def enable(self):
import fcntl
- fcntl.ioctl(self.fd, 0x00002400, 0)
+ fcntl.ioctl(self.fd, ioctl_numbers['ENABLE'], 0)
def disable(self):
import fcntl
- fcntl.ioctl(self.fd, 0x00002401, 0)
+ fcntl.ioctl(self.fd, ioctl_numbers['DISABLE'], 0)
class TracepointProvider(object):
def __init__(self):
@@ -311,18 +347,30 @@
self.select(fields)
def fields(self):
return self._fields
+
+ def _online_cpus(self):
+ l = []
+ pattern = r'cpu([0-9]+)'
+ basedir = '/sys/devices/system/cpu'
+ for entry in os.listdir(basedir):
+ match = re.match(pattern, entry)
+ if not match:
+ continue
+ path = os.path.join(basedir, entry, 'online')
+ if os.path.exists(path) and open(path).read().strip() != '1':
+ continue
+ l.append(int(match.group(1)))
+ return l
+
def _setup(self, _fields):
self._fields = _fields
- cpure = r'cpu([0-9]+)'
- self.cpus = [int(re.match(cpure, x).group(1))
- for x in os.listdir('/sys/devices/system/cpu')
- if re.match(cpure, x)]
+ cpus = self._online_cpus()
import resource
- nfiles = len(self.cpus) * 1000
+ nfiles = len(cpus) * 1000
resource.setrlimit(resource.RLIMIT_NOFILE, (nfiles, nfiles))
events = []
self.group_leaders = []
- for cpu in self.cpus:
+ for cpu in cpus:
group = Group(cpu)
for name in _fields:
tracepoint = name
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 3a3c48a..80d2c07 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -748,7 +748,6 @@
} else {
TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();
tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), MO_TEQ);
- tcg_gen_qemu_st64(tmp, tcg_addr, get_mem_index(s));
tcg_gen_ld_i64(tmp, cpu_env, fp_reg_hi_offset(s, srcidx));
tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
tcg_gen_qemu_st_i64(tmp, tcg_hiaddr, get_mem_index(s), MO_TEQ);
diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index e194601..e4ccee1 100644
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -442,14 +442,6 @@
return x86_reg_info_32[reg].name;
}
-/* collects per-function cpuid data
- */
-typedef struct model_features_t {
- uint32_t *guest_feat;
- uint32_t *host_feat;
- FeatureWord feat_word;
-} model_features_t;
-
/* KVM-specific features that are automatically added to all CPU models
* when KVM is enabled.
*/
diff --git a/target-i386/translate.c b/target-i386/translate.c
index 418173e..782f7d2 100644
--- a/target-i386/translate.c
+++ b/target-i386/translate.c
@@ -7987,7 +7987,7 @@
if (bp->pc == pc_ptr &&
!((bp->flags & BP_CPU) && (tb->flags & HF_RF_MASK))) {
gen_debug(dc, pc_ptr - dc->cs_base);
- break;
+ goto done_generating;
}
}
}
@@ -8038,6 +8038,7 @@
}
if (tb->cflags & CF_LAST_IO)
gen_io_end();
+done_generating:
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
/* we don't forget to fill the last values */
diff --git a/target-xtensa/core-dc232b.c b/target-xtensa/core-dc232b.c
index c51e11e..a3b914b 100644
--- a/target-xtensa/core-dc232b.c
+++ b/target-xtensa/core-dc232b.c
@@ -33,7 +33,7 @@
#include "core-dc232b/core-isa.h"
#include "overlay_tool.h"
-static const XtensaConfig dc232b = {
+static const XtensaConfig dc232b __attribute__((unused)) = {
.name = "dc232b",
.gdb_regmap = {
.num_regs = 120,
diff --git a/target-xtensa/core-dc233c.c b/target-xtensa/core-dc233c.c
index 42dd64f..ac745d1 100644
--- a/target-xtensa/core-dc233c.c
+++ b/target-xtensa/core-dc233c.c
@@ -34,7 +34,7 @@
#include "core-dc233c/core-isa.h"
#include "overlay_tool.h"
-static const XtensaConfig dc233c = {
+static const XtensaConfig dc233c __attribute__((unused)) = {
.name = "dc233c",
.gdb_regmap = {
.num_regs = 121,
diff --git a/target-xtensa/core-fsf.c b/target-xtensa/core-fsf.c
index 6859bee..cfcc840 100644
--- a/target-xtensa/core-fsf.c
+++ b/target-xtensa/core-fsf.c
@@ -33,7 +33,7 @@
#include "core-fsf/core-isa.h"
#include "overlay_tool.h"
-static const XtensaConfig fsf = {
+static const XtensaConfig fsf __attribute__((unused)) = {
.name = "fsf",
/* GDB for this core is not supported currently */
.clock_freq_khz = 10000,
diff --git a/target-xtensa/cpu.h b/target-xtensa/cpu.h
index 9cf5275..beb5486 100644
--- a/target-xtensa/cpu.h
+++ b/target-xtensa/cpu.h
@@ -266,6 +266,7 @@
INTTYPE_TIMER,
INTTYPE_DEBUG,
INTTYPE_WRITE_ERR,
+ INTTYPE_PROFILING,
INTTYPE_MAX
} interrupt_type;
diff --git a/target-xtensa/import_core.sh b/target-xtensa/import_core.sh
new file mode 100755
index 0000000..73791ec
--- /dev/null
+++ b/target-xtensa/import_core.sh
@@ -0,0 +1,53 @@
+#! /bin/bash -e
+
+OVERLAY="$1"
+NAME="$2"
+FREQ=40000
+BASE=$(dirname "$0")
+TARGET="$BASE"/core-$NAME
+
+[ $# -ge 2 -a -f "$OVERLAY" ] || { cat <<EOF
+Usage: $0 overlay-archive-to-import core-name [frequency-in-KHz]
+ overlay-archive-to-import: file name of xtensa-config-overlay.tar.gz
+ to import configuration from.
+ core-name: QEMU name of the imported core. Must be valid
+ C identifier.
+ frequency-in-KHz: core frequency (40MHz if not specified).
+EOF
+exit
+}
+
+[ $# -ge 3 ] && FREQ="$3"
+mkdir -p "$TARGET"
+tar -xf "$OVERLAY" -C "$TARGET" --strip-components=1 \
+ --xform='s/core/core-isa/' config/core.h
+tar -xf "$OVERLAY" -O gdb/xtensa-config.c | \
+ sed -n '1,/*\//p;/pc/,/a15/p' > "$TARGET"/gdb-config.c
+NUM_REGS=$(grep XTREG "$TARGET"/gdb-config.c | wc -l)
+
+cat <<EOF > "${TARGET}.c"
+#include "cpu.h"
+#include "exec/exec-all.h"
+#include "exec/gdbstub.h"
+#include "qemu/host-utils.h"
+
+#include "core-$NAME/core-isa.h"
+#include "overlay_tool.h"
+
+static const XtensaConfig $NAME __attribute__((unused)) = {
+ .name = "$NAME",
+ .gdb_regmap = {
+ .num_regs = $NUM_REGS,
+ .reg = {
+#include "core-$NAME/gdb-config.c"
+ }
+ },
+ .clock_freq_khz = $FREQ,
+ DEFAULT_SECTIONS
+};
+
+REGISTER_CORE($NAME)
+EOF
+
+grep -q core-${NAME}.o "$BASE"/Makefile.objs || \
+ echo "obj-y += core-${NAME}.o" >> "$BASE"/Makefile.objs
diff --git a/target-xtensa/overlay_tool.h b/target-xtensa/overlay_tool.h
index 4c0de7f..6105d4c 100644
--- a/target-xtensa/overlay_tool.h
+++ b/target-xtensa/overlay_tool.h
@@ -108,20 +108,27 @@
#define XCHAL_WINDOW_UF12_VECOFS 0x00000140
#endif
+#if XCHAL_HAVE_WINDOWED
+#define WINDOW_VECTORS \
+ [EXC_WINDOW_OVERFLOW4] = XCHAL_WINDOW_OF4_VECOFS + \
+ XCHAL_WINDOW_VECTORS_VADDR, \
+ [EXC_WINDOW_UNDERFLOW4] = XCHAL_WINDOW_UF4_VECOFS + \
+ XCHAL_WINDOW_VECTORS_VADDR, \
+ [EXC_WINDOW_OVERFLOW8] = XCHAL_WINDOW_OF8_VECOFS + \
+ XCHAL_WINDOW_VECTORS_VADDR, \
+ [EXC_WINDOW_UNDERFLOW8] = XCHAL_WINDOW_UF8_VECOFS + \
+ XCHAL_WINDOW_VECTORS_VADDR, \
+ [EXC_WINDOW_OVERFLOW12] = XCHAL_WINDOW_OF12_VECOFS + \
+ XCHAL_WINDOW_VECTORS_VADDR, \
+ [EXC_WINDOW_UNDERFLOW12] = XCHAL_WINDOW_UF12_VECOFS + \
+ XCHAL_WINDOW_VECTORS_VADDR,
+#else
+#define WINDOW_VECTORS
+#endif
+
#define EXCEPTION_VECTORS { \
[EXC_RESET] = XCHAL_RESET_VECTOR_VADDR, \
- [EXC_WINDOW_OVERFLOW4] = XCHAL_WINDOW_OF4_VECOFS + \
- XCHAL_WINDOW_VECTORS_VADDR, \
- [EXC_WINDOW_UNDERFLOW4] = XCHAL_WINDOW_UF4_VECOFS + \
- XCHAL_WINDOW_VECTORS_VADDR, \
- [EXC_WINDOW_OVERFLOW8] = XCHAL_WINDOW_OF8_VECOFS + \
- XCHAL_WINDOW_VECTORS_VADDR, \
- [EXC_WINDOW_UNDERFLOW8] = XCHAL_WINDOW_UF8_VECOFS + \
- XCHAL_WINDOW_VECTORS_VADDR, \
- [EXC_WINDOW_OVERFLOW12] = XCHAL_WINDOW_OF12_VECOFS + \
- XCHAL_WINDOW_VECTORS_VADDR, \
- [EXC_WINDOW_UNDERFLOW12] = XCHAL_WINDOW_UF12_VECOFS + \
- XCHAL_WINDOW_VECTORS_VADDR, \
+ WINDOW_VECTORS \
[EXC_KERNEL] = XCHAL_KERNEL_VECTOR_VADDR, \
[EXC_USER] = XCHAL_USER_VECTOR_VADDR, \
[EXC_DOUBLE] = XCHAL_DOUBLEEXC_VECTOR_VADDR, \
@@ -163,6 +170,7 @@
#define XTHAL_INTTYPE_TBD1 INTTYPE_DEBUG
#define XTHAL_INTTYPE_TBD2 INTTYPE_WRITE_ERR
#define XTHAL_INTTYPE_WRITE_ERROR INTTYPE_WRITE_ERR
+#define XTHAL_INTTYPE_PROFILING INTTYPE_PROFILING
#define INTERRUPT(i) { \
diff --git a/tests/qemu-iotests/040 b/tests/qemu-iotests/040
index f1e16c1..2b432ad 100755
--- a/tests/qemu-iotests/040
+++ b/tests/qemu-iotests/040
@@ -43,8 +43,7 @@
if event['event'] == 'BLOCK_JOB_COMPLETED':
self.assert_qmp(event, 'data/type', 'commit')
self.assert_qmp(event, 'data/device', 'drive0')
- self.assert_qmp(event, 'data/offset', self.image_len)
- self.assert_qmp(event, 'data/len', self.image_len)
+ self.assert_qmp(event, 'data/offset', event['data']['len'])
if need_ready:
self.assertTrue(ready, "Expecting BLOCK_JOB_COMPLETED event")
completed = True
@@ -52,7 +51,6 @@
ready = True
self.assert_qmp(event, 'data/type', 'commit')
self.assert_qmp(event, 'data/device', 'drive0')
- self.assert_qmp(event, 'data/len', self.image_len)
self.vm.qmp('block-job-complete', device='drive0')
self.assert_no_active_block_jobs()
diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041
index 5dbd4ee..59a8f73 100755
--- a/tests/qemu-iotests/041
+++ b/tests/qemu-iotests/041
@@ -52,8 +52,7 @@
event = self.cancel_and_wait(drive=drive)
self.assertEquals(event['event'], 'BLOCK_JOB_COMPLETED')
self.assert_qmp(event, 'data/type', 'mirror')
- self.assert_qmp(event, 'data/offset', self.image_len)
- self.assert_qmp(event, 'data/len', self.image_len)
+ self.assert_qmp(event, 'data/offset', event['data']['len'])
def complete_and_wait(self, drive='drive0', wait_ready=True):
'''Complete a block job and wait for it to finish'''
@@ -417,7 +416,6 @@
self.assert_qmp(event, 'data/type', 'mirror')
self.assert_qmp(event, 'data/device', 'drive0')
self.assert_qmp(event, 'data/error', 'Input/output error')
- self.assert_qmp(event, 'data/len', self.image_len)
completed = True
self.assert_no_active_block_jobs()
@@ -568,7 +566,6 @@
self.assert_qmp(event, 'data/type', 'mirror')
self.assert_qmp(event, 'data/device', 'drive0')
self.assert_qmp(event, 'data/error', 'Input/output error')
- self.assert_qmp(event, 'data/len', self.image_len)
completed = True
self.assert_no_active_block_jobs()
diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061
index ab98def..8d37f8a 100755
--- a/tests/qemu-iotests/061
+++ b/tests/qemu-iotests/061
@@ -209,6 +209,31 @@
_check_test_img
$QEMU_IO -c "read -P 0 0 64M" "$TEST_IMG" | _filter_qemu_io
+echo
+echo "=== Testing progress report without snapshot ==="
+echo
+IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 4G
+IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 4G
+$QEMU_IO -c "write -z 0 64k" \
+ -c "write -z 1G 64k" \
+ -c "write -z 2G 64k" \
+ -c "write -z 3G 64k" "$TEST_IMG" | _filter_qemu_io
+$QEMU_IMG amend -p -o "compat=0.10" "$TEST_IMG"
+_check_test_img
+
+echo
+echo "=== Testing progress report with snapshot ==="
+echo
+IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 4G
+IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 4G
+$QEMU_IO -c "write -z 0 64k" \
+ -c "write -z 1G 64k" \
+ -c "write -z 2G 64k" \
+ -c "write -z 3G 64k" "$TEST_IMG" | _filter_qemu_io
+$QEMU_IMG snapshot -c foo "$TEST_IMG"
+$QEMU_IMG amend -p -o "compat=0.10" "$TEST_IMG"
+_check_test_img
+
# success, all done
echo "*** done"
rm -f $seq.full
diff --git a/tests/qemu-iotests/061.out b/tests/qemu-iotests/061.out
index 4ae6472..9045544 100644
--- a/tests/qemu-iotests/061.out
+++ b/tests/qemu-iotests/061.out
Binary files differ
diff --git a/tests/qemu-iotests/076 b/tests/qemu-iotests/076
index bc47457..ed2be35 100755
--- a/tests/qemu-iotests/076
+++ b/tests/qemu-iotests/076
@@ -47,29 +47,34 @@
nb_sectors_offset=$((0x24))
echo
-echo "== Read from a valid (enough) image =="
-_use_sample_img fake.parallels.bz2
+echo "== Read from a valid v1 image =="
+_use_sample_img parallels-v1.bz2
{ $QEMU_IO -c "read -P 0x11 0 64k" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir
echo
echo "== Negative catalog size =="
-_use_sample_img fake.parallels.bz2
+_use_sample_img parallels-v1.bz2
poke_file "$TEST_IMG" "$catalog_entries_offset" "\xff\xff\xff\xff"
{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir
echo
echo "== Overflow in catalog allocation =="
-_use_sample_img fake.parallels.bz2
+_use_sample_img parallels-v1.bz2
poke_file "$TEST_IMG" "$nb_sectors_offset" "\xff\xff\xff\xff"
poke_file "$TEST_IMG" "$catalog_entries_offset" "\x01\x00\x00\x40"
{ $QEMU_IO -c "read 64M 64M" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir
echo
echo "== Zero sectors per track =="
-_use_sample_img fake.parallels.bz2
+_use_sample_img parallels-v1.bz2
poke_file "$TEST_IMG" "$tracks_offset" "\x00\x00\x00\x00"
{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir
+echo
+echo "== Read from a valid v2 image =="
+_use_sample_img parallels-v2.bz2
+{ $QEMU_IO -c "read -P 0x11 0 64k" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir
+
# success, all done
echo "*** done"
rm -f $seq.full
diff --git a/tests/qemu-iotests/076.out b/tests/qemu-iotests/076.out
index f7745d8..32ade08 100644
--- a/tests/qemu-iotests/076.out
+++ b/tests/qemu-iotests/076.out
@@ -1,18 +1,22 @@
QA output created by 076
-== Read from a valid (enough) image ==
+== Read from a valid v1 image ==
read 65536/65536 bytes at offset 0
64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
== Negative catalog size ==
-qemu-io: can't open device TEST_DIR/fake.parallels: Catalog too large
+qemu-io: can't open device TEST_DIR/parallels-v1: Catalog too large
no file open, try 'help open'
== Overflow in catalog allocation ==
-qemu-io: can't open device TEST_DIR/fake.parallels: Catalog too large
+qemu-io: can't open device TEST_DIR/parallels-v1: Catalog too large
no file open, try 'help open'
== Zero sectors per track ==
-qemu-io: can't open device TEST_DIR/fake.parallels: Invalid image: Zero sectors per track
+qemu-io: can't open device TEST_DIR/parallels-v1: Invalid image: Zero sectors per track
no file open, try 'help open'
+
+== Read from a valid v2 image ==
+read 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
*** done
diff --git a/tests/qemu-iotests/097 b/tests/qemu-iotests/097
new file mode 100755
index 0000000..c7a613b
--- /dev/null
+++ b/tests/qemu-iotests/097
@@ -0,0 +1,122 @@
+#!/bin/bash
+#
+# Commit changes into backing chains and empty the top image if the
+# backing image is not explicitly specified
+#
+# Copyright (C) 2014 Red Hat, Inc.
+#
+# 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 of the License, or
+# (at your option) any later version.
+#
+# 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/>.
+#
+
+# creator
+owner=mreitz@redhat.com
+
+seq="$(basename $0)"
+echo "QA output created by $seq"
+
+here="$PWD"
+tmp=/tmp/$$
+status=1 # failure is the default!
+
+_cleanup()
+{
+ _cleanup_test_img
+ _rm_test_img "$TEST_IMG.itmd"
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+. ./common.pattern
+
+# Any format supporting backing files and bdrv_make_empty
+_supported_fmt qcow qcow2
+_supported_proto file
+_supported_os Linux
+
+
+# Four passes:
+# 0: Two-layer backing chain, commit to upper backing file (implicitly)
+# (in this case, the top image will be emptied)
+# 1: Two-layer backing chain, commit to upper backing file (explicitly)
+# (in this case, the top image will implicitly stay unchanged)
+# 2: Two-layer backing chain, commit to upper backing file (implicitly with -d)
+# (in this case, the top image will explicitly stay unchanged)
+# 3: Two-layer backing chain, commit to lower backing file
+# (in this case, the top image will implicitly stay unchanged)
+#
+# 020 already tests committing, so this only tests whether image chains are
+# working properly and that all images above the base are emptied; therefore,
+# no complicated patterns are necessary
+for i in 0 1 2 3; do
+
+echo
+echo "=== Test pass $i ==="
+echo
+
+TEST_IMG="$TEST_IMG.base" _make_test_img 64M
+TEST_IMG="$TEST_IMG.itmd" _make_test_img -b "$TEST_IMG.base" 64M
+_make_test_img -b "$TEST_IMG.itmd" 64M
+
+$QEMU_IO -c 'write -P 1 0 192k' "$TEST_IMG.base" | _filter_qemu_io
+$QEMU_IO -c 'write -P 2 64k 128k' "$TEST_IMG.itmd" | _filter_qemu_io
+$QEMU_IO -c 'write -P 3 128k 64k' "$TEST_IMG" | _filter_qemu_io
+
+if [ $i -lt 3 ]; then
+ if [ $i == 0 ]; then
+ # -b "$TEST_IMG.itmd" should be the default (that is, committing to the
+ # first backing file in the chain)
+ $QEMU_IMG commit "$TEST_IMG"
+ elif [ $i == 1 ]; then
+ # explicitly specify the commit target (this should imply -d)
+ $QEMU_IMG commit -b "$TEST_IMG.itmd" "$TEST_IMG"
+ else
+ # do not explicitly specify the commit target, but use -d to leave the
+ # top image unchanged
+ $QEMU_IMG commit -d "$TEST_IMG"
+ fi
+
+ # Bottom should be unchanged
+ $QEMU_IO -c 'read -P 1 0 192k' "$TEST_IMG.base" | _filter_qemu_io
+
+ # Intermediate should contain changes from top
+ $QEMU_IO -c 'read -P 1 0 64k' "$TEST_IMG.itmd" | _filter_qemu_io
+ $QEMU_IO -c 'read -P 2 64k 64k' "$TEST_IMG.itmd" | _filter_qemu_io
+ $QEMU_IO -c 'read -P 3 128k 64k' "$TEST_IMG.itmd" | _filter_qemu_io
+
+ # And in pass 0, the top image should be empty, whereas in both other passes
+ # it should be unchanged (which is both checked by qemu-img map)
+else
+ $QEMU_IMG commit -b "$TEST_IMG.base" "$TEST_IMG"
+
+ # Bottom should contain all changes
+ $QEMU_IO -c 'read -P 1 0 64k' "$TEST_IMG.base" | _filter_qemu_io
+ $QEMU_IO -c 'read -P 2 64k 64k' "$TEST_IMG.base" | _filter_qemu_io
+ $QEMU_IO -c 'read -P 3 128k 64k' "$TEST_IMG.base" | _filter_qemu_io
+
+ # Both top and intermediate should be unchanged
+fi
+
+$QEMU_IMG map "$TEST_IMG.base" | _filter_qemu_img_map
+$QEMU_IMG map "$TEST_IMG.itmd" | _filter_qemu_img_map
+$QEMU_IMG map "$TEST_IMG" | _filter_qemu_img_map
+
+done
+
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0
diff --git a/tests/qemu-iotests/097.out b/tests/qemu-iotests/097.out
new file mode 100644
index 0000000..1cb7764
--- /dev/null
+++ b/tests/qemu-iotests/097.out
@@ -0,0 +1,119 @@
+QA output created by 097
+
+=== Test pass 0 ===
+
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT.itmd', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.base'
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.itmd'
+wrote 196608/196608 bytes at offset 0
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 131072/131072 bytes at offset 65536
+128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 65536/65536 bytes at offset 131072
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Image committed.
+read 196608/196608 bytes at offset 0
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 65536
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 131072
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Offset Length File
+0 0x30000 TEST_DIR/t.IMGFMT.base
+Offset Length File
+0 0x10000 TEST_DIR/t.IMGFMT.base
+0x10000 0x20000 TEST_DIR/t.IMGFMT.itmd
+Offset Length File
+0 0x10000 TEST_DIR/t.IMGFMT.base
+0x10000 0x20000 TEST_DIR/t.IMGFMT.itmd
+
+=== Test pass 1 ===
+
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT.itmd', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.base'
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.itmd'
+wrote 196608/196608 bytes at offset 0
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 131072/131072 bytes at offset 65536
+128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 65536/65536 bytes at offset 131072
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Image committed.
+read 196608/196608 bytes at offset 0
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 65536
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 131072
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Offset Length File
+0 0x30000 TEST_DIR/t.IMGFMT.base
+Offset Length File
+0 0x10000 TEST_DIR/t.IMGFMT.base
+0x10000 0x20000 TEST_DIR/t.IMGFMT.itmd
+Offset Length File
+0 0x10000 TEST_DIR/t.IMGFMT.base
+0x10000 0x10000 TEST_DIR/t.IMGFMT.itmd
+0x20000 0x10000 TEST_DIR/t.IMGFMT
+
+=== Test pass 2 ===
+
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT.itmd', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.base'
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.itmd'
+wrote 196608/196608 bytes at offset 0
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 131072/131072 bytes at offset 65536
+128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 65536/65536 bytes at offset 131072
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Image committed.
+read 196608/196608 bytes at offset 0
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 65536
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 131072
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Offset Length File
+0 0x30000 TEST_DIR/t.IMGFMT.base
+Offset Length File
+0 0x10000 TEST_DIR/t.IMGFMT.base
+0x10000 0x20000 TEST_DIR/t.IMGFMT.itmd
+Offset Length File
+0 0x10000 TEST_DIR/t.IMGFMT.base
+0x10000 0x10000 TEST_DIR/t.IMGFMT.itmd
+0x20000 0x10000 TEST_DIR/t.IMGFMT
+
+=== Test pass 3 ===
+
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT.itmd', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.base'
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.itmd'
+wrote 196608/196608 bytes at offset 0
+192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 131072/131072 bytes at offset 65536
+128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 65536/65536 bytes at offset 131072
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Image committed.
+read 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 65536
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 65536/65536 bytes at offset 131072
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Offset Length File
+0 0x30000 TEST_DIR/t.IMGFMT.base
+Offset Length File
+0 0x10000 TEST_DIR/t.IMGFMT.base
+0x10000 0x20000 TEST_DIR/t.IMGFMT.itmd
+Offset Length File
+0 0x10000 TEST_DIR/t.IMGFMT.base
+0x10000 0x10000 TEST_DIR/t.IMGFMT.itmd
+0x20000 0x10000 TEST_DIR/t.IMGFMT
+*** done
diff --git a/tests/qemu-iotests/098 b/tests/qemu-iotests/098
new file mode 100755
index 0000000..e2230ad
--- /dev/null
+++ b/tests/qemu-iotests/098
@@ -0,0 +1,82 @@
+#!/bin/bash
+#
+# Test qcow2's bdrv_make_empty for images without internal snapshots
+#
+# Copyright (C) 2014 Red Hat, Inc.
+#
+# 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 of the License, or
+# (at your option) any later version.
+#
+# 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/>.
+#
+
+# creator
+owner=mreitz@redhat.com
+
+seq="$(basename $0)"
+echo "QA output created by $seq"
+
+here="$PWD"
+tmp=/tmp/$$
+status=1 # failure is the default!
+
+_cleanup()
+{
+ _cleanup_test_img
+ rm -f "$TEST_DIR/blkdebug.conf"
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+. ./common.pattern
+
+_supported_fmt qcow2
+_supported_proto file
+_supported_os Linux
+
+IMGOPTS="compat=1.1"
+
+for event in l1_update empty_image_prepare reftable_update refblock_alloc; do
+
+echo
+echo "=== $event ==="
+echo
+
+TEST_IMG="$TEST_IMG.base" _make_test_img 64M
+_make_test_img -b "$TEST_IMG.base" 64M
+
+# Some data that can be leaked when emptying the top image
+$QEMU_IO -c 'write 0 64k' "$TEST_IMG" | _filter_qemu_io
+
+cat > "$TEST_DIR/blkdebug.conf" <<EOF
+[inject-error]
+event = "$event"
+EOF
+
+$QEMU_IMG commit "blkdebug:$TEST_DIR/blkdebug.conf:$TEST_IMG" 2>&1 \
+ | _filter_testdir | _filter_imgfmt
+
+# There may be errors, but they should be fixed by opening the image
+$QEMU_IO -c close "$TEST_IMG"
+
+_check_test_img
+
+done
+
+
+rm -f "$TEST_DIR/blkdebug.conf"
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0
diff --git a/tests/qemu-iotests/098.out b/tests/qemu-iotests/098.out
new file mode 100644
index 0000000..586dfc8
--- /dev/null
+++ b/tests/qemu-iotests/098.out
@@ -0,0 +1,52 @@
+QA output created by 098
+
+=== l1_update ===
+
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.base'
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+qemu-img: Could not empty blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error
+No errors were found on the image.
+
+=== empty_image_prepare ===
+
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.base'
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+qemu-img: Could not empty blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error
+Leaked cluster 4 refcount=1 reference=0
+Leaked cluster 5 refcount=1 reference=0
+Repairing cluster 4 refcount=1 reference=0
+Repairing cluster 5 refcount=1 reference=0
+No errors were found on the image.
+
+=== reftable_update ===
+
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.base'
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+qemu-img: Could not empty blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error
+ERROR cluster 0 refcount=0 reference=1
+ERROR cluster 1 refcount=0 reference=1
+ERROR cluster 3 refcount=0 reference=1
+Rebuilding refcount structure
+Repairing cluster 1 refcount=1 reference=0
+No errors were found on the image.
+
+=== refblock_alloc ===
+
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.base'
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+qemu-img: Could not empty blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error
+ERROR cluster 0 refcount=0 reference=1
+ERROR cluster 1 refcount=0 reference=1
+ERROR cluster 3 refcount=0 reference=1
+Rebuilding refcount structure
+Repairing cluster 1 refcount=1 reference=0
+No errors were found on the image.
+*** done
diff --git a/tests/qemu-iotests/102 b/tests/qemu-iotests/102
index 34b363f..161b197 100755
--- a/tests/qemu-iotests/102
+++ b/tests/qemu-iotests/102
@@ -34,9 +34,10 @@
}
trap "_cleanup; exit \$status" 0 1 2 3 15
-# get standard environment, filters and checks
+# get standard environment, filters and qemu instance handling
. ./common.rc
. ./common.filter
+. ./common.qemu
_supported_fmt qcow2
_supported_proto file
@@ -53,11 +54,27 @@
$QEMU_IO -c 'write 0 64k' "$TEST_IMG" | _filter_qemu_io
# Remove data cluster from image (first cluster: image header, second: reftable,
# third: refblock, fourth: L1 table, fifth: L2 table)
-truncate -s $((5 * 64 * 1024)) "$TEST_IMG"
+$QEMU_IMG resize -f raw "$TEST_IMG" $((5 * 64 * 1024))
$QEMU_IO -c map "$TEST_IMG"
$QEMU_IMG map "$TEST_IMG"
+echo
+echo '=== Testing map on an image file truncated outside of qemu ==='
+echo
+
+# Same as above, only now we concurrently truncate and map the image
+_make_test_img $IMG_SIZE
+$QEMU_IO -c 'write 0 64k' "$TEST_IMG" | _filter_qemu_io
+
+qemu_comm_method=monitor _launch_qemu -drive if=none,file="$TEST_IMG",id=drv0
+
+$QEMU_IMG resize -f raw "$TEST_IMG" $((5 * 64 * 1024))
+
+_send_qemu_cmd $QEMU_HANDLE 'qemu-io drv0 map' 'allocated' \
+ | sed -e 's/^(qemu).*qemu-io drv0 map...$/(qemu) qemu-io drv0 map/'
+_send_qemu_cmd $QEMU_HANDLE 'quit' ''
+
# success, all done
echo '*** done'
rm -f $seq.full
diff --git a/tests/qemu-iotests/102.out b/tests/qemu-iotests/102.out
index e0e9cdc..eecde16 100644
--- a/tests/qemu-iotests/102.out
+++ b/tests/qemu-iotests/102.out
@@ -5,6 +5,17 @@
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=65536
wrote 65536/65536 bytes at offset 0
64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Image resized.
[ 0] 128/ 128 sectors allocated at offset 0 bytes (1)
Offset Length Mapped to File
+
+=== Testing map on an image file truncated outside of qemu ===
+
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=65536
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Image resized.
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) qemu-io drv0 map
+[ 0] 128/ 128 sectors allocated at offset 0 bytes (1)
*** done
diff --git a/tests/qemu-iotests/107 b/tests/qemu-iotests/107
index cad1cf9..9862030 100755
--- a/tests/qemu-iotests/107
+++ b/tests/qemu-iotests/107
@@ -39,7 +39,7 @@
. ./common.filter
_supported_fmt qcow2
-_supported_proto file
+_supported_proto file nfs
_supported_os Linux
diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index f69cb6b..3acdb30 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -213,5 +213,12 @@
-e "s/archipelago:a/TEST_DIR\//g"
}
+# filter out offsets and file names from qemu-img map
+_filter_qemu_img_map()
+{
+ sed -e 's/\([0-9a-fx]* *[0-9a-fx]* *\)[0-9a-fx]* */\1/g' \
+ -e 's/Mapped to *//' | _filter_testdir | _filter_imgfmt
+}
+
# make sure this script returns success
/bin/true
diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group
index 9bbd5d3..7b2c666 100644
--- a/tests/qemu-iotests/group
+++ b/tests/qemu-iotests/group
@@ -67,7 +67,7 @@
058 rw auto quick
059 rw auto quick
060 rw auto quick
-061 rw auto quick
+061 rw auto
062 rw auto quick
063 rw auto quick
064 rw auto quick
@@ -100,6 +100,8 @@
091 rw auto quick
092 rw auto quick
095 rw auto quick
+097 rw auto backing
+098 rw auto backing quick
099 rw auto quick
100 rw auto quick
101 rw auto quick
diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
index 39a4cfc..f57f154 100644
--- a/tests/qemu-iotests/iotests.py
+++ b/tests/qemu-iotests/iotests.py
@@ -267,8 +267,7 @@
self.assert_qmp(event, 'data/device', drive)
self.assert_qmp_absent(event, 'data/error')
if check_offset:
- self.assert_qmp(event, 'data/offset', self.image_len)
- self.assert_qmp(event, 'data/len', self.image_len)
+ self.assert_qmp(event, 'data/offset', event['data']['len'])
completed = True
self.assert_no_active_block_jobs()
diff --git a/tests/qemu-iotests/sample_images/fake.parallels.bz2 b/tests/qemu-iotests/sample_images/fake.parallels.bz2
deleted file mode 100644
index ffb5f13..0000000
--- a/tests/qemu-iotests/sample_images/fake.parallels.bz2
+++ /dev/null
Binary files differ
diff --git a/tests/qemu-iotests/sample_images/parallels-v1.bz2 b/tests/qemu-iotests/sample_images/parallels-v1.bz2
new file mode 100644
index 0000000..d1ef142
--- /dev/null
+++ b/tests/qemu-iotests/sample_images/parallels-v1.bz2
Binary files differ
diff --git a/tests/qemu-iotests/sample_images/parallels-v2.bz2 b/tests/qemu-iotests/sample_images/parallels-v2.bz2
new file mode 100644
index 0000000..fd8614d
--- /dev/null
+++ b/tests/qemu-iotests/sample_images/parallels-v2.bz2
Binary files differ
diff --git a/tests/tcg/xtensa/Makefile b/tests/tcg/xtensa/Makefile
index a70c92b..522a63e 100644
--- a/tests/tcg/xtensa/Makefile
+++ b/tests/tcg/xtensa/Makefile
@@ -13,6 +13,7 @@
SIMDEBUG = --gdbserve=0
endif
+HOST_CC = gcc
CC = $(CROSS)gcc
AS = $(CROSS)gcc -x assembler-with-cpp
LD = $(CROSS)ld
@@ -21,7 +22,7 @@
INCLUDE_DIRS = $(XTENSA_SRC_PATH) $(SRC_PATH)/target-xtensa/core-$(CORE)
XTENSA_INC = $(addprefix -I,$(INCLUDE_DIRS))
-LDFLAGS = -T$(XTENSA_SRC_PATH)/linker.ld
+LDFLAGS = -Tlinker.ld
CRT = crt.o vectors.o
@@ -59,13 +60,16 @@
all: build
+linker.ld: $(XTENSA_SRC_PATH)/linker.ld.S
+ $(HOST_CC) $(XTENSA_INC) -E -P $< -o $@
+
%.o: $(XTENSA_SRC_PATH)/%.c
$(CC) $(XTENSA_INC) $(CFLAGS) -c $< -o $@
%.o: $(XTENSA_SRC_PATH)/%.S
$(CC) $(XTENSA_INC) $(ASFLAGS) -c $< -o $@
-%.tst: %.o $(XTENSA_SRC_PATH)/macros.inc $(CRT) Makefile
+%.tst: %.o linker.ld $(XTENSA_SRC_PATH)/macros.inc $(CRT) Makefile
$(LD) $(LDFLAGS) $(NOSTDFLAGS) $(CRT) $< -o $@
build: $(TESTCASES)
@@ -85,4 +89,4 @@
gdb --args $(SIM) $(SIMFLAGS) ./$<
clean:
- $(RM) -fr $(TESTCASES) $(CRT)
+ $(RM) -fr $(TESTCASES) $(CRT) linker.ld
diff --git a/tests/tcg/xtensa/linker.ld b/tests/tcg/xtensa/linker.ld
deleted file mode 100644
index 4d0b307..0000000
--- a/tests/tcg/xtensa/linker.ld
+++ /dev/null
@@ -1,112 +0,0 @@
-OUTPUT_FORMAT("elf32-xtensa-le")
-ENTRY(_start)
-
-__DYNAMIC = 0;
-
-MEMORY {
- ram : ORIGIN = 0xd0000000, LENGTH = 0x08000000 /* 128M */
- rom : ORIGIN = 0xfe000000, LENGTH = 0x00001000 /* 4k */
-}
-
-SECTIONS
-{
- .init :
- {
- *(.init)
- *(.init.*)
- } > rom
-
- .vector :
- {
- . = 0x00000000;
- *(.vector.window_overflow_4)
- *(.vector.window_overflow_4.*)
- . = 0x00000040;
- *(.vector.window_underflow_4)
- *(.vector.window_underflow_4.*)
- . = 0x00000080;
- *(.vector.window_overflow_8)
- *(.vector.window_overflow_8.*)
- . = 0x000000c0;
- *(.vector.window_underflow_8)
- *(.vector.window_underflow_8.*)
- . = 0x00000100;
- *(.vector.window_overflow_12)
- *(.vector.window_overflow_12.*)
- . = 0x00000140;
- *(.vector.window_underflow_12)
- *(.vector.window_underflow_12.*)
-
- . = 0x00000180;
- *(.vector.level2)
- *(.vector.level2.*)
- . = 0x000001c0;
- *(.vector.level3)
- *(.vector.level3.*)
- . = 0x00000200;
- *(.vector.level4)
- *(.vector.level4.*)
- . = 0x00000240;
- *(.vector.level5)
- *(.vector.level5.*)
- . = 0x00000280;
- *(.vector.level6)
- *(.vector.level6.*)
- . = 0x000002c0;
- *(.vector.level7)
- *(.vector.level7.*)
-
- . = 0x00000300;
- *(.vector.kernel)
- *(.vector.kernel.*)
- . = 0x00000340;
- *(.vector.user)
- *(.vector.user.*)
- . = 0x000003c0;
- *(.vector.double)
- *(.vector.double.*)
- } > ram
-
- .text :
- {
- _ftext = .;
- *(.text .stub .text.* .gnu.linkonce.t.* .literal .literal.*)
- _etext = .;
- } > ram
-
- .rodata :
- {
- . = ALIGN(4);
- _frodata = .;
- *(.rodata .rodata.* .gnu.linkonce.r.*)
- *(.rodata1)
- _erodata = .;
- } > ram
-
- .data :
- {
- . = ALIGN(4);
- _fdata = .;
- *(.data .data.* .gnu.linkonce.d.*)
- *(.data1)
- _gp = ALIGN(16);
- *(.sdata .sdata.* .gnu.linkonce.s.*)
- _edata = .;
- } > ram
-
- .bss :
- {
- . = ALIGN(4);
- _fbss = .;
- *(.dynsbss)
- *(.sbss .sbss.* .gnu.linkonce.sb.*)
- *(.scommon)
- *(.dynbss)
- *(.bss .bss.* .gnu.linkonce.b.*)
- *(COMMON)
- _ebss = .;
- _end = .;
- } > ram
-}
-
-PROVIDE(_fstack = ORIGIN(ram) + LENGTH(ram) - 4);
diff --git a/tests/tcg/xtensa/linker.ld.S b/tests/tcg/xtensa/linker.ld.S
new file mode 100644
index 0000000..f1e7fa9
--- /dev/null
+++ b/tests/tcg/xtensa/linker.ld.S
@@ -0,0 +1,130 @@
+#include <core-isa.h>
+
+#if XTENSA_HAVE_BE
+OUTPUT_FORMAT("elf32-xtensa-be")
+#else
+OUTPUT_FORMAT("elf32-xtensa-le")
+#endif
+ENTRY(_start)
+
+__DYNAMIC = 0;
+
+MEMORY {
+ ram : ORIGIN = XCHAL_VECBASE_RESET_VADDR, LENGTH = 0x08000000 /* 128M */
+ rom : ORIGIN = XCHAL_RESET_VECTOR_VADDR, LENGTH = 0x00001000 /* 4k */
+}
+
+SECTIONS
+{
+ .init :
+ {
+ *(.init)
+ *(.init.*)
+ } > rom
+
+ .vector :
+ {
+ . = XCHAL_WINDOW_OF4_VECOFS;
+ *(.vector.window_overflow_4)
+ *(.vector.window_overflow_4.*)
+ . = XCHAL_WINDOW_UF4_VECOFS;
+ *(.vector.window_underflow_4)
+ *(.vector.window_underflow_4.*)
+ . = XCHAL_WINDOW_OF8_VECOFS;
+ *(.vector.window_overflow_8)
+ *(.vector.window_overflow_8.*)
+ . = XCHAL_WINDOW_UF8_VECOFS;
+ *(.vector.window_underflow_8)
+ *(.vector.window_underflow_8.*)
+ . = XCHAL_WINDOW_OF12_VECOFS;
+ *(.vector.window_overflow_12)
+ *(.vector.window_overflow_12.*)
+ . = XCHAL_WINDOW_UF12_VECOFS;
+ *(.vector.window_underflow_12)
+ *(.vector.window_underflow_12.*)
+
+#if XCHAL_NUM_INTLEVELS + XCHAL_HAVE_NMI >= 2
+ . = XCHAL_INTLEVEL2_VECOFS;
+ *(.vector.level2)
+ *(.vector.level2.*)
+#endif
+#if XCHAL_NUM_INTLEVELS + XCHAL_HAVE_NMI >= 3
+ . = XCHAL_INTLEVEL3_VECOFS;
+ *(.vector.level3)
+ *(.vector.level3.*)
+#endif
+#if XCHAL_NUM_INTLEVELS + XCHAL_HAVE_NMI >= 4
+ . = XCHAL_INTLEVEL4_VECOFS;
+ *(.vector.level4)
+ *(.vector.level4.*)
+#endif
+#if XCHAL_NUM_INTLEVELS + XCHAL_HAVE_NMI >= 5
+ . = XCHAL_INTLEVEL5_VECOFS;
+ *(.vector.level5)
+ *(.vector.level5.*)
+#endif
+#if XCHAL_NUM_INTLEVELS + XCHAL_HAVE_NMI >= 6
+ . = XCHAL_INTLEVEL6_VECOFS;
+ *(.vector.level6)
+ *(.vector.level6.*)
+#endif
+#if XCHAL_NUM_INTLEVELS + XCHAL_HAVE_NMI >= 7
+ . = XCHAL_INTLEVEL7_VECOFS;
+ *(.vector.level7)
+ *(.vector.level7.*)
+#endif
+
+ . = XCHAL_KERNEL_VECOFS;
+ *(.vector.kernel)
+ *(.vector.kernel.*)
+ . = XCHAL_USER_VECOFS;
+ *(.vector.user)
+ *(.vector.user.*)
+ . = XCHAL_DOUBLEEXC_VECOFS;
+ *(.vector.double)
+ *(.vector.double.*)
+ } > ram
+
+ .text :
+ {
+ _ftext = .;
+ *(.text .stub .text.* .gnu.linkonce.t.* .literal .literal.*)
+ _etext = .;
+ } > ram
+
+ .rodata :
+ {
+ . = ALIGN(4);
+ _frodata = .;
+ *(.rodata .rodata.* .gnu.linkonce.r.*)
+ *(.rodata1)
+ _erodata = .;
+ } > ram
+
+ .data :
+ {
+ . = ALIGN(4);
+ _fdata = .;
+ *(.data .data.* .gnu.linkonce.d.*)
+ *(.data1)
+ _gp = ALIGN(16);
+ *(.sdata .sdata.* .gnu.linkonce.s.*)
+ _edata = .;
+ } > ram
+
+ .bss :
+ {
+ . = ALIGN(4);
+ _fbss = .;
+ *(.dynsbss)
+ *(.sbss .sbss.* .gnu.linkonce.sb.*)
+ *(.scommon)
+ *(.dynbss)
+ *(.bss .bss.* .gnu.linkonce.b.*)
+ *(COMMON)
+ _ebss = .;
+ _end = .;
+ } > ram
+}
+
+PROVIDE(_fstack = (ORIGIN(ram) & 0xf0000000) + LENGTH(ram) - 16);
diff --git a/tests/test-bitops.c b/tests/test-bitops.c
index 8238eb5..47b5d3e 100644
--- a/tests/test-bitops.c
+++ b/tests/test-bitops.c
@@ -8,6 +8,7 @@
#include <glib.h>
#include <stdint.h>
+#include "qemu/osdep.h"
#include "qemu/bitops.h"
typedef struct {
diff --git a/trace-events b/trace-events
index 6c3a400..b5722ea 100644
--- a/trace-events
+++ b/trace-events
@@ -697,35 +697,36 @@
megasas_init_firmware(uint64_t pa) "pa %" PRIx64 " "
megasas_init_queue(uint64_t queue_pa, int queue_len, uint64_t head, uint64_t tail, uint32_t flags) "queue at %" PRIx64 " len %d head %" PRIx64 " tail %" PRIx64 " flags %x"
megasas_initq_map_failed(int frame) "scmd %d: failed to map queue"
+megasas_initq_mapped(uint64_t pa) "queue already mapped at %" PRIx64 ""
megasas_initq_mismatch(int queue_len, int fw_cmds) "queue size %d max fw cmds %d"
-megasas_qf_found(unsigned int index, uint64_t pa) "found mapped frame %x pa %" PRIx64 ""
-megasas_qf_new(unsigned int index, void *cmd) "return new frame %x cmd %p"
-megasas_qf_failed(unsigned long pa) "all frames busy for frame %lx"
-megasas_qf_enqueue(unsigned int index, unsigned int count, uint64_t context, unsigned int tail, int busy) "enqueue frame %x count %d context %" PRIx64 " tail %x busy %d"
-megasas_qf_update(unsigned int head, unsigned int busy) "update reply queue head %x busy %d"
+megasas_qf_mapped(unsigned int index) "skip mapped frame %x"
+megasas_qf_new(unsigned int index, uint64_t frame) "frame %x addr %" PRIx64 ""
+megasas_qf_busy(unsigned long pa) "all frames busy for frame %lx"
+megasas_qf_enqueue(unsigned int index, unsigned int count, uint64_t context, unsigned int head, unsigned int tail, int busy) "frame %x count %d context %" PRIx64 " head %x tail %x busy %d"
+megasas_qf_update(unsigned int head, unsigned int tail, unsigned int busy) "head %x tail %x busy %d"
megasas_qf_map_failed(int cmd, unsigned long frame) "scmd %d: frame %lu"
megasas_qf_complete_noirq(uint64_t context) "context %" PRIx64 " "
-megasas_qf_complete(uint64_t context, unsigned int tail, unsigned int offset, int busy, unsigned int doorbell) "context %" PRIx64 " tail %x offset %d busy %d doorbell %x"
+megasas_qf_complete(uint64_t context, unsigned int head, unsigned int tail, int busy) "context %" PRIx64 " head %x tail %x busy %d"
megasas_frame_busy(uint64_t addr) "frame %" PRIx64 " busy"
-megasas_unhandled_frame_cmd(int cmd, uint8_t frame_cmd) "scmd %d: Unhandled MFI cmd %x"
+megasas_unhandled_frame_cmd(int cmd, uint8_t frame_cmd) "scmd %d: MFI cmd %x"
megasas_handle_scsi(const char *frame, int bus, int dev, int lun, void *sdev, unsigned long size) "%s dev %x/%x/%x sdev %p xfer %lu"
-megasas_scsi_target_not_present(const char *frame, int bus, int dev, int lun) "%s dev %x/%x/%x target not present"
+megasas_scsi_target_not_present(const char *frame, int bus, int dev, int lun) "%s dev %x/%x/%x"
megasas_scsi_invalid_cdb_len(const char *frame, int bus, int dev, int lun, int len) "%s dev %x/%x/%x invalid cdb len %d"
megasas_iov_read_overflow(int cmd, int bytes, int len) "scmd %d: %d/%d bytes"
megasas_iov_write_overflow(int cmd, int bytes, int len) "scmd %d: %d/%d bytes"
megasas_iov_read_underflow(int cmd, int bytes, int len) "scmd %d: %d/%d bytes"
megasas_iov_write_underflow(int cmd, int bytes, int len) "scmd %d: %d/%d bytes"
-megasas_scsi_req_alloc_failed(const char *frame, int dev, int lun) "%s dev %x/%x req allocation failed"
+megasas_scsi_req_alloc_failed(const char *frame, int dev, int lun) "%s dev %x/%x"
megasas_scsi_read_start(int cmd, int len) "scmd %d: transfer %d bytes of data"
megasas_scsi_write_start(int cmd, int len) "scmd %d: transfer %d bytes of data"
megasas_scsi_nodata(int cmd) "scmd %d: no data to be transferred"
-megasas_scsi_complete(int cmd, uint32_t status, int len, int xfer) "scmd %d: finished with status %x, len %u/%u"
-megasas_command_complete(int cmd, uint32_t status, uint32_t resid) "scmd %d: command completed, status %x, residual %d"
+megasas_scsi_complete(int cmd, uint32_t status, int len, int xfer) "scmd %d: status %x, len %u/%u"
+megasas_command_complete(int cmd, uint32_t status, uint32_t resid) "scmd %d: status %x, residual %d"
megasas_handle_io(int cmd, const char *frame, int dev, int lun, unsigned long lba, unsigned long count) "scmd %d: %s dev %x/%x lba %lx count %lu"
megasas_io_target_not_present(int cmd, const char *frame, int dev, int lun) "scmd %d: %s dev 1/%x/%x LUN not present"
megasas_io_read_start(int cmd, unsigned long lba, unsigned long count, unsigned long len) "scmd %d: start LBA %lx %lu blocks (%lu bytes)"
megasas_io_write_start(int cmd, unsigned long lba, unsigned long count, unsigned long len) "scmd %d: start LBA %lx %lu blocks (%lu bytes)"
-megasas_io_complete(int cmd, uint32_t len) "scmd %d: %d bytes completed"
+megasas_io_complete(int cmd, uint32_t len) "scmd %d: %d bytes"
megasas_iovec_sgl_overflow(int cmd, int index, int limit) "scmd %d: iovec count %d limit %d"
megasas_iovec_sgl_underflow(int cmd, int index) "scmd %d: iovec count %d"
megasas_iovec_sgl_invalid(int cmd, int index, uint64_t pa, uint32_t len) "scmd %d: element %d pa %" PRIx64 " len %u"
@@ -733,28 +734,29 @@
megasas_iovec_underflow(int cmd, int len, int limit) "scmd %d: len %d limit %d"
megasas_handle_dcmd(int cmd, int opcode) "scmd %d: MFI DCMD opcode %x"
megasas_finish_dcmd(int cmd, int size) "scmd %d: MFI DCMD wrote %d bytes"
-megasas_dcmd_req_alloc_failed(int cmd, const char *desc) "scmd %d: %s alloc failed"
+megasas_dcmd_req_alloc_failed(int cmd, const char *desc) "scmd %d: %s"
megasas_dcmd_internal_submit(int cmd, const char *desc, int dev) "scmd %d: %s to dev %d"
-megasas_dcmd_internal_finish(int cmd, int opcode, int lun) "scmd %d: DCMD finish internal cmd %x lun %d"
-megasas_dcmd_internal_invalid(int cmd, int opcode) "scmd %d: Invalid internal DCMD %x"
+megasas_dcmd_internal_finish(int cmd, int opcode, int lun) "scmd %d: cmd %x lun %d"
+megasas_dcmd_internal_invalid(int cmd, int opcode) "scmd %d: DCMD %x"
megasas_dcmd_unhandled(int cmd, int opcode, int len) "scmd %d: opcode %x, len %d"
megasas_dcmd_zero_sge(int cmd) "scmd %d: zero DCMD sge count"
-megasas_dcmd_invalid_sge(int cmd, int count) "scmd %d: invalid DCMD sge count %d"
-megasas_dcmd_invalid_xfer_len(int cmd, unsigned long size, unsigned long max) "scmd %d: invalid xfer len %ld, max %ld"
+megasas_dcmd_invalid_sge(int cmd, int count) "scmd %d: DCMD sge count %d"
+megasas_dcmd_invalid_xfer_len(int cmd, unsigned long size, unsigned long max) "scmd %d: xfer len %ld, max %ld"
megasas_dcmd_enter(int cmd, const char *dcmd, int len) "scmd %d: DCMD %s len %d"
-megasas_dcmd_dummy(int cmd, unsigned long size) "scmd %d: DCMD dummy xfer len %ld"
+megasas_dcmd_dummy(int cmd, unsigned long size) "scmd %d: xfer len %ld"
megasas_dcmd_set_fw_time(int cmd, unsigned long time) "scmd %d: Set FW time %lx"
megasas_dcmd_pd_get_list(int cmd, int num, int max, int offset) "scmd %d: DCMD PD get list: %d / %d PDs, size %d"
megasas_dcmd_ld_get_list(int cmd, int num, int max) "scmd %d: DCMD LD get list: found %d / %d LDs"
-megasas_dcmd_ld_get_info(int cmd, int ld_id) "scmd %d: DCMD LD get info for dev %d"
-megasas_dcmd_pd_get_info(int cmd, int pd_id) "scmd %d: DCMD PD get info for dev %d"
-megasas_dcmd_pd_list_query(int cmd, int flags) "scmd %d: DCMD PD list query flags %x"
-megasas_dcmd_ld_list_query(int cmd, int flags) "scmd %d: DCMD LD list query flags %x"
+megasas_dcmd_ld_get_info(int cmd, int ld_id) "scmd %d: dev %d"
+megasas_dcmd_ld_list_query(int cmd, int flags) "scmd %d: query flags %x"
+megasas_dcmd_pd_get_info(int cmd, int pd_id) "scmd %d: dev %d"
+megasas_dcmd_pd_list_query(int cmd, int flags) "scmd %d: query flags %x"
+megasas_dcmd_reset_ld(int cmd, int target_id) "scmd %d: dev %d"
megasas_dcmd_unsupported(int cmd, unsigned long size) "scmd %d: set properties len %ld"
-megasas_abort_frame(int cmd, int abort_cmd) "scmd %d: aborting frame %x"
+megasas_abort_frame(int cmd, int abort_cmd) "scmd %d: frame %x"
megasas_abort_no_cmd(int cmd, uint64_t context) "scmd %d: no active command for frame context %" PRIx64 ""
megasas_abort_invalid_context(int cmd, uint64_t context, int abort_cmd) "scmd %d: invalid frame context %" PRIx64 " for abort frame %x"
-megasas_reset(void) "Reset"
+megasas_reset(int fw_state) "firmware state %x"
megasas_init(int sges, int cmds, const char *mode) "Using %d sges, %d cmds, %s mode"
megasas_msix_raise(int vector) "vector %d"
megasas_msi_raise(int vector) "vector %d"
@@ -764,9 +766,9 @@
megasas_intr_disabled(void) "Interrupts disabled"
megasas_msix_enabled(int vector) "vector %d"
megasas_msi_enabled(int vector) "vector %d"
-megasas_mmio_readl(unsigned long addr, uint32_t val) "addr 0x%lx: 0x%x"
+megasas_mmio_readl(const char *reg, uint32_t val) "reg %s: 0x%x"
megasas_mmio_invalid_readl(unsigned long addr) "addr 0x%lx"
-megasas_mmio_writel(uint32_t addr, uint32_t val) "addr 0x%x: 0x%x"
+megasas_mmio_writel(const char *reg, uint32_t val) "reg %s: 0x%x"
megasas_mmio_invalid_writel(uint32_t addr, uint32_t val) "addr 0x%x: 0x%x"
# hw/audio/milkymist-ac97.c
diff --git a/ui/Makefile.objs b/ui/Makefile.objs
index 6afb52a..801cba2 100644
--- a/ui/Makefile.objs
+++ b/ui/Makefile.objs
@@ -10,12 +10,13 @@
common-obj-y += keymaps.o console.o cursor.o qemu-pixman.o
common-obj-y += input.o input-keymap.o input-legacy.o
common-obj-$(CONFIG_SPICE) += spice-core.o spice-input.o spice-display.o
-common-obj-$(CONFIG_SDL) += sdl.o sdl_zoom.o x_keymap.o sdl2.o
+common-obj-$(CONFIG_SDL) += sdl.mo x_keymap.o
common-obj-$(CONFIG_COCOA) += cocoa.o
common-obj-$(CONFIG_CURSES) += curses.o
common-obj-$(CONFIG_VNC) += $(vnc-obj-y)
common-obj-$(CONFIG_GTK) += gtk.o x_keymap.o
-$(obj)/sdl.o $(obj)/sdl_zoom.o $(obj)/sdl2.o: QEMU_CFLAGS += $(SDL_CFLAGS)
+sdl.mo-objs := sdl.o sdl_zoom.o sdl2.o
+sdl.mo-cflags := $(SDL_CFLAGS)
gtk.o-cflags := $(GTK_CFLAGS) $(VTE_CFLAGS)
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index 016a047..8c9d80e 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -390,7 +390,8 @@
pthread_sigmask(SIG_UNBLOCK, &set, &oldset);
if (sigsetjmp(sigjump, 1)) {
- fprintf(stderr, "os_mem_prealloc: failed to preallocate pages\n");
+ fprintf(stderr, "os_mem_prealloc: Insufficient free host memory "
+ "pages available to allocate guest RAM\n");
exit(1);
} else {
int i;
diff --git a/vl.c b/vl.c
index f6b3546..409cc47 100644
--- a/vl.c
+++ b/vl.c
@@ -376,6 +376,10 @@
.name = PC_MACHINE_MAX_RAM_BELOW_4G,
.type = QEMU_OPT_SIZE,
.help = "maximum ram below the 4G boundary (32bit boundary)",
+ }, {
+ .name = PC_MACHINE_VMPORT,
+ .type = QEMU_OPT_BOOL,
+ .help = "Enable vmport (pc & q35)",
},{
.name = "iommu",
.type = QEMU_OPT_BOOL,
@@ -3746,6 +3750,11 @@
configure_msg(opts);
break;
case QEMU_OPTION_dump_vmstate:
+ if (vmstate_dump_file) {
+ fprintf(stderr, "qemu: only one '-dump-vmstate' "
+ "option may be given\n");
+ exit(1);
+ }
vmstate_dump_file = fopen(optarg, "w");
if (vmstate_dump_file == NULL) {
fprintf(stderr, "open %s: %s\n", optarg, strerror(errno));
@@ -3999,7 +4008,7 @@
#endif
if (pid_file && qemu_create_pidfile(pid_file) != 0) {
- os_pidfile_error();
+ fprintf(stderr, "Could not acquire pid file: %s\n", strerror(errno));
exit(1);
}
