Merge remote-tracking branch 'remotes/thuth-gitlab/tags/s390x-pull-request-2021-09-07' into staging
* Some CSS related fixes
* Storage key related fixes
* Test SIGILL and SIGSEGV handling in usermode emulation
* Fix SETPREFIX instruction
* Replace PAGE_SIZE, PAGE_SHIFT and PAGE_MASK to fix Alpine compilation
* Add more feature to gen16 default model
# gpg: Signature made Tue 07 Sep 2021 14:07:38 BST
# gpg: using RSA key 27B88847EEE0250118F3EAB92ED9D774FE702DB5
# gpg: issuer "thuth@redhat.com"
# gpg: Good signature from "Thomas Huth <th.huth@gmx.de>" [full]
# gpg: aka "Thomas Huth <thuth@redhat.com>" [full]
# gpg: aka "Thomas Huth <huth@tuxfamily.org>" [full]
# gpg: aka "Thomas Huth <th.huth@posteo.de>" [unknown]
# Primary key fingerprint: 27B8 8847 EEE0 2501 18F3 EAB9 2ED9 D774 FE70 2DB5
* remotes/thuth-gitlab/tags/s390x-pull-request-2021-09-07:
s390x/cpumodel: Add more feature to gen16 default model
s390x: Replace PAGE_SIZE, PAGE_SHIFT and PAGE_MASK
hw/s390x/s390-skeys: lazy storage key enablement under TCG
hw/s390x/s390-skeys: rename skeys_enabled to skeys_are_enabled
hw/s390x/s390-skeys: check if an address is valid before dumping the key
hw/s390x/s390-skeys: use memory mapping to detect which storage keys to dump
hw/s390x/s390-skeys: use memory mapping to detect which storage keys to migrate
s390x/mmu_helper: avoid setting the storage key if nothing changed
s390x/mmu_helper: move address validation into mmu_translate*()
s390x/mmu_helper: fixup mmu_translate() documentation
s390x/mmu_helper: no need to pass access type to mmu_translate_asce()
s390x/tcg: check for addressing exceptions for RRBE, SSKE and ISKE
s390x/tcg: convert real to absolute address for RRBE, SSKE and ISKE
s390x/tcg: fix ignoring bit 63 when setting the storage key in SSKE
s390x/tcg: wrap address for RRBE
s390x/ioinst: Fix wrong MSCH alignment check on little endian
s390x/tcg: fix and optimize SPX (SET PREFIX)
tests/tcg/s390x: Test SIGILL and SIGSEGV handling
css: fix actl handling for unit exceptions
vfio-ccw: forward halt/clear errors
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/block/nvme.c b/block/nvme.c
index e8dbbc2..abfe305 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -176,12 +176,11 @@
return false;
}
memset(q->queue, 0, bytes);
- r = qemu_vfio_dma_map(s->vfio, q->queue, bytes, false, &q->iova);
+ r = qemu_vfio_dma_map(s->vfio, q->queue, bytes, false, &q->iova, errp);
if (r) {
- error_setg(errp, "Cannot map queue");
- return false;
+ error_prepend(errp, "Cannot map queue: ");
}
- return true;
+ return r == 0;
}
static void nvme_free_queue_pair(NVMeQueuePair *q)
@@ -220,6 +219,7 @@
q = g_try_new0(NVMeQueuePair, 1);
if (!q) {
+ error_setg(errp, "Cannot allocate queue pair");
return NULL;
}
trace_nvme_create_queue_pair(idx, q, size, aio_context,
@@ -228,6 +228,7 @@
qemu_real_host_page_size);
q->prp_list_pages = qemu_try_memalign(qemu_real_host_page_size, bytes);
if (!q->prp_list_pages) {
+ error_setg(errp, "Cannot allocate PRP page list");
goto fail;
}
memset(q->prp_list_pages, 0, bytes);
@@ -237,8 +238,9 @@
qemu_co_queue_init(&q->free_req_queue);
q->completion_bh = aio_bh_new(aio_context, nvme_process_completion_bh, q);
r = qemu_vfio_dma_map(s->vfio, q->prp_list_pages, bytes,
- false, &prp_list_iova);
+ false, &prp_list_iova, errp);
if (r) {
+ error_prepend(errp, "Cannot map buffer for DMA: ");
goto fail;
}
q->free_req_head = -1;
@@ -531,9 +533,9 @@
error_setg(errp, "Cannot allocate buffer for identify response");
goto out;
}
- r = qemu_vfio_dma_map(s->vfio, id, id_size, true, &iova);
+ r = qemu_vfio_dma_map(s->vfio, id, id_size, true, &iova, errp);
if (r) {
- error_setg(errp, "Cannot map buffer for DMA");
+ error_prepend(errp, "Cannot map buffer for DMA: ");
goto out;
}
@@ -1017,6 +1019,7 @@
uint64_t *pagelist = req->prp_list_page;
int i, j, r;
int entries = 0;
+ Error *local_err = NULL, **errp = NULL;
assert(qiov->size);
assert(QEMU_IS_ALIGNED(qiov->size, s->page_size));
@@ -1029,7 +1032,7 @@
try_map:
r = qemu_vfio_dma_map(s->vfio,
qiov->iov[i].iov_base,
- len, true, &iova);
+ len, true, &iova, errp);
if (r == -ENOSPC) {
/*
* In addition to the -ENOMEM error, the VFIO_IOMMU_MAP_DMA
@@ -1064,6 +1067,8 @@
goto fail;
}
}
+ errp = &local_err;
+
goto try_map;
}
if (r) {
@@ -1107,6 +1112,9 @@
* because they are already mapped before calling this function; for
* temporary mappings, a later nvme_cmd_(un)map_qiov will reclaim by
* calling qemu_vfio_dma_reset_temporary when necessary. */
+ if (local_err) {
+ error_reportf_err(local_err, "Cannot map buffer for DMA: ");
+ }
return r;
}
@@ -1521,14 +1529,15 @@
static void nvme_register_buf(BlockDriverState *bs, void *host, size_t size)
{
int ret;
+ Error *local_err = NULL;
BDRVNVMeState *s = bs->opaque;
- ret = qemu_vfio_dma_map(s->vfio, host, size, false, NULL);
+ ret = qemu_vfio_dma_map(s->vfio, host, size, false, NULL, &local_err);
if (ret) {
/* FIXME: we may run out of IOVA addresses after repeated
* bdrv_register_buf/bdrv_unregister_buf, because nvme_vfio_dma_unmap
* doesn't reclaim addresses for fixed mappings. */
- error_report("nvme_register_buf failed: %s", strerror(-ret));
+ error_reportf_err(local_err, "nvme_register_buf failed: ");
}
}
diff --git a/block/trace-events b/block/trace-events
index b3d2b1e..f4f1267 100644
--- a/block/trace-events
+++ b/block/trace-events
@@ -156,7 +156,7 @@
nvme_dsm_done(void *s, uint64_t offset, uint64_t bytes, int ret) "s %p offset 0x%"PRIx64" bytes %"PRId64" ret %d"
nvme_dma_map_flush(void *s) "s %p"
nvme_free_req_queue_wait(void *s, unsigned q_index) "s %p q #%u"
-nvme_create_queue_pair(unsigned q_index, void *q, unsigned size, void *aio_context, int fd) "index %u q %p size %u aioctx %p fd %d"
+nvme_create_queue_pair(unsigned q_index, void *q, size_t size, void *aio_context, int fd) "index %u q %p size %zu aioctx %p fd %d"
nvme_free_queue_pair(unsigned q_index, void *q) "index %u q %p"
nvme_cmd_map_qiov(void *s, void *cmd, void *req, void *qiov, int entries) "s %p cmd %p req %p qiov %p entries %d"
nvme_cmd_map_qiov_pages(void *s, int i, uint64_t page) "s %p page[%d] 0x%"PRIx64
diff --git a/include/qemu/vfio-helpers.h b/include/qemu/vfio-helpers.h
index 4491c8e..bde9495 100644
--- a/include/qemu/vfio-helpers.h
+++ b/include/qemu/vfio-helpers.h
@@ -18,7 +18,7 @@
QEMUVFIOState *qemu_vfio_open_pci(const char *device, Error **errp);
void qemu_vfio_close(QEMUVFIOState *s);
int qemu_vfio_dma_map(QEMUVFIOState *s, void *host, size_t size,
- bool temporary, uint64_t *iova_list);
+ bool temporary, uint64_t *iova_list, Error **errp);
int qemu_vfio_dma_reset_temporary(QEMUVFIOState *s);
void qemu_vfio_dma_unmap(QEMUVFIOState *s, void *host);
void *qemu_vfio_pci_map_bar(QEMUVFIOState *s, int index,
diff --git a/util/qemu-sockets.c b/util/qemu-sockets.c
index f2f3676..c504399 100644
--- a/util/qemu-sockets.c
+++ b/util/qemu-sockets.c
@@ -1345,25 +1345,22 @@
SocketAddress *addr;
struct sockaddr_un *su = (struct sockaddr_un *)sa;
- assert(salen >= sizeof(su->sun_family) + 1 &&
- salen <= sizeof(struct sockaddr_un));
-
addr = g_new0(SocketAddress, 1);
addr->type = SOCKET_ADDRESS_TYPE_UNIX;
+ salen -= offsetof(struct sockaddr_un, sun_path);
#ifdef CONFIG_LINUX
- if (!su->sun_path[0]) {
+ if (salen > 0 && !su->sun_path[0]) {
/* Linux abstract socket */
- addr->u.q_unix.path = g_strndup(su->sun_path + 1,
- salen - sizeof(su->sun_family) - 1);
+ addr->u.q_unix.path = g_strndup(su->sun_path + 1, salen - 1);
addr->u.q_unix.has_abstract = true;
addr->u.q_unix.abstract = true;
addr->u.q_unix.has_tight = true;
- addr->u.q_unix.tight = salen < sizeof(*su);
+ addr->u.q_unix.tight = salen < sizeof(su->sun_path);
return addr;
}
#endif
- addr->u.q_unix.path = g_strndup(su->sun_path, sizeof(su->sun_path));
+ addr->u.q_unix.path = g_strndup(su->sun_path, salen);
return addr;
}
#endif /* WIN32 */
diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c
index 911115b..00a8043 100644
--- a/util/vfio-helpers.c
+++ b/util/vfio-helpers.c
@@ -463,13 +463,15 @@
size_t size, size_t max_size)
{
QEMUVFIOState *s = container_of(n, QEMUVFIOState, ram_notifier);
+ Error *local_err = NULL;
int ret;
trace_qemu_vfio_ram_block_added(s, host, max_size);
- ret = qemu_vfio_dma_map(s, host, max_size, false, NULL);
+ ret = qemu_vfio_dma_map(s, host, max_size, false, NULL, &local_err);
if (ret) {
- error_report("qemu_vfio_dma_map(%p, %zu) failed: %s", host, max_size,
- strerror(-ret));
+ error_reportf_err(local_err,
+ "qemu_vfio_dma_map(%p, %zu) failed: ",
+ host, max_size);
}
}
@@ -608,7 +610,7 @@
/* Do the DMA mapping with VFIO. */
static int qemu_vfio_do_mapping(QEMUVFIOState *s, void *host, size_t size,
- uint64_t iova)
+ uint64_t iova, Error **errp)
{
struct vfio_iommu_type1_dma_map dma_map = {
.argsz = sizeof(dma_map),
@@ -620,7 +622,7 @@
trace_qemu_vfio_do_mapping(s, host, iova, size);
if (ioctl(s->container, VFIO_IOMMU_MAP_DMA, &dma_map)) {
- error_report("VFIO_MAP_DMA failed: %s", strerror(errno));
+ error_setg_errno(errp, errno, "VFIO_MAP_DMA failed");
return -errno;
}
return 0;
@@ -660,13 +662,13 @@
if (QEMU_VFIO_DEBUG) {
for (i = 0; i < s->nr_mappings - 1; ++i) {
if (!(s->mappings[i].host < s->mappings[i + 1].host)) {
- fprintf(stderr, "item %d not sorted!\n", i);
+ error_report("item %d not sorted!", i);
qemu_vfio_dump_mappings(s);
return false;
}
if (!(s->mappings[i].host + s->mappings[i].size <=
s->mappings[i + 1].host)) {
- fprintf(stderr, "item %d overlap with next!\n", i);
+ error_report("item %d overlap with next!", i);
qemu_vfio_dump_mappings(s);
return false;
}
@@ -675,8 +677,8 @@
return true;
}
-static int
-qemu_vfio_find_fixed_iova(QEMUVFIOState *s, size_t size, uint64_t *iova)
+static bool qemu_vfio_find_fixed_iova(QEMUVFIOState *s, size_t size,
+ uint64_t *iova, Error **errp)
{
int i;
@@ -691,14 +693,16 @@
s->usable_iova_ranges[i].end - s->low_water_mark + 1 == 0) {
*iova = s->low_water_mark;
s->low_water_mark += size;
- return 0;
+ return true;
}
}
- return -ENOMEM;
+ error_setg(errp, "fixed iova range not found");
+
+ return false;
}
-static int
-qemu_vfio_find_temp_iova(QEMUVFIOState *s, size_t size, uint64_t *iova)
+static bool qemu_vfio_find_temp_iova(QEMUVFIOState *s, size_t size,
+ uint64_t *iova, Error **errp)
{
int i;
@@ -713,10 +717,27 @@
s->high_water_mark - s->usable_iova_ranges[i].start + 1 == 0) {
*iova = s->high_water_mark - size;
s->high_water_mark = *iova;
- return 0;
+ return true;
}
}
- return -ENOMEM;
+ error_setg(errp, "temporary iova range not found");
+
+ return false;
+}
+
+/**
+ * qemu_vfio_water_mark_reached:
+ *
+ * Returns %true if high watermark has been reached, %false otherwise.
+ */
+static bool qemu_vfio_water_mark_reached(QEMUVFIOState *s, size_t size,
+ Error **errp)
+{
+ if (s->high_water_mark - s->low_water_mark + 1 < size) {
+ error_setg(errp, "iova exhausted (water mark reached)");
+ return true;
+ }
+ return false;
}
/* Map [host, host + size) area into a contiguous IOVA address space, and store
@@ -725,9 +746,8 @@
* mapping status within this area is not allowed).
*/
int qemu_vfio_dma_map(QEMUVFIOState *s, void *host, size_t size,
- bool temporary, uint64_t *iova)
+ bool temporary, uint64_t *iova, Error **errp)
{
- int ret = 0;
int index;
IOVAMapping *mapping;
uint64_t iova0;
@@ -735,41 +755,36 @@
assert(QEMU_PTR_IS_ALIGNED(host, qemu_real_host_page_size));
assert(QEMU_IS_ALIGNED(size, qemu_real_host_page_size));
trace_qemu_vfio_dma_map(s, host, size, temporary, iova);
- qemu_mutex_lock(&s->lock);
+ QEMU_LOCK_GUARD(&s->lock);
mapping = qemu_vfio_find_mapping(s, host, &index);
if (mapping) {
iova0 = mapping->iova + ((uint8_t *)host - (uint8_t *)mapping->host);
} else {
- if (s->high_water_mark - s->low_water_mark + 1 < size) {
- ret = -ENOMEM;
- goto out;
+ int ret;
+
+ if (qemu_vfio_water_mark_reached(s, size, errp)) {
+ return -ENOMEM;
}
if (!temporary) {
- if (qemu_vfio_find_fixed_iova(s, size, &iova0)) {
- ret = -ENOMEM;
- goto out;
+ if (!qemu_vfio_find_fixed_iova(s, size, &iova0, errp)) {
+ return -ENOMEM;
}
mapping = qemu_vfio_add_mapping(s, host, size, index + 1, iova0);
- if (!mapping) {
- ret = -ENOMEM;
- goto out;
- }
assert(qemu_vfio_verify_mappings(s));
- ret = qemu_vfio_do_mapping(s, host, size, iova0);
- if (ret) {
+ ret = qemu_vfio_do_mapping(s, host, size, iova0, errp);
+ if (ret < 0) {
qemu_vfio_undo_mapping(s, mapping, NULL);
- goto out;
+ return ret;
}
qemu_vfio_dump_mappings(s);
} else {
- if (qemu_vfio_find_temp_iova(s, size, &iova0)) {
- ret = -ENOMEM;
- goto out;
+ if (!qemu_vfio_find_temp_iova(s, size, &iova0, errp)) {
+ return -ENOMEM;
}
- ret = qemu_vfio_do_mapping(s, host, size, iova0);
- if (ret) {
- goto out;
+ ret = qemu_vfio_do_mapping(s, host, size, iova0, errp);
+ if (ret < 0) {
+ return ret;
}
}
}
@@ -777,9 +792,7 @@
if (iova) {
*iova = iova0;
}
-out:
- qemu_mutex_unlock(&s->lock);
- return ret;
+ return 0;
}
/* Reset the high watermark and free all "temporary" mappings. */
@@ -813,14 +826,12 @@
}
trace_qemu_vfio_dma_unmap(s, host);
- qemu_mutex_lock(&s->lock);
+ QEMU_LOCK_GUARD(&s->lock);
m = qemu_vfio_find_mapping(s, host, &index);
if (!m) {
- goto out;
+ return;
}
qemu_vfio_undo_mapping(s, m, NULL);
-out:
- qemu_mutex_unlock(&s->lock);
}
static void qemu_vfio_reset(QEMUVFIOState *s)
