Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

* NBD bugfix (Changlong)
* NBD write zeroes support (Eric)
* Memory backend fixes (Haozhong)
* Atomics fix (Alex)
* New AVX512 features (Luwei)
* "make check" logging fix (Paolo)
* Chardev refactoring fallout (Paolo)
* Small checkpatch improvements (Paolo, Jeff)

# gpg: Signature made Wed 02 Nov 2016 08:31:11 AM GMT
# gpg:                using RSA key 0xBFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream: (30 commits)
  main-loop: Suppress I/O thread warning under qtest
  docs/rcu.txt: Fix minor typo
  vl: exit qemu on guest panic if -no-shutdown is not set
  checkpatch: allow spaces before parenthesis for 'coroutine_fn'
  x86: add AVX512_4VNNIW and AVX512_4FMAPS features
  slirp: fix CharDriver breakage
  qemu-char: do not forward events through the mux until QEMU has started
  nbd: Implement NBD_CMD_WRITE_ZEROES on client
  nbd: Implement NBD_CMD_WRITE_ZEROES on server
  nbd: Improve server handling of shutdown requests
  nbd: Refactor conversion to errno to silence checkpatch
  nbd: Support shorter handshake
  nbd: Less allocation during NBD_OPT_LIST
  nbd: Let client skip portions of server reply
  nbd: Let server know when client gives up negotiation
  nbd: Share common option-sending code in client
  nbd: Send message along with server NBD_REP_ERR errors
  nbd: Share common reply-sending code in server
  nbd: Rename struct nbd_request and nbd_reply
  nbd: Rename NbdClientSession to NBDClientSession
  ...
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

block/nbd-client.c

 /*
  * QEMU Block driver for  NBD
  *
+ * Copyright (C) 2016 Red Hat, Inc.
  * Copyright (C) 2008 Bull S.A.S.
  *     Author: Laurent Vivier <Laurent.Vivier@bull.net>
  *
@@ -32,7 +33,7 @@
 #define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
 #define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))
 
-static void nbd_recv_coroutines_enter_all(NbdClientSession *s)
+static void nbd_recv_coroutines_enter_all(NBDClientSession *s)
 {
     int i;
 
@@ -45,7 +46,7 @@ static void nbd_recv_coroutines_enter_all(NbdClientSession *s)
 
 static void nbd_teardown_connection(BlockDriverState *bs)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
+    NBDClientSession *client = nbd_get_client_session(bs);
 
     if (!client->ioc) { /* Already closed */
         return;
@@ -67,7 +68,7 @@ static void nbd_teardown_connection(BlockDriverState *bs)
 static void nbd_reply_ready(void *opaque)
 {
     BlockDriverState *bs = opaque;
-    NbdClientSession *s = nbd_get_client_session(bs);
+    NBDClientSession *s = nbd_get_client_session(bs);
     uint64_t i;
     int ret;
 
@@ -115,10 +116,10 @@ static void nbd_restart_write(void *opaque)
 }
 
 static int nbd_co_send_request(BlockDriverState *bs,
-                               struct nbd_request *request,
+                               NBDRequest *request,
                                QEMUIOVector *qiov)
 {
-    NbdClientSession *s = nbd_get_client_session(bs);
+    NBDClientSession *s = nbd_get_client_session(bs);
     AioContext *aio_context;
     int rc, ret, i;
 
@@ -166,9 +167,9 @@ static int nbd_co_send_request(BlockDriverState *bs,
     return rc;
 }
 
-static void nbd_co_receive_reply(NbdClientSession *s,
-                                 struct nbd_request *request,
-                                 struct nbd_reply *reply,
+static void nbd_co_receive_reply(NBDClientSession *s,
+                                 NBDRequest *request,
+                                 NBDReply *reply,
                                  QEMUIOVector *qiov)
 {
     int ret;
@@ -194,13 +195,13 @@ static void nbd_co_receive_reply(NbdClientSession *s,
     }
 }
 
-static void nbd_coroutine_start(NbdClientSession *s,
-   struct nbd_request *request)
+static void nbd_coroutine_start(NBDClientSession *s,
+                                NBDRequest *request)
 {
     /* Poor man semaphore.  The free_sema is locked when no other request
      * can be accepted, and unlocked after receiving one reply.  */
-    if (s->in_flight >= MAX_NBD_REQUESTS - 1) {
-        qemu_co_mutex_lock(&s->free_sema);
+    if (s->in_flight == MAX_NBD_REQUESTS) {
+        qemu_co_queue_wait(&s->free_sema);
         assert(s->in_flight < MAX_NBD_REQUESTS);
     }
     s->in_flight++;
@@ -208,26 +209,26 @@ static void nbd_coroutine_start(NbdClientSession *s,
     /* s->recv_coroutine[i] is set as soon as we get the send_lock.  */
 }
 
-static void nbd_coroutine_end(NbdClientSession *s,
-    struct nbd_request *request)
+static void nbd_coroutine_end(NBDClientSession *s,
+                              NBDRequest *request)
 {
     int i = HANDLE_TO_INDEX(s, request->handle);
     s->recv_coroutine[i] = NULL;
     if (s->in_flight-- == MAX_NBD_REQUESTS) {
-        qemu_co_mutex_unlock(&s->free_sema);
+        qemu_co_queue_next(&s->free_sema);
     }
 }
 
 int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset,
                          uint64_t bytes, QEMUIOVector *qiov, int flags)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
-    struct nbd_request request = {
+    NBDClientSession *client = nbd_get_client_session(bs);
+    NBDRequest request = {
         .type = NBD_CMD_READ,
         .from = offset,
         .len = bytes,
     };
-    struct nbd_reply reply;
+    NBDReply reply;
     ssize_t ret;
 
     assert(bytes <= NBD_MAX_BUFFER_SIZE);
@@ -247,18 +248,18 @@ int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset,
 int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
                           uint64_t bytes, QEMUIOVector *qiov, int flags)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
-    struct nbd_request request = {
+    NBDClientSession *client = nbd_get_client_session(bs);
+    NBDRequest request = {
         .type = NBD_CMD_WRITE,
         .from = offset,
         .len = bytes,
     };
-    struct nbd_reply reply;
+    NBDReply reply;
     ssize_t ret;
 
     if (flags & BDRV_REQ_FUA) {
         assert(client->nbdflags & NBD_FLAG_SEND_FUA);
-        request.type |= NBD_CMD_FLAG_FUA;
+        request.flags |= NBD_CMD_FLAG_FUA;
     }
 
     assert(bytes <= NBD_MAX_BUFFER_SIZE);
@@ -274,11 +275,46 @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
     return -reply.error;
 }
 
+int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
+                                int count, BdrvRequestFlags flags)
+{
+    ssize_t ret;
+    NBDClientSession *client = nbd_get_client_session(bs);
+    NBDRequest request = {
+        .type = NBD_CMD_WRITE_ZEROES,
+        .from = offset,
+        .len = count,
+    };
+    NBDReply reply;
+
+    if (!(client->nbdflags & NBD_FLAG_SEND_WRITE_ZEROES)) {
+        return -ENOTSUP;
+    }
+
+    if (flags & BDRV_REQ_FUA) {
+        assert(client->nbdflags & NBD_FLAG_SEND_FUA);
+        request.flags |= NBD_CMD_FLAG_FUA;
+    }
+    if (!(flags & BDRV_REQ_MAY_UNMAP)) {
+        request.flags |= NBD_CMD_FLAG_NO_HOLE;
+    }
+
+    nbd_coroutine_start(client, &request);
+    ret = nbd_co_send_request(bs, &request, NULL);
+    if (ret < 0) {
+        reply.error = -ret;
+    } else {
+        nbd_co_receive_reply(client, &request, &reply, NULL);
+    }
+    nbd_coroutine_end(client, &request);
+    return -reply.error;
+}
+
 int nbd_client_co_flush(BlockDriverState *bs)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
-    struct nbd_request request = { .type = NBD_CMD_FLUSH };
-    struct nbd_reply reply;
+    NBDClientSession *client = nbd_get_client_session(bs);
+    NBDRequest request = { .type = NBD_CMD_FLUSH };
+    NBDReply reply;
     ssize_t ret;
 
     if (!(client->nbdflags & NBD_FLAG_SEND_FLUSH)) {
@@ -301,13 +337,13 @@ int nbd_client_co_flush(BlockDriverState *bs)
 
 int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
-    struct nbd_request request = {
+    NBDClientSession *client = nbd_get_client_session(bs);
+    NBDRequest request = {
         .type = NBD_CMD_TRIM,
         .from = offset,
         .len = count,
     };
-    struct nbd_reply reply;
+    NBDReply reply;
     ssize_t ret;
 
     if (!(client->nbdflags & NBD_FLAG_SEND_TRIM)) {
@@ -342,12 +378,8 @@ void nbd_client_attach_aio_context(BlockDriverState *bs,
 
 void nbd_client_close(BlockDriverState *bs)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
-    struct nbd_request request = {
-        .type = NBD_CMD_DISC,
-        .from = 0,
-        .len = 0
-    };
+    NBDClientSession *client = nbd_get_client_session(bs);
+    NBDRequest request = { .type = NBD_CMD_DISC };
 
     if (client->ioc == NULL) {
         return;
@@ -365,7 +397,7 @@ int nbd_client_init(BlockDriverState *bs,
                     const char *hostname,
                     Error **errp)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
+    NBDClientSession *client = nbd_get_client_session(bs);
     int ret;
 
     /* NBD handshake */
@@ -386,7 +418,7 @@ int nbd_client_init(BlockDriverState *bs,
     }
 
     qemu_co_mutex_init(&client->send_mutex);
-    qemu_co_mutex_init(&client->free_sema);
+    qemu_co_queue_init(&client->free_sema);
     client->sioc = sioc;
     object_ref(OBJECT(client->sioc));
 

block/nbd-client.h

@@ -17,24 +17,24 @@
 
 #define MAX_NBD_REQUESTS    16
 
-typedef struct NbdClientSession {
+typedef struct NBDClientSession {
     QIOChannelSocket *sioc; /* The master data channel */
     QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
     uint16_t nbdflags;
     off_t size;
 
     CoMutex send_mutex;
-    CoMutex free_sema;
+    CoQueue free_sema;
     Coroutine *send_coroutine;
     int in_flight;
 
     Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
-    struct nbd_reply reply;
+    NBDReply reply;
 
     bool is_unix;
-} NbdClientSession;
+} NBDClientSession;
 
-NbdClientSession *nbd_get_client_session(BlockDriverState *bs);
+NBDClientSession *nbd_get_client_session(BlockDriverState *bs);
 
 int nbd_client_init(BlockDriverState *bs,
                     QIOChannelSocket *sock,
@@ -48,6 +48,8 @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count);
 int nbd_client_co_flush(BlockDriverState *bs);
 int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
                           uint64_t bytes, QEMUIOVector *qiov, int flags);
+int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
+                                int count, BdrvRequestFlags flags);
 int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset,
                          uint64_t bytes, QEMUIOVector *qiov, int flags);
 

block/nbd.c

@@ -44,7 +44,7 @@
 #define EN_OPTSTR ":exportname="
 
 typedef struct BDRVNBDState {
-    NbdClientSession client;
+    NBDClientSession client;
 
     /* For nbd_refresh_filename() */
     SocketAddress *saddr;
@@ -294,7 +294,7 @@ done:
     return saddr;
 }
 
-NbdClientSession *nbd_get_client_session(BlockDriverState *bs)
+NBDClientSession *nbd_get_client_session(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
     return &s->client;
@@ -466,6 +466,7 @@ static int nbd_co_flush(BlockDriverState *bs)
 static void nbd_refresh_limits(BlockDriverState *bs, Error **errp)
 {
     bs->bl.max_pdiscard = NBD_MAX_BUFFER_SIZE;
+    bs->bl.max_pwrite_zeroes = NBD_MAX_BUFFER_SIZE;
     bs->bl.max_transfer = NBD_MAX_BUFFER_SIZE;
 }
 
@@ -558,6 +559,7 @@ static BlockDriver bdrv_nbd = {
     .bdrv_file_open             = nbd_open,
     .bdrv_co_preadv             = nbd_client_co_preadv,
     .bdrv_co_pwritev            = nbd_client_co_pwritev,
+    .bdrv_co_pwrite_zeroes      = nbd_client_co_pwrite_zeroes,
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
     .bdrv_co_pdiscard           = nbd_client_co_pdiscard,
@@ -576,6 +578,7 @@ static BlockDriver bdrv_nbd_tcp = {
     .bdrv_file_open             = nbd_open,
     .bdrv_co_preadv             = nbd_client_co_preadv,
     .bdrv_co_pwritev            = nbd_client_co_pwritev,
+    .bdrv_co_pwrite_zeroes      = nbd_client_co_pwrite_zeroes,
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
     .bdrv_co_pdiscard           = nbd_client_co_pdiscard,
@@ -594,6 +597,7 @@ static BlockDriver bdrv_nbd_unix = {
     .bdrv_file_open             = nbd_open,
     .bdrv_co_preadv             = nbd_client_co_preadv,
     .bdrv_co_pwritev            = nbd_client_co_pwritev,
+    .bdrv_co_pwrite_zeroes      = nbd_client_co_pwrite_zeroes,
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
     .bdrv_co_pdiscard           = nbd_client_co_pdiscard,

docs/rcu.txt

@@ -145,7 +145,7 @@ The core RCU API is small:
         and then read from there.
 
         RCU read-side critical sections must use atomic_rcu_read() to
-        read data, unless concurrent writes are presented by another
+        read data, unless concurrent writes are prevented by another
         synchronization mechanism.
 
         Furthermore, RCU read-side critical sections should traverse the

exec.c

@@ -493,7 +493,7 @@ address_space_translate_for_iotlb(CPUState *cpu, int asidx, hwaddr addr,
                                   hwaddr *xlat, hwaddr *plen)
 {
     MemoryRegionSection *section;
-    AddressSpaceDispatch *d = cpu->cpu_ases[asidx].memory_dispatch;
+    AddressSpaceDispatch *d = atomic_rcu_read(&cpu->cpu_ases[asidx].memory_dispatch);
 
     section = address_space_translate_internal(d, addr, xlat, plen, false);
 
@@ -1231,6 +1231,15 @@ void qemu_mutex_unlock_ramlist(void)
 }
 
 #ifdef __linux__
+static int64_t get_file_size(int fd)
+{
+    int64_t size = lseek(fd, 0, SEEK_END);
+    if (size < 0) {
+        return -errno;
+    }
+    return size;
+}
+
 static void *file_ram_alloc(RAMBlock *block,
                             ram_addr_t memory,
                             const char *path,
@@ -1242,6 +1251,7 @@ static void *file_ram_alloc(RAMBlock *block,
     char *c;
     void *area = MAP_FAILED;
     int fd = -1;
+    int64_t file_size;
 
     if (kvm_enabled() && !kvm_has_sync_mmu()) {
         error_setg(errp,
@@ -1304,6 +1314,8 @@ static void *file_ram_alloc(RAMBlock *block,
     }
 #endif
 
+    file_size = get_file_size(fd);
+
     if (memory < block->page_size) {
         error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
                    "or larger than page size 0x%zx",
@@ -1311,6 +1323,13 @@ static void *file_ram_alloc(RAMBlock *block,
         goto error;
     }
 
+    if (file_size > 0 && file_size < memory) {
+        error_setg(errp, "backing store %s size 0x%" PRIx64
+                   " does not match 'size' option 0x" RAM_ADDR_FMT,
+                   path, file_size, memory);
+        goto error;
+    }
+
     memory = ROUND_UP(memory, block->page_size);
 
     /*
@@ -1318,8 +1337,16 @@ static void *file_ram_alloc(RAMBlock *block,
      * hosts, so don't bother bailing out on errors.
      * If anything goes wrong with it under other filesystems,
      * mmap will fail.
+     *
+     * Do not truncate the non-empty backend file to avoid corrupting
+     * the existing data in the file. Disabling shrinking is not
+     * enough. For example, the current vNVDIMM implementation stores
+     * the guest NVDIMM labels at the end of the backend file. If the
+     * backend file is later extended, QEMU will not be able to find
+     * those labels. Therefore, extending the non-empty backend file
+     * is disabled as well.
      */
-    if (ftruncate(fd, memory)) {
+    if (!file_size && ftruncate(fd, memory)) {
         perror("ftruncate");
     }
 
@@ -2378,7 +2405,7 @@ static void tcg_commit(MemoryListener *listener)
      * may have split the RCU critical section.
      */
     d = atomic_rcu_read(&cpuas->as->dispatch);
-    cpuas->memory_dispatch = d;
+    atomic_rcu_set(&cpuas->memory_dispatch, d);
     tlb_flush(cpuas->cpu, 1);
 }
 

include/block/nbd.h

 /*
+ *  Copyright (C) 2016 Red Hat, Inc.
  *  Copyright (C) 2005  Anthony Liguori <anthony@codemonkey.ws>
  *
  *  Network Block Device
@@ -25,52 +26,89 @@
 #include "io/channel-socket.h"
 #include "crypto/tlscreds.h"
 
-/* Note: these are _NOT_ the same as the network representation of an NBD
+/* Handshake phase structs - this struct is passed on the wire */
+
+struct nbd_option {
+    uint64_t magic; /* NBD_OPTS_MAGIC */
+    uint32_t option; /* NBD_OPT_* */
+    uint32_t length;
+} QEMU_PACKED;
+typedef struct nbd_option nbd_option;
+
+struct nbd_opt_reply {
+    uint64_t magic; /* NBD_REP_MAGIC */
+    uint32_t option; /* NBD_OPT_* */
+    uint32_t type; /* NBD_REP_* */
+    uint32_t length;
+} QEMU_PACKED;
+typedef struct nbd_opt_reply nbd_opt_reply;
+
+/* Transmission phase structs
+ *
+ * Note: these are _NOT_ the same as the network representation of an NBD
  * request and reply!
  */
-struct nbd_request {
+struct NBDRequest {
     uint64_t handle;
     uint64_t from;
     uint32_t len;
-    uint32_t type;
+    uint16_t flags; /* NBD_CMD_FLAG_* */
+    uint16_t type; /* NBD_CMD_* */
 };
+typedef struct NBDRequest NBDRequest;
 
-struct nbd_reply {
+struct NBDReply {
     uint64_t handle;
     uint32_t error;
 };
+typedef struct NBDReply NBDReply;
 
+/* Transmission (export) flags: sent from server to client during handshake,
+   but describe what will happen during transmission */
 #define NBD_FLAG_HAS_FLAGS      (1 << 0)        /* Flags are there */
 #define NBD_FLAG_READ_ONLY      (1 << 1)        /* Device is read-only */
 #define NBD_FLAG_SEND_FLUSH     (1 << 2)        /* Send FLUSH */
 #define NBD_FLAG_SEND_FUA       (1 << 3)        /* Send FUA (Force Unit Access) */
 #define NBD_FLAG_ROTATIONAL     (1 << 4)        /* Use elevator algorithm - rotational media */
 #define NBD_FLAG_SEND_TRIM      (1 << 5)        /* Send TRIM (discard) */
+#define NBD_FLAG_SEND_WRITE_ZEROES (1 << 6)     /* Send WRITE_ZEROES */
 
-/* New-style global flags. */
+/* New-style handshake (global) flags, sent from server to client, and
+   control what will happen during handshake phase. */
 #define NBD_FLAG_FIXED_NEWSTYLE   (1 << 0) /* Fixed newstyle protocol. */
+#define NBD_FLAG_NO_ZEROES        (1 << 1) /* End handshake without zeroes. */
 
-/* New-style client flags. */
+/* New-style client flags, sent from client to server to control what happens
+   during handshake phase. */
 #define NBD_FLAG_C_FIXED_NEWSTYLE (1 << 0) /* Fixed newstyle protocol. */
+#define NBD_FLAG_C_NO_ZEROES      (1 << 1) /* End handshake without zeroes. */
 
 /* Reply types. */
+#define NBD_REP_ERR(value) ((UINT32_C(1) << 31) | (value))
+
 #define NBD_REP_ACK             (1)             /* Data sending finished. */
 #define NBD_REP_SERVER          (2)             /* Export description. */
-#define NBD_REP_ERR_UNSUP       ((UINT32_C(1) << 31) | 1) /* Unknown option. */
-#define NBD_REP_ERR_POLICY      ((UINT32_C(1) << 31) | 2) /* Server denied */
-#define NBD_REP_ERR_INVALID     ((UINT32_C(1) << 31) | 3) /* Invalid length. */
-#define NBD_REP_ERR_TLS_REQD    ((UINT32_C(1) << 31) | 5) /* TLS required */
 
+#define NBD_REP_ERR_UNSUP       NBD_REP_ERR(1)  /* Unknown option */
+#define NBD_REP_ERR_POLICY      NBD_REP_ERR(2)  /* Server denied */
+#define NBD_REP_ERR_INVALID     NBD_REP_ERR(3)  /* Invalid length */
+#define NBD_REP_ERR_PLATFORM    NBD_REP_ERR(4)  /* Not compiled in */
+#define NBD_REP_ERR_TLS_REQD    NBD_REP_ERR(5)  /* TLS required */
+#define NBD_REP_ERR_SHUTDOWN    NBD_REP_ERR(7)  /* Server shutting down */
 
-#define NBD_CMD_MASK_COMMAND	0x0000ffff
-#define NBD_CMD_FLAG_FUA	(1 << 16)
+/* Request flags, sent from client to server during transmission phase */
+#define NBD_CMD_FLAG_FUA        (1 << 0) /* 'force unit access' during write */
+#define NBD_CMD_FLAG_NO_HOLE    (1 << 1) /* don't punch hole on zero run */
 
+/* Supported request types */
 enum {
     NBD_CMD_READ = 0,
     NBD_CMD_WRITE = 1,
     NBD_CMD_DISC = 2,
     NBD_CMD_FLUSH = 3,
-    NBD_CMD_TRIM = 4
+    NBD_CMD_TRIM = 4,
+    /* 5 reserved for failed experiment NBD_CMD_CACHE */
+    NBD_CMD_WRITE_ZEROES = 6,
 };
 
 #define NBD_DEFAULT_PORT	10809
@@ -95,8 +133,8 @@ int nbd_receive_negotiate(QIOChannel *ioc, const char *name, uint16_t *flags,
                           QIOChannel **outioc,
                           off_t *size, Error **errp);
 int nbd_init(int fd, QIOChannelSocket *sioc, uint16_t flags, off_t size);
-ssize_t nbd_send_request(QIOChannel *ioc, struct nbd_request *request);
-ssize_t nbd_receive_reply(QIOChannel *ioc, struct nbd_reply *reply);
+ssize_t nbd_send_request(QIOChannel *ioc, NBDRequest *request);
+ssize_t nbd_receive_reply(QIOChannel *ioc, NBDReply *reply);
 int nbd_client(int fd);
 int nbd_disconnect(int fd);
 
@@ -115,6 +153,7 @@ BlockBackend *nbd_export_get_blockdev(NBDExport *exp);
 
 NBDExport *nbd_export_find(const char *name);
 void nbd_export_set_name(NBDExport *exp, const char *name);
+void nbd_export_set_description(NBDExport *exp, const char *description);
 void nbd_export_close_all(void);
 
 void nbd_client_new(NBDExport *exp,

include/glib-compat.h

@@ -315,4 +315,17 @@ static inline void g_source_set_name_by_id(guint tag, const char *name)
 }
 #endif
 
+#if !GLIB_CHECK_VERSION(2, 36, 0)
+/* Always fail.  This will not include error_report output in the test log,
+ * sending it instead to stderr.
+ */
+#define g_test_initialized() (0)
+#endif
+#if !GLIB_CHECK_VERSION(2, 38, 0)
+#ifdef CONFIG_HAS_GLIB_SUBPROCESS_TESTS
+#error schizophrenic detection of glib subprocess testing
+#endif
+#define g_test_subprocess() (0)
+#endif
+
 #endif

include/qemu/error-report.h

@@ -32,6 +32,7 @@ void loc_set_file(const char *fname, int lno);
 
 void error_vprintf(const char *fmt, va_list ap) GCC_FMT_ATTR(1, 0);
 void error_printf(const char *fmt, ...) GCC_FMT_ATTR(1, 2);
+void error_vprintf_unless_qmp(const char *fmt, va_list ap) GCC_FMT_ATTR(1, 0);
 void error_printf_unless_qmp(const char *fmt, ...) GCC_FMT_ATTR(1, 2);
 void error_set_progname(const char *argv0);
 void error_vreport(const char *fmt, va_list ap) GCC_FMT_ATTR(1, 0);

include/qemu/osdep.h

@@ -128,6 +128,9 @@ extern int daemon(int, int);
 #if !defined(EMEDIUMTYPE)
 #define EMEDIUMTYPE 4098
 #endif
+#if !defined(ESHUTDOWN)
+#define ESHUTDOWN 4099
+#endif
 #ifndef TIME_MAX
 #define TIME_MAX LONG_MAX
 #endif

main-loop.c

@@ -234,7 +234,7 @@ static int os_host_main_loop_wait(int64_t timeout)
     if (!timeout && (spin_counter > MAX_MAIN_LOOP_SPIN)) {
         static bool notified;
 
-        if (!notified && !qtest_driver()) {
+        if (!notified && !qtest_enabled() && !qtest_driver()) {
             fprintf(stderr,
                     "main-loop: WARNING: I/O thread spun for %d iterations\n",
                     MAX_MAIN_LOOP_SPIN);

monitor.c

@@ -3955,6 +3955,27 @@ static void monitor_readline_flush(void *opaque)
     monitor_flush(opaque);
 }
 
+/*
+ * Print to current monitor if we have one, else to stderr.
+ * TODO should return int, so callers can calculate width, but that
+ * requires surgery to monitor_vprintf().  Left for another day.
+ */
+void error_vprintf(const char *fmt, va_list ap)
+{
+    if (cur_mon && !monitor_cur_is_qmp()) {
+        monitor_vprintf(cur_mon, fmt, ap);
+    } else {
+        vfprintf(stderr, fmt, ap);
+    }
+}
+
+void error_vprintf_unless_qmp(const char *fmt, va_list ap)
+{
+    if (cur_mon && !monitor_cur_is_qmp()) {
+        monitor_vprintf(cur_mon, fmt, ap);
+    }
+}
+
 static void __attribute__((constructor)) monitor_lock_init(void)
 {
     qemu_mutex_init(&monitor_lock);

nbd/nbd-internal.h

@@ -53,16 +53,16 @@
 /* This is all part of the "official" NBD API.
  *
  * The most up-to-date documentation is available at:
- * https://github.com/yoe/nbd/blob/master/doc/proto.txt
+ * https://github.com/yoe/nbd/blob/master/doc/proto.md
  */
 
-#define NBD_REQUEST_SIZE        (4 + 4 + 8 + 8 + 4)
+#define NBD_REQUEST_SIZE        (4 + 2 + 2 + 8 + 8 + 4)
 #define NBD_REPLY_SIZE          (4 + 4 + 8)
 #define NBD_REQUEST_MAGIC       0x25609513
 #define NBD_REPLY_MAGIC         0x67446698
 #define NBD_OPTS_MAGIC          0x49484156454F5054LL
 #define NBD_CLIENT_MAGIC        0x0000420281861253LL
-#define NBD_REP_MAGIC           0x3e889045565a9LL
+#define NBD_REP_MAGIC           0x0003e889045565a9LL
 
 #define NBD_SET_SOCK            _IO(0xab, 0)
 #define NBD_SET_BLKSIZE         _IO(0xab, 1)
@@ -92,6 +92,7 @@
 #define NBD_ENOMEM     12
 #define NBD_EINVAL     22
 #define NBD_ENOSPC     28
+#define NBD_ESHUTDOWN  108
 
 static inline ssize_t read_sync(QIOChannel *ioc, void *buffer, size_t size)
 {
@@ -104,9 +105,10 @@ static inline ssize_t read_sync(QIOChannel *ioc, void *buffer, size_t size)
     return nbd_wr_syncv(ioc, &iov, 1, size, true);
 }
 
-static inline ssize_t write_sync(QIOChannel *ioc, void *buffer, size_t size)
+static inline ssize_t write_sync(QIOChannel *ioc, const void *buffer,
+                                 size_t size)
 {
-    struct iovec iov = { .iov_base = buffer, .iov_len = size };
+    struct iovec iov = { .iov_base = (void *) buffer, .iov_len = size };
 
     return nbd_wr_syncv(ioc, &iov, 1, size, false);
 }

net/slirp.c

@@ -763,8 +763,7 @@ static int slirp_guestfwd(SlirpState *s, const char *config_str,
             return -1;
         }
 
-        if (slirp_add_exec(s->slirp, 3, qemu_chr_fe_get_driver(&fwd->hd),
-                           &server, port) < 0) {
+        if (slirp_add_exec(s->slirp, 3, &fwd->hd, &server, port) < 0) {
             error_report("conflicting/invalid host:port in guest forwarding "
                          "rule '%s'", config_str);
             g_free(fwd);

qapi-schema.json

@@ -4621,10 +4621,10 @@
 #
 # @pause: system pauses
 #
-# Since: 2.1
+# Since: 2.1 (poweroff since 2.8)
 ##
 { 'enum': 'GuestPanicAction',
-  'data': [ 'pause' ] }
+  'data': [ 'pause', 'poweroff' ] }
 
 ##
 # @rtc-reset-reinjection

qemu-char.c

@@ -735,19 +735,23 @@ static void mux_chr_read(void *opaque, const uint8_t *buf, int size)
         }
 }
 
+static bool muxes_realized;
+
 static void mux_chr_event(void *opaque, int event)
 {
     CharDriverState *chr = opaque;
     MuxDriver *d = chr->opaque;
     int i;
 
+    if (!muxes_realized) {
+        return;
+    }
+
     /* Send the event to all registered listeners */
     for (i = 0; i < d->mux_cnt; i++)
         mux_chr_send_event(d, i, event);
 }
 
-static bool muxes_realized;
-
 /**
  * Called after processing of default and command-line-specified
  * chardevs to deliver CHR_EVENT_OPENED events to any FEs attached

qemu-nbd.c

@@ -83,6 +83,7 @@ static void usage(const char *name)
 "  -t, --persistent          don't exit on the last connection\n"
 "  -v, --verbose             display extra debugging information\n"
 "  -x, --export-name=NAME    expose export by name\n"
+"  -D, --description=TEXT    with -x, also export a human-readable description\n"
 "\n"
 "Exposing part of the image:\n"
 "  -o, --offset=OFFSET       offset into the image\n"
@@ -477,7 +478,7 @@ int main(int argc, char **argv)
     off_t fd_size;
     QemuOpts *sn_opts = NULL;
     const char *sn_id_or_name = NULL;
-    const char *sopt = "hVb:o:p:rsnP:c:dvk:e:f:tl:x:T:";
+    const char *sopt = "hVb:o:p:rsnP:c:dvk:e:f:tl:x:T:D:";
     struct option lopt[] = {
         { "help", no_argument, NULL, 'h' },
         { "version", no_argument, NULL, 'V' },
@@ -503,6 +504,7 @@ int main(int argc, char **argv)
         { "verbose", no_argument, NULL, 'v' },
         { "object", required_argument, NULL, QEMU_NBD_OPT_OBJECT },
         { "export-name", required_argument, NULL, 'x' },
+        { "description", required_argument, NULL, 'D' },
         { "tls-creds", required_argument, NULL, QEMU_NBD_OPT_TLSCREDS },
         { "image-opts", no_argument, NULL, QEMU_NBD_OPT_IMAGE_OPTS },
         { "trace", required_argument, NULL, 'T' },
@@ -524,6 +526,7 @@ int main(int argc, char **argv)
     BlockdevDetectZeroesOptions detect_zeroes = BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
     QDict *options = NULL;
     const char *export_name = NULL;
+    const char *export_description = NULL;
     const char *tlscredsid = NULL;
     bool imageOpts = false;
     bool writethrough = true;
@@ -689,6 +692,9 @@ int main(int argc, char **argv)
         case 'x':
             export_name = optarg;
             break;
+        case 'D':
+            export_description = optarg;
+            break;
         case 'v':
             verbose = 1;
             break;
@@ -937,7 +943,11 @@ int main(int argc, char **argv)
     }
     if (export_name) {
         nbd_export_set_name(exp, export_name);
+        nbd_export_set_description(exp, export_description);
         newproto = true;
+    } else if (export_description) {
+        error_report("Export description requires an export name");
+        exit(EXIT_FAILURE);
     }
 
     server_ioc = qio_channel_socket_new();

qemu-nbd.texi

@@ -79,9 +79,12 @@ Disconnect the device @var{dev}
 Allow up to @var{num} clients to share the device (default @samp{1})
 @item -t, --persistent
 Don't exit on the last connection
-@item -x NAME, --export-name=NAME
+@item -x, --export-name=@var{name}
 Set the NBD volume export name. This switches the server to use
 the new style NBD protocol negotiation
+@item -D, --description=@var{description}
+Set the NBD volume export description, as a human-readable
+string. Requires the use of @option{-x}
 @item --tls-creds=ID
 Enable mandatory TLS encryption for the server by setting the ID
 of the TLS credentials object previously created with the --object

scripts/checkpatch.pl

@@ -1754,7 +1754,7 @@ sub process {
 			# Ignore those directives where spaces _are_ permitted.
 			if ($name =~ /^(?:
 				if|for|while|switch|return|case|
-				volatile|__volatile__|
+				volatile|__volatile__|coroutine_fn|
 				__attribute__|format|__extension__|
 				asm|__asm__)$/x)
 			{
@@ -2498,8 +2498,8 @@ sub process {
 				VMStateDescription|
 				VMStateInfo}x;
 		if ($line !~ /\bconst\b/ &&
-		    $line =~ /\b($struct_ops)\b/) {
-			ERROR("struct $1 should normally be const\n" .
+		    $line =~ /\b($struct_ops)\b.*=/) {
+			ERROR("initializer for struct $1 should normally be const\n" .
 				$herecurr);
 		}
 

stubs/Makefile.objs

@@ -9,6 +9,7 @@ stub-obj-y += clock-warp.o
 stub-obj-y += cpu-get-clock.o
 stub-obj-y += cpu-get-icount.o
 stub-obj-y += dump.o
+stub-obj-y += error-printf.o
 stub-obj-y += fdset-add-fd.o
 stub-obj-y += fdset-find-fd.o
 stub-obj-y += fdset-get-fd.o
@@ -23,7 +24,6 @@ stub-obj-y += is-daemonized.o
 stub-obj-y += machine-init-done.o
 stub-obj-y += migr-blocker.o
 stub-obj-y += mon-is-qmp.o
-stub-obj-y += mon-printf.o
 stub-obj-y += monitor-init.o
 stub-obj-y += notify-event.o
 stub-obj-y += qtest.o

stubs/error-printf.c

+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "qemu/error-report.h"
+
+void error_vprintf(const char *fmt, va_list ap)
+{
+    if (g_test_initialized() && !g_test_subprocess()) {
+        char *msg = g_strdup_vprintf(fmt, ap);
+        g_test_message("%s", msg);
+        g_free(msg);
+    } else {
+        vfprintf(stderr, fmt, ap);
+    }
+}
+
+void error_vprintf_unless_qmp(const char *fmt, va_list ap)
+{
+    error_vprintf(fmt, ap);
+}

stubs/mon-printf.c

-#include "qemu/osdep.h"
-#include "qemu-common.h"
-#include "monitor/monitor.h"
-
-void monitor_printf(Monitor *mon, const char *fmt, ...)
-{
-}
-
-void monitor_vprintf(Monitor *mon, const char *fmt, va_list ap)
-{
-}

target-i386/cpu.c

@@ -239,6 +239,7 @@ static void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
           CPUID_7_0_EBX_INVPCID, CPUID_7_0_EBX_RTM,
           CPUID_7_0_EBX_RDSEED */
 #define TCG_7_0_ECX_FEATURES (CPUID_7_0_ECX_PKU | CPUID_7_0_ECX_OSPKE)
+#define TCG_7_0_EDX_FEATURES 0
 #define TCG_APM_FEATURES 0
 #define TCG_6_EAX_FEATURES CPUID_6_EAX_ARAT
 #define TCG_XSAVE_FEATURES (CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XGETBV1)
@@ -444,6 +445,22 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
         .cpuid_reg = R_ECX,
         .tcg_features = TCG_7_0_ECX_FEATURES,
     },
+    [FEAT_7_0_EDX] = {
+        .feat_names = {
+            NULL, NULL, "avx512-4vnniw", "avx512-4fmaps",
+            NULL, NULL, NULL, NULL,
+            NULL, NULL, NULL, NULL,
+            NULL, NULL, NULL, NULL,
+            NULL, NULL, NULL, NULL,
+            NULL, NULL, NULL, NULL,
+            NULL, NULL, NULL, NULL,
+            NULL, NULL, NULL, NULL,
+        },
+        .cpuid_eax = 7,
+        .cpuid_needs_ecx = true, .cpuid_ecx = 0,
+        .cpuid_reg = R_EDX,
+        .tcg_features = TCG_7_0_EDX_FEATURES,
+    },
     [FEAT_8000_0007_EDX] = {
         .feat_names = {
             NULL, NULL, NULL, NULL,
@@ -2560,7 +2577,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
             if ((*ecx & CPUID_7_0_ECX_PKU) && env->cr[4] & CR4_PKE_MASK) {
                 *ecx |= CPUID_7_0_ECX_OSPKE;
             }
-            *edx = 0; /* Reserved */
+            *edx = env->features[FEAT_7_0_EDX]; /* Feature flags */
         } else {
             *eax = 0;
             *ebx = 0;

target-i386/cpu.h

@@ -443,6 +443,7 @@ typedef enum FeatureWord {
     FEAT_1_ECX,         /* CPUID[1].ECX */
     FEAT_7_0_EBX,       /* CPUID[EAX=7,ECX=0].EBX */
     FEAT_7_0_ECX,       /* CPUID[EAX=7,ECX=0].ECX */
+    FEAT_7_0_EDX,       /* CPUID[EAX=7,ECX=0].EDX */
     FEAT_8000_0001_EDX, /* CPUID[8000_0001].EDX */
     FEAT_8000_0001_ECX, /* CPUID[8000_0001].ECX */
     FEAT_8000_0007_EDX, /* CPUID[8000_0007].EDX */
@@ -629,6 +630,9 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS];
 #define CPUID_7_0_ECX_OSPKE    (1U << 4)
 #define CPUID_7_0_ECX_RDPID    (1U << 22)
 
+#define CPUID_7_0_EDX_AVX512_4VNNIW (1U << 2) /* AVX512 Neural Network Instructions */
+#define CPUID_7_0_EDX_AVX512_4FMAPS (1U << 3) /* AVX512 Multiply Accumulation Single Precision */
+
 #define CPUID_XSAVE_XSAVEOPT   (1U << 0)
 #define CPUID_XSAVE_XSAVEC     (1U << 1)
 #define CPUID_XSAVE_XGETBV1    (1U << 2)

util/qemu-error.c

@@ -14,24 +14,6 @@
 #include "monitor/monitor.h"
 #include "qemu/error-report.h"
 
-/*
- * Print to current monitor if we have one, else to stderr.
- * TODO should return int, so callers can calculate width, but that
- * requires surgery to monitor_vprintf().  Left for another day.
- */
-void error_vprintf(const char *fmt, va_list ap)
-{
-    if (cur_mon && !monitor_cur_is_qmp()) {
-        monitor_vprintf(cur_mon, fmt, ap);
-    } else {
-        vfprintf(stderr, fmt, ap);
-    }
-}
-
-/*
- * Print to current monitor if we have one, else to stderr.
- * TODO just like error_vprintf()
- */
 void error_printf(const char *fmt, ...)
 {
     va_list ap;
@@ -45,11 +27,9 @@ void error_printf_unless_qmp(const char *fmt, ...)
 {
     va_list ap;
 
-    if (!monitor_cur_is_qmp()) {
     va_start(ap, fmt);
-        error_vprintf(fmt, ap);
+    error_vprintf_unless_qmp(fmt, ap);
     va_end(ap);
-    }
 }
 
 static Location std_loc = {

vl.c

@@ -1792,6 +1792,11 @@ void qemu_system_guest_panicked(void)
     }
     qapi_event_send_guest_panicked(GUEST_PANIC_ACTION_PAUSE, &error_abort);
     vm_stop(RUN_STATE_GUEST_PANICKED);
+    if (!no_shutdown) {
+        qapi_event_send_guest_panicked(GUEST_PANIC_ACTION_POWEROFF,
+                                       &error_abort);
+        qemu_system_shutdown_request();
+    }
 }
 
 void qemu_system_reset_request(void)