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: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 30 insertions, 3 deletions

diff --git a/exec.c b/exec.c
index b1094c0..3d867f1 100644
--- a/exec.c
+++ b/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);
 }