Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

virtio,vhost,pci,pc: features, cleanups

SRAT tables for DIMM devices
new virtio net flags for speed/duplex
post-copy migration support in vhost
cleanups in pci

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Tue 20 Mar 2018 14:40:43 GMT
# gpg:                using RSA key 281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream: (51 commits)
  postcopy shared docs
  libvhost-user: Claim support for postcopy
  postcopy: Allow shared memory
  vhost: Huge page align and merge
  vhost+postcopy: Wire up POSTCOPY_END notify
  vhost-user: Add VHOST_USER_POSTCOPY_END message
  libvhost-user: mprotect & madvises for postcopy
  vhost+postcopy: Call wakeups
  vhost+postcopy: Add vhost waker
  postcopy: postcopy_notify_shared_wake
  postcopy: helper for waking shared
  vhost+postcopy: Resolve client address
  postcopy-ram: add a stub for postcopy_request_shared_page
  vhost+postcopy: Helper to send requests to source for shared pages
  vhost+postcopy: Stash RAMBlock and offset
  vhost+postcopy: Send address back to qemu
  libvhost-user+postcopy: Register new regions with the ufd
  migration/ram: ramblock_recv_bitmap_test_byte_offset
  postcopy+vhost-user: Split set_mem_table for postcopy
  vhost+postcopy: Transmit 'listen' to slave
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

# Conflicts:
#	scripts/update-linux-headers.sh

1 files changed, 72 insertions, 14 deletions

diff --git a/exec.c b/exec.c
index bc643fc50f..c09bd93df3 100644
--- a/exec.c
+++ b/exec.c
@@ -99,6 +99,11 @@ static MemoryRegion io_mem_unassigned;
  */
 #define RAM_RESIZEABLE (1 << 2)
 
+/* UFFDIO_ZEROPAGE is available on this RAMBlock to atomically
+ * zero the page and wake waiting processes.
+ * (Set during postcopy)
+ */
+#define RAM_UF_ZEROPAGE (1 << 3)
 #endif
 
 #ifdef TARGET_PAGE_BITS_VARY
@@ -1790,6 +1795,17 @@ bool qemu_ram_is_shared(RAMBlock *rb)
     return rb->flags & RAM_SHARED;
 }
 
+/* Note: Only set at the start of postcopy */
+bool qemu_ram_is_uf_zeroable(RAMBlock *rb)
+{
+    return rb->flags & RAM_UF_ZEROPAGE;
+}
+
+void qemu_ram_set_uf_zeroable(RAMBlock *rb)
+{
+    rb->flags |= RAM_UF_ZEROPAGE;
+}
+
 /* Called with iothread lock held.  */
 void qemu_ram_set_idstr(RAMBlock *new_block, const char *name, DeviceState *dev)
 {
@@ -2320,6 +2336,16 @@ static void *qemu_ram_ptr_length(RAMBlock *ram_block, ram_addr_t addr,
     return ramblock_ptr(block, addr);
 }
 
+/* Return the offset of a hostpointer within a ramblock */
+ram_addr_t qemu_ram_block_host_offset(RAMBlock *rb, void *host)
+{
+    ram_addr_t res = (uint8_t *)host - (uint8_t *)rb->host;
+    assert((uintptr_t)host >= (uintptr_t)rb->host);
+    assert(res < rb->max_length);
+
+    return res;
+}
+
 /*
  * Translates a host ptr back to a RAMBlock, a ram_addr and an offset
  * in that RAMBlock.
@@ -3744,6 +3770,7 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
     }
 
     if ((start + length) <= rb->used_length) {
+        bool need_madvise, need_fallocate;
         uint8_t *host_endaddr = host_startaddr + length;
         if ((uintptr_t)host_endaddr & (rb->page_size - 1)) {
             error_report("ram_block_discard_range: Unaligned end address: %p",
@@ -3753,29 +3780,60 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
 
         errno = ENOTSUP; /* If we are missing MADVISE etc */
 
-        if (rb->page_size == qemu_host_page_size) {
-#if defined(CONFIG_MADVISE)
-            /* Note: We need the madvise MADV_DONTNEED behaviour of definitely
-             * freeing the page.
-             */
-            ret = madvise(host_startaddr, length, MADV_DONTNEED);
-#endif
-        } else {
-            /* Huge page case  - unfortunately it can't do DONTNEED, but
-             * it can do the equivalent by FALLOC_FL_PUNCH_HOLE in the
-             * huge page file.
+        /* The logic here is messy;
+         *    madvise DONTNEED fails for hugepages
+         *    fallocate works on hugepages and shmem
+         */
+        need_madvise = (rb->page_size == qemu_host_page_size);
+        need_fallocate = rb->fd != -1;
+        if (need_fallocate) {
+            /* For a file, this causes the area of the file to be zero'd
+             * if read, and for hugetlbfs also causes it to be unmapped
+             * so a userfault will trigger.
              */
 #ifdef CONFIG_FALLOCATE_PUNCH_HOLE
             ret = fallocate(rb->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
                             start, length);
+            if (ret) {
+                ret = -errno;
+                error_report("ram_block_discard_range: Failed to fallocate "
+                             "%s:%" PRIx64 " +%zx (%d)",
+                             rb->idstr, start, length, ret);
+                goto err;
+            }
+#else
+            ret = -ENOSYS;
+            error_report("ram_block_discard_range: fallocate not available/file"
+                         "%s:%" PRIx64 " +%zx (%d)",
+                         rb->idstr, start, length, ret);
+            goto err;
 #endif
         }
-        if (ret) {
-            ret = -errno;
-            error_report("ram_block_discard_range: Failed to discard range "
+        if (need_madvise) {
+            /* For normal RAM this causes it to be unmapped,
+             * for shared memory it causes the local mapping to disappear
+             * and to fall back on the file contents (which we just
+             * fallocate'd away).
+             */
+#if defined(CONFIG_MADVISE)
+            ret =  madvise(host_startaddr, length, MADV_DONTNEED);
+            if (ret) {
+                ret = -errno;
+                error_report("ram_block_discard_range: Failed to discard range "
+                             "%s:%" PRIx64 " +%zx (%d)",
+                             rb->idstr, start, length, ret);
+                goto err;
+            }
+#else
+            ret = -ENOSYS;
+            error_report("ram_block_discard_range: MADVISE not available"
                          "%s:%" PRIx64 " +%zx (%d)",
                          rb->idstr, start, length, ret);
+            goto err;
+#endif
         }
+        trace_ram_block_discard_range(rb->idstr, host_startaddr, length,
+                                      need_madvise, need_fallocate, ret);
     } else {
         error_report("ram_block_discard_range: Overrun block '%s' (%" PRIu64
                      "/%zx/" RAM_ADDR_FMT")",