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

* icount fix (Clement)
* dumping fixes for non-volatile memory (Marc-André, myself)
* x86 emulation fix (Rudolf)
* recent Hyper-V CPUID flag (Vitaly)
* Q35 doc fix (Daniel)
* lsi fix (Prasad)
* SCSI block limits emulation fixes (myself)
* qemu_thread_atexit rework (Peter)
* ivshmem memory leak fix (Igor)

# gpg: Signature made Tue 06 Nov 2018 21:34:30 GMT
# gpg:                using RSA key BFFBD25F78C7AE83
# 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:
  util/qemu-thread-posix: Fix qemu_thread_atexit* for OSX
  include/qemu/thread.h: Document qemu_thread_atexit* API
  scsi-generic: do not do VPD emulation for sense other than ILLEGAL_REQUEST
  scsi-generic: avoid invalid access to struct when emulating block limits
  scsi-generic: avoid out-of-bounds access to VPD page list
  scsi-generic: keep VPD page list sorted
  lsi53c895a: check message length value is valid
  scripts/dump-guest-memory: Synchronize with guest_phys_blocks_region_add
  memory-mapping: skip non-volatile memory regions in GuestPhysBlockList
  nvdimm: set non-volatile on the memory region
  memory: learn about non-volatile memory region
  target/i386: Clear RF on SYSCALL instruction
  MAINTAINERS: remove or downgrade myself to reviewer from some subsystems
  ivshmem: fix memory backend leak
  i386: clarify that the Q35 machine type implements a P35 chipset
  x86: hv_evmcs CPU flag support
  icount: fix deadlock when all cpus are sleeping

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

8 files changed, 135 insertions, 92 deletions

diff --git a/hw/mem/nvdimm.c b/hw/mem/nvdimm.c
index 49324f3fae..bf2adf5e16 100644
--- a/hw/mem/nvdimm.c
+++ b/hw/mem/nvdimm.c
@@ -116,6 +116,7 @@ static void nvdimm_prepare_memory_region(NVDIMMDevice *nvdimm, Error **errp)
     nvdimm->nvdimm_mr = g_new(MemoryRegion, 1);
     memory_region_init_alias(nvdimm->nvdimm_mr, OBJECT(dimm),
                              "nvdimm-memory", mr, 0, pmem_size);
+    memory_region_set_nonvolatile(nvdimm->nvdimm_mr, true);
     nvdimm->nvdimm_mr->align = align;
 }
 
diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c
index f88910e55c..ecfd10a29a 100644
--- a/hw/misc/ivshmem.c
+++ b/hw/misc/ivshmem.c
@@ -1279,6 +1279,7 @@ static void desugar_shm(IVShmemState *s)
     object_property_set_bool(obj, true, "share", &error_abort);
     object_property_add_child(OBJECT(s), "internal-shm-backend", obj,
                               &error_abort);
+    object_unref(obj);
     user_creatable_complete(obj, &error_abort);
     s->hostmem = MEMORY_BACKEND(obj);
 }
diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c
index 0c38a8dfd3..7b871b5734 100644
--- a/hw/pci-host/q35.c
+++ b/hw/pci-host/q35.c
@@ -629,7 +629,15 @@ static void mch_class_init(ObjectClass *klass, void *data)
     dc->desc = "Host bridge";
     dc->vmsd = &vmstate_mch;
     k->vendor_id = PCI_VENDOR_ID_INTEL;
-    k->device_id = PCI_DEVICE_ID_INTEL_Q35_MCH;
+    /*
+     * The 'q35' machine type implements an Intel Series 3 chipset,
+     * of which there are several variants. The key difference between
+     * the 82P35 MCH ('p35') and 82Q35 GMCH ('q35') variants is that
+     * the latter has an integrated graphics adapter. QEMU does not
+     * implement integrated graphics, so uses the PCI ID for the 82P35
+     * chipset.
+     */
+    k->device_id = PCI_DEVICE_ID_INTEL_P35_MCH;
     k->revision = MCH_HOST_BRIDGE_REVISION_DEFAULT;
     k->class_id = PCI_CLASS_BRIDGE_HOST;
     /*
diff --git a/hw/scsi/Makefile.objs b/hw/scsi/Makefile.objs
index 718b4c2a68..45167baeaf 100644
--- a/hw/scsi/Makefile.objs
+++ b/hw/scsi/Makefile.objs
@@ -1,4 +1,4 @@
-common-obj-y += scsi-disk.o
+common-obj-y += scsi-disk.o emulation.o
 common-obj-y += scsi-generic.o scsi-bus.o
 common-obj-$(CONFIG_LSI_SCSI_PCI) += lsi53c895a.o
 common-obj-$(CONFIG_MPTSAS_SCSI_PCI) += mptsas.o mptconfig.o mptendian.o
diff --git a/hw/scsi/emulation.c b/hw/scsi/emulation.c
new file mode 100644
index 0000000000..06d62f3c38
--- /dev/null
+++ b/hw/scsi/emulation.c
@@ -0,0 +1,42 @@
+#include "qemu/osdep.h"
+#include "qemu/units.h"
+#include "qemu/bswap.h"
+#include "hw/scsi/emulation.h"
+
+int scsi_emulate_block_limits(uint8_t *outbuf, const SCSIBlockLimits *bl)
+{
+    /* required VPD size with unmap support */
+    memset(outbuf, 0, 0x3c);
+
+    outbuf[0] = bl->wsnz; /* wsnz */
+
+    if (bl->max_io_sectors) {
+        /* optimal transfer length granularity.  This field and the optimal
+         * transfer length can't be greater than maximum transfer length.
+         */
+        stw_be_p(outbuf + 2, MIN(bl->min_io_size, bl->max_io_sectors));
+
+        /* maximum transfer length */
+        stl_be_p(outbuf + 4, bl->max_io_sectors);
+
+        /* optimal transfer length */
+        stl_be_p(outbuf + 8, MIN(bl->opt_io_size, bl->max_io_sectors));
+    } else {
+        stw_be_p(outbuf + 2, bl->min_io_size);
+        stl_be_p(outbuf + 8, bl->opt_io_size);
+    }
+
+    /* max unmap LBA count */
+    stl_be_p(outbuf + 16, bl->max_unmap_sectors);
+
+    /* max unmap descriptors */
+    stl_be_p(outbuf + 20, bl->max_unmap_descr);
+
+    /* optimal unmap granularity; alignment is zero */
+    stl_be_p(outbuf + 24, bl->unmap_sectors);
+
+    /* max write same size, make it the same as maximum transfer length */
+    stl_be_p(outbuf + 36, bl->max_io_sectors);
+
+    return 0x3c;
+}
diff --git a/hw/scsi/lsi53c895a.c b/hw/scsi/lsi53c895a.c
index d1e6534311..3f207f607c 100644
--- a/hw/scsi/lsi53c895a.c
+++ b/hw/scsi/lsi53c895a.c
@@ -861,10 +861,11 @@ static void lsi_do_status(LSIState *s)
 
 static void lsi_do_msgin(LSIState *s)
 {
-    int len;
+    uint8_t len;
     trace_lsi_do_msgin(s->dbc, s->msg_len);
     s->sfbr = s->msg[0];
     len = s->msg_len;
+    assert(len > 0 && len <= LSI_MAX_MSGIN_LEN);
     if (len > s->dbc)
         len = s->dbc;
     pci_dma_write(PCI_DEVICE(s), s->dnad, s->msg, len);
@@ -1705,8 +1706,10 @@ static uint8_t lsi_reg_readb(LSIState *s, int offset)
         break;
     case 0x58: /* SBDL */
         /* Some drivers peek at the data bus during the MSG IN phase.  */
-        if ((s->sstat1 & PHASE_MASK) == PHASE_MI)
+        if ((s->sstat1 & PHASE_MASK) == PHASE_MI) {
+            assert(s->msg_len > 0);
             return s->msg[0];
+        }
         ret = 0;
         break;
     case 0x59: /* SBDL high */
@@ -2103,11 +2106,23 @@ static int lsi_pre_save(void *opaque)
     return 0;
 }
 
+static int lsi_post_load(void *opaque, int version_id)
+{
+    LSIState *s = opaque;
+
+    if (s->msg_len < 0 || s->msg_len > LSI_MAX_MSGIN_LEN) {
+        return -EINVAL;
+    }
+
+    return 0;
+}
+
 static const VMStateDescription vmstate_lsi_scsi = {
     .name = "lsiscsi",
     .version_id = 0,
     .minimum_version_id = 0,
     .pre_save = lsi_pre_save,
+    .post_load = lsi_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_PCI_DEVICE(parent_obj, LSIState),
 
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index e2c5408aa2..6eb258d3f3 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -33,6 +33,7 @@ do { printf("scsi-disk: " fmt , ## __VA_ARGS__); } while (0)
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "hw/scsi/scsi.h"
+#include "hw/scsi/emulation.h"
 #include "scsi/constants.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/block-backend.h"
@@ -589,7 +590,7 @@ static uint8_t *scsi_get_buf(SCSIRequest *req)
     return (uint8_t *)r->iov.iov_base;
 }
 
-int scsi_disk_emulate_vpd_page(SCSIRequest *req, uint8_t *outbuf)
+static int scsi_disk_emulate_vpd_page(SCSIRequest *req, uint8_t *outbuf)
 {
     SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, req->dev);
     uint8_t page_code = req->cmd.buf[2];
@@ -691,89 +692,36 @@ int scsi_disk_emulate_vpd_page(SCSIRequest *req, uint8_t *outbuf)
     }
     case 0xb0: /* block limits */
     {
-        unsigned int unmap_sectors =
-            s->qdev.conf.discard_granularity / s->qdev.blocksize;
-        unsigned int min_io_size =
-            s->qdev.conf.min_io_size / s->qdev.blocksize;
-        unsigned int opt_io_size =
-            s->qdev.conf.opt_io_size / s->qdev.blocksize;
-        unsigned int max_unmap_sectors =
-            s->max_unmap_size / s->qdev.blocksize;
-        unsigned int max_io_sectors =
-            s->max_io_size / s->qdev.blocksize;
+        SCSIBlockLimits bl = {};
 
         if (s->qdev.type == TYPE_ROM) {
             DPRINTF("Inquiry (EVPD[%02X] not supported for CDROM\n",
                     page_code);
             return -1;
         }
+        bl.wsnz = 1;
+        bl.unmap_sectors =
+            s->qdev.conf.discard_granularity / s->qdev.blocksize;
+        bl.min_io_size =
+            s->qdev.conf.min_io_size / s->qdev.blocksize;
+        bl.opt_io_size =
+            s->qdev.conf.opt_io_size / s->qdev.blocksize;
+        bl.max_unmap_sectors =
+            s->max_unmap_size / s->qdev.blocksize;
+        bl.max_io_sectors =
+            s->max_io_size / s->qdev.blocksize;
+        /* 255 descriptors fit in 4 KiB with an 8-byte header */
+        bl.max_unmap_descr = 255;
+
         if (s->qdev.type == TYPE_DISK) {
             int max_transfer_blk = blk_get_max_transfer(s->qdev.conf.blk);
             int max_io_sectors_blk =
                 max_transfer_blk / s->qdev.blocksize;
 
-            max_io_sectors =
-                MIN_NON_ZERO(max_io_sectors_blk, max_io_sectors);
-
-            /* min_io_size and opt_io_size can't be greater than
-             * max_io_sectors */
-            if (min_io_size) {
-                min_io_size = MIN(min_io_size, max_io_sectors);
-            }
-            if (opt_io_size) {
-                opt_io_size = MIN(opt_io_size, max_io_sectors);
-            }
+            bl.max_io_sectors =
+                MIN_NON_ZERO(max_io_sectors_blk, bl.max_io_sectors);
         }
-        /* required VPD size with unmap support */
-        buflen = 0x40;
-        memset(outbuf + 4, 0, buflen - 4);
-
-        outbuf[4] = 0x1; /* wsnz */
-
-        /* optimal transfer length granularity */
-        outbuf[6] = (min_io_size >> 8) & 0xff;
-        outbuf[7] = min_io_size & 0xff;
-
-        /* maximum transfer length */
-        outbuf[8] = (max_io_sectors >> 24) & 0xff;
-        outbuf[9] = (max_io_sectors >> 16) & 0xff;
-        outbuf[10] = (max_io_sectors >> 8) & 0xff;
-        outbuf[11] = max_io_sectors & 0xff;
-
-        /* optimal transfer length */
-        outbuf[12] = (opt_io_size >> 24) & 0xff;
-        outbuf[13] = (opt_io_size >> 16) & 0xff;
-        outbuf[14] = (opt_io_size >> 8) & 0xff;
-        outbuf[15] = opt_io_size & 0xff;
-
-        /* max unmap LBA count, default is 1GB */
-        outbuf[20] = (max_unmap_sectors >> 24) & 0xff;
-        outbuf[21] = (max_unmap_sectors >> 16) & 0xff;
-        outbuf[22] = (max_unmap_sectors >> 8) & 0xff;
-        outbuf[23] = max_unmap_sectors & 0xff;
-
-        /* max unmap descriptors, 255 fit in 4 kb with an 8-byte header */
-        outbuf[24] = 0;
-        outbuf[25] = 0;
-        outbuf[26] = 0;
-        outbuf[27] = 255;
-
-        /* optimal unmap granularity */
-        outbuf[28] = (unmap_sectors >> 24) & 0xff;
-        outbuf[29] = (unmap_sectors >> 16) & 0xff;
-        outbuf[30] = (unmap_sectors >> 8) & 0xff;
-        outbuf[31] = unmap_sectors & 0xff;
-
-        /* max write same size */
-        outbuf[36] = 0;
-        outbuf[37] = 0;
-        outbuf[38] = 0;
-        outbuf[39] = 0;
-
-        outbuf[40] = (max_io_sectors >> 24) & 0xff;
-        outbuf[41] = (max_io_sectors >> 16) & 0xff;
-        outbuf[42] = (max_io_sectors >> 8) & 0xff;
-        outbuf[43] = max_io_sectors & 0xff;
+        buflen += scsi_emulate_block_limits(outbuf + buflen, &bl);
         break;
     }
     case 0xb1: /* block device characteristics */
diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
index d60c4d0fcf..7237b4162e 100644
--- a/hw/scsi/scsi-generic.c
+++ b/hw/scsi/scsi-generic.c
@@ -16,6 +16,7 @@
 #include "qemu-common.h"
 #include "qemu/error-report.h"
 #include "hw/scsi/scsi.h"
+#include "hw/scsi/emulation.h"
 #include "sysemu/block-backend.h"
 
 #ifdef __linux__
@@ -144,7 +145,7 @@ static int execute_command(BlockBackend *blk,
 
 static void scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s)
 {
-    uint8_t page, page_len;
+    uint8_t page, page_idx;
 
     /*
      *  EVPD set to zero returns the standard INQUIRY data.
@@ -181,7 +182,7 @@ static void scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s)
             /* Also take care of the opt xfer len. */
             stl_be_p(&r->buf[12],
                     MIN_NON_ZERO(max_transfer, ldl_be_p(&r->buf[12])));
-        } else if (page == 0x00 && s->needs_vpd_bl_emulation) {
+        } else if (s->needs_vpd_bl_emulation && page == 0x00) {
             /*
              * Now we're capable of supplying the VPD Block Limits
              * response if the hardware can't. Add it in the INQUIRY
@@ -190,17 +191,43 @@ static void scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s)
              *
              * This way, the guest kernel will be aware of the support
              * and will use it to proper setup the SCSI device.
+             *
+             * VPD page numbers must be sorted, so insert 0xb0 at the
+             * right place with an in-place insert.  After the initialization
+             * part of the for loop is executed, the device response is
+             * at r[0] to r[page_idx - 1].
              */
-            page_len = r->buf[3];
-            r->buf[page_len + 4] = 0xb0;
-            r->buf[3] = ++page_len;
+            for (page_idx = lduw_be_p(r->buf + 2) + 4;
+                 page_idx > 4 && r->buf[page_idx - 1] >= 0xb0;
+                 page_idx--) {
+                if (page_idx < r->buflen) {
+                    r->buf[page_idx] = r->buf[page_idx - 1];
+                }
+            }
+            r->buf[page_idx] = 0xb0;
+            stw_be_p(r->buf + 2, lduw_be_p(r->buf + 2) + 1);
         }
     }
 }
 
-static int scsi_emulate_block_limits(SCSIGenericReq *r)
+static int scsi_generic_emulate_block_limits(SCSIGenericReq *r, SCSIDevice *s)
 {
-    r->buflen = scsi_disk_emulate_vpd_page(&r->req, r->buf);
+    int len;
+    uint8_t buf[64];
+
+    SCSIBlockLimits bl = {
+        .max_io_sectors = blk_get_max_transfer(s->conf.blk) / s->blocksize
+    };
+
+    memset(r->buf, 0, r->buflen);
+    stb_p(buf, s->type);
+    stb_p(buf + 1, 0xb0);
+    len = scsi_emulate_block_limits(buf + 4, &bl);
+    assert(len <= sizeof(buf) - 4);
+    stw_be_p(buf + 2, len);
+
+    memcpy(r->buf, buf, MIN(r->buflen, len + 4));
+
     r->io_header.sb_len_wr = 0;
 
     /*
@@ -219,7 +246,6 @@ static void scsi_read_complete(void * opaque, int ret)
 {
     SCSIGenericReq *r = (SCSIGenericReq *)opaque;
     SCSIDevice *s = r->req.dev;
-    SCSISense sense;
     int len;
 
     assert(r->req.aiocb != NULL);
@@ -242,13 +268,15 @@ static void scsi_read_complete(void * opaque, int ret)
      * resulted in sense error but would need emulation.
      * In this case, emulate a valid VPD response.
      */
-    if (s->needs_vpd_bl_emulation) {
-        int is_vpd_bl = r->req.cmd.buf[0] == INQUIRY &&
-                         r->req.cmd.buf[1] & 0x01 &&
-                         r->req.cmd.buf[2] == 0xb0;
-
-        if (is_vpd_bl && sg_io_sense_from_errno(-ret, &r->io_header, &sense)) {
-            len = scsi_emulate_block_limits(r);
+    if (s->needs_vpd_bl_emulation && ret == 0 &&
+        (r->io_header.driver_status & SG_ERR_DRIVER_SENSE) &&
+        r->req.cmd.buf[0] == INQUIRY &&
+        (r->req.cmd.buf[1] & 0x01) &&
+        r->req.cmd.buf[2] == 0xb0) {
+        SCSISense sense =
+            scsi_parse_sense_buf(r->req.sense, r->io_header.sb_len_wr);
+        if (sense.key == ILLEGAL_REQUEST) {
+            len = scsi_generic_emulate_block_limits(r, s);
             /*
              * No need to let scsi_read_complete go on and handle an
              * INQUIRY VPD BL request we created manually.
@@ -527,7 +555,7 @@ static void scsi_generic_set_vpd_bl_emulation(SCSIDevice *s)
     }
 
     page_len = buf[3];
-    for (i = 4; i < page_len + 4; i++) {
+    for (i = 4; i < MIN(sizeof(buf), page_len + 4); i++) {
         if (buf[i] == 0xb0) {
             s->needs_vpd_bl_emulation = false;
             return;