Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-2.7-20160527' into staging

ppc patch queue for 2016-05-27 (first pull for qemu-2.7)

I'm back from holidays now, and have re-collated the ppc patch queue.
This is a first pull request against the qemu-2.7 branch, mostly
consisting of patches which were posted before the 2.6 freeze, but
weren't suitable for late inclusion in the 2.6 branch.

 * Assorted bugfixes and cleanups
 * Some preliminary patches towards dynamic DMA windows and CPU hotplug
 * Significant performance impovement for the spapr-llan device
 * Added myself to MAINTAINERS for ppc (overdue)

# gpg: Signature made Fri 27 May 2016 04:04:15 BST using RSA key ID 20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>"
# gpg:                 aka "David Gibson (Red Hat) <dgibson@redhat.com>"
# gpg:                 aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E  87DC 6C38 CACA 20D9 B392

* remotes/dgibson/tags/ppc-for-2.7-20160527:
  MAINTAINERS: Add David Gibson as ppc maintainer
  spapr_iommu: Move table allocation to helpers
  spapr_iommu: Finish renaming vfio_accel to need_vfio
  spapr_pci: Use correct DMA LIOBN when composing the device tree
  spapr: ensure device trees are always associated with DRC
  PPC/KVM: early validation of vcpu id
  Added negative check for get_image_size()
  hw/net/spapr_llan: Provide counter with dropped rx frames to the guest
  hw/net/spapr_llan: Delay flushing of the RX queue while adding new RX buffers
  target-ppc: Cleanups to rldinm, rldnm, rldimi
  target-ppc: Use 32-bit rotate instead of deposit + 64-bit rotate
  target-ppc: Use movcond in isel
  target-ppc: Correct KVM synchronization for ppc_hash64_set_external_hpt()

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

4 files changed, 97 insertions, 40 deletions

diff --git a/hw/net/spapr_llan.c b/hw/net/spapr_llan.c
index a8266f8..8b2eebd 100644
--- a/hw/net/spapr_llan.c
+++ b/hw/net/spapr_llan.c
@@ -110,6 +110,7 @@ typedef struct VIOsPAPRVLANDevice {
     hwaddr buf_list;
     uint32_t add_buf_ptr, use_buf_ptr, rx_bufs;
     hwaddr rxq_ptr;
+    QEMUTimer *rxp_timer;
     uint32_t compat_flags;             /* Compatability flags for migration */
     RxBufPool *rx_pool[RX_MAX_POOLS];  /* Receive buffer descriptor pools */
 } VIOsPAPRVLANDevice;
@@ -122,6 +123,21 @@ static int spapr_vlan_can_receive(NetClientState *nc)
 }
 
 /**
+ * The last 8 bytes of the receive buffer list page (that has been
+ * supplied by the guest with the H_REGISTER_LOGICAL_LAN call) contain
+ * a counter for frames that have been dropped because there was no
+ * suitable receive buffer available. This function is used to increase
+ * this counter by one.
+ */
+static void spapr_vlan_record_dropped_rx_frame(VIOsPAPRVLANDevice *dev)
+{
+    uint64_t cnt;
+
+    cnt = vio_ldq(&dev->sdev, dev->buf_list + 4096 - 8);
+    vio_stq(&dev->sdev, dev->buf_list + 4096 - 8, cnt + 1);
+}
+
+/**
  * Get buffer descriptor from one of our receive buffer pools
  */
 static vlan_bd_t spapr_vlan_get_rx_bd_from_pool(VIOsPAPRVLANDevice *dev,
@@ -206,7 +222,8 @@ static ssize_t spapr_vlan_receive(NetClientState *nc, const uint8_t *buf,
     }
 
     if (!dev->rx_bufs) {
-        return -1;
+        spapr_vlan_record_dropped_rx_frame(dev);
+        return 0;
     }
 
     if (dev->compat_flags & SPAPRVLAN_FLAG_RX_BUF_POOLS) {
@@ -215,7 +232,8 @@ static ssize_t spapr_vlan_receive(NetClientState *nc, const uint8_t *buf,
         bd = spapr_vlan_get_rx_bd_from_page(dev, size);
     }
     if (!bd) {
-        return -1;
+        spapr_vlan_record_dropped_rx_frame(dev);
+        return 0;
     }
 
     dev->rx_bufs--;
@@ -266,6 +284,13 @@ static NetClientInfo net_spapr_vlan_info = {
     .receive = spapr_vlan_receive,
 };
 
+static void spapr_vlan_flush_rx_queue(void *opaque)
+{
+    VIOsPAPRVLANDevice *dev = opaque;
+
+    qemu_flush_queued_packets(qemu_get_queue(dev->nic));
+}
+
 static void spapr_vlan_reset_rx_pool(RxBufPool *rxp)
 {
     /*
@@ -302,6 +327,9 @@ static void spapr_vlan_realize(VIOsPAPRDevice *sdev, Error **errp)
     dev->nic = qemu_new_nic(&net_spapr_vlan_info, &dev->nicconf,
                             object_get_typename(OBJECT(sdev)), sdev->qdev.id, dev);
     qemu_format_nic_info_str(qemu_get_queue(dev->nic), dev->nicconf.macaddr.a);
+
+    dev->rxp_timer = timer_new_us(QEMU_CLOCK_VIRTUAL, spapr_vlan_flush_rx_queue,
+                                  dev);
 }
 
 static void spapr_vlan_instance_init(Object *obj)
@@ -332,6 +360,11 @@ static void spapr_vlan_instance_finalize(Object *obj)
             dev->rx_pool[i] = NULL;
         }
     }
+
+    if (dev->rxp_timer) {
+        timer_del(dev->rxp_timer);
+        timer_free(dev->rxp_timer);
+    }
 }
 
 void spapr_vlan_create(VIOsPAPRBus *bus, NICInfo *nd)
@@ -629,7 +662,13 @@ static target_ulong h_add_logical_lan_buffer(PowerPCCPU *cpu,
 
     dev->rx_bufs++;
 
-    qemu_flush_queued_packets(qemu_get_queue(dev->nic));
+    /*
+     * Give guest some more time to add additional RX buffers before we
+     * flush the receive queue, so that e.g. fragmented IP packets can
+     * be passed to the guest in one go later (instead of passing single
+     * fragments if there is only one receive buffer available).
+     */
+    timer_mod(dev->rxp_timer, qemu_clock_get_us(QEMU_CLOCK_VIRTUAL) + 500);
 
     return H_SUCCESS;
 }
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index add68ac..44e401a 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1842,6 +1842,10 @@ static void ppc_spapr_init(MachineState *machine)
         exit(1);
     }
     spapr->rtas_size = get_image_size(filename);
+    if (spapr->rtas_size < 0) {
+        error_report("Could not get size of LPAR rtas '%s'", filename);
+        exit(1);
+    }
     spapr->rtas_blob = g_malloc(spapr->rtas_size);
     if (load_image_size(filename, spapr->rtas_blob, spapr->rtas_size) < 0) {
         error_report("Could not load LPAR rtas '%s'", filename);
@@ -2132,15 +2136,6 @@ static void spapr_add_lmbs(DeviceState *dev, uint64_t addr, uint64_t size,
     int i, fdt_offset, fdt_size;
     void *fdt;
 
-    /*
-     * Check for DRC connectors and send hotplug notification to the
-     * guest only in case of hotplugged memory. This allows cold plugged
-     * memory to be specified at boot time.
-     */
-    if (!dev->hotplugged) {
-        return;
-    }
-
     for (i = 0; i < nr_lmbs; i++) {
         drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB,
                 addr/SPAPR_MEMORY_BLOCK_SIZE);
@@ -2154,7 +2149,12 @@ static void spapr_add_lmbs(DeviceState *dev, uint64_t addr, uint64_t size,
         drck->attach(drc, dev, fdt, fdt_offset, !dev->hotplugged, errp);
         addr += SPAPR_MEMORY_BLOCK_SIZE;
     }
-    spapr_hotplug_req_add_by_count(SPAPR_DR_CONNECTOR_TYPE_LMB, nr_lmbs);
+    /* send hotplug notification to the
+     * guest only in case of hotplugged memory
+     */
+    if (dev->hotplugged) {
+       spapr_hotplug_req_add_by_count(SPAPR_DR_CONNECTOR_TYPE_LMB, nr_lmbs);
+    }
 }
 
 static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
index b6fe1dd..96bb018 100644
--- a/hw/ppc/spapr_iommu.c
+++ b/hw/ppc/spapr_iommu.c
@@ -76,6 +76,37 @@ static IOMMUAccessFlags spapr_tce_iommu_access_flags(uint64_t tce)
     }
 }
 
+static uint64_t *spapr_tce_alloc_table(uint32_t liobn,
+                                       uint32_t page_shift,
+                                       uint32_t nb_table,
+                                       int *fd,
+                                       bool need_vfio)
+{
+    uint64_t *table = NULL;
+    uint64_t window_size = (uint64_t)nb_table << page_shift;
+
+    if (kvm_enabled() && !(window_size >> 32)) {
+        table = kvmppc_create_spapr_tce(liobn, window_size, fd, need_vfio);
+    }
+
+    if (!table) {
+        *fd = -1;
+        table = g_malloc0(nb_table * sizeof(uint64_t));
+    }
+
+    trace_spapr_iommu_new_table(liobn, table, *fd);
+
+    return table;
+}
+
+static void spapr_tce_free_table(uint64_t *table, int fd, uint32_t nb_table)
+{
+    if (!kvm_enabled() ||
+        (kvmppc_remove_spapr_tce(table, fd, nb_table) != 0)) {
+        g_free(table);
+    }
+}
+
 /* Called from RCU critical section */
 static IOMMUTLBEntry spapr_tce_translate_iommu(MemoryRegion *iommu, hwaddr addr,
                                                bool is_write)
@@ -142,21 +173,13 @@ static MemoryRegionIOMMUOps spapr_iommu_ops = {
 static int spapr_tce_table_realize(DeviceState *dev)
 {
     sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev);
-    uint64_t window_size = (uint64_t)tcet->nb_table << tcet->page_shift;
-
-    if (kvm_enabled() && !(window_size >> 32)) {
-        tcet->table = kvmppc_create_spapr_tce(tcet->liobn,
-                                              window_size,
-                                              &tcet->fd,
-                                              tcet->need_vfio);
-    }
 
-    if (!tcet->table) {
-        size_t table_size = tcet->nb_table * sizeof(uint64_t);
-        tcet->table = g_malloc0(table_size);
-    }
-
-    trace_spapr_iommu_new_table(tcet->liobn, tcet, tcet->table, tcet->fd);
+    tcet->fd = -1;
+    tcet->table = spapr_tce_alloc_table(tcet->liobn,
+                                        tcet->page_shift,
+                                        tcet->nb_table,
+                                        &tcet->fd,
+                                        tcet->need_vfio);
 
     memory_region_init_iommu(&tcet->iommu, OBJECT(dev), &spapr_iommu_ops,
                              "iommu-spapr",
@@ -242,11 +265,8 @@ static void spapr_tce_table_unrealize(DeviceState *dev, Error **errp)
 
     QLIST_REMOVE(tcet, list);
 
-    if (!kvm_enabled() ||
-        (kvmppc_remove_spapr_tce(tcet->table, tcet->fd,
-                                 tcet->nb_table) != 0)) {
-        g_free(tcet->table);
-    }
+    spapr_tce_free_table(tcet->table, tcet->fd, tcet->nb_table);
+    tcet->fd = -1;
 }
 
 MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet)
diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
index e55b505..856aec7 100644
--- a/hw/ppc/spapr_pci.c
+++ b/hw/ppc/spapr_pci.c
@@ -1093,13 +1093,11 @@ static void spapr_phb_add_pci_device(sPAPRDRConnector *drc,
         spapr_tce_set_need_vfio(tcet, true);
     }
 
-    if (dev->hotplugged) {
-        fdt = create_device_tree(&fdt_size);
-        fdt_start_offset = spapr_create_pci_child_dt(phb, pdev, fdt, 0);
-        if (!fdt_start_offset) {
-            error_setg(errp, "Failed to create pci child device tree node");
-            goto out;
-        }
+    fdt = create_device_tree(&fdt_size);
+    fdt_start_offset = spapr_create_pci_child_dt(phb, pdev, fdt, 0);
+    if (!fdt_start_offset) {
+        error_setg(errp, "Failed to create pci child device tree node");
+        goto out;
     }
 
     drck->attach(drc, DEVICE(pdev),
@@ -1816,7 +1814,7 @@ int spapr_populate_pci_dt(sPAPRPHBState *phb,
     _FDT(fdt_setprop(fdt, bus_off, "interrupt-map", &interrupt_map,
                      sizeof(interrupt_map)));
 
-    tcet = spapr_tce_find_by_liobn(SPAPR_PCI_LIOBN(phb->index, 0));
+    tcet = spapr_tce_find_by_liobn(phb->dma_liobn);
     if (!tcet) {
         return -1;
     }