Merge tag 'v2.5.0' into tizen_3.0_qemu_2.5

v2.5.0 release

Signed-off-by: SeokYeon Hwang <syeon.hwang@samsung.com>

7 files changed, 113 insertions, 47 deletions

diff --git a/hw/pci/msi.c b/hw/pci/msi.c
index f9c0484420..c1dd5318c8 100644
--- a/hw/pci/msi.c
+++ b/hw/pci/msi.c
@@ -294,7 +294,7 @@ void msi_send_message(PCIDevice *dev, MSIMessage msg)
 {
     MemTxAttrs attrs = {};
 
-    attrs.stream_id = (pci_bus_num(dev->bus) << 8) | dev->devfn;
+    attrs.requester_id = pci_requester_id(dev);
     address_space_stl_le(&dev->bus_master_as, msg.address, msg.data,
                          attrs, NULL);
 }
diff --git a/hw/pci/msix.c b/hw/pci/msix.c
index 7716bf3649..64c93d83d6 100644
--- a/hw/pci/msix.c
+++ b/hw/pci/msix.c
@@ -200,8 +200,14 @@ static uint64_t msix_pba_mmio_read(void *opaque, hwaddr addr,
     return pci_get_long(dev->msix_pba + addr);
 }
 
+static void msix_pba_mmio_write(void *opaque, hwaddr addr,
+                                uint64_t val, unsigned size)
+{
+}
+
 static const MemoryRegionOps msix_pba_mmio_ops = {
     .read = msix_pba_mmio_read,
+    .write = msix_pba_mmio_write,
     .endianness = DEVICE_LITTLE_ENDIAN,
     .valid = {
         .min_access_size = 4,
@@ -314,9 +320,7 @@ int msix_init_exclusive_bar(PCIDevice *dev, unsigned short nentries,
         bar_size = bar_pba_offset + bar_pba_size;
     }
 
-    if (bar_size & (bar_size - 1)) {
-        bar_size = 1 << qemu_fls(bar_size);
-    }
+    bar_size = pow2ceil(bar_size);
 
     name = g_strdup_printf("%s-msix", dev->name);
     memory_region_init(&dev->msix_exclusive_bar, OBJECT(dev), name, bar_size);
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 8b41042393..7ef7b6d988 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -38,6 +38,7 @@
 #include "hw/pci/msix.h"
 #include "exec/address-spaces.h"
 #include "hw/hotplug.h"
+#include "hw/boards.h"
 
 //#define DEBUG_PCI
 #ifdef DEBUG_PCI
@@ -846,6 +847,9 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, PCIBus *bus,
     PCIConfigWriteFunc *config_write = pc->config_write;
     Error *local_err = NULL;
     AddressSpace *dma_as;
+    DeviceState *dev = DEVICE(pci_dev);
+
+    pci_dev->bus = bus;
 
     if (devfn < 0) {
         for(devfn = bus->devfn_min ; devfn < ARRAY_SIZE(bus->devices);
@@ -863,9 +867,17 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, PCIBus *bus,
                    PCI_SLOT(devfn), PCI_FUNC(devfn), name,
                    bus->devices[devfn]->name);
         return NULL;
+    } else if (dev->hotplugged &&
+               pci_get_function_0(pci_dev)) {
+        error_setg(errp, "PCI: slot %d function 0 already ocuppied by %s,"
+                   " new func %s cannot be exposed to guest.",
+                   PCI_SLOT(devfn),
+                   bus->devices[PCI_DEVFN(PCI_SLOT(devfn), 0)]->name,
+                   name);
+
+       return NULL;
     }
 
-    pci_dev->bus = bus;
     pci_dev->devfn = devfn;
     dma_as = pci_device_iommu_address_space(pci_dev);
 
@@ -1065,6 +1077,10 @@ static pcibus_t pci_bar_address(PCIDevice *d,
     pcibus_t new_addr, last_addr;
     int bar = pci_bar(d, reg);
     uint16_t cmd = pci_get_word(d->config + PCI_COMMAND);
+    Object *machine = qdev_get_machine();
+    ObjectClass *oc = object_get_class(machine);
+    MachineClass *mc = MACHINE_CLASS(oc);
+    bool allow_0_address = mc->pci_allow_0_address;
 
     if (type & PCI_BASE_ADDRESS_SPACE_IO) {
         if (!(cmd & PCI_COMMAND_IO)) {
@@ -1075,7 +1091,8 @@ static pcibus_t pci_bar_address(PCIDevice *d,
         /* Check if 32 bit BAR wraps around explicitly.
          * TODO: make priorities correct and remove this work around.
          */
-        if (last_addr <= new_addr || new_addr == 0 || last_addr >= UINT32_MAX) {
+        if (last_addr <= new_addr || last_addr >= UINT32_MAX ||
+            (!allow_0_address && new_addr == 0)) {
             return PCI_BAR_UNMAPPED;
         }
         return new_addr;
@@ -1099,8 +1116,8 @@ static pcibus_t pci_bar_address(PCIDevice *d,
     /* XXX: as we cannot support really dynamic
        mappings, we handle specific values as invalid
        mappings. */
-    if (last_addr <= new_addr || new_addr == 0 ||
-        last_addr == PCI_BAR_UNMAPPED) {
+    if (last_addr <= new_addr || last_addr == PCI_BAR_UNMAPPED ||
+        (!allow_0_address && new_addr == 0)) {
         return PCI_BAR_UNMAPPED;
     }
 
@@ -1148,16 +1165,16 @@ static void pci_update_mappings(PCIDevice *d)
         /* now do the real mapping */
         if (r->addr != PCI_BAR_UNMAPPED) {
             trace_pci_update_mappings_del(d, pci_bus_num(d->bus),
-                                          PCI_FUNC(d->devfn),
                                           PCI_SLOT(d->devfn),
+                                          PCI_FUNC(d->devfn),
                                           i, r->addr, r->size);
             memory_region_del_subregion(r->address_space, r->memory);
         }
         r->addr = new_addr;
         if (r->addr != PCI_BAR_UNMAPPED) {
             trace_pci_update_mappings_add(d, pci_bus_num(d->bus),
-                                          PCI_FUNC(d->devfn),
                                           PCI_SLOT(d->devfn),
+                                          PCI_FUNC(d->devfn),
                                           i, r->addr, r->size);
             memory_region_add_subregion_overlap(r->address_space,
                                                 r->addr, r->memory, 1);
@@ -2065,9 +2082,7 @@ static void pci_add_option_rom(PCIDevice *pdev, bool is_default_rom,
         g_free(path);
         return;
     }
-    if (size & (size - 1)) {
-        size = 1 << qemu_fls(size);
-    }
+    size = pow2ceil(size);
 
     vmsd = qdev_get_vmsd(DEVICE(pdev));
 
@@ -2077,7 +2092,7 @@ static void pci_add_option_rom(PCIDevice *pdev, bool is_default_rom,
         snprintf(name, sizeof(name), "%s.rom", object_get_typename(OBJECT(pdev)));
     }
     pdev->has_rom = true;
-    memory_region_init_ram(&pdev->rom, OBJECT(pdev), name, size, &error_abort);
+    memory_region_init_ram(&pdev->rom, OBJECT(pdev), name, size, &error_fatal);
     vmstate_register_ram(&pdev->rom, &pdev->qdev);
     ptr = memory_region_get_ram_ptr(&pdev->rom);
     load_image(path, ptr);
@@ -2383,17 +2398,14 @@ static void pci_device_class_init(ObjectClass *klass, void *data)
 AddressSpace *pci_device_iommu_address_space(PCIDevice *dev)
 {
     PCIBus *bus = PCI_BUS(dev->bus);
+    PCIBus *iommu_bus = bus;
 
-    if (bus->iommu_fn) {
-        return bus->iommu_fn(bus, bus->iommu_opaque, dev->devfn);
+    while(iommu_bus && !iommu_bus->iommu_fn && iommu_bus->parent_dev) {
+        iommu_bus = PCI_BUS(iommu_bus->parent_dev->bus);
     }
-
-    if (bus->parent_dev) {
-        /** We are ignoring the bus master DMA bit of the bridge
-         *  as it would complicate things such as VFIO for no good reason */
-        return pci_device_iommu_address_space(bus->parent_dev);
+    if (iommu_bus && iommu_bus->iommu_fn) {
+        return iommu_bus->iommu_fn(bus, iommu_bus->iommu_opaque, dev->devfn);
     }
-
     return &address_space_memory;
 }
 
@@ -2457,6 +2469,33 @@ void pci_bus_get_w64_range(PCIBus *bus, Range *range)
     pci_for_each_device_under_bus(bus, pci_dev_get_w64, range);
 }
 
+static bool pcie_has_upstream_port(PCIDevice *dev)
+{
+    PCIDevice *parent_dev = pci_bridge_get_device(dev->bus);
+
+    /* Device associated with an upstream port.
+     * As there are several types of these, it's easier to check the
+     * parent device: upstream ports are always connected to
+     * root or downstream ports.
+     */
+    return parent_dev &&
+        pci_is_express(parent_dev) &&
+        parent_dev->exp.exp_cap &&
+        (pcie_cap_get_type(parent_dev) == PCI_EXP_TYPE_ROOT_PORT ||
+         pcie_cap_get_type(parent_dev) == PCI_EXP_TYPE_DOWNSTREAM);
+}
+
+PCIDevice *pci_get_function_0(PCIDevice *pci_dev)
+{
+    if(pcie_has_upstream_port(pci_dev)) {
+        /* With an upstream PCIe port, we only support 1 device at slot 0 */
+        return pci_dev->bus->devices[0];
+    } else {
+        /* Other bus types might support multiple devices at slots 0-31 */
+        return pci_dev->bus->devices[PCI_DEVFN(PCI_SLOT(pci_dev->devfn), 0)];
+    }
+}
+
 static const TypeInfo pci_device_type_info = {
     .name = TYPE_PCI_DEVICE,
     .parent = TYPE_DEVICE,
diff --git a/hw/pci/pci_host.c b/hw/pci/pci_host.c
index 3e26f9256c..49f59a5dbc 100644
--- a/hw/pci/pci_host.c
+++ b/hw/pci/pci_host.c
@@ -20,6 +20,7 @@
 
 #include "hw/pci/pci.h"
 #include "hw/pci/pci_host.h"
+#include "hw/pci/pci_bus.h"
 #include "trace.h"
 
 /* debug PCI */
@@ -52,6 +53,13 @@ void pci_host_config_write_common(PCIDevice *pci_dev, uint32_t addr,
                                   uint32_t limit, uint32_t val, uint32_t len)
 {
     assert(len <= 4);
+    /* non-zero functions are only exposed when function 0 is present,
+     * allowing direct removal of unexposed functions.
+     */
+    if (pci_dev->qdev.hotplugged && !pci_get_function_0(pci_dev)) {
+        return;
+    }
+
     trace_pci_cfg_write(pci_dev->name, PCI_SLOT(pci_dev->devfn),
                         PCI_FUNC(pci_dev->devfn), addr, val);
     pci_dev->config_write(pci_dev, addr, val, MIN(len, limit - addr));
@@ -63,6 +71,13 @@ uint32_t pci_host_config_read_common(PCIDevice *pci_dev, uint32_t addr,
     uint32_t ret;
 
     assert(len <= 4);
+    /* non-zero functions are only exposed when function 0 is present,
+     * allowing direct removal of unexposed functions.
+     */
+    if (pci_dev->qdev.hotplugged && !pci_get_function_0(pci_dev)) {
+        return ~0x0;
+    }
+
     ret = pci_dev->config_read(pci_dev, addr, MIN(len, limit - addr));
     trace_pci_cfg_read(pci_dev->name, PCI_SLOT(pci_dev->devfn),
                        PCI_FUNC(pci_dev->devfn), addr, ret);
diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
index 6e28985bd1..0eab29d534 100644
--- a/hw/pci/pcie.c
+++ b/hw/pci/pcie.c
@@ -249,25 +249,43 @@ void pcie_cap_slot_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
         return;
     }
 
-    /* TODO: multifunction hot-plug.
-     * Right now, only a device of function = 0 is allowed to be
-     * hot plugged/unplugged.
+    /* To enable multifunction hot-plug, we just ensure the function
+     * 0 added last. When function 0 is added, we set the sltsta and
+     * inform OS via event notification.
      */
-    assert(PCI_FUNC(pci_dev->devfn) == 0);
+    if (pci_get_function_0(pci_dev)) {
+        pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
+                                   PCI_EXP_SLTSTA_PDS);
+        pcie_cap_slot_event(PCI_DEVICE(hotplug_dev),
+                            PCI_EXP_HP_EV_PDC | PCI_EXP_HP_EV_ABP);
+    }
+}
 
-    pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
-                               PCI_EXP_SLTSTA_PDS);
-    pcie_cap_slot_event(PCI_DEVICE(hotplug_dev),
-                        PCI_EXP_HP_EV_PDC | PCI_EXP_HP_EV_ABP);
+static void pcie_unplug_device(PCIBus *bus, PCIDevice *dev, void *opaque)
+{
+    object_unparent(OBJECT(dev));
 }
 
 void pcie_cap_slot_hot_unplug_request_cb(HotplugHandler *hotplug_dev,
                                          DeviceState *dev, Error **errp)
 {
     uint8_t *exp_cap;
+    PCIDevice *pci_dev = PCI_DEVICE(dev);
+    PCIBus *bus = pci_dev->bus;
 
     pcie_cap_slot_hotplug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp);
 
+    /* In case user cancel the operation of multi-function hot-add,
+     * remove the function that is unexposed to guest individually,
+     * without interaction with guest.
+     */
+    if (pci_dev->devfn &&
+        !bus->devices[0]) {
+        pcie_unplug_device(bus, pci_dev, NULL);
+
+        return;
+    }
+
     pcie_cap_slot_push_attention_button(PCI_DEVICE(hotplug_dev));
 }
 
@@ -378,11 +396,6 @@ void pcie_cap_slot_reset(PCIDevice *dev)
     hotplug_event_update_event_status(dev);
 }
 
-static void pcie_unplug_device(PCIBus *bus, PCIDevice *dev, void *opaque)
-{
-    object_unparent(OBJECT(dev));
-}
-
 void pcie_cap_slot_write_config(PCIDevice *dev,
                                 uint32_t addr, uint32_t val, int len)
 {
@@ -413,13 +426,13 @@ void pcie_cap_slot_write_config(PCIDevice *dev,
      */
     if ((sltsta & PCI_EXP_SLTSTA_PDS) && (val & PCI_EXP_SLTCTL_PCC) &&
         ((val & PCI_EXP_SLTCTL_PIC_OFF) == PCI_EXP_SLTCTL_PIC_OFF)) {
-            PCIBus *sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(dev));
-            pci_for_each_device(sec_bus, pci_bus_num(sec_bus),
-                                pcie_unplug_device, NULL);
+        PCIBus *sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(dev));
+        pci_for_each_device(sec_bus, pci_bus_num(sec_bus),
+                            pcie_unplug_device, NULL);
 
-            pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTSTA,
-                                         PCI_EXP_SLTSTA_PDS);
-            pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
+        pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTSTA,
+                                     PCI_EXP_SLTSTA_PDS);
+        pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
                                        PCI_EXP_SLTSTA_PDC);
     }
 
diff --git a/hw/pci/pcie_aer.c b/hw/pci/pcie_aer.c
index f1847ac210..98d2c183b0 100644
--- a/hw/pci/pcie_aer.c
+++ b/hw/pci/pcie_aer.c
@@ -827,10 +827,6 @@ typedef struct PCIEAERErrorName {
  */
 static const struct PCIEAERErrorName pcie_aer_error_list[] = {
     {
-        .name = "TRAIN",
-        .val = PCI_ERR_UNC_TRAIN,
-        .correctable = false,
-    }, {
         .name = "DLP",
         .val = PCI_ERR_UNC_DLP,
         .correctable = false,
@@ -983,7 +979,7 @@ static int do_pcie_aer_inject_error(Monitor *mon,
         }
     }
     err.status = error_status;
-    err.source_id = (pci_bus_num(dev->bus) << 8) | dev->devfn;
+    err.source_id = pci_requester_id(dev);
 
     err.flags = 0;
     if (correctable) {
diff --git a/hw/pci/shpc.c b/hw/pci/shpc.c
index bfb4d31b62..d34fdf3ecb 100644
--- a/hw/pci/shpc.c
+++ b/hw/pci/shpc.c
@@ -1,5 +1,4 @@
 #include "qemu-common.h"
-#include <strings.h>
 #include <stdint.h>
 #include "qemu/range.h"
 #include "qemu/error-report.h"