[Qemu-devel] [PATCH] pci: implement bridge filtering

["Michael S. Tsirkin" <mst@redhat.com>]

Support bridge filtering on top of the memory
API as suggested by Avi Kivity:

Create a memory region for the bridge's address space.  This region is
not directly added to system_memory or its descendants.  Devices under
the bridge see this region as its pci_address_space().  The region is
as large as the entire address space - it does not take into account
any windows.

For each of the three windows (pref, non-pref, vga), create an alias
with the appropriate start and size.  Map the alias into the bridge's
parent's pci_address_space(), as subregions.

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

The below seems to work fine for me so I applied this.
Still need to test bridge filtering, any help with this
appreciated.

 hw/pci.c           |   70 +---------------------------------------
 hw/pci.h           |    2 -
 hw/pci_bridge.c    |   89 +++++++++++++++++++++++++++++++++++++++++++++++++---
 hw/pci_internals.h |    3 ++
 4 files changed, 89 insertions(+), 75 deletions(-)

diff --git a/hw/pci.c b/hw/pci.c
index 57ff7b1..56dfa18 100644
--- a/hw/pci.c
+++ b/hw/pci.c
@@ -889,7 +889,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num,
     r = &pci_dev->io_regions[region_num];
     r->addr = PCI_BAR_UNMAPPED;
     r->size = size;
-    r->filtered_size = size;
     r->type = type;
     r->memory = NULL;
 
@@ -920,41 +919,6 @@ pcibus_t pci_get_bar_addr(PCIDevice *pci_dev, int region_num)
     return pci_dev->io_regions[region_num].addr;
 }
 
-static void pci_bridge_filter(PCIDevice *d, pcibus_t *addr, pcibus_t *size,
-                              uint8_t type)
-{
-    pcibus_t base = *addr;
-    pcibus_t limit = *addr + *size - 1;
-    PCIDevice *br;
-
-    for (br = d->bus->parent_dev; br; br = br->bus->parent_dev) {
-        uint16_t cmd = pci_get_word(d->config + PCI_COMMAND);
-
-        if (type & PCI_BASE_ADDRESS_SPACE_IO) {
-            if (!(cmd & PCI_COMMAND_IO)) {
-                goto no_map;
-            }
-        } else {
-            if (!(cmd & PCI_COMMAND_MEMORY)) {
-                goto no_map;
-            }
-        }
-
-        base = MAX(base, pci_bridge_get_base(br, type));
-        limit = MIN(limit, pci_bridge_get_limit(br, type));
-    }
-
-    if (base > limit) {
-        goto no_map;
-    }
-    *addr = base;
-    *size = limit - base + 1;
-    return;
-no_map:
-    *addr = PCI_BAR_UNMAPPED;
-    *size = 0;
-}
-
 static pcibus_t pci_bar_address(PCIDevice *d,
 				int reg, uint8_t type, pcibus_t size)
 {
@@ -1024,7 +988,7 @@ static void pci_update_mappings(PCIDevice *d)
 {
     PCIIORegion *r;
     int i;
-    pcibus_t new_addr, filtered_size;
+    pcibus_t new_addr;
 
     for(i = 0; i < PCI_NUM_REGIONS; i++) {
         r = &d->io_regions[i];
@@ -1035,14 +999,8 @@ static void pci_update_mappings(PCIDevice *d)
 
         new_addr = pci_bar_address(d, i, r->type, r->size);
 
-        /* bridge filtering */
-        filtered_size = r->size;
-        if (new_addr != PCI_BAR_UNMAPPED) {
-            pci_bridge_filter(d, &new_addr, &filtered_size, r->type);
-        }
-
         /* This bar isn't changed */
-        if (new_addr == r->addr && filtered_size == r->filtered_size)
+        if (new_addr == r->addr)
             continue;
 
         /* now do the real mapping */
@@ -1050,15 +1008,7 @@ static void pci_update_mappings(PCIDevice *d)
             memory_region_del_subregion(r->address_space, r->memory);
         }
         r->addr = new_addr;
-        r->filtered_size = filtered_size;
         if (r->addr != PCI_BAR_UNMAPPED) {
-            /*
-             * TODO: currently almost all the map funcions assumes
-             * filtered_size == size and addr & ~(size - 1) == addr.
-             * However with bridge filtering, they aren't always true.
-             * Teach them such cases, such that filtered_size < size and
-             * addr & (size - 1) != 0.
-             */
             if (r->type & PCI_BASE_ADDRESS_SPACE_IO) {
                 memory_region_add_subregion_overlap(r->address_space,
                                                     r->addr,
@@ -1576,22 +1526,6 @@ PCIDevice *pci_nic_init_nofail(NICInfo *nd, const char *default_model,
     return res;
 }
 
-static void pci_bridge_update_mappings_fn(PCIBus *b, PCIDevice *d)
-{
-    pci_update_mappings(d);
-}
-
-void pci_bridge_update_mappings(PCIBus *b)
-{
-    PCIBus *child;
-
-    pci_for_each_device_under_bus(b, pci_bridge_update_mappings_fn);
-
-    QLIST_FOREACH(child, &b->child, sibling) {
-        pci_bridge_update_mappings(child);
-    }
-}
-
 /* Whether a given bus number is in range of the secondary
  * bus of the given bridge device. */
 static bool pci_secondary_bus_in_range(PCIDevice *dev, int bus_num)
diff --git a/hw/pci.h b/hw/pci.h
index 391217e..65e1568 100644
--- a/hw/pci.h
+++ b/hw/pci.h
@@ -90,7 +90,6 @@ typedef struct PCIIORegion {
     pcibus_t addr; /* current PCI mapping address. -1 means not mapped */
 #define PCI_BAR_UNMAPPED (~(pcibus_t)0)
     pcibus_t size;
-    pcibus_t filtered_size;
     uint8_t type;
     MemoryRegion *memory;
     MemoryRegion *address_space;
@@ -277,7 +276,6 @@ int pci_read_devaddr(Monitor *mon, const char *addr, int *domp, int *busp,
 
 void do_pci_info_print(Monitor *mon, const QObject *data);
 void do_pci_info(Monitor *mon, QObject **ret_data);
-void pci_bridge_update_mappings(PCIBus *b);
 
 void pci_device_deassert_intx(PCIDevice *dev);
 
diff --git a/hw/pci_bridge.c b/hw/pci_bridge.c
index e0b339e..b488f06 100644
--- a/hw/pci_bridge.c
+++ b/hw/pci_bridge.c
@@ -135,6 +135,72 @@ pcibus_t pci_bridge_get_limit(const PCIDevice *bridge, uint8_t type)
     return limit;
 }
 
+static void pci_bridge_init_alias(PCIBridge *bridge, MemoryRegion *alias,
+                                  uint8_t type, const char *name,
+                                  MemoryRegion *space,
+                                  MemoryRegion *parent_space)
+{
+    pcibus_t base = pci_bridge_get_base(&bridge->dev, type);
+    pcibus_t limit = pci_bridge_get_limit(&bridge->dev, type);
+    /* TODO: this doesn't handle base = 0 limit = 2^64 - 1 correctly.
+     * Apparently no way to do this with existing memory APIs. */
+    pcibus_t size = limit >= base ? limit + 1 - base : 0;
+
+    memory_region_init_alias(alias, name, space, base, size);
+    memory_region_add_subregion_overlap(parent_space, base, alias, 1);
+}
+
+static void pci_bridge_cleanup_alias(MemoryRegion *alias,
+                                     MemoryRegion *parent_space)
+{
+    memory_region_del_subregion(parent_space, alias);
+    memory_region_destroy(alias);
+}
+
+static void pci_bridge_region_init(PCIBridge *br)
+{
+    PCIBus *sec_bus = &br->sec_bus;
+    PCIBus *parent = br->dev.bus;
+    pci_bridge_init_alias(br, sec_bus->alias_pref_mem,
+                          PCI_BASE_ADDRESS_MEM_PREFETCH,
+                          "pci_bridge_pref_mem",
+                          sec_bus->address_space_mem,
+                          parent->address_space_mem);
+    pci_bridge_init_alias(br, sec_bus->alias_mem,
+                          PCI_BASE_ADDRESS_SPACE_MEMORY,
+                          "pci_bridge_mem",
+                          sec_bus->address_space_mem,
+                          parent->address_space_mem);
+    pci_bridge_init_alias(br, sec_bus->alias_io,
+                          PCI_BASE_ADDRESS_SPACE_IO,
+                          "pci_bridge_io",
+                          sec_bus->address_space_io,
+                          parent->address_space_io);
+   /* TODO: VGA and VGA palatte snooping support. */
+}
+
+static void pci_bridge_region_cleanup(PCIBridge *br)
+{
+    PCIBus *sec_bus = &br->sec_bus;
+    PCIBus *parent = br->dev.bus;
+    pci_bridge_cleanup_alias(sec_bus->alias_io,
+                             parent->address_space_io);
+    pci_bridge_cleanup_alias(sec_bus->alias_mem,
+                             parent->address_space_mem);
+    pci_bridge_cleanup_alias(sec_bus->alias_pref_mem,
+                             parent->address_space_mem);
+}
+
+static void pci_bridge_update_mappings(PCIBridge *br)
+{
+    /* Make updates atomic to: handle the case of one VCPU updating the bridge
+     * while another accesses an unaffected region. */
+    memory_region_transaction_begin();
+    pci_bridge_region_cleanup(br);
+    pci_bridge_region_init(br);
+    memory_region_transaction_commit();
+}
+
 /* default write_config function for PCI-to-PCI bridge */
 void pci_bridge_write_config(PCIDevice *d,
                              uint32_t address, uint32_t val, int len)
@@ -151,7 +217,7 @@ void pci_bridge_write_config(PCIDevice *d,
         /* memory base/limit, prefetchable base/limit and
            io base/limit upper 16 */
         ranges_overlap(address, len, PCI_MEMORY_BASE, 20)) {
-        pci_bridge_update_mappings(&s->sec_bus);
+        pci_bridge_update_mappings(s);
     }
 
     newctl = pci_get_word(d->config + PCI_BRIDGE_CONTROL);
@@ -246,10 +312,14 @@ int pci_bridge_initfn(PCIDevice *dev)
                         br->bus_name);
     sec_bus->parent_dev = dev;
     sec_bus->map_irq = br->map_irq;
-    /* TODO: use memory API to perform memory filtering. */
-    sec_bus->address_space_mem = parent->address_space_mem;
-    sec_bus->address_space_io = parent->address_space_io;
-
+    sec_bus->address_space_mem = g_new(MemoryRegion, 1);
+    memory_region_init(sec_bus->address_space_mem, "pci_pridge_pci", INT64_MAX);
+    sec_bus->address_space_io = g_new(MemoryRegion, 1);
+    memory_region_init(sec_bus->address_space_io, "pci_bridge_io", 65536);
+    sec_bus->alias_pref_mem = g_new(MemoryRegion, 1);
+    sec_bus->alias_mem = g_new(MemoryRegion, 1);
+    sec_bus->alias_io = g_new(MemoryRegion, 1);
+    pci_bridge_region_init(br);
     QLIST_INIT(&sec_bus->child);
     QLIST_INSERT_HEAD(&parent->child, sec_bus, sibling);
     return 0;
@@ -259,8 +329,17 @@ int pci_bridge_initfn(PCIDevice *dev)
 int pci_bridge_exitfn(PCIDevice *pci_dev)
 {
     PCIBridge *s = DO_UPCAST(PCIBridge, dev, pci_dev);
+    PCIBus *sec_bus = &s->sec_bus;
     assert(QLIST_EMPTY(&s->sec_bus.child));
     QLIST_REMOVE(&s->sec_bus, sibling);
+    pci_bridge_region_cleanup(s);
+    g_free(sec_bus->alias_pref_mem);
+    g_free(sec_bus->alias_mem);
+    g_free(sec_bus->alias_io);
+    memory_region_destroy(sec_bus->address_space_mem);
+    g_free(sec_bus->address_space_mem);
+    memory_region_destroy(sec_bus->address_space_io);
+    g_free(sec_bus->address_space_io);
     /* qbus_free() is called automatically by qdev_free() */
     return 0;
 }
diff --git a/hw/pci_internals.h b/hw/pci_internals.h
index c7fd23d..578c8d2 100644
--- a/hw/pci_internals.h
+++ b/hw/pci_internals.h
@@ -27,6 +27,9 @@ struct PCIBus {
     target_phys_addr_t mem_base;
     MemoryRegion *address_space_mem;
     MemoryRegion *address_space_io;
+    MemoryRegion *alias_pref_mem;
+    MemoryRegion *alias_mem;
+    MemoryRegion *alias_io;
 
     QLIST_HEAD(, PCIBus) child; /* this will be replaced by qdev later */
     QLIST_ENTRY(PCIBus) sibling;/* this will be replaced by qdev later */
-- 
1.7.5.53.gc233e