Merge remote-tracking branch 'qemu-kvm/memory/core' into staging

* qemu-kvm/memory/core: (30 commits)
  memory: allow phys_map tree paths to terminate early
  memory: unify PhysPageEntry::node and ::leaf
  memory: change phys_page_set() to set multiple pages
  memory: switch phys_page_set() to a recursive implementation
  memory: replace phys_page_find_alloc() with phys_page_set()
  memory: simplify multipage/subpage registration
  memory: give phys_page_find() its own tree search loop
  memory: make phys_page_find() return a MemoryRegionSection
  memory: move tlb flush to MemoryListener commit callback
  memory: unify the two branches of cpu_register_physical_memory_log()
  memory: fix RAM subpages in newly initialized pages
  memory: compress phys_map node pointers to 16 bits
  memory: store MemoryRegionSection pointers in phys_map
  memory: unify phys_map last level with intermediate levels
  memory: remove first level of l1_phys_map
  memory: change memory registration to rebuild the memory map on each change
  memory: support stateless memory listeners
  memory: split memory listener for the two address spaces
  xen: ignore I/O memory regions
  memory: allow MemoryListeners to observe a specific address space
  ...

exec-obsolete.h

@@ -37,7 +37,7 @@ void cpu_unregister_io_memory(int table_address);
 
 struct MemoryRegionSection;
 void cpu_register_physical_memory_log(struct MemoryRegionSection *section,
-                                      bool readable, bool readonly);
+                                      bool readonly);
 
 void qemu_register_coalesced_mmio(target_phys_addr_t addr, ram_addr_t size);
 void qemu_unregister_coalesced_mmio(target_phys_addr_t addr, ram_addr_t size);
@@ -121,6 +121,9 @@ static inline void cpu_physical_memory_mask_dirty_range(ram_addr_t start,
 
 void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
                                      int dirty_flags);
+
+extern const IORangeOps memory_region_iorange_ops;
+
 #endif
 
 #endif

hw/vhost.c

@@ -436,6 +436,14 @@ static bool vhost_section(MemoryRegionSection *section)
         && memory_region_is_ram(section->mr);
 }
 
+static void vhost_begin(MemoryListener *listener)
+{
+}
+
+static void vhost_commit(MemoryListener *listener)
+{
+}
+
 static void vhost_region_add(MemoryListener *listener,
                              MemoryRegionSection *section)
 {
@@ -476,6 +484,11 @@ static void vhost_region_del(MemoryListener *listener,
     }
 }
 
+static void vhost_region_nop(MemoryListener *listener,
+                             MemoryRegionSection *section)
+{
+}
+
 static int vhost_virtqueue_set_addr(struct vhost_dev *dev,
                                     struct vhost_virtqueue *vq,
                                     unsigned idx, bool enable_log)
@@ -720,6 +733,18 @@ static void vhost_virtqueue_cleanup(struct vhost_dev *dev,
                               0, virtio_queue_get_desc_size(vdev, idx));
 }
 
+static void vhost_eventfd_add(MemoryListener *listener,
+                              MemoryRegionSection *section,
+                              bool match_data, uint64_t data, int fd)
+{
+}
+
+static void vhost_eventfd_del(MemoryListener *listener,
+                              MemoryRegionSection *section,
+                              bool match_data, uint64_t data, int fd)
+{
+}
+
 int vhost_dev_init(struct vhost_dev *hdev, int devfd, bool force)
 {
     uint64_t features;
@@ -744,13 +769,19 @@ int vhost_dev_init(struct vhost_dev *hdev, int devfd, bool force)
     hdev->features = features;
 
     hdev->memory_listener = (MemoryListener) {
+        .begin = vhost_begin,
+        .commit = vhost_commit,
         .region_add = vhost_region_add,
         .region_del = vhost_region_del,
+        .region_nop = vhost_region_nop,
         .log_start = vhost_log_start,
         .log_stop = vhost_log_stop,
         .log_sync = vhost_log_sync,
         .log_global_start = vhost_log_global_start,
         .log_global_stop = vhost_log_global_stop,
+        .eventfd_add = vhost_eventfd_add,
+        .eventfd_del = vhost_eventfd_del,
+        .priority = 10
     };
     hdev->mem = g_malloc0(offsetof(struct vhost_memory, regions));
     hdev->n_mem_sections = 0;
@@ -759,7 +790,7 @@ int vhost_dev_init(struct vhost_dev *hdev, int devfd, bool force)
     hdev->log_size = 0;
     hdev->log_enabled = false;
     hdev->started = false;
-    memory_listener_register(&hdev->memory_listener);
+    memory_listener_register(&hdev->memory_listener, NULL);
     hdev->force = force;
     return 0;
 fail:

ioport.c

@@ -328,6 +328,7 @@ void portio_list_init(PortioList *piolist,
     piolist->ports = callbacks;
     piolist->nr = 0;
     piolist->regions = g_new0(MemoryRegion *, n);
+    piolist->aliases = g_new0(MemoryRegion *, n);
     piolist->address_space = NULL;
     piolist->opaque = opaque;
     piolist->name = name;
@@ -336,6 +337,7 @@ void portio_list_init(PortioList *piolist,
 void portio_list_destroy(PortioList *piolist)
 {
     g_free(piolist->regions);
+    g_free(piolist->aliases);
 }
 
 static void portio_list_add_1(PortioList *piolist,
@@ -345,7 +347,7 @@ static void portio_list_add_1(PortioList *piolist,
 {
     MemoryRegionPortio *pio;
     MemoryRegionOps *ops;
-    MemoryRegion *region;
+    MemoryRegion *region, *alias;
     unsigned i;
 
     /* Copy the sub-list and null-terminate it.  */
@@ -362,12 +364,20 @@ static void portio_list_add_1(PortioList *piolist,
     ops->old_portio = pio;
 
     region = g_new(MemoryRegion, 1);
+    alias = g_new(MemoryRegion, 1);
+    /*
+     * Use an alias so that the callback is called with an absolute address,
+     * rather than an offset relative to to start + off_low.
+     */
     memory_region_init_io(region, ops, piolist->opaque, piolist->name,
-                          off_high - off_low);
-    memory_region_set_offset(region, start + off_low);
+                          UINT64_MAX);
+    memory_region_init_alias(alias, piolist->name,
+                             region, start + off_low, off_high - off_low);
     memory_region_add_subregion(piolist->address_space,
-                                start + off_low, region);
-    piolist->regions[piolist->nr++] = region;
+                                start + off_low, alias);
+    piolist->regions[piolist->nr] = region;
+    piolist->aliases[piolist->nr] = alias;
+    ++piolist->nr;
 }
 
 void portio_list_add(PortioList *piolist,
@@ -409,15 +419,19 @@ void portio_list_add(PortioList *piolist,
 
 void portio_list_del(PortioList *piolist)
 {
-    MemoryRegion *mr;
+    MemoryRegion *mr, *alias;
     unsigned i;
 
     for (i = 0; i < piolist->nr; ++i) {
         mr = piolist->regions[i];
-        memory_region_del_subregion(piolist->address_space, mr);
+        alias = piolist->aliases[i];
+        memory_region_del_subregion(piolist->address_space, alias);
+        memory_region_destroy(alias);
         memory_region_destroy(mr);
         g_free((MemoryRegionOps *)mr->ops);
         g_free(mr);
+        g_free(alias);
         piolist->regions[i] = NULL;
+        piolist->aliases[i] = NULL;
     }
 }

ioport.h

@@ -60,6 +60,7 @@ typedef struct PortioList {
     struct MemoryRegion *address_space;
     unsigned nr;
     struct MemoryRegion **regions;
+    struct MemoryRegion **aliases;
     void *opaque;
     const char *name;
 } PortioList;

kvm-all.c

@@ -28,6 +28,7 @@
 #include "kvm.h"
 #include "bswap.h"
 #include "memory.h"
+#include "exec-memory.h"
 
 /* This check must be after config-host.h is included */
 #ifdef CONFIG_EVENTFD
@@ -674,6 +675,14 @@ static void kvm_set_phys_mem(MemoryRegionSection *section, bool add)
     }
 }
 
+static void kvm_begin(MemoryListener *listener)
+{
+}
+
+static void kvm_commit(MemoryListener *listener)
+{
+}
+
 static void kvm_region_add(MemoryListener *listener,
                            MemoryRegionSection *section)
 {
@@ -686,6 +695,11 @@ static void kvm_region_del(MemoryListener *listener,
     kvm_set_phys_mem(section, false);
 }
 
+static void kvm_region_nop(MemoryListener *listener,
+                           MemoryRegionSection *section)
+{
+}
+
 static void kvm_log_sync(MemoryListener *listener,
                          MemoryRegionSection *section)
 {
@@ -713,14 +727,95 @@ static void kvm_log_global_stop(struct MemoryListener *listener)
     assert(r >= 0);
 }
 
+static void kvm_mem_ioeventfd_add(MemoryRegionSection *section,
+                                  bool match_data, uint64_t data, int fd)
+{
+    int r;
+
+    assert(match_data && section->size == 4);
+
+    r = kvm_set_ioeventfd_mmio_long(fd, section->offset_within_address_space,
+                                    data, true);
+    if (r < 0) {
+        abort();
+    }
+}
+
+static void kvm_mem_ioeventfd_del(MemoryRegionSection *section,
+                                  bool match_data, uint64_t data, int fd)
+{
+    int r;
+
+    r = kvm_set_ioeventfd_mmio_long(fd, section->offset_within_address_space,
+                                    data, false);
+    if (r < 0) {
+        abort();
+    }
+}
+
+static void kvm_io_ioeventfd_add(MemoryRegionSection *section,
+                                 bool match_data, uint64_t data, int fd)
+{
+    int r;
+
+    assert(match_data && section->size == 2);
+
+    r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
+                                   data, true);
+    if (r < 0) {
+        abort();
+    }
+}
+
+static void kvm_io_ioeventfd_del(MemoryRegionSection *section,
+                                 bool match_data, uint64_t data, int fd)
+
+{
+    int r;
+
+    r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
+                                   data, false);
+    if (r < 0) {
+        abort();
+    }
+}
+
+static void kvm_eventfd_add(MemoryListener *listener,
+                            MemoryRegionSection *section,
+                            bool match_data, uint64_t data, int fd)
+{
+    if (section->address_space == get_system_memory()) {
+        kvm_mem_ioeventfd_add(section, match_data, data, fd);
+    } else {
+        kvm_io_ioeventfd_add(section, match_data, data, fd);
+    }
+}
+
+static void kvm_eventfd_del(MemoryListener *listener,
+                            MemoryRegionSection *section,
+                            bool match_data, uint64_t data, int fd)
+{
+    if (section->address_space == get_system_memory()) {
+        kvm_mem_ioeventfd_del(section, match_data, data, fd);
+    } else {
+        kvm_io_ioeventfd_del(section, match_data, data, fd);
+    }
+}
+
 static MemoryListener kvm_memory_listener = {
+    .begin = kvm_begin,
+    .commit = kvm_commit,
     .region_add = kvm_region_add,
     .region_del = kvm_region_del,
+    .region_nop = kvm_region_nop,
     .log_start = kvm_log_start,
     .log_stop = kvm_log_stop,
     .log_sync = kvm_log_sync,
     .log_global_start = kvm_log_global_start,
     .log_global_stop = kvm_log_global_stop,
+    .eventfd_add = kvm_eventfd_add,
+    .eventfd_del = kvm_eventfd_del,
+    .priority = 10,
 };
 
 static void kvm_handle_interrupt(CPUState *env, int mask)
@@ -965,7 +1060,7 @@ int kvm_init(void)
     }
 
     kvm_state = s;
-    memory_listener_register(&kvm_memory_listener);
+    memory_listener_register(&kvm_memory_listener, NULL);
 
     s->many_ioeventfds = kvm_check_many_ioeventfds();
 

memory.h

@@ -115,7 +115,6 @@ struct MemoryRegion {
     MemoryRegion *parent;
     Int128 size;
     target_phys_addr_t addr;
-    target_phys_addr_t offset;
     void (*destructor)(MemoryRegion *mr);
     ram_addr_t ram_addr;
     IORange iorange;
@@ -161,6 +160,7 @@ typedef struct MemoryRegionSection MemoryRegionSection;
  * @size: the size of the section; will not exceed @mr's boundaries
  * @offset_within_address_space: the address of the first byte of the section
  *     relative to the region's address space
+ * @readonly: writes to this section are ignored
  */
 struct MemoryRegionSection {
     MemoryRegion *mr;
@@ -168,6 +168,7 @@ struct MemoryRegionSection {
     target_phys_addr_t offset_within_region;
     uint64_t size;
     target_phys_addr_t offset_within_address_space;
+    bool readonly;
 };
 
 typedef struct MemoryListener MemoryListener;
@@ -179,14 +180,24 @@ typedef struct MemoryListener MemoryListener;
  * Use with memory_listener_register() and memory_listener_unregister().
  */
 struct MemoryListener {
+    void (*begin)(MemoryListener *listener);
+    void (*commit)(MemoryListener *listener);
     void (*region_add)(MemoryListener *listener, MemoryRegionSection *section);
     void (*region_del)(MemoryListener *listener, MemoryRegionSection *section);
+    void (*region_nop)(MemoryListener *listener, MemoryRegionSection *section);
     void (*log_start)(MemoryListener *listener, MemoryRegionSection *section);
     void (*log_stop)(MemoryListener *listener, MemoryRegionSection *section);
     void (*log_sync)(MemoryListener *listener, MemoryRegionSection *section);
     void (*log_global_start)(MemoryListener *listener);
     void (*log_global_stop)(MemoryListener *listener);
-    QLIST_ENTRY(MemoryListener) link;
+    void (*eventfd_add)(MemoryListener *listener, MemoryRegionSection *section,
+                        bool match_data, uint64_t data, int fd);
+    void (*eventfd_del)(MemoryListener *listener, MemoryRegionSection *section,
+                        bool match_data, uint64_t data, int fd);
+    /* Lower = earlier (during add), later (during del) */
+    unsigned priority;
+    MemoryRegion *address_space_filter;
+    QTAILQ_ENTRY(MemoryListener) link;
 };
 
 /**
@@ -358,14 +369,6 @@ bool memory_region_is_rom(MemoryRegion *mr);
  */
 void *memory_region_get_ram_ptr(MemoryRegion *mr);
 
-/**
- * memory_region_set_offset: Sets an offset to be added to MemoryRegionOps
- *                           callbacks.
- *
- * This function is deprecated and should not be used in new code.
- */
-void memory_region_set_offset(MemoryRegion *mr, target_phys_addr_t offset);
-
 /**
  * memory_region_set_log: Turn dirty logging on or off for a region.
  *
@@ -686,8 +689,9 @@ void memory_region_transaction_commit(void);
  *                           space
  *
  * @listener: an object containing the callbacks to be called
+ * @filter: if non-%NULL, only regions in this address space will be observed
  */
-void memory_listener_register(MemoryListener *listener);
+void memory_listener_register(MemoryListener *listener, MemoryRegion *filter);
 
 /**
  * memory_listener_unregister: undo the effect of memory_listener_register()

xen-all.c

@@ -392,6 +392,14 @@ static void xen_set_memory(struct MemoryListener *listener,
     }
 }
 
+static void xen_begin(MemoryListener *listener)
+{
+}
+
+static void xen_commit(MemoryListener *listener)
+{
+}
+
 static void xen_region_add(MemoryListener *listener,
                            MemoryRegionSection *section)
 {
@@ -404,6 +412,11 @@ static void xen_region_del(MemoryListener *listener,
     xen_set_memory(listener, section, false);
 }
 
+static void xen_region_nop(MemoryListener *listener,
+                           MemoryRegionSection *section)
+{
+}
+
 static void xen_sync_dirty_bitmap(XenIOState *state,
                                   target_phys_addr_t start_addr,
                                   ram_addr_t size)
@@ -485,14 +498,32 @@ static void xen_log_global_stop(MemoryListener *listener)
 {
 }
 
+static void xen_eventfd_add(MemoryListener *listener,
+                            MemoryRegionSection *section,
+                            bool match_data, uint64_t data, int fd)
+{
+}
+
+static void xen_eventfd_del(MemoryListener *listener,
+                            MemoryRegionSection *section,
+                            bool match_data, uint64_t data, int fd)
+{
+}
+
 static MemoryListener xen_memory_listener = {
+    .begin = xen_begin,
+    .commit = xen_commit,
     .region_add = xen_region_add,
     .region_del = xen_region_del,
+    .region_nop = xen_region_nop,
     .log_start = xen_log_start,
     .log_stop = xen_log_stop,
     .log_sync = xen_log_sync,
     .log_global_start = xen_log_global_start,
     .log_global_stop = xen_log_global_stop,
+    .eventfd_add = xen_eventfd_add,
+    .eventfd_del = xen_eventfd_del,
+    .priority = 10,
 };
 
 /* VCPU Operations, MMIO, IO ring ... */
@@ -975,7 +1006,7 @@ int xen_hvm_init(void)
 
     state->memory_listener = xen_memory_listener;
     QLIST_INIT(&state->physmap);
-    memory_listener_register(&state->memory_listener);
+    memory_listener_register(&state->memory_listener, get_system_memory());
     state->log_for_dirtybit = NULL;
 
     /* Initialize backend core & drivers */