Merge tag 'migration-20240909-pull-request' of https://gitlab.com/peterx/qemu into staging

Migration pull request for 9.2

- Mattias's patch to support concurrent bounce buffers for PCI devices
- David's memory leak fix in dirty_memory_extend()
- Fabiano's CI fix to disable vmstate-static-checker test in compat tests
- Denis's patch that adds one more trace point for cpu throttle changes
- Yichen's multifd qatzip compressor support

# -----BEGIN PGP SIGNATURE-----
#
# iIgEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCZt9VlhIccGV0ZXJ4QHJl
# ZGhhdC5jb20ACgkQO1/MzfOr1wZ+4QD+NPzprFD7RF2DPHT5bdo6NTWFSZxW4dyD
# oFp2vhYDEAYA/A5TTfOh3QpYBOaP2PxztZIZSLgs1bokhp+sLM3/PVsK
# =6JYP
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 09 Sep 2024 21:07:50 BST
# gpg:                using EDDSA key B9184DC20CC457DACF7DD1A93B5FCCCDF3ABD706
# gpg:                issuer "peterx@redhat.com"
# gpg: Good signature from "Peter Xu <xzpeter@gmail.com>" [marginal]
# gpg:                 aka "Peter Xu <peterx@redhat.com>" [marginal]
# 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: B918 4DC2 0CC4 57DA CF7D  D1A9 3B5F CCCD F3AB D706

* tag 'migration-20240909-pull-request' of https://gitlab.com/peterx/qemu:
  system: improve migration debug
  tests/migration: Add integration test for 'qatzip' compression method
  migration: Introduce 'qatzip' compression method
  migration: Add migration parameters for QATzip
  meson: Introduce 'qatzip' feature to the build system
  docs/migration: add qatzip compression feature
  ci: migration: Don't run python tests in the compat job
  softmmu/physmem: fix memory leak in dirty_memory_extend()
  softmmu: Support concurrent bounce buffers

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

4 files changed, 75 insertions, 53 deletions

diff --git a/system/cpu-throttle.c b/system/cpu-throttle.c
index c951a6c65e..7632dc6143 100644
--- a/system/cpu-throttle.c
+++ b/system/cpu-throttle.c
@@ -28,6 +28,7 @@
 #include "qemu/main-loop.h"
 #include "sysemu/cpus.h"
 #include "sysemu/cpu-throttle.h"
+#include "trace.h"
 
 /* vcpu throttling controls */
 static QEMUTimer *throttle_timer;
@@ -95,6 +96,8 @@ void cpu_throttle_set(int new_throttle_pct)
      */
     bool throttle_active = cpu_throttle_active();
 
+    trace_cpu_throttle_set(new_throttle_pct);
+
     /* Ensure throttle percentage is within valid range */
     new_throttle_pct = MIN(new_throttle_pct, CPU_THROTTLE_PCT_MAX);
     new_throttle_pct = MAX(new_throttle_pct, CPU_THROTTLE_PCT_MIN);
diff --git a/system/memory.c b/system/memory.c
index 5e6eb459d5..f6f6fee6d8 100644
--- a/system/memory.c
+++ b/system/memory.c
@@ -3148,7 +3148,8 @@ void address_space_init(AddressSpace *as, MemoryRegion *root, const char *name)
     as->ioeventfds = NULL;
     QTAILQ_INIT(&as->listeners);
     QTAILQ_INSERT_TAIL(&address_spaces, as, address_spaces_link);
-    as->bounce.in_use = false;
+    as->max_bounce_buffer_size = DEFAULT_MAX_BOUNCE_BUFFER_SIZE;
+    as->bounce_buffer_size = 0;
     qemu_mutex_init(&as->map_client_list_lock);
     QLIST_INIT(&as->map_client_list);
     as->name = g_strdup(name ? name : "anonymous");
@@ -3158,7 +3159,7 @@ void address_space_init(AddressSpace *as, MemoryRegion *root, const char *name)
 
 static void do_address_space_destroy(AddressSpace *as)
 {
-    assert(!qatomic_read(&as->bounce.in_use));
+    assert(qatomic_read(&as->bounce_buffer_size) == 0);
     assert(QLIST_EMPTY(&as->map_client_list));
     qemu_mutex_destroy(&as->map_client_list_lock);
 
diff --git a/system/physmem.c b/system/physmem.c
index 94600a33ec..d71a2b1bbd 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -1534,18 +1534,6 @@ static ram_addr_t find_ram_offset(ram_addr_t size)
     return offset;
 }
 
-static unsigned long last_ram_page(void)
-{
-    RAMBlock *block;
-    ram_addr_t last = 0;
-
-    RCU_READ_LOCK_GUARD();
-    RAMBLOCK_FOREACH(block) {
-        last = MAX(last, block->offset + block->max_length);
-    }
-    return last >> TARGET_PAGE_BITS;
-}
-
 static void qemu_ram_setup_dump(void *addr, ram_addr_t size)
 {
     int ret;
@@ -1799,13 +1787,11 @@ void qemu_ram_msync(RAMBlock *block, ram_addr_t start, ram_addr_t length)
 }
 
 /* Called with ram_list.mutex held */
-static void dirty_memory_extend(ram_addr_t old_ram_size,
-                                ram_addr_t new_ram_size)
+static void dirty_memory_extend(ram_addr_t new_ram_size)
 {
-    ram_addr_t old_num_blocks = DIV_ROUND_UP(old_ram_size,
-                                             DIRTY_MEMORY_BLOCK_SIZE);
-    ram_addr_t new_num_blocks = DIV_ROUND_UP(new_ram_size,
-                                             DIRTY_MEMORY_BLOCK_SIZE);
+    unsigned int old_num_blocks = ram_list.num_dirty_blocks;
+    unsigned int new_num_blocks = DIV_ROUND_UP(new_ram_size,
+                                               DIRTY_MEMORY_BLOCK_SIZE);
     int i;
 
     /* Only need to extend if block count increased */
@@ -1837,6 +1823,8 @@ static void dirty_memory_extend(ram_addr_t old_ram_size,
             g_free_rcu(old_blocks, rcu);
         }
     }
+
+    ram_list.num_dirty_blocks = new_num_blocks;
 }
 
 static void ram_block_add(RAMBlock *new_block, Error **errp)
@@ -1846,11 +1834,9 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
     RAMBlock *block;
     RAMBlock *last_block = NULL;
     bool free_on_error = false;
-    ram_addr_t old_ram_size, new_ram_size;
+    ram_addr_t ram_size;
     Error *err = NULL;
 
-    old_ram_size = last_ram_page();
-
     qemu_mutex_lock_ramlist();
     new_block->offset = find_ram_offset(new_block->max_length);
 
@@ -1901,11 +1887,8 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
         }
     }
 
-    new_ram_size = MAX(old_ram_size,
-              (new_block->offset + new_block->max_length) >> TARGET_PAGE_BITS);
-    if (new_ram_size > old_ram_size) {
-        dirty_memory_extend(old_ram_size, new_ram_size);
-    }
+    ram_size = (new_block->offset + new_block->max_length) >> TARGET_PAGE_BITS;
+    dirty_memory_extend(ram_size);
     /* Keep the list sorted from biggest to smallest block.  Unlike QTAILQ,
      * QLIST (which has an RCU-friendly variant) does not have insertion at
      * tail, so save the last element in last_block.
@@ -3095,6 +3078,20 @@ void cpu_flush_icache_range(hwaddr start, hwaddr len)
                                      NULL, len, FLUSH_CACHE);
 }
 
+/*
+ * A magic value stored in the first 8 bytes of the bounce buffer struct. Used
+ * to detect illegal pointers passed to address_space_unmap.
+ */
+#define BOUNCE_BUFFER_MAGIC 0xb4017ceb4ffe12ed
+
+typedef struct {
+    uint64_t magic;
+    MemoryRegion *mr;
+    hwaddr addr;
+    size_t len;
+    uint8_t buffer[];
+} BounceBuffer;
+
 static void
 address_space_unregister_map_client_do(AddressSpaceMapClient *client)
 {
@@ -3120,9 +3117,9 @@ void address_space_register_map_client(AddressSpace *as, QEMUBH *bh)
     QEMU_LOCK_GUARD(&as->map_client_list_lock);
     client->bh = bh;
     QLIST_INSERT_HEAD(&as->map_client_list, client, link);
-    /* Write map_client_list before reading in_use.  */
+    /* Write map_client_list before reading bounce_buffer_size. */
     smp_mb();
-    if (!qatomic_read(&as->bounce.in_use)) {
+    if (qatomic_read(&as->bounce_buffer_size) < as->max_bounce_buffer_size) {
         address_space_notify_map_clients_locked(as);
     }
 }
@@ -3251,28 +3248,40 @@ void *address_space_map(AddressSpace *as,
     mr = flatview_translate(fv, addr, &xlat, &l, is_write, attrs);
 
     if (!memory_access_is_direct(mr, is_write)) {
-        if (qatomic_xchg(&as->bounce.in_use, true)) {
+        size_t used = qatomic_read(&as->bounce_buffer_size);
+        for (;;) {
+            hwaddr alloc = MIN(as->max_bounce_buffer_size - used, l);
+            size_t new_size = used + alloc;
+            size_t actual =
+                qatomic_cmpxchg(&as->bounce_buffer_size, used, new_size);
+            if (actual == used) {
+                l = alloc;
+                break;
+            }
+            used = actual;
+        }
+
+        if (l == 0) {
             *plen = 0;
             return NULL;
         }
-        /* Avoid unbounded allocations */
-        l = MIN(l, TARGET_PAGE_SIZE);
-        as->bounce.buffer = qemu_memalign(TARGET_PAGE_SIZE, l);
-        as->bounce.addr = addr;
-        as->bounce.len = l;
 
+        BounceBuffer *bounce = g_malloc0(l + sizeof(BounceBuffer));
+        bounce->magic = BOUNCE_BUFFER_MAGIC;
         memory_region_ref(mr);
-        as->bounce.mr = mr;
+        bounce->mr = mr;
+        bounce->addr = addr;
+        bounce->len = l;
+
         if (!is_write) {
             flatview_read(fv, addr, MEMTXATTRS_UNSPECIFIED,
-                          as->bounce.buffer, l);
+                          bounce->buffer, l);
         }
 
         *plen = l;
-        return as->bounce.buffer;
+        return bounce->buffer;
     }
 
-
     memory_region_ref(mr);
     *plen = flatview_extend_translation(fv, addr, len, mr, xlat,
                                         l, is_write, attrs);
@@ -3287,12 +3296,11 @@ void *address_space_map(AddressSpace *as,
 void address_space_unmap(AddressSpace *as, void *buffer, hwaddr len,
                          bool is_write, hwaddr access_len)
 {
-    if (buffer != as->bounce.buffer) {
-        MemoryRegion *mr;
-        ram_addr_t addr1;
+    MemoryRegion *mr;
+    ram_addr_t addr1;
 
-        mr = memory_region_from_host(buffer, &addr1);
-        assert(mr != NULL);
+    mr = memory_region_from_host(buffer, &addr1);
+    if (mr != NULL) {
         if (is_write) {
             invalidate_and_set_dirty(mr, addr1, access_len);
         }
@@ -3302,15 +3310,22 @@ void address_space_unmap(AddressSpace *as, void *buffer, hwaddr len,
         memory_region_unref(mr);
         return;
     }
+
+
+    BounceBuffer *bounce = container_of(buffer, BounceBuffer, buffer);
+    assert(bounce->magic == BOUNCE_BUFFER_MAGIC);
+
     if (is_write) {
-        address_space_write(as, as->bounce.addr, MEMTXATTRS_UNSPECIFIED,
-                            as->bounce.buffer, access_len);
-    }
-    qemu_vfree(as->bounce.buffer);
-    as->bounce.buffer = NULL;
-    memory_region_unref(as->bounce.mr);
-    /* Clear in_use before reading map_client_list.  */
-    qatomic_set_mb(&as->bounce.in_use, false);
+        address_space_write(as, bounce->addr, MEMTXATTRS_UNSPECIFIED,
+                            bounce->buffer, access_len);
+    }
+
+    qatomic_sub(&as->bounce_buffer_size, bounce->len);
+    bounce->magic = ~BOUNCE_BUFFER_MAGIC;
+    memory_region_unref(bounce->mr);
+    g_free(bounce);
+    /* Write bounce_buffer_size before reading map_client_list. */
+    smp_mb();
     address_space_notify_map_clients(as);
 }
 
diff --git a/system/trace-events b/system/trace-events
index 2ed1d59b1f..074d001e90 100644
--- a/system/trace-events
+++ b/system/trace-events
@@ -44,3 +44,6 @@ dirtylimit_state_finalize(void)
 dirtylimit_throttle_pct(int cpu_index, uint64_t pct, int64_t time_us) "CPU[%d] throttle percent: %" PRIu64 ", throttle adjust time %"PRIi64 " us"
 dirtylimit_set_vcpu(int cpu_index, uint64_t quota) "CPU[%d] set dirty page rate limit %"PRIu64
 dirtylimit_vcpu_execute(int cpu_index, int64_t sleep_time_us) "CPU[%d] sleep %"PRIi64 " us"
+
+# cpu-throttle.c
+cpu_throttle_set(int new_throttle_pct)  "set guest CPU throttled by %d%%"