Merge tag 'next-8.0-pull-request' of https://gitlab.com/juan.quintela/qemu into staging

Migration patches for 8.0

Hi

This are the patches that I had to drop form the last PULL request because they werent fixes:
- AVX2 is dropped, intel posted a fix, I have to redo it
- Fix for out of order channels is out
  Daniel nacked it and I need to redo it

# gpg: Signature made Thu 15 Dec 2022 09:38:29 GMT
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [full]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [full]
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* tag 'next-8.0-pull-request' of https://gitlab.com/juan.quintela/qemu:
  migration: Drop rs->f
  migration: Remove old preempt code around state maintainance
  migration: Send requested page directly in rp-return thread
  migration: Move last_sent_block into PageSearchStatus
  migration: Make PageSearchStatus part of RAMState
  migration: Add pss_init()
  migration: Introduce pss_channel
  migration: Teach PSS about host page
  migration: Use atomic ops properly for page accountings
  migration: Yield bitmap_mutex properly when sending/sleeping
  migration: Remove RAMState.f references in compression code
  migration: Trivial cleanup save_page_header() on same block check
  migration: Cleanup xbzrle zero page cache update logic
  migration: Add postcopy_preempt_active()
  migration: Take bitmap mutex when completing ram migration
  migration: Export ram_release_page()
  migration: Export ram_transferred_ram()
  multifd: Create page_count fields into both MultiFD{Recv,Send}Params
  multifd: Create page_size fields into both MultiFD{Recv,Send}Params

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

migration/migration.c

@@ -1045,13 +1045,13 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
     size_t page_size = qemu_target_page_size();
 
     info->ram = g_malloc0(sizeof(*info->ram));
-    info->ram->transferred = ram_counters.transferred;
+    info->ram->transferred = stat64_get(&ram_atomic_counters.transferred);
     info->ram->total = ram_bytes_total();
-    info->ram->duplicate = ram_counters.duplicate;
+    info->ram->duplicate = stat64_get(&ram_atomic_counters.duplicate);
     /* legacy value.  It is not used anymore */
     info->ram->skipped = 0;
-    info->ram->normal = ram_counters.normal;
-    info->ram->normal_bytes = ram_counters.normal * page_size;
+    info->ram->normal = stat64_get(&ram_atomic_counters.normal);
+    info->ram->normal_bytes = info->ram->normal * page_size;
     info->ram->mbps = s->mbps;
     info->ram->dirty_sync_count = ram_counters.dirty_sync_count;
     info->ram->dirty_sync_missed_zero_copy =
@@ -1062,7 +1062,7 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
     info->ram->pages_per_second = s->pages_per_second;
     info->ram->precopy_bytes = ram_counters.precopy_bytes;
     info->ram->downtime_bytes = ram_counters.downtime_bytes;
-    info->ram->postcopy_bytes = ram_counters.postcopy_bytes;
+    info->ram->postcopy_bytes = stat64_get(&ram_atomic_counters.postcopy_bytes);
 
     if (migrate_use_xbzrle()) {
         info->xbzrle_cache = g_malloc0(sizeof(*info->xbzrle_cache));
@@ -2840,8 +2840,11 @@ static int migrate_handle_rp_resume_ack(MigrationState *s, uint32_t value)
     return 0;
 }
 
-/* Release ms->rp_state.from_dst_file in a safe way */
-static void migration_release_from_dst_file(MigrationState *ms)
+/*
+ * Release ms->rp_state.from_dst_file (and postcopy_qemufile_src if
+ * existed) in a safe way.
+ */
+static void migration_release_dst_files(MigrationState *ms)
 {
     QEMUFile *file;
 
@@ -2854,6 +2857,18 @@ static void migration_release_from_dst_file(MigrationState *ms)
         ms->rp_state.from_dst_file = NULL;
     }
 
+    /*
+     * Do the same to postcopy fast path socket too if there is.  No
+     * locking needed because this qemufile should only be managed by
+     * return path thread.
+     */
+    if (ms->postcopy_qemufile_src) {
+        migration_ioc_unregister_yank_from_file(ms->postcopy_qemufile_src);
+        qemu_file_shutdown(ms->postcopy_qemufile_src);
+        qemu_fclose(ms->postcopy_qemufile_src);
+        ms->postcopy_qemufile_src = NULL;
+    }
+
     qemu_fclose(file);
 }
 
@@ -2998,7 +3013,7 @@ out:
              * Maybe there is something we can do: it looks like a
              * network down issue, and we pause for a recovery.
              */
-            migration_release_from_dst_file(ms);
+            migration_release_dst_files(ms);
             rp = NULL;
             if (postcopy_pause_return_path_thread(ms)) {
                 /*
@@ -3016,7 +3031,7 @@ out:
     }
 
     trace_source_return_path_thread_end();
-    migration_release_from_dst_file(ms);
+    migration_release_dst_files(ms);
     rcu_unregister_thread();
     return NULL;
 }
@@ -3539,18 +3554,6 @@ static MigThrError postcopy_pause(MigrationState *s)
         qemu_file_shutdown(file);
         qemu_fclose(file);
 
-        /*
-         * Do the same to postcopy fast path socket too if there is.  No
-         * locking needed because no racer as long as we do this before setting
-         * status to paused.
-         */
-        if (s->postcopy_qemufile_src) {
-            migration_ioc_unregister_yank_from_file(s->postcopy_qemufile_src);
-            qemu_file_shutdown(s->postcopy_qemufile_src);
-            qemu_fclose(s->postcopy_qemufile_src);
-            s->postcopy_qemufile_src = NULL;
-        }
-
         migrate_set_state(&s->state, s->state,
                           MIGRATION_STATUS_POSTCOPY_PAUSED);
 
@@ -4391,8 +4394,6 @@ static Property migration_properties[] = {
     DEFINE_PROP_SIZE("announce-step", MigrationState,
                       parameters.announce_step,
                       DEFAULT_MIGRATE_ANNOUNCE_STEP),
-    DEFINE_PROP_BOOL("x-postcopy-preempt-break-huge", MigrationState,
-                      postcopy_preempt_break_huge, true),
     DEFINE_PROP_STRING("tls-creds", MigrationState, parameters.tls_creds),
     DEFINE_PROP_STRING("tls-hostname", MigrationState, parameters.tls_hostname),
     DEFINE_PROP_STRING("tls-authz", MigrationState, parameters.tls_authz),

migration/migration.h

@@ -340,13 +340,6 @@ struct MigrationState {
     bool send_configuration;
     /* Whether we send section footer during migration */
     bool send_section_footer;
-    /*
-     * Whether we allow break sending huge pages when postcopy preempt is
-     * enabled.  When disabled, we won't interrupt precopy within sending a
-     * host huge page, which is the old behavior of vanilla postcopy.
-     * NOTE: this parameter is ignored if postcopy preempt is not enabled.
-     */
-    bool postcopy_preempt_break_huge;
 
     /* Needed by postcopy-pause state */
     QemuSemaphore postcopy_pause_sem;

migration/multifd-zlib.c

@@ -116,7 +116,6 @@ static void zlib_send_cleanup(MultiFDSendParams *p, Error **errp)
 static int zlib_send_prepare(MultiFDSendParams *p, Error **errp)
 {
     struct zlib_data *z = p->data;
-    size_t page_size = qemu_target_page_size();
     z_stream *zs = &z->zs;
     uint32_t out_size = 0;
     int ret;
@@ -135,8 +134,8 @@ static int zlib_send_prepare(MultiFDSendParams *p, Error **errp)
          * with compression. zlib does not guarantee that this is safe,
          * therefore copy the page before calling deflate().
          */
-        memcpy(z->buf, p->pages->block->host + p->normal[i], page_size);
-        zs->avail_in = page_size;
+        memcpy(z->buf, p->pages->block->host + p->normal[i], p->page_size);
+        zs->avail_in = p->page_size;
         zs->next_in = z->buf;
 
         zs->avail_out = available;
@@ -242,12 +241,11 @@ static void zlib_recv_cleanup(MultiFDRecvParams *p)
 static int zlib_recv_pages(MultiFDRecvParams *p, Error **errp)
 {
     struct zlib_data *z = p->data;
-    size_t page_size = qemu_target_page_size();
     z_stream *zs = &z->zs;
     uint32_t in_size = p->next_packet_size;
     /* we measure the change of total_out */
     uint32_t out_size = zs->total_out;
-    uint32_t expected_size = p->normal_num * page_size;
+    uint32_t expected_size = p->normal_num * p->page_size;
     uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
     int ret;
     int i;
@@ -274,7 +272,7 @@ static int zlib_recv_pages(MultiFDRecvParams *p, Error **errp)
             flush = Z_SYNC_FLUSH;
         }
 
-        zs->avail_out = page_size;
+        zs->avail_out = p->page_size;
         zs->next_out = p->host + p->normal[i];
 
         /*
@@ -288,8 +286,8 @@ static int zlib_recv_pages(MultiFDRecvParams *p, Error **errp)
         do {
             ret = inflate(zs, flush);
         } while (ret == Z_OK && zs->avail_in
-                             && (zs->total_out - start) < page_size);
-        if (ret == Z_OK && (zs->total_out - start) < page_size) {
+                             && (zs->total_out - start) < p->page_size);
+        if (ret == Z_OK && (zs->total_out - start) < p->page_size) {
             error_setg(errp, "multifd %u: inflate generated too few output",
                        p->id);
             return -1;

migration/multifd-zstd.c

@@ -113,7 +113,6 @@ static void zstd_send_cleanup(MultiFDSendParams *p, Error **errp)
 static int zstd_send_prepare(MultiFDSendParams *p, Error **errp)
 {
     struct zstd_data *z = p->data;
-    size_t page_size = qemu_target_page_size();
     int ret;
     uint32_t i;
 
@@ -128,7 +127,7 @@ static int zstd_send_prepare(MultiFDSendParams *p, Error **errp)
             flush = ZSTD_e_flush;
         }
         z->in.src = p->pages->block->host + p->normal[i];
-        z->in.size = page_size;
+        z->in.size = p->page_size;
         z->in.pos = 0;
 
         /*
@@ -241,8 +240,7 @@ static int zstd_recv_pages(MultiFDRecvParams *p, Error **errp)
 {
     uint32_t in_size = p->next_packet_size;
     uint32_t out_size = 0;
-    size_t page_size = qemu_target_page_size();
-    uint32_t expected_size = p->normal_num * page_size;
+    uint32_t expected_size = p->normal_num * p->page_size;
     uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
     struct zstd_data *z = p->data;
     int ret;
@@ -265,7 +263,7 @@ static int zstd_recv_pages(MultiFDRecvParams *p, Error **errp)
 
     for (i = 0; i < p->normal_num; i++) {
         z->out.dst = p->host + p->normal[i];
-        z->out.size = page_size;
+        z->out.size = p->page_size;
         z->out.pos = 0;
 
         /*
@@ -279,8 +277,8 @@ static int zstd_recv_pages(MultiFDRecvParams *p, Error **errp)
         do {
             ret = ZSTD_decompressStream(z->zds, &z->out, &z->in);
         } while (ret > 0 && (z->in.size - z->in.pos > 0)
-                         && (z->out.pos < page_size));
-        if (ret > 0 && (z->out.pos < page_size)) {
+                         && (z->out.pos < p->page_size));
+        if (ret > 0 && (z->out.pos < p->page_size)) {
             error_setg(errp, "multifd %u: decompressStream buffer too small",
                        p->id);
             return -1;

migration/multifd.c

@@ -87,15 +87,14 @@ static void nocomp_send_cleanup(MultiFDSendParams *p, Error **errp)
 static int nocomp_send_prepare(MultiFDSendParams *p, Error **errp)
 {
     MultiFDPages_t *pages = p->pages;
-    size_t page_size = qemu_target_page_size();
 
     for (int i = 0; i < p->normal_num; i++) {
         p->iov[p->iovs_num].iov_base = pages->block->host + p->normal[i];
-        p->iov[p->iovs_num].iov_len = page_size;
+        p->iov[p->iovs_num].iov_len = p->page_size;
         p->iovs_num++;
     }
 
-    p->next_packet_size = p->normal_num * page_size;
+    p->next_packet_size = p->normal_num * p->page_size;
     p->flags |= MULTIFD_FLAG_NOCOMP;
     return 0;
 }
@@ -139,7 +138,6 @@ static void nocomp_recv_cleanup(MultiFDRecvParams *p)
 static int nocomp_recv_pages(MultiFDRecvParams *p, Error **errp)
 {
     uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
-    size_t page_size = qemu_target_page_size();
 
     if (flags != MULTIFD_FLAG_NOCOMP) {
         error_setg(errp, "multifd %u: flags received %x flags expected %x",
@@ -148,7 +146,7 @@ static int nocomp_recv_pages(MultiFDRecvParams *p, Error **errp)
     }
     for (int i = 0; i < p->normal_num; i++) {
         p->iov[i].iov_base = p->host + p->normal[i];
-        p->iov[i].iov_len = page_size;
+        p->iov[i].iov_len = p->page_size;
     }
     return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp);
 }
@@ -281,8 +279,6 @@ static void multifd_send_fill_packet(MultiFDSendParams *p)
 static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
 {
     MultiFDPacket_t *packet = p->packet;
-    size_t page_size = qemu_target_page_size();
-    uint32_t page_count = MULTIFD_PACKET_SIZE / page_size;
     RAMBlock *block;
     int i;
 
@@ -309,10 +305,10 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
      * If we received a packet that is 100 times bigger than expected
      * just stop migration.  It is a magic number.
      */
-    if (packet->pages_alloc > page_count) {
+    if (packet->pages_alloc > p->page_count) {
         error_setg(errp, "multifd: received packet "
                    "with size %u and expected a size of %u",
-                   packet->pages_alloc, page_count) ;
+                   packet->pages_alloc, p->page_count) ;
         return -1;
     }
 
@@ -344,7 +340,7 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
     for (i = 0; i < p->normal_num; i++) {
         uint64_t offset = be64_to_cpu(packet->offset[i]);
 
-        if (offset > (block->used_length - page_size)) {
+        if (offset > (block->used_length - p->page_size)) {
             error_setg(errp, "multifd: offset too long %" PRIu64
                        " (max " RAM_ADDR_FMT ")",
                        offset, block->used_length);
@@ -433,11 +429,10 @@ static int multifd_send_pages(QEMUFile *f)
     p->packet_num = multifd_send_state->packet_num++;
     multifd_send_state->pages = p->pages;
     p->pages = pages;
-    transferred = ((uint64_t) pages->num) * qemu_target_page_size()
-                + p->packet_len;
+    transferred = ((uint64_t) pages->num) * p->page_size + p->packet_len;
     qemu_file_acct_rate_limit(f, transferred);
     ram_counters.multifd_bytes += transferred;
-    ram_counters.transferred += transferred;
+    stat64_add(&ram_atomic_counters.transferred, transferred);
     qemu_mutex_unlock(&p->mutex);
     qemu_sem_post(&p->sem);
 
@@ -629,7 +624,7 @@ int multifd_send_sync_main(QEMUFile *f)
         p->pending_job++;
         qemu_file_acct_rate_limit(f, p->packet_len);
         ram_counters.multifd_bytes += p->packet_len;
-        ram_counters.transferred += p->packet_len;
+        stat64_add(&ram_atomic_counters.transferred, p->packet_len);
         qemu_mutex_unlock(&p->mutex);
         qemu_sem_post(&p->sem);
 
@@ -947,6 +942,8 @@ int multifd_save_setup(Error **errp)
         /* We need one extra place for the packet header */
         p->iov = g_new0(struct iovec, page_count + 1);
         p->normal = g_new0(ram_addr_t, page_count);
+        p->page_size = qemu_target_page_size();
+        p->page_count = page_count;
 
         if (migrate_use_zero_copy_send()) {
             p->write_flags = QIO_CHANNEL_WRITE_FLAG_ZERO_COPY;
@@ -1194,6 +1191,8 @@ int multifd_load_setup(Error **errp)
         p->name = g_strdup_printf("multifdrecv_%d", i);
         p->iov = g_new0(struct iovec, page_count);
         p->normal = g_new0(ram_addr_t, page_count);
+        p->page_count = page_count;
+        p->page_size = qemu_target_page_size();
     }
 
     for (i = 0; i < thread_count; i++) {

migration/multifd.h

@@ -80,6 +80,10 @@ typedef struct {
     bool registered_yank;
     /* packet allocated len */
     uint32_t packet_len;
+    /* guest page size */
+    uint32_t page_size;
+    /* number of pages in a full packet */
+    uint32_t page_count;
     /* multifd flags for sending ram */
     int write_flags;
 
@@ -143,6 +147,10 @@ typedef struct {
     QIOChannel *c;
     /* packet allocated len */
     uint32_t packet_len;
+    /* guest page size */
+    uint32_t page_size;
+    /* number of pages in a full packet */
+    uint32_t page_count;
 
     /* syncs main thread and channels */
     QemuSemaphore sem_sync;

migration/ram.h

@@ -32,7 +32,27 @@
 #include "qapi/qapi-types-migration.h"
 #include "exec/cpu-common.h"
 #include "io/channel.h"
+#include "qemu/stats64.h"
 
+/*
+ * These are the migration statistic counters that need to be updated using
+ * atomic ops (can be accessed by more than one thread).  Here since we
+ * cannot modify MigrationStats directly to use Stat64 as it was defined in
+ * the QAPI scheme, we define an internal structure to hold them, and we
+ * propagate the real values when QMP queries happen.
+ *
+ * IOW, the corresponding fields within ram_counters on these specific
+ * fields will be always zero and not being used at all; they're just
+ * placeholders to make it QAPI-compatible.
+ */
+typedef struct {
+    Stat64 transferred;
+    Stat64 duplicate;
+    Stat64 normal;
+    Stat64 postcopy_bytes;
+} MigrationAtomicStats;
+
+extern MigrationAtomicStats ram_atomic_counters;
 extern MigrationStats ram_counters;
 extern XBZRLECacheStats xbzrle_counters;
 extern CompressionStats compression_counters;
@@ -65,6 +85,9 @@ int ram_load_postcopy(QEMUFile *f, int channel);
 
 void ram_handle_compressed(void *host, uint8_t ch, uint64_t size);
 
+void ram_transferred_add(uint64_t bytes);
+void ram_release_page(const char *rbname, uint64_t offset);
+
 int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr);
 bool ramblock_recv_bitmap_test_byte_offset(RAMBlock *rb, uint64_t byte_offset);
 void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr);