Merge remote-tracking branch 'remotes/juanquintela/tags/migration.next-pull-request' into staging

Migration Pull request (3rd try)

Hi

This should fix all the freebsd problems.

Please apply,

# gpg: Signature made Tue 19 Oct 2021 02:28:51 AM PDT
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [full]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [full]

* remotes/juanquintela/tags/migration.next-pull-request:
  migration/rdma: advise prefetch write for ODP region
  migration/rdma: Try to register On-Demand Paging memory region
  migration: allow enabling mutilfd for specific protocol only
  migration: allow multifd for socket protocol only
  migration/ram: Don't passs RAMState to migration_clear_memory_region_dirty_bitmap_*()
  multifd: Unconditionally unregister yank function
  multifd: Implement yank for multifd send side

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

7 files changed, 152 insertions, 35 deletions

diff --git a/meson.build b/meson.build
index 5e79467..9ed9a99 100644
--- a/meson.build
+++ b/meson.build
@@ -1530,6 +1530,12 @@ config_host_data.set('HAVE_COPY_FILE_RANGE', cc.has_function('copy_file_range'))
 config_host_data.set('HAVE_OPENPTY', cc.has_function('openpty', dependencies: util))
 config_host_data.set('HAVE_STRCHRNUL', cc.has_function('strchrnul'))
 config_host_data.set('HAVE_SYSTEM_FUNCTION', cc.has_function('system', prefix: '#include <stdlib.h>'))
+if rdma.found()
+  config_host_data.set('HAVE_IBV_ADVISE_MR',
+                       cc.has_function('ibv_advise_mr',
+                                       args: config_host['RDMA_LIBS'].split(),
+                                       prefix: '#include <infiniband/verbs.h>'))
+endif
 
 # has_header_symbol
 config_host_data.set('CONFIG_BYTESWAP_H',
diff --git a/migration/migration.c b/migration/migration.c
index 6ac807e..9172686 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -453,10 +453,12 @@ static void qemu_start_incoming_migration(const char *uri, Error **errp)
 {
     const char *p = NULL;
 
+    migrate_protocol_allow_multifd(false); /* reset it anyway */
     qapi_event_send_migration(MIGRATION_STATUS_SETUP);
     if (strstart(uri, "tcp:", &p) ||
         strstart(uri, "unix:", NULL) ||
         strstart(uri, "vsock:", NULL)) {
+        migrate_protocol_allow_multifd(true);
         socket_start_incoming_migration(p ? p : uri, errp);
 #ifdef CONFIG_RDMA
     } else if (strstart(uri, "rdma:", &p)) {
@@ -1235,6 +1237,14 @@ static bool migrate_caps_check(bool *cap_list,
         }
     }
 
+    /* incoming side only */
+    if (runstate_check(RUN_STATE_INMIGRATE) &&
+        !migrate_multifd_is_allowed() &&
+        cap_list[MIGRATION_CAPABILITY_MULTIFD]) {
+        error_setg(errp, "multifd is not supported by current protocol");
+        return false;
+    }
+
     return true;
 }
 
@@ -2280,9 +2290,11 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
         }
     }
 
+    migrate_protocol_allow_multifd(false);
     if (strstart(uri, "tcp:", &p) ||
         strstart(uri, "unix:", NULL) ||
         strstart(uri, "vsock:", NULL)) {
+        migrate_protocol_allow_multifd(true);
         socket_start_outgoing_migration(s, p ? p : uri, &local_err);
 #ifdef CONFIG_RDMA
     } else if (strstart(uri, "rdma:", &p)) {
diff --git a/migration/multifd.c b/migration/multifd.c
index 377da78..7c9deb1 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -531,7 +531,7 @@ void multifd_save_cleanup(void)
 {
     int i;
 
-    if (!migrate_use_multifd()) {
+    if (!migrate_use_multifd() || !migrate_multifd_is_allowed()) {
         return;
     }
     multifd_send_terminate_threads(NULL);
@@ -546,6 +546,9 @@ void multifd_save_cleanup(void)
         MultiFDSendParams *p = &multifd_send_state->params[i];
         Error *local_err = NULL;
 
+        if (p->registered_yank) {
+            migration_ioc_unregister_yank(p->c);
+        }
         socket_send_channel_destroy(p->c);
         p->c = NULL;
         qemu_mutex_destroy(&p->mutex);
@@ -813,7 +816,8 @@ static bool multifd_channel_connect(MultiFDSendParams *p,
                 return false;
             }
         } else {
-            /* update for tls qio channel */
+            migration_ioc_register_yank(ioc);
+            p->registered_yank = true;
             p->c = ioc;
             qemu_thread_create(&p->thread, p->name, multifd_send_thread, p,
                                    QEMU_THREAD_JOINABLE);
@@ -864,6 +868,17 @@ cleanup:
     multifd_new_send_channel_cleanup(p, sioc, local_err);
 }
 
+static bool migrate_allow_multifd = true;
+void migrate_protocol_allow_multifd(bool allow)
+{
+    migrate_allow_multifd = allow;
+}
+
+bool migrate_multifd_is_allowed(void)
+{
+    return migrate_allow_multifd;
+}
+
 int multifd_save_setup(Error **errp)
 {
     int thread_count;
@@ -874,6 +889,11 @@ int multifd_save_setup(Error **errp)
     if (!migrate_use_multifd()) {
         return 0;
     }
+    if (!migrate_multifd_is_allowed()) {
+        error_setg(errp, "multifd is not supported by current protocol");
+        return -1;
+    }
+
     s = migrate_get_current();
     thread_count = migrate_multifd_channels();
     multifd_send_state = g_malloc0(sizeof(*multifd_send_state));
@@ -967,7 +987,7 @@ int multifd_load_cleanup(Error **errp)
 {
     int i;
 
-    if (!migrate_use_multifd()) {
+    if (!migrate_use_multifd() || !migrate_multifd_is_allowed()) {
         return 0;
     }
     multifd_recv_terminate_threads(NULL);
@@ -987,10 +1007,7 @@ int multifd_load_cleanup(Error **errp)
     for (i = 0; i < migrate_multifd_channels(); i++) {
         MultiFDRecvParams *p = &multifd_recv_state->params[i];
 
-        if (OBJECT(p->c)->ref == 1) {
-            migration_ioc_unregister_yank(p->c);
-        }
-
+        migration_ioc_unregister_yank(p->c);
         object_unref(OBJECT(p->c));
         p->c = NULL;
         qemu_mutex_destroy(&p->mutex);
@@ -1119,6 +1136,10 @@ int multifd_load_setup(Error **errp)
     if (!migrate_use_multifd()) {
         return 0;
     }
+    if (!migrate_multifd_is_allowed()) {
+        error_setg(errp, "multifd is not supported by current protocol");
+        return -1;
+    }
     thread_count = migrate_multifd_channels();
     multifd_recv_state = g_malloc0(sizeof(*multifd_recv_state));
     multifd_recv_state->params = g_new0(MultiFDRecvParams, thread_count);
diff --git a/migration/multifd.h b/migration/multifd.h
index 8d6751f..15c50ca 100644
--- a/migration/multifd.h
+++ b/migration/multifd.h
@@ -13,6 +13,8 @@
 #ifndef QEMU_MIGRATION_MULTIFD_H
 #define QEMU_MIGRATION_MULTIFD_H
 
+bool migrate_multifd_is_allowed(void);
+void migrate_protocol_allow_multifd(bool allow);
 int multifd_save_setup(Error **errp);
 void multifd_save_cleanup(void);
 int multifd_load_setup(Error **errp);
@@ -85,6 +87,8 @@ typedef struct {
     bool running;
     /* should this thread finish */
     bool quit;
+    /* is the yank function registered */
+    bool registered_yank;
     /* thread has work to do */
     int pending_job;
     /* array of pages to sent */
diff --git a/migration/ram.c b/migration/ram.c
index 7a43bfd..bb90882 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -789,8 +789,7 @@ unsigned long migration_bitmap_find_dirty(RAMState *rs, RAMBlock *rb,
     return find_next_bit(bitmap, size, start);
 }
 
-static void migration_clear_memory_region_dirty_bitmap(RAMState *rs,
-                                                       RAMBlock *rb,
+static void migration_clear_memory_region_dirty_bitmap(RAMBlock *rb,
                                                        unsigned long page)
 {
     uint8_t shift;
@@ -818,8 +817,7 @@ static void migration_clear_memory_region_dirty_bitmap(RAMState *rs,
 }
 
 static void
-migration_clear_memory_region_dirty_bitmap_range(RAMState *rs,
-                                                 RAMBlock *rb,
+migration_clear_memory_region_dirty_bitmap_range(RAMBlock *rb,
                                                  unsigned long start,
                                                  unsigned long npages)
 {
@@ -832,7 +830,7 @@ migration_clear_memory_region_dirty_bitmap_range(RAMState *rs,
      * exclusive.
      */
     for (i = chunk_start; i < chunk_end; i += chunk_pages) {
-        migration_clear_memory_region_dirty_bitmap(rs, rb, i);
+        migration_clear_memory_region_dirty_bitmap(rb, i);
     }
 }
 
@@ -850,7 +848,7 @@ static inline bool migration_bitmap_clear_dirty(RAMState *rs,
      * the page in the chunk we clear the remote dirty bitmap for all.
      * Clearing it earlier won't be a problem, but too late will.
      */
-    migration_clear_memory_region_dirty_bitmap(rs, rb, page);
+    migration_clear_memory_region_dirty_bitmap(rb, page);
 
     ret = test_and_clear_bit(page, rb->bmap);
     if (ret) {
@@ -2777,8 +2775,7 @@ void qemu_guest_free_page_hint(void *addr, size_t len)
          * are initially set. Otherwise those skipped pages will be sent in
          * the next round after syncing from the memory region bitmap.
          */
-        migration_clear_memory_region_dirty_bitmap_range(ram_state, block,
-                                                         start, npages);
+        migration_clear_memory_region_dirty_bitmap_range(block, start, npages);
         ram_state->migration_dirty_pages -=
                       bitmap_count_one_with_offset(block->bmap, start, npages);
         bitmap_clear(block->bmap, start, npages);
diff --git a/migration/rdma.c b/migration/rdma.c
index 5c2d113..2a3c788 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -1117,19 +1117,82 @@ static int qemu_rdma_alloc_qp(RDMAContext *rdma)
     return 0;
 }
 
+/* Check whether On-Demand Paging is supported by RDAM device */
+static bool rdma_support_odp(struct ibv_context *dev)
+{
+    struct ibv_device_attr_ex attr = {0};
+    int ret = ibv_query_device_ex(dev, NULL, &attr);
+    if (ret) {
+        return false;
+    }
+
+    if (attr.odp_caps.general_caps & IBV_ODP_SUPPORT) {
+        return true;
+    }
+
+    return false;
+}
+
+/*
+ * ibv_advise_mr to avoid RNR NAK error as far as possible.
+ * The responder mr registering with ODP will sent RNR NAK back to
+ * the requester in the face of the page fault.
+ */
+static void qemu_rdma_advise_prefetch_mr(struct ibv_pd *pd, uint64_t addr,
+                                         uint32_t len,  uint32_t lkey,
+                                         const char *name, bool wr)
+{
+#ifdef HAVE_IBV_ADVISE_MR
+    int ret;
+    int advice = wr ? IBV_ADVISE_MR_ADVICE_PREFETCH_WRITE :
+                 IBV_ADVISE_MR_ADVICE_PREFETCH;
+    struct ibv_sge sg_list = {.lkey = lkey, .addr = addr, .length = len};
+
+    ret = ibv_advise_mr(pd, advice,
+                        IBV_ADVISE_MR_FLAG_FLUSH, &sg_list, 1);
+    /* ignore the error */
+    if (ret) {
+        trace_qemu_rdma_advise_mr(name, len, addr, strerror(errno));
+    } else {
+        trace_qemu_rdma_advise_mr(name, len, addr, "successed");
+    }
+#endif
+}
+
 static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma)
 {
     int i;
     RDMALocalBlocks *local = &rdma->local_ram_blocks;
 
     for (i = 0; i < local->nb_blocks; i++) {
+        int access = IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE;
+
         local->block[i].mr =
             ibv_reg_mr(rdma->pd,
                     local->block[i].local_host_addr,
-                    local->block[i].length,
-                    IBV_ACCESS_LOCAL_WRITE |
-                    IBV_ACCESS_REMOTE_WRITE
+                    local->block[i].length, access
                     );
+
+        if (!local->block[i].mr &&
+            errno == ENOTSUP && rdma_support_odp(rdma->verbs)) {
+                access |= IBV_ACCESS_ON_DEMAND;
+                /* register ODP mr */
+                local->block[i].mr =
+                    ibv_reg_mr(rdma->pd,
+                               local->block[i].local_host_addr,
+                               local->block[i].length, access);
+                trace_qemu_rdma_register_odp_mr(local->block[i].block_name);
+
+                if (local->block[i].mr) {
+                    qemu_rdma_advise_prefetch_mr(rdma->pd,
+                                    (uintptr_t)local->block[i].local_host_addr,
+                                    local->block[i].length,
+                                    local->block[i].mr->lkey,
+                                    local->block[i].block_name,
+                                    true);
+                }
+        }
+
         if (!local->block[i].mr) {
             perror("Failed to register local dest ram block!");
             break;
@@ -1215,28 +1278,40 @@ static int qemu_rdma_register_and_get_keys(RDMAContext *rdma,
      */
     if (!block->pmr[chunk]) {
         uint64_t len = chunk_end - chunk_start;
+        int access = rkey ? IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE :
+                     0;
 
         trace_qemu_rdma_register_and_get_keys(len, chunk_start);
 
-        block->pmr[chunk] = ibv_reg_mr(rdma->pd,
-                chunk_start, len,
-                (rkey ? (IBV_ACCESS_LOCAL_WRITE |
-                        IBV_ACCESS_REMOTE_WRITE) : 0));
-
-        if (!block->pmr[chunk]) {
-            perror("Failed to register chunk!");
-            fprintf(stderr, "Chunk details: block: %d chunk index %d"
-                            " start %" PRIuPTR " end %" PRIuPTR
-                            " host %" PRIuPTR
-                            " local %" PRIuPTR " registrations: %d\n",
-                            block->index, chunk, (uintptr_t)chunk_start,
-                            (uintptr_t)chunk_end, host_addr,
-                            (uintptr_t)block->local_host_addr,
-                            rdma->total_registrations);
-            return -1;
+        block->pmr[chunk] = ibv_reg_mr(rdma->pd, chunk_start, len, access);
+        if (!block->pmr[chunk] &&
+            errno == ENOTSUP && rdma_support_odp(rdma->verbs)) {
+            access |= IBV_ACCESS_ON_DEMAND;
+            /* register ODP mr */
+            block->pmr[chunk] = ibv_reg_mr(rdma->pd, chunk_start, len, access);
+            trace_qemu_rdma_register_odp_mr(block->block_name);
+
+            if (block->pmr[chunk]) {
+                qemu_rdma_advise_prefetch_mr(rdma->pd, (uintptr_t)chunk_start,
+                                            len, block->pmr[chunk]->lkey,
+                                            block->block_name, rkey);
+
+            }
         }
-        rdma->total_registrations++;
     }
+    if (!block->pmr[chunk]) {
+        perror("Failed to register chunk!");
+        fprintf(stderr, "Chunk details: block: %d chunk index %d"
+                        " start %" PRIuPTR " end %" PRIuPTR
+                        " host %" PRIuPTR
+                        " local %" PRIuPTR " registrations: %d\n",
+                        block->index, chunk, (uintptr_t)chunk_start,
+                        (uintptr_t)chunk_end, host_addr,
+                        (uintptr_t)block->local_host_addr,
+                        rdma->total_registrations);
+        return -1;
+    }
+    rdma->total_registrations++;
 
     if (lkey) {
         *lkey = block->pmr[chunk]->lkey;
diff --git a/migration/trace-events b/migration/trace-events
index a1c0f03..a8ae163 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -212,6 +212,8 @@ qemu_rdma_poll_write(const char *compstr, int64_t comp, int left, uint64_t block
 qemu_rdma_poll_other(const char *compstr, int64_t comp, int left) "other completion %s (%" PRId64 ") received left %d"
 qemu_rdma_post_send_control(const char *desc) "CONTROL: sending %s.."
 qemu_rdma_register_and_get_keys(uint64_t len, void *start) "Registering %" PRIu64 " bytes @ %p"
+qemu_rdma_register_odp_mr(const char *name) "Try to register On-Demand Paging memory region: %s"
+qemu_rdma_advise_mr(const char *name, uint32_t len, uint64_t addr, const char *res) "Try to advise block %s prefetch at %" PRIu32 "@0x%" PRIx64 ": %s"
 qemu_rdma_registration_handle_compress(int64_t length, int index, int64_t offset) "Zapping zero chunk: %" PRId64 " bytes, index %d, offset %" PRId64
 qemu_rdma_registration_handle_finished(void) ""
 qemu_rdma_registration_handle_ram_blocks(void) ""