Merge tag 'pull-migration-20220623b' of https://gitlab.com/dagrh/qemu into staging

[v3] Migration pull 2022-06-23

This replaces my and Juan's earlier pulls over the last 2 days;
4th time lucky?

Compared to my pull earlier:
  Removed Hyman's dirty ring set

In this migration PULL request:
- Dainiel Berrangé - qemufileops cleanup
- Leonardo Bras  - cleanups for zero copy
- Juan Quintela  - RDMA cleanups

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEERfXHG0oMt/uXep+pBRYzHrxb/ecFAmK0mnwACgkQBRYzHrxb
# /ecJYQ/8DdQBVYpJjpHj3mBx39aXodM7uM4Jt1okuSF92y9KRSNdIs3nvvwWAZbL
# dWAUHUZBNOfZF7Eqe6WWCIDNxUTz88RkMM16N3+a5sqBa0xU6rP6cvyw9vYrnsmx
# aHVQ1ESosTby2qcb1ofjYRXWNt7GhDtRIH55m3mSalP/WAgjMe3MsrAtz66T4w55
# 4paTVwgS/WMuLD9dqyESyofePnvtM8z3ye2a75JRscBQYmpO+XuX3IX5ah6m439s
# fI1BezQU2Q4YNDmCEWvdfZ2tqgcfi8dHnu0JB9QTfbkPVh9jw25VPpnymimMB7iW
# MlXAlDr7m9HQI6OjIkq8pXBcgWQpbVGMon1CcrDmGCReEjnQ5lTsb27fkXzf/Nwu
# 09iuNfYGcSGAbZ8GZa/lrRTGeINrSj99uOVxrTvVS0db2+1va3hkamGMULhsdX6O
# smOrje79pVLAr7JJSMH2bqFv9cKtLu77HndSVtswkRRMhtDU+VQI5FxYlwueuawJ
# toDM4DJMd3pJHIpPrUwxlo4D9dkdxPfqC1GATDPxw9/vYgbORn8fkt5g9EYxBzc0
# pWRY9SNuw0MC54JGEoFc77+VKJXK1A97j9GoF+Vyoh30yTgZ3q9tm2eElpYwtHDy
# t8zEVC9QadcgMdRAnJqgZgaWdfwKiHpjplSn5lOGDLOo7gfSmik=
# =ajVU
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 23 Jun 2022 09:53:16 AM PDT
# gpg:                using RSA key 45F5C71B4A0CB7FB977A9FA90516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <dgilbert@redhat.com>" [full]

* tag 'pull-migration-20220623b' of https://gitlab.com/dagrh/qemu: (25 commits)
  migration: remove the QEMUFileOps abstraction
  migration: remove the QEMUFileOps 'get_return_path' callback
  migration: remove the QEMUFileOps 'writev_buffer' callback
  migration: remove the QEMUFileOps 'get_buffer' callback
  migration: remove the QEMUFileOps 'close' callback
  migration: remove the QEMUFileOps 'set_blocking' callback
  migration: remove the QEMUFileOps 'shut_down' callback
  migration: remove unused QEMUFileGetFD typedef / qemu_get_fd method
  migration: introduce new constructors for QEMUFile
  migration: hardcode assumption that QEMUFile is backed with QIOChannel
  migration: stop passing 'opaque' parameter to QEMUFile hooks
  migration: convert savevm to use QIOChannelBlock for VMState
  migration: introduce a QIOChannel impl for BlockDriverState VMState
  migration: rename qemu_file_update_transfer to qemu_file_acct_rate_limit
  migration: rename qemu_update_position to qemu_file_credit_transfer
  migration: rename qemu_ftell to qemu_file_total_transferred
  migration: rename 'pos' field in QEMUFile to 'bytes_processed'
  migration: rename rate limiting fields in QEMUFile
  migration: remove unreachble RDMA code in save_hook impl
  migration: switch to use QIOChannelNull for dummy channel
  ...

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

1 files changed, 33 insertions, 152 deletions

diff --git a/migration/rdma.c b/migration/rdma.c
index 672d1958a9..94a55dd95b 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -21,7 +21,6 @@
 #include "migration.h"
 #include "qemu-file.h"
 #include "ram.h"
-#include "qemu-file-channel.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
 #include "qemu/module.h"
@@ -1371,30 +1370,6 @@ const char *print_wrid(int wrid)
 }
 
 /*
- * RDMA requires memory registration (mlock/pinning), but this is not good for
- * overcommitment.
- *
- * In preparation for the future where LRU information or workload-specific
- * writable writable working set memory access behavior is available to QEMU
- * it would be nice to have in place the ability to UN-register/UN-pin
- * particular memory regions from the RDMA hardware when it is determine that
- * those regions of memory will likely not be accessed again in the near future.
- *
- * While we do not yet have such information right now, the following
- * compile-time option allows us to perform a non-optimized version of this
- * behavior.
- *
- * By uncommenting this option, you will cause *all* RDMA transfers to be
- * unregistered immediately after the transfer completes on both sides of the
- * connection. This has no effect in 'rdma-pin-all' mode, only regular mode.
- *
- * This will have a terrible impact on migration performance, so until future
- * workload information or LRU information is available, do not attempt to use
- * this feature except for basic testing.
- */
-/* #define RDMA_UNREGISTRATION_EXAMPLE */
-
-/*
  * Perform a non-optimized memory unregistration after every transfer
  * for demonstration purposes, only if pin-all is not requested.
  *
@@ -1487,34 +1462,6 @@ static uint64_t qemu_rdma_make_wrid(uint64_t wr_id, uint64_t index,
 }
 
 /*
- * Set bit for unregistration in the next iteration.
- * We cannot transmit right here, but will unpin later.
- */
-static void qemu_rdma_signal_unregister(RDMAContext *rdma, uint64_t index,
-                                        uint64_t chunk, uint64_t wr_id)
-{
-    if (rdma->unregistrations[rdma->unregister_next] != 0) {
-        error_report("rdma migration: queue is full");
-    } else {
-        RDMALocalBlock *block = &(rdma->local_ram_blocks.block[index]);
-
-        if (!test_and_set_bit(chunk, block->unregister_bitmap)) {
-            trace_qemu_rdma_signal_unregister_append(chunk,
-                                                     rdma->unregister_next);
-
-            rdma->unregistrations[rdma->unregister_next++] =
-                    qemu_rdma_make_wrid(wr_id, index, chunk);
-
-            if (rdma->unregister_next == RDMA_SIGNALED_SEND_MAX) {
-                rdma->unregister_next = 0;
-            }
-        } else {
-            trace_qemu_rdma_signal_unregister_already(chunk);
-        }
-    }
-}
-
-/*
  * Consult the connection manager to see a work request
  * (of any kind) has completed.
  * Return the work request ID that completed.
@@ -1571,18 +1518,6 @@ static uint64_t qemu_rdma_poll(RDMAContext *rdma, struct ibv_cq *cq,
         if (rdma->nb_sent > 0) {
             rdma->nb_sent--;
         }
-
-        if (!rdma->pin_all) {
-            /*
-             * FYI: If one wanted to signal a specific chunk to be unregistered
-             * using LRU or workload-specific information, this is the function
-             * you would call to do so. That chunk would then get asynchronously
-             * unregistered later.
-             */
-#ifdef RDMA_UNREGISTRATION_EXAMPLE
-            qemu_rdma_signal_unregister(rdma, index, chunk, wc.wr_id);
-#endif
-        }
     } else {
         trace_qemu_rdma_poll_other(print_wrid(wr_id), wr_id, rdma->nb_sent);
     }
@@ -2137,11 +2072,6 @@ retry:
 
     chunk_end = ram_chunk_end(block, chunk + chunks);
 
-    if (!rdma->pin_all) {
-#ifdef RDMA_UNREGISTRATION_EXAMPLE
-        qemu_rdma_unregister_waiting(rdma);
-#endif
-    }
 
     while (test_bit(chunk, block->transit_bitmap)) {
         (void)count;
@@ -3278,33 +3208,17 @@ qio_channel_rdma_shutdown(QIOChannel *ioc,
  *        Offset is an offset to be added to block_offset and used
  *        to also lookup the corresponding RAMBlock.
  *
- *    @size > 0 :
- *        Initiate an transfer this size.
- *
- *    @size == 0 :
- *        A 'hint' or 'advice' that means that we wish to speculatively
- *        and asynchronously unregister this memory. In this case, there is no
- *        guarantee that the unregister will actually happen, for example,
- *        if the memory is being actively transmitted. Additionally, the memory
- *        may be re-registered at any future time if a write within the same
- *        chunk was requested again, even if you attempted to unregister it
- *        here.
- *
- *    @size < 0 : TODO, not yet supported
- *        Unregister the memory NOW. This means that the caller does not
- *        expect there to be any future RDMA transfers and we just want to clean
- *        things up. This is used in case the upper layer owns the memory and
- *        cannot wait for qemu_fclose() to occur.
+ *    @size : Number of bytes to transfer
  *
  *    @bytes_sent : User-specificed pointer to indicate how many bytes were
  *                  sent. Usually, this will not be more than a few bytes of
  *                  the protocol because most transfers are sent asynchronously.
  */
-static size_t qemu_rdma_save_page(QEMUFile *f, void *opaque,
+static size_t qemu_rdma_save_page(QEMUFile *f,
                                   ram_addr_t block_offset, ram_addr_t offset,
                                   size_t size, uint64_t *bytes_sent)
 {
-    QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(opaque);
+    QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f));
     RDMAContext *rdma;
     int ret;
 
@@ -3323,61 +3237,27 @@ static size_t qemu_rdma_save_page(QEMUFile *f, void *opaque,
 
     qemu_fflush(f);
 
-    if (size > 0) {
-        /*
-         * Add this page to the current 'chunk'. If the chunk
-         * is full, or the page doesn't belong to the current chunk,
-         * an actual RDMA write will occur and a new chunk will be formed.
-         */
-        ret = qemu_rdma_write(f, rdma, block_offset, offset, size);
-        if (ret < 0) {
-            error_report("rdma migration: write error! %d", ret);
-            goto err;
-        }
-
-        /*
-         * We always return 1 bytes because the RDMA
-         * protocol is completely asynchronous. We do not yet know
-         * whether an  identified chunk is zero or not because we're
-         * waiting for other pages to potentially be merged with
-         * the current chunk. So, we have to call qemu_update_position()
-         * later on when the actual write occurs.
-         */
-        if (bytes_sent) {
-            *bytes_sent = 1;
-        }
-    } else {
-        uint64_t index, chunk;
-
-        /* TODO: Change QEMUFileOps prototype to be signed: size_t => long
-        if (size < 0) {
-            ret = qemu_rdma_drain_cq(f, rdma);
-            if (ret < 0) {
-                fprintf(stderr, "rdma: failed to synchronously drain"
-                                " completion queue before unregistration.\n");
-                goto err;
-            }
-        }
-        */
-
-        ret = qemu_rdma_search_ram_block(rdma, block_offset,
-                                         offset, size, &index, &chunk);
-
-        if (ret) {
-            error_report("ram block search failed");
-            goto err;
-        }
-
-        qemu_rdma_signal_unregister(rdma, index, chunk, 0);
+    /*
+     * Add this page to the current 'chunk'. If the chunk
+     * is full, or the page doesn't belong to the current chunk,
+     * an actual RDMA write will occur and a new chunk will be formed.
+     */
+    ret = qemu_rdma_write(f, rdma, block_offset, offset, size);
+    if (ret < 0) {
+        error_report("rdma migration: write error! %d", ret);
+        goto err;
+    }
 
-        /*
-         * TODO: Synchronous, guaranteed unregistration (should not occur during
-         * fast-path). Otherwise, unregisters will process on the next call to
-         * qemu_rdma_drain_cq()
-        if (size < 0) {
-            qemu_rdma_unregister_waiting(rdma);
-        }
-        */
+    /*
+     * We always return 1 bytes because the RDMA
+     * protocol is completely asynchronous. We do not yet know
+     * whether an  identified chunk is zero or not because we're
+     * waiting for other pages to potentially be merged with
+     * the current chunk. So, we have to call qemu_update_position()
+     * later on when the actual write occurs.
+     */
+    if (bytes_sent) {
+        *bytes_sent = 1;
     }
 
     /*
@@ -3950,14 +3830,15 @@ rdma_block_notification_handle(QIOChannelRDMA *rioc, const char *name)
     return 0;
 }
 
-static int rdma_load_hook(QEMUFile *f, void *opaque, uint64_t flags, void *data)
+static int rdma_load_hook(QEMUFile *f, uint64_t flags, void *data)
 {
+    QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f));
     switch (flags) {
     case RAM_CONTROL_BLOCK_REG:
-        return rdma_block_notification_handle(opaque, data);
+        return rdma_block_notification_handle(rioc, data);
 
     case RAM_CONTROL_HOOK:
-        return qemu_rdma_registration_handle(f, opaque);
+        return qemu_rdma_registration_handle(f, rioc);
 
     default:
         /* Shouldn't be called with any other values */
@@ -3965,10 +3846,10 @@ static int rdma_load_hook(QEMUFile *f, void *opaque, uint64_t flags, void *data)
     }
 }
 
-static int qemu_rdma_registration_start(QEMUFile *f, void *opaque,
+static int qemu_rdma_registration_start(QEMUFile *f,
                                         uint64_t flags, void *data)
 {
-    QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(opaque);
+    QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f));
     RDMAContext *rdma;
 
     RCU_READ_LOCK_GUARD();
@@ -3994,10 +3875,10 @@ static int qemu_rdma_registration_start(QEMUFile *f, void *opaque,
  * Inform dest that dynamic registrations are done for now.
  * First, flush writes, if any.
  */
-static int qemu_rdma_registration_stop(QEMUFile *f, void *opaque,
+static int qemu_rdma_registration_stop(QEMUFile *f,
                                        uint64_t flags, void *data)
 {
-    QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(opaque);
+    QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f));
     RDMAContext *rdma;
     RDMAControlHeader head = { .len = 0, .repeat = 1 };
     int ret = 0;
@@ -4170,12 +4051,12 @@ static QEMUFile *qemu_fopen_rdma(RDMAContext *rdma, const char *mode)
     rioc = QIO_CHANNEL_RDMA(object_new(TYPE_QIO_CHANNEL_RDMA));
 
     if (mode[0] == 'w') {
-        rioc->file = qemu_fopen_channel_output(QIO_CHANNEL(rioc));
+        rioc->file = qemu_file_new_output(QIO_CHANNEL(rioc));
         rioc->rdmaout = rdma;
         rioc->rdmain = rdma->return_path;
         qemu_file_set_hooks(rioc->file, &rdma_write_hooks);
     } else {
-        rioc->file = qemu_fopen_channel_input(QIO_CHANNEL(rioc));
+        rioc->file = qemu_file_new_input(QIO_CHANNEL(rioc));
         rioc->rdmain = rdma;
         rioc->rdmaout = rdma->return_path;
         qemu_file_set_hooks(rioc->file, &rdma_read_hooks);