[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH v4 21/47] Add wrappers and handlers for sending/rece
From: |
Dr. David Alan Gilbert (git) |
Subject: |
[Qemu-devel] [PATCH v4 21/47] Add wrappers and handlers for sending/receiving the postcopy-ram migration messages. |
Date: |
Fri, 3 Oct 2014 18:47:27 +0100 |
From: "Dr. David Alan Gilbert" <address@hidden>
Add state variable showing current incoming postcopy state.
Signed-off-by: Dr. David Alan Gilbert <address@hidden>
---
include/migration/migration.h | 8 +
include/sysemu/sysemu.h | 20 +++
savevm.c | 335 ++++++++++++++++++++++++++++++++++++++++++
3 files changed, 363 insertions(+)
diff --git a/include/migration/migration.h b/include/migration/migration.h
index 0d9f62d..2c078c4 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -61,6 +61,14 @@ typedef struct MigrationState MigrationState;
struct MigrationIncomingState {
QEMUFile *file;
+ volatile enum {
+ POSTCOPY_RAM_INCOMING_NONE = 0, /* Initial state - no postcopy */
+ POSTCOPY_RAM_INCOMING_ADVISE,
+ POSTCOPY_RAM_INCOMING_LISTENING,
+ POSTCOPY_RAM_INCOMING_RUNNING,
+ POSTCOPY_RAM_INCOMING_END
+ } postcopy_ram_state;
+
QEMUFile *return_path;
QemuMutex rp_mutex; /* We send replies from multiple threads */
};
diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index ad96f2a..102dd93 100644
--- a/include/sysemu/sysemu.h
+++ b/include/sysemu/sysemu.h
@@ -88,6 +88,16 @@ enum qemu_vm_cmd {
QEMU_VM_CMD_OPENRP, /* Tell the dest to open the Return path */
QEMU_VM_CMD_REQACK, /* Request an ACK on the RP */
+ QEMU_VM_CMD_POSTCOPY_RAM_ADVISE = 20, /* Prior to any page transfers, just
+ warn we might want to do PC */
+ QEMU_VM_CMD_POSTCOPY_RAM_DISCARD, /* A list of pages to discard that
+ were previously sent during
+ precopy but are dirty. */
+ QEMU_VM_CMD_POSTCOPY_RAM_LISTEN, /* Start listening for incoming
+ pages as it's running. */
+ QEMU_VM_CMD_POSTCOPY_RAM_RUN, /* Start execution */
+ QEMU_VM_CMD_POSTCOPY_RAM_END, /* Postcopy is finished. */
+
QEMU_VM_CMD_AFTERLASTVALID
};
@@ -102,6 +112,16 @@ void qemu_savevm_command_send(QEMUFile *f, enum
qemu_vm_cmd command,
uint16_t len, uint8_t *data);
void qemu_savevm_send_reqack(QEMUFile *f, uint32_t value);
void qemu_savevm_send_openrp(QEMUFile *f);
+void qemu_savevm_send_postcopy_ram_advise(QEMUFile *f);
+void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name,
+ uint16_t len, uint8_t offset,
+ uint64_t *addrlist,
+ uint32_t *masklist);
+
+void qemu_savevm_send_postcopy_ram_listen(QEMUFile *f);
+void qemu_savevm_send_postcopy_ram_run(QEMUFile *f);
+void qemu_savevm_send_postcopy_ram_end(QEMUFile *f, uint8_t status);
+
int qemu_loadvm_state(QEMUFile *f);
/* SLIRP */
diff --git a/savevm.c b/savevm.c
index 7236232..b942e8c 100644
--- a/savevm.c
+++ b/savevm.c
@@ -39,6 +39,7 @@
#include "exec/memory.h"
#include "qmp-commands.h"
#include "trace.h"
+#include "qemu/bitops.h"
#include "qemu/iov.h"
#include "block/snapshot.h"
#include "block/qapi.h"
@@ -624,6 +625,92 @@ void qemu_savevm_send_openrp(QEMUFile *f)
{
qemu_savevm_command_send(f, QEMU_VM_CMD_OPENRP, 0, NULL);
}
+
+/* Send prior to any RAM transfer */
+void qemu_savevm_send_postcopy_ram_advise(QEMUFile *f)
+{
+ DPRINTF("send postcopy-ram-advise");
+ uint64_t tmp[2];
+ tmp[0] = cpu_to_be64(sysconf(_SC_PAGESIZE));
+ tmp[1] = cpu_to_be64(1ul << qemu_target_page_bits());
+
+ qemu_savevm_command_send(f, QEMU_VM_CMD_POSTCOPY_RAM_ADVISE, 16,
+ (uint8_t *)tmp);
+}
+
+/* Prior to running, to cause pages that have been dirtied after precopy
+ * started to be discarded on the destination.
+ * CMD_POSTCOPY_RAM_DISCARD consist of:
+ * 3 byte header (filled in by qemu_savevm_send_postcopy_ram_discard)
+ * byte version (0)
+ * byte offset into the 1st data word containing 1st page of RAMBlock
+ * byte Length of name field
+ * n x byte RAM block name (NOT 0 terminated)
+ * n x
+ * be64 Page addresses for start of an invalidation range
+ * be32 mask of 32 pages, '1' to discard'
+ *
+ * Hopefully this is pretty sparse so we don't get too many entries,
+ * and using the mask should deal with most pagesize differences
+ * just ending up as a single full mask
+ *
+ * The mask is always 32bits irrespective of the long size
+ *
+ * name: RAMBlock name that these entries are part of
+ * len: Number of page entries
+ * addrlist: 'len' addresses
+ * masklist: 'len' masks (corresponding to the addresses)
+ */
+void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name,
+ uint16_t len, uint8_t offset,
+ uint64_t *addrlist,
+ uint32_t *masklist)
+{
+ uint8_t *buf;
+ uint16_t tmplen;
+ uint16_t t;
+
+ DPRINTF("send postcopy-ram-discard");
+ buf = g_malloc0(len*12 + strlen(name) + 3);
+ buf[0] = 0; /* Version */
+ buf[1] = offset;
+ assert(strlen(name) < 256);
+ buf[2] = strlen(name);
+ memcpy(buf+3, name, strlen(name));
+ tmplen = 3+strlen(name);
+
+ for (t = 0; t < len; t++) {
+ cpu_to_be64w((uint64_t *)(buf + tmplen), addrlist[t]);
+ tmplen += 8;
+ cpu_to_be32w((uint32_t *)(buf + tmplen), masklist[t]);
+ tmplen += 4;
+ }
+ qemu_savevm_command_send(f, QEMU_VM_CMD_POSTCOPY_RAM_DISCARD,
+ tmplen, buf);
+ g_free(buf);
+}
+
+/* Get the destination into a state where it can receive page data. */
+void qemu_savevm_send_postcopy_ram_listen(QEMUFile *f)
+{
+ DPRINTF("send postcopy-ram-listen");
+ qemu_savevm_command_send(f, QEMU_VM_CMD_POSTCOPY_RAM_LISTEN, 0, NULL);
+}
+
+/* Kick the destination into running */
+void qemu_savevm_send_postcopy_ram_run(QEMUFile *f)
+{
+ DPRINTF("send postcopy-ram-run");
+ qemu_savevm_command_send(f, QEMU_VM_CMD_POSTCOPY_RAM_RUN, 0, NULL);
+}
+
+/* End of postcopy - with a status byte; 0 is good, anything else is a fail */
+void qemu_savevm_send_postcopy_ram_end(QEMUFile *f, uint8_t status)
+{
+ DPRINTF("send postcopy-ram-end");
+ qemu_savevm_command_send(f, QEMU_VM_CMD_POSTCOPY_RAM_END, 1, &status);
+}
+
bool qemu_savevm_state_blocked(Error **errp)
{
SaveStateEntry *se;
@@ -935,6 +1022,220 @@ static LoadStateEntry_Head loadvm_handlers =
static int qemu_loadvm_state_main(QEMUFile *f,
LoadStateEntry_Head *loadvm_handlers);
+/* ------ incoming postcopy-ram messages ------ */
+/* 'advise' arrives before any RAM transfers just to tell us that a postcopy
+ * *might* happen - it might be skipped if precopy transferred everything
+ * quickly.
+ */
+static int loadvm_postcopy_ram_handle_advise(MigrationIncomingState *mis,
+ uint64_t remote_hps,
+ uint64_t remote_tps)
+{
+ DPRINTF("%s", __func__);
+ if (mis->postcopy_ram_state != POSTCOPY_RAM_INCOMING_NONE) {
+ error_report("CMD_POSTCOPY_RAM_ADVISE in wrong postcopy state (%d)",
+ mis->postcopy_ram_state);
+ return -1;
+ }
+
+ if (remote_hps != sysconf(_SC_PAGESIZE)) {
+ /*
+ * Some combinations of mismatch are probably possible but it gets
+ * a bit more complicated. In particular we need to place whole
+ * host pages on the dest at once, and we need to ensure that we
+ * handle dirtying to make sure we never end up sending part of
+ * a hostpage on it's own.
+ */
+ error_report("Postcopy needs matching host page sizes (s=%d d=%d)",
+ (int)remote_hps, (int)sysconf(_SC_PAGESIZE));
+ return -1;
+ }
+
+ if (remote_tps != (1ul << qemu_target_page_bits())) {
+ /*
+ * Again, some differences could be dealt with, but for now keep it
+ * simple.
+ */
+ error_report("Postcopy needs matching target page sizes (s=%d d=%d)",
+ (int)remote_tps, 1 << qemu_target_page_bits());
+ return -1;
+ }
+
+ mis->postcopy_ram_state = POSTCOPY_RAM_INCOMING_ADVISE;
+
+ /*
+ * Postcopy will be sending lots of small messages along the return path
+ * that it needs quick answers to.
+ */
+ socket_set_nodelay(qemu_get_fd(mis->return_path));
+
+ return 0;
+}
+
+/* After postcopy we will be told to throw some pages away since they're
+ * dirty and will have to be demand fetched. Must happen before CPU is
+ * started.
+ * There can be 0..many of these messages, each encoding multiple pages.
+ * Bits set in the message represent a page in the source VMs bitmap, but
+ * since the guest/target page sizes can be different on s/d then we have
+ * to convert.
+ */
+static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis,
+ uint16_t len)
+{
+ int tmp;
+ unsigned int first_bit_offset;
+ char ramid[256];
+
+ DPRINTF("%s", __func__);
+
+ if (mis->postcopy_ram_state != POSTCOPY_RAM_INCOMING_ADVISE) {
+ error_report("CMD_POSTCOPY_RAM_DISCARD in wrong postcopy state (%d)",
+ mis->postcopy_ram_state);
+ return -1;
+ }
+ /* We're expecting a
+ * 3 byte header,
+ * a RAM ID string
+ * then at least 1 12 byte chunks
+ */
+ if (len < 16) {
+ error_report("CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len);
+ return -1;
+ }
+
+ tmp = qemu_get_byte(mis->file);
+ if (tmp != 0) {
+ error_report("CMD_POSTCOPY_RAM_DISCARD invalid version (%d)", tmp);
+ return -1;
+ }
+ first_bit_offset = qemu_get_byte(mis->file);
+
+ if (qemu_get_counted_string(mis->file, (uint8_t *)ramid)) {
+ error_report("CMD_POSTCOPY_RAM_DISCARD Failed to read RAMBlock ID");
+ return -1;
+ }
+
+ len -= 3+strlen(ramid);
+ if (len % 12) {
+ error_report("CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len);
+ return -1;
+ }
+ while (len) {
+ uint64_t startaddr;
+ uint32_t mask;
+ /*
+ * We now have pairs of address, mask
+ * The mask is 32 bits of bitmask starting at 'startaddr'-offset
+ * RAMBlock; e.g. if the RAMBlock started at 8k where TPS=4k
+ * then first_bit_offset=2 and the 1st 2 bits of the mask
+ * aren't relevant to this RAMBlock, and bit 2 corresponds
+ * to the 1st page of this RAMBlock
+ */
+ startaddr = qemu_get_be64(mis->file);
+ mask = qemu_get_be32(mis->file);
+
+ len -= 12;
+
+ while (mask) {
+ /* mask= .....?10...0 */
+ /* ^fs */
+ int firstset = ctz32(mask);
+
+ /* tmp32=.....?11...1 */
+ /* ^fs */
+ uint32_t tmp32 = mask | ((((uint32_t)1)<<firstset)-1);
+
+ /* mask= .?01..10...0 */
+ /* ^fz ^fs */
+ int firstzero = cto32(tmp32);
+
+ if ((startaddr == 0) && (firstset < first_bit_offset)) {
+ error_report("CMD_POSTCOPY_RAM_DISCARD bad data; bit set"
+ " prior to block; block=%s offset=%d"
+ " firstset=%d\n", ramid, first_bit_offset,
+ firstzero);
+ return -1;
+ }
+
+ /*
+ * we know there must be at least 1 bit set due to the loop entry
+ * If there is no 0 firstzero will be 32
+ */
+ /* TODO - ram_discard_range gets added in a later patch
+ int ret = ram_discard_range(mis, ramid,
+ startaddr + firstset - first_bit_offset,
+ startaddr + (firstzero - 1) -
first_bit_offset);
+ ret = -1;
+ if (ret) {
+ return ret;
+ }
+ */
+
+ /* mask= .?0000000000 */
+ /* ^fz ^fs */
+ if (firstzero != 32) {
+ mask &= (((uint32_t)-1) << firstzero);
+ } else {
+ mask = 0;
+ }
+ }
+ }
+ DPRINTF("%s finished", __func__);
+
+ return 0;
+}
+
+/* After this message we must be able to immediately receive page data */
+static int loadvm_postcopy_ram_handle_listen(MigrationIncomingState *mis)
+{
+ DPRINTF("%s", __func__);
+ if (mis->postcopy_ram_state != POSTCOPY_RAM_INCOMING_ADVISE) {
+ error_report("CMD_POSTCOPY_RAM_LISTEN in wrong postcopy state (%d)",
+ mis->postcopy_ram_state);
+ return -1;
+ }
+
+ mis->postcopy_ram_state = POSTCOPY_RAM_INCOMING_LISTENING;
+
+ /* TODO start up the postcopy listening thread */
+ return 0;
+}
+
+/* After all discards we can start running and asking for pages */
+static int loadvm_postcopy_ram_handle_run(MigrationIncomingState *mis)
+{
+ DPRINTF("%s", __func__);
+ if (mis->postcopy_ram_state != POSTCOPY_RAM_INCOMING_LISTENING) {
+ error_report("CMD_POSTCOPY_RAM_RUN in wrong postcopy state (%d)",
+ mis->postcopy_ram_state);
+ return -1;
+ }
+
+ mis->postcopy_ram_state = POSTCOPY_RAM_INCOMING_RUNNING;
+ if (autostart) {
+ /* Hold onto your hats, starting the CPU */
+ vm_start();
+ } else {
+ /* leave it paused and let management decide when to start the CPU */
+ runstate_set(RUN_STATE_PAUSED);
+ }
+
+ return 0;
+}
+
+/* The end - with a byte from the source which can tell us to fail. */
+static int loadvm_postcopy_ram_handle_end(MigrationIncomingState *mis)
+{
+ DPRINTF("%s", __func__);
+ if (mis->postcopy_ram_state == POSTCOPY_RAM_INCOMING_NONE) {
+ error_report("CMD_POSTCOPY_RAM_END in wrong postcopy state (%d)",
+ mis->postcopy_ram_state);
+ return -1;
+ }
+ return -1; /* TODO - expecting 1 byte good/fail */
+}
+
static int loadvm_process_command_simple_lencheck(const char *name,
unsigned int actual,
unsigned int expected)
@@ -961,6 +1262,7 @@ static int loadvm_process_command(QEMUFile *f,
uint16_t com;
uint16_t len;
uint32_t tmp32;
+ uint64_t tmp64a, tmp64b;
com = qemu_get_be16(f);
len = qemu_get_be16(f);
@@ -997,6 +1299,39 @@ static int loadvm_process_command(QEMUFile *f,
migrate_send_rp_ack(mis, tmp32);
break;
+ case QEMU_VM_CMD_POSTCOPY_RAM_ADVISE:
+ if (loadvm_process_command_simple_lencheck("CMD_POSTCOPY_RAM_ADVISE",
+ len, 16)) {
+ return -1;
+ }
+ tmp64a = qemu_get_be64(f); /* hps */
+ tmp64b = qemu_get_be64(f); /* tps */
+ return loadvm_postcopy_ram_handle_advise(mis, tmp64a, tmp64b);
+
+ case QEMU_VM_CMD_POSTCOPY_RAM_DISCARD:
+ return loadvm_postcopy_ram_handle_discard(mis, len);
+
+ case QEMU_VM_CMD_POSTCOPY_RAM_LISTEN:
+ if (loadvm_process_command_simple_lencheck("CMD_POSTCOPY_RAM_LISTEN",
+ len, 0)) {
+ return -1;
+ }
+ return loadvm_postcopy_ram_handle_listen(mis);
+
+ case QEMU_VM_CMD_POSTCOPY_RAM_RUN:
+ if (loadvm_process_command_simple_lencheck("CMD_POSTCOPY_RAM_RUN",
+ len, 0)) {
+ return -1;
+ }
+ return loadvm_postcopy_ram_handle_run(mis);
+
+ case QEMU_VM_CMD_POSTCOPY_RAM_END:
+ if (loadvm_process_command_simple_lencheck("CMD_POSTCOPY_RAM_END",
+ len, 1)) {
+ return -1;
+ }
+ return loadvm_postcopy_ram_handle_end(mis);
+
default:
error_report("VM_COMMAND 0x%x unknown (len 0x%x)", com, len);
return -1;
--
1.9.3
- [Qemu-devel] [PATCH v4 17/47] qemu_loadvm errors and debug, (continued)
[Qemu-devel] [PATCH v4 20/47] Add migration-capability boolean for postcopy-ram., Dr. David Alan Gilbert (git), 2014/10/03
[Qemu-devel] [PATCH v4 21/47] Add wrappers and handlers for sending/receiving the postcopy-ram migration messages.,
Dr. David Alan Gilbert (git) <=
[Qemu-devel] [PATCH v4 22/47] QEMU_VM_CMD_PACKAGED: Send a packaged chunk of migration stream, Dr. David Alan Gilbert (git), 2014/10/03
[Qemu-devel] [PATCH v4 23/47] migrate_init: Call from savevm, Dr. David Alan Gilbert (git), 2014/10/03
[Qemu-devel] [PATCH v4 24/47] Allow savevm handlers to state whether they could go into postcopy, Dr. David Alan Gilbert (git), 2014/10/03
[Qemu-devel] [PATCH v4 25/47] postcopy: OS support test, Dr. David Alan Gilbert (git), 2014/10/03
[Qemu-devel] [PATCH v4 26/47] migrate_start_postcopy: Command to trigger transition to postcopy, Dr. David Alan Gilbert (git), 2014/10/03
[Qemu-devel] [PATCH v4 27/47] MIG_STATE_POSTCOPY_ACTIVE: Add new migration state, Dr. David Alan Gilbert (git), 2014/10/03
[Qemu-devel] [PATCH v4 28/47] qemu_savevm_state_complete: Postcopy changes, Dr. David Alan Gilbert (git), 2014/10/03
[Qemu-devel] [PATCH v4 29/47] Postcopy page-map-incoming (PMI) structure, Dr. David Alan Gilbert (git), 2014/10/03
[Qemu-devel] [PATCH v4 30/47] Postcopy: Maintain sentmap and calculate discard, Dr. David Alan Gilbert (git), 2014/10/03