From: Andrey Gruzdev via <qemu-devel@nongnu.org>
To: qemu-devel@nongnu.org
Cc: Den Lunev <den@openvz.org>, Eric Blake <eblake@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Juan Quintela <quintela@redhat.com>,
"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
Markus Armbruster <armbru@redhat.com>,
Peter Xu <peterx@redhat.com>,
Andrey Gruzdev <andrey.gruzdev@virtuozzo.com>
Subject: [PATCH v3 2/7] introduce UFFD-WP low-level interface helpers
Date: Thu, 19 Nov 2020 15:59:35 +0300 [thread overview]
Message-ID: <20201119125940.20017-3-andrey.gruzdev@virtuozzo.com> (raw)
In-Reply-To: <20201119125940.20017-1-andrey.gruzdev@virtuozzo.com>
Implemented support for the whole RAM block memory
protection/un-protection. Introduced higher level
ram_write_tracking_start() and ram_write_tracking_stop()
to start/stop tracking guest memory writes.
Signed-off-by: Andrey Gruzdev <andrey.gruzdev@virtuozzo.com>
---
include/exec/memory.h | 7 ++
migration/ram.c | 267 ++++++++++++++++++++++++++++++++++++++++++
migration/ram.h | 4 +
3 files changed, 278 insertions(+)
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 0f3e6bcd5e..3d798fce16 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -139,6 +139,13 @@ typedef struct IOMMUNotifier IOMMUNotifier;
/* RAM is a persistent kind memory */
#define RAM_PMEM (1 << 5)
+/*
+ * UFFDIO_WRITEPROTECT is used on this RAMBlock to
+ * support 'write-tracking' migration type.
+ * Implies ram_state->ram_wt_enabled.
+ */
+#define RAM_UF_WRITEPROTECT (1 << 6)
+
static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn,
IOMMUNotifierFlag flags,
hwaddr start, hwaddr end,
diff --git a/migration/ram.c b/migration/ram.c
index 7811cde643..7f273c9996 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -56,6 +56,12 @@
#include "savevm.h"
#include "qemu/iov.h"
#include "multifd.h"
+#include <inttypes.h>
+#include <poll.h>
+#include <sys/syscall.h>
+#include <sys/ioctl.h>
+#include <linux/userfaultfd.h>
+#include "sysemu/runstate.h"
/***********************************************************/
/* ram save/restore */
@@ -298,6 +304,8 @@ struct RAMSrcPageRequest {
struct RAMState {
/* QEMUFile used for this migration */
QEMUFile *f;
+ /* UFFD file descriptor, used in 'write-tracking' migration */
+ int uffdio_fd;
/* Last block that we have visited searching for dirty pages */
RAMBlock *last_seen_block;
/* Last block from where we have sent data */
@@ -453,6 +461,181 @@ static QemuThread *decompress_threads;
static QemuMutex decomp_done_lock;
static QemuCond decomp_done_cond;
+/**
+ * uffd_create_fd: create UFFD file descriptor
+ *
+ * Returns non-negative file descriptor or negative value in case of an error
+ */
+static int uffd_create_fd(void)
+{
+ int uffd;
+ struct uffdio_api api_struct;
+ uint64_t ioctl_mask = BIT(_UFFDIO_REGISTER) | BIT(_UFFDIO_UNREGISTER);
+
+ uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+ if (uffd < 0) {
+ error_report("uffd_create_fd() failed: UFFD not supported");
+ return -1;
+ }
+
+ api_struct.api = UFFD_API;
+ api_struct.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP;
+ if (ioctl(uffd, UFFDIO_API, &api_struct)) {
+ error_report("uffd_create_fd() failed: "
+ "API version not supported version=%llx errno=%i",
+ api_struct.api, errno);
+ goto fail;
+ }
+
+ if ((api_struct.ioctls & ioctl_mask) != ioctl_mask) {
+ error_report("uffd_create_fd() failed: "
+ "PAGEFAULT_FLAG_WP feature missing");
+ goto fail;
+ }
+
+ return uffd;
+
+fail:
+ close(uffd);
+ return -1;
+}
+
+/**
+ * uffd_close_fd: close UFFD file descriptor
+ *
+ * @uffd: UFFD file descriptor
+ */
+static void uffd_close_fd(int uffd)
+{
+ assert(uffd >= 0);
+ close(uffd);
+}
+
+/**
+ * uffd_register_memory: register memory range with UFFD
+ *
+ * Returns 0 in case of success, negative value on error
+ *
+ * @uffd: UFFD file descriptor
+ * @start: starting virtual address of memory range
+ * @length: length of memory range
+ * @track_missing: generate events on missing-page faults
+ * @track_wp: generate events on write-protected-page faults
+ */
+static int uffd_register_memory(int uffd, hwaddr start, hwaddr length,
+ bool track_missing, bool track_wp)
+{
+ struct uffdio_register uffd_register;
+
+ uffd_register.range.start = start;
+ uffd_register.range.len = length;
+ uffd_register.mode = (track_missing ? UFFDIO_REGISTER_MODE_MISSING : 0) |
+ (track_wp ? UFFDIO_REGISTER_MODE_WP : 0);
+
+ if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) {
+ error_report("uffd_register_memory() failed: "
+ "start=%0"PRIx64" len=%"PRIu64" mode=%llu errno=%i",
+ start, length, uffd_register.mode, errno);
+ return -1;
+ }
+
+ return 0;
+}
+
+/**
+ * uffd_protect_memory: protect/unprotect memory range for writes with UFFD
+ *
+ * Returns 0 on success or negative value in case of error
+ *
+ * @uffd: UFFD file descriptor
+ * @start: starting virtual address of memory range
+ * @length: length of memory range
+ * @wp: write-protect/unprotect
+ */
+static int uffd_protect_memory(int uffd, hwaddr start, hwaddr length, bool wp)
+{
+ struct uffdio_writeprotect uffd_writeprotect;
+ int res;
+
+ uffd_writeprotect.range.start = start;
+ uffd_writeprotect.range.len = length;
+ uffd_writeprotect.mode = (wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0);
+
+ do {
+ res = ioctl(uffd, UFFDIO_WRITEPROTECT, &uffd_writeprotect);
+ } while (res < 0 && errno == EINTR);
+ if (res < 0) {
+ error_report("uffd_protect_memory() failed: "
+ "start=%0"PRIx64" len=%"PRIu64" mode=%llu errno=%i",
+ start, length, uffd_writeprotect.mode, errno);
+ return -1;
+ }
+
+ return 0;
+}
+
+__attribute__ ((unused))
+static int uffd_read_events(int uffd, struct uffd_msg *msgs, int count);
+__attribute__ ((unused))
+static bool uffd_poll_events(int uffd, int tmo);
+
+/**
+ * uffd_read_events: read pending UFFD events
+ *
+ * Returns number of fetched messages, 0 if non is available or
+ * negative value in case of an error
+ *
+ * @uffd: UFFD file descriptor
+ * @msgs: pointer to message buffer
+ * @count: number of messages that can fit in the buffer
+ */
+static int uffd_read_events(int uffd, struct uffd_msg *msgs, int count)
+{
+ ssize_t res;
+ do {
+ res = read(uffd, msgs, count * sizeof(struct uffd_msg));
+ } while (res < 0 && errno == EINTR);
+
+ if ((res < 0 && errno == EAGAIN)) {
+ return 0;
+ }
+ if (res < 0) {
+ error_report("uffd_read_events() failed: errno=%i", errno);
+ return -1;
+ }
+
+ return (int) (res / sizeof(struct uffd_msg));
+}
+
+/**
+ * uffd_poll_events: poll UFFD file descriptor for read
+ *
+ * Returns true if events are available for read, false otherwise
+ *
+ * @uffd: UFFD file descriptor
+ * @tmo: timeout in milliseconds, 0 for non-blocking operation,
+ * negative value for infinite wait
+ */
+static bool uffd_poll_events(int uffd, int tmo)
+{
+ int res;
+ struct pollfd poll_fd = { .fd = uffd, .events = POLLIN, .revents = 0 };
+
+ do {
+ res = poll(&poll_fd, 1, tmo);
+ } while (res < 0 && errno == EINTR);
+
+ if (res == 0) {
+ return false;
+ }
+ if (res < 0) {
+ error_report("uffd_poll_events() failed: errno=%i", errno);
+ return false;
+ }
+
+ return (poll_fd.revents & POLLIN) != 0;
+}
+
static bool do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block,
ram_addr_t offset, uint8_t *source_buf);
@@ -3788,6 +3971,90 @@ static int ram_resume_prepare(MigrationState *s, void *opaque)
return 0;
}
+/**
+ * ram_write_tracking_start: start UFFD-WP memory tracking
+ *
+ * Returns 0 for success or negative value in case of error
+ *
+ */
+int ram_write_tracking_start(void)
+{
+ int uffd;
+ RAMState *rs = ram_state;
+ RAMBlock *bs;
+
+ /* Open UFFD file descriptor */
+ uffd = uffd_create_fd();
+ if (uffd < 0) {
+ return uffd;
+ }
+ rs->uffdio_fd = uffd;
+
+ RAMBLOCK_FOREACH_NOT_IGNORED(bs) {
+ /* Nothing to do with read-only and MMIO-writable regions */
+ if (bs->mr->readonly || bs->mr->rom_device) {
+ continue;
+ }
+
+ /* Register block memory with UFFD to track writes */
+ if (uffd_register_memory(rs->uffdio_fd, (hwaddr) bs->host,
+ bs->max_length, false, true)) {
+ goto fail;
+ }
+ /* Apply UFFD write protection to the block memory range */
+ if (uffd_protect_memory(rs->uffdio_fd, (hwaddr) bs->host,
+ bs->max_length, true)) {
+ goto fail;
+ }
+ bs->flags |= RAM_UF_WRITEPROTECT;
+
+ info_report("UFFD-WP write-tracking enabled: "
+ "block_id=%s page_size=%zu start=%p length=%lu "
+ "romd_mode=%i ram=%i readonly=%i nonvolatile=%i rom_device=%i",
+ bs->idstr, bs->page_size, bs->host, bs->max_length,
+ bs->mr->romd_mode, bs->mr->ram, bs->mr->readonly,
+ bs->mr->nonvolatile, bs->mr->rom_device);
+ }
+
+ return 0;
+
+fail:
+ uffd_close_fd(uffd);
+ rs->uffdio_fd = -1;
+ return -1;
+}
+
+/**
+ * ram_write_tracking_stop: stop UFFD-WP memory tracking and remove protection
+ */
+void ram_write_tracking_stop(void)
+{
+ RAMState *rs = ram_state;
+ RAMBlock *bs;
+ assert(rs->uffdio_fd >= 0);
+
+ RAMBLOCK_FOREACH_NOT_IGNORED(bs) {
+ if ((bs->flags & RAM_UF_WRITEPROTECT) == 0) {
+ continue;
+ }
+ info_report("UFFD-WP write-tracking disabled: "
+ "block_id=%s page_size=%zu start=%p length=%lu "
+ "romd_mode=%i ram=%i readonly=%i nonvolatile=%i rom_device=%i",
+ bs->idstr, bs->page_size, bs->host, bs->max_length,
+ bs->mr->romd_mode, bs->mr->ram, bs->mr->readonly,
+ bs->mr->nonvolatile, bs->mr->rom_device);
+ /* Cleanup flags */
+ bs->flags &= ~RAM_UF_WRITEPROTECT;
+ }
+
+ /*
+ * Close UFFD file descriptor to remove protection,
+ * release registered memory regions and flush wait queues
+ */
+ uffd_close_fd(rs->uffdio_fd);
+ rs->uffdio_fd = -1;
+}
+
static SaveVMHandlers savevm_ram_handlers = {
.save_setup = ram_save_setup,
.save_live_iterate = ram_save_iterate,
diff --git a/migration/ram.h b/migration/ram.h
index 011e85414e..3611cb51de 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -79,4 +79,8 @@ void colo_flush_ram_cache(void);
void colo_release_ram_cache(void);
void colo_incoming_start_dirty_log(void);
+/* Live snapshots */
+int ram_write_tracking_start(void);
+void ram_write_tracking_stop(void);
+
#endif
--
2.25.1
next prev parent reply other threads:[~2020-11-19 13:04 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-19 12:59 [PATCH v3 0/7] UFFD write-tracking migration/snapshots Andrey Gruzdev via
2020-11-19 12:59 ` [PATCH v3 1/7] introduce 'track-writes-ram' migration capability Andrey Gruzdev via
2020-11-19 18:51 ` Peter Xu
2020-11-19 19:07 ` Peter Xu
2020-11-20 11:35 ` Andrey Gruzdev
2020-11-24 16:55 ` Dr. David Alan Gilbert
2020-11-24 17:25 ` Andrey Gruzdev
2020-11-20 11:32 ` Andrey Gruzdev
2020-11-19 12:59 ` Andrey Gruzdev via [this message]
2020-11-19 18:39 ` [PATCH v3 2/7] introduce UFFD-WP low-level interface helpers Peter Xu
2020-11-20 11:04 ` Andrey Gruzdev
2020-11-20 15:01 ` Peter Xu
2020-11-20 15:43 ` Andrey Gruzdev
2020-11-24 17:57 ` Dr. David Alan Gilbert
2020-11-25 8:11 ` Andrey Gruzdev
2020-11-25 18:43 ` Dr. David Alan Gilbert
2020-11-25 19:17 ` Andrey Gruzdev
2020-11-19 12:59 ` [PATCH v3 3/7] support UFFD write fault processing in ram_save_iterate() Andrey Gruzdev via
2020-11-19 18:25 ` Peter Xu
2020-11-20 10:44 ` Andrey Gruzdev
2020-11-20 15:07 ` Peter Xu
2020-11-20 16:15 ` Andrey Gruzdev
2020-11-20 16:43 ` Peter Xu
2020-11-20 16:53 ` Andrey Gruzdev
2020-11-23 21:34 ` Peter Xu
2020-11-24 8:02 ` Andrey Gruzdev
2020-11-24 15:17 ` Peter Xu
2020-11-24 17:40 ` Andrey Gruzdev
2020-11-25 13:08 ` Dr. David Alan Gilbert
2020-11-25 14:40 ` Andrey Gruzdev
2020-11-25 18:41 ` Dr. David Alan Gilbert
2020-11-25 19:12 ` Andrey Gruzdev
2020-11-19 12:59 ` [PATCH v3 4/7] implementation of write-tracking migration thread Andrey Gruzdev via
2020-11-19 18:47 ` Peter Xu
2020-11-20 11:41 ` Andrey Gruzdev
2020-11-19 12:59 ` [PATCH v3 5/7] implementation of vm_start() BH Andrey Gruzdev via
2020-11-19 18:46 ` Peter Xu
2020-11-20 11:13 ` Andrey Gruzdev
2020-11-19 12:59 ` [PATCH v3 6/7] the rest of write tracking migration code Andrey Gruzdev via
2020-11-19 12:59 ` [PATCH v3 7/7] introduce simple linear scan rate limiting mechanism Andrey Gruzdev via
2020-11-19 20:02 ` Peter Xu
2020-11-20 12:06 ` Andrey Gruzdev
2020-11-20 15:23 ` Peter Xu
2020-11-24 16:41 ` [PATCH v3 0/7] UFFD write-tracking migration/snapshots Dr. David Alan Gilbert
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201119125940.20017-3-andrey.gruzdev@virtuozzo.com \
--to=qemu-devel@nongnu.org \
--cc=andrey.gruzdev@virtuozzo.com \
--cc=armbru@redhat.com \
--cc=den@openvz.org \
--cc=dgilbert@redhat.com \
--cc=eblake@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=quintela@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).