From: "Dr. David Alan Gilbert" <dgilb...@redhat.com>
userfaultfd is a Linux syscall that gives an fd that receives a stream
of notifications of accesses to pages marked as MADV_USERFAULT, and
allows the program to acknowledge those stalls and tell the accessing
thread to carry on.
Signed-off-by: Dr. David Alan Gilbert <dgilb...@redhat.com>
---
postcopy-ram.c | 95 ++++++++++++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 89 insertions(+), 6 deletions(-)
diff --git a/postcopy-ram.c b/postcopy-ram.c
index 8d0a225..466c42b 100644
--- a/postcopy-ram.c
+++ b/postcopy-ram.c
@@ -68,6 +68,14 @@
#define __NR_remap_anon_pages 317
#endif
+#ifndef __NR_userfaultfd
+#define __NR_userfaultfd 318
+#endif
+
+#ifndef USERFAULTFD_PROTOCOL
+#define USERFAULTFD_PROTOCOL (uint64_t)0xaa
+#endif
+
/* ---------------------------------------------------------------------- */
/* Postcopy pagemap-inbound (pmi) - data structures that record the */
/* state of each page used by the inbound postcopy */
@@ -192,6 +200,7 @@ int postcopy_ram_hosttest(void)
*/
void *testarea, *testarea2;
long pagesize = getpagesize();
+ int ufd;
testarea = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE |
MAP_ANONYMOUS, -1, 0);
@@ -201,15 +210,24 @@ int postcopy_ram_hosttest(void)
}
g_assert(((size_t)testarea & (pagesize-1)) == 0);
+ ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
+ if (ufd == -1) {
+ perror("postcopy_ram_hosttest: userfaultfd not available");
+ munmap(testarea, pagesize);
+ return -1;
+ }
+
if (madvise(testarea, pagesize, MADV_USERFAULT)) {
perror("postcopy_ram_hosttest: MADV_USERFAULT not available");
munmap(testarea, pagesize);
+ close(ufd);
return -1;
}
if (madvise(testarea, pagesize, MADV_NOUSERFAULT)) {
perror("postcopy_ram_hosttest: MADV_NOUSERFAULT not available");
munmap(testarea, pagesize);
+ close(ufd);
return -1;
}
@@ -226,11 +244,13 @@ int postcopy_ram_hosttest(void)
perror("postcopy_ram_hosttest: remap_anon_pages not available");
munmap(testarea, pagesize);
munmap(testarea2, pagesize);
+ close(ufd);
return -1;
}
munmap(testarea, pagesize);
munmap(testarea2, pagesize);
+ close(ufd);
return 0;
}
@@ -361,6 +381,39 @@ static int postcopy_ram_sensitise_area(const char
*block_name, void *host_addr,
}
/*
+ * Tell the kernel that we've now got some memory it previously asked for.
+ * Note: We're not allowed to ack a page which wasn't requested.
+ */
+static int ack_userfault(MigrationIncomingState *mis, void *start, size_t len)
+{
+ uint64_t tmp[2];
+
+ /* Kernel wants the range that's now safe to access */
+ tmp[0] = (uint64_t)start;
+ tmp[1] = (uint64_t)start + (uint64_t)(len-1);
+
+ if (write(mis->userfault_fd, tmp, 16) != 16) {
+ int e = errno;
+
+ if (e == ENOENT) {
+ /* Kernel said it wasn't waiting - one case where this can
+ * happen is where two threads triggered the userfault
+ * and we receive the page and ack it just after we received
+ * the 2nd request and that ends up deciding it should ack it
+ * We could optimise it out, but it's rare.
+ */
+ /*fprintf(stderr, "ack_userfault: %p/%zx ENOENT\n", start, len); */
+ return 0;
+ }
+ error_report("postcopy_ram: Failed to notify kernel for %p/%zx (%d)",
+ start, len, e);
+ return -errno;
+ }
+
+ return 0;
+}
+
+/*
* Handle faults detected by the USERFAULT markings
*/
static void *postcopy_ram_fault_thread(void *opaque)
@@ -420,10 +473,9 @@ static void *postcopy_ram_fault_thread(void *opaque)
/* Already arrived - no state change, just kick the kernel */
DPRINTF("postcopy_ram_fault_thread: notify pre of %p",
hostaddr);
- /* TODO! Send ack
if (ack_userfault(mis, hostaddr, hostpagesize)) {
assert(0);
- } */
+ }
break;
case POSTCOPY_PMI_MISSING:
@@ -464,8 +516,33 @@ static void *postcopy_ram_fault_thread(void *opaque)
int postcopy_ram_enable_notify(MigrationIncomingState *mis)
{
- /* Create the fault handler thread and wait for it to be ready */
- mis->userfault_fd = -1; /* TODO */
+ uint64_t tmp64;
+
+ /* Open the fd for the kernel to give us userfaults */
+ mis->userfault_fd = syscall(__NR_userfaultfd, O_CLOEXEC);
+ if (mis->userfault_fd == -1) {
+ perror("Failed to open userfault fd");
+ return -1;
+ }
+
+ /*
+ * Version handshake, we send it the version we want and expect to get the
+ * same back.
+ */
+ tmp64 = USERFAULTFD_PROTOCOL;
+ if (write(mis->userfault_fd, &tmp64, sizeof(tmp64)) != sizeof(tmp64)) {
+ perror("Writing userfaultfd version");
+ return -1;
+ }
+ if (read(mis->userfault_fd, &tmp64, sizeof(tmp64)) != sizeof(tmp64)) {
+ perror("Reading userfaultfd version");
+ return -1;
+ }
+ if (tmp64 != USERFAULTFD_PROTOCOL) {
+ error_report("Mismatched userfaultfd version, expected %zx, got %zx",
+ (size_t)USERFAULTFD_PROTOCOL, (size_t)tmp64);
+ }
+
qemu_sem_init(&mis->fault_thread_sem, 0);
qemu_thread_create(&mis->fault_thread, "postcopy/fault",
postcopy_ram_fault_thread, mis, QEMU_THREAD_JOINABLE);
@@ -476,6 +553,8 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
return -1;
}
+ DPRINTF("postcopy_ram_enable_notify: Sensitised");
+
return 0;
}
@@ -509,11 +588,12 @@ int postcopy_place_page(MigrationIncomingState *mis, void
*host, void *from,
if (syscall(__NR_remap_anon_pages, host, from, getpagesize(), 0) !=
getpagesize()) {
+ int e = errno;
perror("remap_anon_pages in postcopy_place_page");
fprintf(stderr, "host: %p from: %p pmi=%d\n", host, from,
postcopy_pmi_get_state(mis, bitmap_offset));
- return -errno;
+ return -e;
}
tmp_state = postcopy_pmi_get_state(mis, bitmap_offset);
@@ -526,7 +606,10 @@ int postcopy_place_page(MigrationIncomingState *mis, void
*host, void *from,
if (old_state == POSTCOPY_PMI_REQUESTED) {
- /* TODO: Notify kernel */
+ /* Send the kernel the host address that should now be accessible */
+ DPRINTF("%s: Notifying kernel bitmap_offset=0x%lx host=%p",
+ __func__, bitmap_offset, host);
+ return ack_userfault(mis, host, getpagesize());
}
/* TODO: hostpagesize!=targetpagesize case */
--
1.9.3
