From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:50238) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yi4HQ-0007IY-LR for qemu-devel@nongnu.org; Tue, 14 Apr 2015 13:05:46 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Yi4HL-0002xg-SD for qemu-devel@nongnu.org; Tue, 14 Apr 2015 13:05:44 -0400 Received: from mx1.redhat.com ([209.132.183.28]:48701) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yi4HL-0002xO-Cc for qemu-devel@nongnu.org; Tue, 14 Apr 2015 13:05:39 -0400 From: "Dr. David Alan Gilbert (git)" Date: Tue, 14 Apr 2015 18:03:56 +0100 Message-Id: <1429031053-4454-31-git-send-email-dgilbert@redhat.com> In-Reply-To: <1429031053-4454-1-git-send-email-dgilbert@redhat.com> References: <1429031053-4454-1-git-send-email-dgilbert@redhat.com> Subject: [Qemu-devel] [PATCH v6 30/47] postcopy: Incoming initialisation List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: aarcange@redhat.com, yamahata@private.email.ne.jp, quintela@redhat.com, amit.shah@redhat.com, pbonzini@redhat.com, david@gibson.dropbear.id.au, yayanghy@cn.fujitsu.com From: "Dr. David Alan Gilbert" Signed-off-by: Dr. David Alan Gilbert Reviewed-by: David Gibson --- arch_init.c | 11 ++++ include/migration/migration.h | 3 + include/migration/postcopy-ram.h | 12 ++++ migration/postcopy-ram.c | 116 +++++++++++++++++++++++++++++++++++++++ savevm.c | 4 ++ trace-events | 2 + 6 files changed, 148 insertions(+) diff --git a/arch_init.c b/arch_init.c index efc2938..2c937d1 100644 --- a/arch_init.c +++ b/arch_init.c @@ -1353,6 +1353,17 @@ void ram_handle_compressed(void *host, uint8_t ch, uint64_t size) } } +/* + * Allocate data structures etc needed by incoming migration with postcopy-ram + * postcopy-ram's similarly names postcopy_ram_incoming_init does the work + */ +int ram_postcopy_incoming_init(MigrationIncomingState *mis) +{ + size_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS; + + return postcopy_ram_incoming_init(mis, ram_pages); +} + static int ram_load(QEMUFile *f, void *opaque, int version_id) { int flags = 0, ret = 0; diff --git a/include/migration/migration.h b/include/migration/migration.h index 15707fc..8c8afc4 100644 --- a/include/migration/migration.h +++ b/include/migration/migration.h @@ -73,6 +73,8 @@ struct MigrationIncomingState { */ QemuEvent main_thread_load_event; + /* For the kernel to send us notifications */ + int userfault_fd; QEMUFile *return_path; QemuMutex rp_mutex; /* We send replies from multiple threads */ }; @@ -190,6 +192,7 @@ int ram_postcopy_send_discard_bitmap(MigrationState *ms); /* For incoming postcopy discard */ int ram_discard_range(MigrationIncomingState *mis, const char *block_name, uint64_t start, uint64_t end); +int ram_postcopy_incoming_init(MigrationIncomingState *mis); /** * @migrate_add_blocker - prevent migration from proceeding diff --git a/include/migration/postcopy-ram.h b/include/migration/postcopy-ram.h index 1d38f76..b46af08 100644 --- a/include/migration/postcopy-ram.h +++ b/include/migration/postcopy-ram.h @@ -17,6 +17,18 @@ bool postcopy_ram_supported_by_host(void); /* + * Initialise postcopy-ram, setting the RAM to a state where we can go into + * postcopy later; must be called prior to any precopy. + * called from arch_init's similarly named ram_postcopy_incoming_init + */ +int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages); + +/* + * At the end of a migration where postcopy_ram_incoming_init was called. + */ +int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis); + +/* * Discard the contents of memory start..end inclusive. * We can assume that if we've been called postcopy_ram_hosttest returned true */ diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index a10f3ca..16b78c2 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -176,6 +176,111 @@ int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start, return 0; } +/* + * Setup an area of RAM so that it *can* be used for postcopy later; this + * must be done right at the start prior to pre-copy. + * opaque should be the MIS. + */ +static int init_area(const char *block_name, void *host_addr, + ram_addr_t offset, ram_addr_t length, void *opaque) +{ + MigrationIncomingState *mis = opaque; + + trace_postcopy_init_area(block_name, host_addr, offset, length); + + /* + * We need the whole of RAM to be truly empty for postcopy, so things + * like ROMs and any data tables built during init must be zero'd + * - we're going to get the copy from the source anyway. + * (Precopy will just overwrite this data, so doesn't need the discard) + */ + if (postcopy_ram_discard_range(mis, host_addr, (host_addr + length - 1))) { + return -1; + } + + /* + * We also need the area to be normal 4k pages, not huge pages + * (otherwise we can't be sure we can atomically place the + * 4k page in later). THP might come along and map a 2MB page + * and when it's partially accessed in precopy it might not break + * it down, but leave a 2MB zero'd page. + */ +#ifdef MADV_NOHUGEPAGE + if (madvise(host_addr, length, MADV_NOHUGEPAGE)) { + error_report("%s: NOHUGEPAGE: %s", __func__, strerror(errno)); + return -1; + } +#endif + + return 0; +} + +/* + * At the end of migration, undo the effects of init_area + * opaque should be the MIS. + */ +static int cleanup_area(const char *block_name, void *host_addr, + ram_addr_t offset, ram_addr_t length, void *opaque) +{ + MigrationIncomingState *mis = opaque; + struct uffdio_range range_struct; + trace_postcopy_cleanup_area(block_name, host_addr, offset, length); + + /* + * We turned off hugepage for the precopy stage with postcopy enabled + * we can turn it back on now. + */ +#ifdef MADV_HUGEPAGE + if (madvise(host_addr, length, MADV_HUGEPAGE)) { + error_report("%s HUGEPAGE: %s", __func__, strerror(errno)); + return -1; + } +#endif + + /* + * We can also turn off userfault now since we should have all the + * pages. It can be useful to leave it on to debug postcopy + * if you're not sure it's always getting every page. + */ + range_struct.start = (uintptr_t)host_addr; + range_struct.len = length; + + if (ioctl(mis->userfault_fd, UFFDIO_UNREGISTER, &range_struct)) { + error_report("%s: userfault unregister %s", __func__, strerror(errno)); + + return -1; + } + + return 0; +} + +/* + * Initialise postcopy-ram, setting the RAM to a state where we can go into + * postcopy later; must be called prior to any precopy. + * called from arch_init's similarly named ram_postcopy_incoming_init + */ +int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages) +{ + if (qemu_ram_foreach_block(init_area, mis)) { + return -1; + } + + return 0; +} + +/* + * At the end of a migration where postcopy_ram_incoming_init was called. + */ +int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis) +{ + /* TODO: Join the fault thread once we're sure it will exit */ + if (qemu_ram_foreach_block(cleanup_area, mis)) { + return -1; + } + + return 0; +} + #else /* No target OS support, stubs just fail */ @@ -185,6 +290,17 @@ bool postcopy_ram_supported_by_host(void) return false; } +int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages) +{ + error_report("postcopy_ram_incoming_init: No OS support"); + return -1; +} + +int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis) +{ + assert(0); +} + int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start, uint8_t *end) { diff --git a/savevm.c b/savevm.c index b7f0846..c383ce0 100644 --- a/savevm.c +++ b/savevm.c @@ -1185,6 +1185,10 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis, return -1; } + if (ram_postcopy_incoming_init(mis)) { + return -1; + } + postcopy_state_set(mis, POSTCOPY_INCOMING_ADVISE); return 0; diff --git a/trace-events b/trace-events index 6ab309d..b2099ee 100644 --- a/trace-events +++ b/trace-events @@ -1482,7 +1482,9 @@ rdma_start_outgoing_migration_after_rdma_source_init(void) "" # migration/postcopy-ram.c postcopy_discard_send_finish(const char *ramblock, int nwords, int ncmds) "%s mask words sent=%d in %d commands" +postcopy_cleanup_area(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=%zx length=%zx" postcopy_ram_discard_range(void *start, void *end) "%p,%p" +postcopy_init_area(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=%zx length=%zx" # kvm-all.c kvm_ioctl(int type, void *arg) "type 0x%x, arg %p" -- 2.1.0