In fast snapshot load, we would like to serve faults as soon as possible hence loading pages directly instead of requesting a source
Add postcopy_mapped_ram_load_page() function which serves single page fault by reading the snapshot file. It uses bitmap_test_and_clear_atomic on pending_bmap to coordinate between threads so each page is loaded exactly once. Non-zero pages are read using qemu_get_buffer_at into a temporary page (for loading page atomically), which is then placed using postcopy_place_page. Zero pages are placed directly using postcopy_place_page_zero. Update postcopy_ram_fault_thread to call postcopy_mapped_ram_load_page instead of requesting source in case of fast snapshot load. to_src_file check is bypassed in fast snapshot load case as there is no source. Call try_mark_postcopy_blocktime_begin on every page fault to support postcopy-blocktime. Allocate another channel in postcopy_temp_pages_setup(like the preempt case), for both the fault thread and eager thread to load pages independently. Add function ramblock_file_bitmap_page_is_nonzero() which searches a range of bits corresponding to a page for a set bit. This is just a bit check for normal pages but for hugepages it checks the range to see if any part of page is non zero. Signed-off-by: Aadeshveer Singh <[email protected]> --- migration/postcopy-ram.c | 121 +++++++++++++++++++++++++++++++++------ migration/ram.c | 11 +++- migration/ram.h | 2 + 3 files changed, 116 insertions(+), 18 deletions(-) diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index 2e2c9fae10..723070b5cd 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -949,6 +949,68 @@ int postcopy_wake_shared(struct PostCopyFD *pcfd, pagesize); } +/** + * postcopy_mapped_ram_load_page() - Load a page to given host address. + * @mis: Migration Incoming State. + * @rb: RAMBlock from where page is loaded. + * @rb_offset: Offset of page in RAMBlock. + * @haddr: Base of page where to load in page. + * @channel: Used to identify between threads and use corresponding temp. + * @errp: Set error in case of failure + * + * Load a page from RAMBlock at offset at given host address. Used by postcopy + * ram fault thread and eager thread in fast snapshot load case. + * + * Return: True on success. + */ +static bool postcopy_mapped_ram_load_page(MigrationIncomingState *mis, + RAMBlock *rb, ram_addr_t rb_offset, + uint64_t haddr, int channel, + Error **errp) +{ + void *place_source = mis->postcopy_tmp_pages[channel].tmp_huge_page; + size_t page; + size_t read; + + page = rb_offset / qemu_ram_pagesize(rb); + + if (bitmap_test_and_clear_atomic(rb->pending_bmap, page, 1)) { + if (ramblock_file_bitmap_page_is_nonzero(rb, page)) { + /* + * This can happen concurrently, but it's thread-safe because + * qemu_get_buffer_at() is thread-safe, and the caller will be using + * different temporary buffers. + */ + read = qemu_get_buffer_at(mis->from_src_file, place_source, + qemu_ram_pagesize(rb), + rb->pages_offset + rb_offset, errp); + + if (read != qemu_ram_pagesize(rb)) { + error_prepend(errp, "Could not read page %zu from RAM Block %s", + page, rb->idstr); + return false; + } + + if (postcopy_place_page(mis, (void *)haddr, place_source, rb)) { + error_setg(errp, + "Failed to place page %zu from RAM Block %s at " + "address %" PRIu64, + page, rb->idstr, haddr); + return false; + } + } else { + if (postcopy_place_page_zero(mis, (void *)haddr, rb)) { + error_setg(errp, + "Failed to place zero page %zu from RAM Block %s at " + "address %" PRIu64, + page, rb->idstr, haddr); + return false; + } + } + } + return true; +} + /* * NOTE: @tid is only used when postcopy-blocktime feature is enabled, and * also optional: when zero is provided, the fault accounting will be ignored. @@ -1310,6 +1372,7 @@ static void *postcopy_ram_fault_thread(void *opaque) int ret; size_t index; RAMBlock *rb = NULL; + Error *local_err = NULL; trace_postcopy_ram_fault_thread_entry(); rcu_register_thread(); @@ -1351,11 +1414,13 @@ static void *postcopy_ram_fault_thread(void *opaque) break; } - if (!mis->to_src_file) { + if (!migrate_mapped_ram() && !mis->to_src_file) { /* - * Possibly someone tells us that the return path is - * broken already using the event. We should hold until - * the channel is rebuilt. + * Possibly someone tells us that the return path is broken already + * using the event. We should hold until the channel is rebuilt. + * Fast snapshot load doesn't support pause and recover, because + * it's not necessary: we can fail right away when QEMU just booted + * with nothing to lose. */ postcopy_pause_fault_thread(mis); } @@ -1418,18 +1483,37 @@ static void *postcopy_ram_fault_thread(void *opaque) qemu_ram_get_idstr(rb), rb_offset, msg.arg.pagefault.feat.ptid); + + if (migrate_mapped_ram()) { + /* Load page directly in case of fast snapshot load */ + + uintptr_t aligned = (uintptr_t)ROUND_DOWN( + msg.arg.pagefault.address, qemu_ram_pagesize(rb)); + + if (try_mark_postcopy_blocktime_begin( + mis, rb, rb_offset, (uintptr_t)aligned, + msg.arg.pagefault.feat.ptid)) { + if (!postcopy_mapped_ram_load_page( + mis, rb, rb_offset, aligned, RAM_CHANNEL_POSTCOPY, + &local_err)) { + error_report_err(local_err); + break; + } + } + } else { retry: - /* - * Send the request to the source - we want to request one - * of our host page sizes (which is >= TPS) - */ - ret = postcopy_request_page(mis, rb, rb_offset, - msg.arg.pagefault.address, - msg.arg.pagefault.feat.ptid); - if (ret) { - /* May be network failure, try to wait for recovery */ - postcopy_pause_fault_thread(mis); - goto retry; + /* + * Send the request to the source - we want to request one + * of our host page sizes (which is >= TPS) + */ + ret = postcopy_request_page(mis, rb, rb_offset, + msg.arg.pagefault.address, + msg.arg.pagefault.feat.ptid); + if (ret) { + /* May be network failure, try to wait for recovery */ + postcopy_pause_fault_thread(mis); + goto retry; + } } } @@ -1501,8 +1585,11 @@ static int postcopy_temp_pages_setup(MigrationIncomingState *mis, Error **errp) unsigned i, channels; void *temp_page; - if (migrate_postcopy_preempt()) { - /* If preemption enabled, need extra channel for urgent requests */ + if (migrate_postcopy_preempt() || migrate_mapped_ram()) { + /* + * If preemption enabled or it is fast snapshot load, need extra channel + * for urgent requests/faults + */ mis->postcopy_channels = RAM_CHANNEL_MAX; } else { /* Both precopy/postcopy on the same channel */ diff --git a/migration/ram.c b/migration/ram.c index 330fceaa43..4ab8e0e750 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -269,12 +269,21 @@ static void ramblock_pending_bmap_init(void) RAMBLOCK_FOREACH_NOT_IGNORED(rb) { assert(!rb->pending_bmap); - size_t size = rb->max_length >> qemu_target_page_bits(); + size_t size = rb->max_length / qemu_ram_pagesize(rb); rb->pending_bmap = bitmap_new(size); bitmap_set(rb->pending_bmap, 0, size); } } +bool ramblock_file_bitmap_page_is_nonzero(RAMBlock *rb, uint64_t page_idx) +{ + int page_bits = qemu_ram_pagesize(rb) / qemu_target_page_size(); + uint64_t bmap_page_start = page_idx * page_bits; + uint64_t bmap_page_end = bmap_page_start + page_bits; + return find_next_bit(rb->file_bmap, bmap_page_end, bmap_page_start) != + bmap_page_end; +} + static void ramblock_recv_map_init(void) { RAMBlock *rb; diff --git a/migration/ram.h b/migration/ram.h index 41697a7599..7e2eac58d3 100644 --- a/migration/ram.h +++ b/migration/ram.h @@ -95,6 +95,8 @@ void ram_handle_zero(void *host, uint64_t size); void ram_transferred_add(uint64_t bytes); void ram_release_page(const char *rbname, uint64_t offset); +bool ramblock_file_bitmap_page_is_nonzero(RAMBlock *rb, uint64_t page_idx); + int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr); bool ramblock_recv_bitmap_test_byte_offset(RAMBlock *rb, uint64_t byte_offset); void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr); -- 2.55.0
