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. Add postcopy-blocktime support by calling mark_postcopy_blocktime_begin on every fault. We need to aqcuire the page_request_mutex lock and check the recv bitmap to make sure we prevent a race condition when a fault occurs but before the fault thread can mark the page for tracking the eager thread loads in the page making us fail the assert for recv bitmap being clear while marking in mark_postcopy_blocktime_begin(). Allocate another channel in postcopy_temp_pages_setup(like the preempt case), for both the fault thread and eager thread to load pages independently. Signed-off-by: Aadeshveer Singh <[email protected]> --- migration/postcopy-ram.c | 121 +++++++++++++++++++++++++++++++++------ 1 file changed, 104 insertions(+), 17 deletions(-) diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index 96a65aa976..be9edac572 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. + * + * 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 (test_bit(page, rb->file_bmap)) { + /* + * 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); + + if (read != qemu_ram_pagesize(rb)) { + error_setg(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. @@ -1279,6 +1341,7 @@ 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(); @@ -1320,11 +1383,13 @@ 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); } @@ -1387,18 +1452,37 @@ 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 */ + WITH_QEMU_LOCK_GUARD(&mis->page_request_mutex) { + if (!ramblock_recv_bitmap_test( + rb, (void *)msg.arg.pagefault.address)) { + mark_postcopy_blocktime_begin( + msg.arg.pagefault.address, + msg.arg.pagefault.feat.ptid, rb); + } + } + if (!postcopy_mapped_ram_load_page( + mis, rb, rb_offset, msg.arg.pagefault.address, + 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; + } } } @@ -1470,8 +1554,11 @@ 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 */ -- 2.54.0
